The initiative, part of the Tennessee Tech University led smart grid modelling and testing ‘Smart Grid Deployment Consortium’ project in the Appalachian region of the US, will focus on creating AI-driven generative models for customer load data.

These will then form inputs to the modelling services of the HILLTOP microgrid simulation platform for modelling and testing new smart grid technologies, in particular for the rural electric utilities that serve much of the region and for example for energy tech startups that are interested in scalability and interoperability.

“This project is a powerful example of how generative AI can transform a sector – in this case, the energy sector,” says Kalyan Veeramachaneni, principal research scientist and principal investigator at the LIDS.

Have you read?
Generative AI solutions for utilities on the rise
The vital role of R&D in the energy transition

“In order to be useful, generative AI technologies and their development have to be closely integrated with domain expertise. I am thrilled to be collaborating with experts in grid modelling, and working alongside them to integrate the latest and greatest from my research group and push the boundaries of these technologies.”

The generative models are expected to have far-reaching applications in that when trained on existing data, they can create additional, realistic data that can augment or replace limited datasets.

For example, in this case generated data can predict the potential load on the grid if an additional 1,000 households were to adopt solar technologies and how that load might change throughout the day

The initiative has been awarded $1.37 million in funding from the Appalachian Regional Commission and will include other participants from across Ohio, Pennsylvania, West Virginia and Tennessee.

Karman is built on a custom module that leverages the NVIDIA Jetson platform for AI in order to capture and analyse data to improve grid operations and manage distributed energy resources (DERs).

A first for the Karman platform, the integration should bring a new level of data insights to Aclara smart meter implementers, with up to a stated 100 times more processing power than traditional solutions.

Local AI models also will continuously learn to improve in areas such as grid planning, grid operations, load management, customer service and more.

Have you read?
Intelligent edge platforms, accelerating grid modernisation
Unlock the business value of Grid Edge Computing

“As the grid becomes increasingly more complex and dynamic, utilities need more technology options to operate a clean and reliable grid,” comments Erik Christian, Division President, Grid Automation of Hubbell, of which Aclara is a division.

“By combining Utilidata’s extensive knowledge of distributed AI with Aclara’s decades of experience providing industry-leading hardware, we’re now able to bring new, innovative, interoperable solutions to our customers, starting with smart meters.”

A company statement reports that the partnership follows the trend of market momentum and federal funding driving the utility industry’s need to modernise and report its operational efficiencies, for which distributed AI holds vast potential.

In October 2023, the Department of Energy announced $3.5 billion in funding for grid modernisation projects, including awards to Portland General Electric, Duquesne Light Company and Commonwealth Edison Company to deploy over 100,000 Karman units to increase reliability and accelerate decarbonisation and electrification.

Elizabeth Cook, Vice President of Technical Strategy of the Association of Edison Illuminating Companies, said that utilities are seeking more options for new and innovative technologies, like distributed AI, for easily accessible and actionable data.

“Utilidata’s partnership with Aclara makes it easier for utilities to integrate this important technology as the industry continues to build a smart and adaptive grid that is resilient and reliable for customers.”

Josh Brumberger, CEO of Utilidata, points to a meter-embedded distributed AI platform as only a beginning.

“There are more opportunities beyond meters within the electric grid ecosystem that can benefit from having easy to access data and predictive analytics.”

The blueprint, which has been prepared by the Interoperability Network for the Energy Transition (int:net), is aimed to guide on transitioning the existing energy sector data infrastructures towards data space solutions and to define a general data space architecture that can enable an initial set of real-world business use cases.

In particular, the architecture is aimed at interconnecting the existing data infrastructures with federated data spaces, in which multiple datasets are mapped.

The concept of data spaces has been gathering momentum in various domains for sharing of data between multiple participants and the establishment of a common energy data space is one of the key actions set out in the EU’s energy sector digitalisation action plan.

Have you read?
First version of the European energy data space is up for funding
Creating data space with smart meter hubs

Foundational aspects that must be considered pertain to security and privacy, data quality and integrity and governance, while other aspects that need to be taken into account include the business model related to data exchange, legal and operational details and the technology, with a primary objective to ensure interoperability both internally and with other data spaces.

The blueprint document states that at the highest level, the CEEDS is foreseen as the common framework that federates different data spaces implemented at national, sub-national or international levels and allows the participation of single users.

Business use cases

The five representative business use cases, in which specific exchanges of data from diverse sources must occur among the involved actors, were defined as:

• Use case #1 – Collective self-consumption and optimised sharing for energy communities
• Use case #2 – Residential home energy management integrating distributed energy resources (DER) flexibility aggregation
• Use case #3 – TSO-DSO coordination for flexibility
• Use case #4 – Electromobility: services roaming, load forecasting and schedule planning
• Use case #5 – Renewables O&M optimisation and grid integration.

Based on these the proposed model corresponds to the creation of the energy data space as the combination of multiple ‘distributed data ecosystems’, i.e. the existing legacy data platforms, with an overarching layer defined as the ‘federated data space’ where the data is indexed and made discoverable and providing a ‘marketplace’ for sharing and possibly trading of data and data services.

Data space connector

The different data space participants are connected through a software component known as the ‘data space connector’, which realises the interconnection and data exchange.

This data space connector should be incorporated into the pre-existing platforms to enable identification, data harmonisation and brokerage towards data spaces, which can be useful for integrating data from different sources or for allowing multiple applications to access the same data without having to duplicate it in multiple places.

Moreover, in this model, the data space connector also enables the exchange of energy data and execution of services both among the existing legacy platforms and through the federated layer.

The document notes that to fully achieve the deployment of the CEEDS, starting from the federation of projects’ data space instances, detailed interoperability measures are necessary including technical interoperability, semantic interoperability and governance interoperability.

The document states that the presented blueprint underscores the critical need to adopt data space solutions within the energy domain, marking a pivotal moment for the transformation of the industry.

“The fundamental pillars of data spaces not only foster the active engagement of key stakeholders across the energy value chain but also promise mutual benefits, ranging from monetary compensations to an elevated quality of services.

“At this scope, the establishment of clear rules, policies and regulatory adaptations is a linchpin in facilitating fair data exchange, paving the way for an open market that fosters the participation of new actors, including data and service providers, as well as data consumers.”

The int:net initiative managed by the Fraunhofer FIT is an EU Horizon Europe-supported project to bring together stakeholders from across the European energy sector to jointly work on developing, testing and deploying interoperable energy services.

Key parties are the projects in the ‘energy data spaces cluster’, i.e. Omega-X, EDDIE, Enershare, Synergies and DATA CELLAR, whose findings have fed into the blueprint, while further inputs should come from the newly launched HEDGE-IoT, ODEON and TwinEU projects.

In the meantime, the blueprint will continue to be updated with version 2 due to be released in June 2024.

The 44 projects, selected from 53 that were submitted for round three of the fund, will be led by energy network companies in partnership with innovators and partner organisations.

Priority challenges for eligibility included:

• Whole system planning and utilisation of networks, to facilitate faster and cheaper network transformation and asset rollout;
• Novel technical, process and market approaches to deliver an equitable and secure net zero power system;
• Unlocking energy system flexibility to accelerate the electrification of heat;
• Enabling power-to-gas (P2G) to provide system flexibility and energy network optimisation.

Project delivery

The SIF, funded by energy regulator Ofgem and delivered by Innovate UK, aims to find potential ideas for energy network challenges and identify those with the greatest promise as quickly as possible.

With their selection into the funding programme, the 44 projects will now enter their initial discovery phase. If successful, they will help customers and the wider electricity sector accelerate their net zero plans, build network resilience, access lower costs and streamline maintenance activities.

In a release, UK Research and Innovation (UKRI), which directs research and innovation funding in the UK, lists examples of selected network and flexibility projects:

Equiflex

Led by SP Energy Networks, Equiflex aims to promote equal access to flexibility markets, ensuring a just transition to net zero.

Equiflex project partners, Frazer-Nash Consulting Ltd, Energy Action Scotland and East Ayrshire Council, are looking at the design of flexibility options targeted at specific groups, such as less engaged and more vulnerable consumers.

They are also looking at the development of a toolkit to help stakeholders, such as local authorities, to evaluate which flexibility options might be best for their local context.

B-Linepack+

The B-Linepack+ project, led by National Gas, is exploring the feasibility of using geological solutions as intermediate scale storage.

The national gas transmission system can pack additional gas into the lines, known as linepacking. However, the amount of energy able to be stored by linepacking will decrease as we move toward decarbonisation of the networks with the use of hydrogen.

The project works with partners from the University of Edinburgh, Gravitricity Ltd, Southern Gas Networks, Revolutionary Engineering & Digital Design Ltd and Energy Reform Ltd.

It is looking at how lined rock shafts, engineered rock caverns and underground silos could provide purpose-built storage to supplement linepack capacity and provide system flexibility. This will enable supply and demand to be managed more effectively for consumers.

Have you read:
NYSERDA selects Reactive Technologies for inertia measurement project
China connects gravity storage and launches three new projects

UKPN flexibility projects

Additionally, UK Power Networks listed three projects selected for funding, including:

• Electric Thames: exploring the viability of electric-powered boats on the River Thames, and the possibility of boat power feeding the electricity grid to increase energy flexibility and reduce peak electricity demand
• KnowMyFlex: a proposal to create energy flexibility certificates, similar to energy performance certificate (or EPC) ratings, to show the existing and future flexibility potential of homes and buildings, helping customers engage with flexibility to reduce their bills
• WASH: an advanced study into the ways heat can be efficiently captured from wastewater and used to help district heat networks decarbonise

Luca Grella, head of innovation at UK Power Networks, said: “We’ve made remarkable strides during our first year with the SIF programme and are excited to be heading into a second with a new wave of projects which have exciting potential to make a real impact on both our communities and the way we work.

“This funding is allowing us to continue building strong bonds with some of the brightest minds in the sector. Our project collaborators play a key role in helping us deliver tangible benefits for our customers, and we can’t wait to reap the rewards of these partnerships.”

Launched in 2021, the UK‘s SIF fund is expected to invest £450 million ($577 million) by 2026.

As I was thinking about the content of this week’s tech talk, an article appeared in the popular press about a proposed plan to sheath the edge of the Thwaites glacier in Antarctica with a 100km long curtain to protect it from melting and potentially raising sea levels up to a suggested three metres.

The argument is that while a slow melt occurs as the warmer undersea current comes into contact with the edge of the glacier, as the climate warms so the undersea currents get warmer and the melting accelerates.

Moreover with that warming also the winter refreezing results in less ice recovery.

Have you read?
What’s on the technology radar for Europe’s DSOs?
How solar can keep its place in Europe’s sun

Such geoengineering, or ‘engineering’ of the climate, is increasingly being talked about as scientists look for ways to slow or halt global warming.

Indeed, it is already being practised in the form of carbon capture from the atmosphere.

John Moore, professor of climate change at the University of Lapland’s Arctic Centre in Finland, is said to be on a mission to save the Thwaites glacier and quoted as expressing confidence the Antarctic Treaty countries will foot the $50 billion bill.

Cool Earth

So too is Yoram Rosen, director of the Asher Space Research Institute at the Technion Israel, who also has been in the news recently with a different type of geoengineering mission – in this case by placing a large shield out in space between the Sun and Earth to reduce the amount of solar radiation reaching the Earth.

The Institute, which claims to be developing a demonstrator in collaboration with the National Centre for Space and Science in the United Arab Emirates and the Israeli geospatial company ImageSat International, believes that a large-scale initiative has the potential to contribute significantly to the reduction of global warming by up to 1.5^oC.

The ‘Cool Earth’ proposal is to place the satellite at the first Lagrange point – a distance of about 1.5 million kilometres from the Earth towards the Sun where the gravitational forces of the two bodies cancel each other allowing a satellite there to remain in essentially a fixed position.

In practice, the satellite would exhibit a slight back-and-forth motion by controlling the shading sail, which also could be used to alter the amount of solar shading according to global climate needs.

“This ground-breaking project offers an original way to cope with the global climate crisis and perhaps even stop its destructive effects,” asserts the Institute’s website.

“Controlling the amount of energy that reaches the earth from the sun may even allow humanity in the future to directly control the desired climate over areas of interest on the earth and possibly prevent droughts and other climate-related natural disasters.”

The Asher researchers have estimated that to achieve the desired temperature reduction, the shade would need to be around 2.5 million km2 in extent – for perspective, in size between the areas of Saudi Arabia and Argentina.

The researchers haven’t stated when they expect the demonstrator to be ready to fly but there are numerous hurdles to be overcome before a large-scale initiative such as this – or any other large-scale geoengineering proposal – could be put into practice, not least the moral with the potential unknown side effect that could occur.

In a recent paper, modelling solar geoengineering – such as the Asher Institute proposal – and carbon dioxide removal, Moore of the Thwaites glacier proposal and the co-authors suggest that combined with the standard mitigation measures they could help to limit global warming.

However, they conclude more cautiously: “Scientific uncertainties surrounding the effectiveness, scalability, and long-term impacts of solar geoengineering and carbon dioxide removal techniques necessitate comprehensive research, rigorous modelling and robust international collaboration to mitigate the risks inherent in unintended consequences and to inform responsible decision-making.”

What are your views on solar geoengineering and should it pursued?

Jonathan Spencer Jones

Specialist writer
Smart Energy International

Follow me on Linked

The project, implemented as part of Enea Operator’s activities to modernise the energy infrastructure and introduce new solutions to improve the quality and security of supply, is aimed to contribute to improving the management of the distribution network.

Its basis is the use of proprietary deep learning algorithms from Polish software developer Affexy, with a focus on the most relevant data enabling continuous improvements that can improve the precision of forecasts and their adaptation to dynamically changing network conditions.

The project is predicated on the need to better adapt the grid to the changing conditions of the electricity market with growing renewable energies and for example new energy efficiency regulations.

Have you read?
EIB invests in Polish and Belgian network modernisation
Although Poland is on its way, a greater push is needed to reach net zero – IEA report

It is focused on three areas, of which the main one is the data analysis to enable understanding of the load on the network and identification of factors that affect the variability of that load.

Prior to that is the processing of the acquired data so that it can be efficiently analysed by the advanced AI models.

In the final step, a report and recommendations will be made with the conclusions from the analysis and suggestion of actions to optimise the data collection process and the quality of the forecasts.

Enea Operator anticipates that benefits will include a better understanding of the network load and the patterns that drive it – aspects that are critical for effective network management.

The project also introduces and pilots the advanced AI techniques, thereby testing the effectiveness of the algorithms in real-world conditions.

With the results and experience obtained, Enea Operator anticipates the implementation of a full-scale system.

Alongside this project, Enea Operator has concluded a PLN1 billion ($255 million) investment loan agreement with the European Investment Bank for distribution works.

These are to include the modernisation and construction of almost 8,000km of medium and low voltage grids, installation of 2.4 million smart meters, connections of 140,000 new customers, upgrading transformers by 633MVA and the connection of 4.3GW of new renewable generation capacity.

If there’s one place where generative AI has the ability to make a tremendous impact, it’s the energy sector. AI could help streamline energy production and distribution, increasing efficiency and cutting carbon emissions from the vital processes that enable us to keep warm, travel and live our modern lives.

While businesses all over the world are investing in generative AI and the talent needed to implement it, the energy sector is facing its own talent issues when it comes to generative AI.

For example, data shows that 40% of businesses in the energy sector find it difficult to hire data scientists with the skills they need. Without the right combination of talent and data necessary to accurately and quickly utilise foundational models, many energy companies will not be able to leverage generative AI fully. They will therefore be at a disadvantage compared to competitors for the future of energy — one that entails a global transition that will likely occur at an increasingly rapid pace. 

So what do you do when there’s a talent shortage but your business needs to add more skills? You train the talent you already have. In 2024 and beyond, as energy demands grow on a global scale, the energy sector will find combining generative AI with proper upskilling to be extremely valuable.

Generative AI’s effect on enterprise talent

For many organisations, a successful approach to upskilling will begin with an understanding of how generative AI can affect almost any position within an organisation.

Some employees will see generative AI agents augment their current position and give them access to more relevant data. Other staff members may collaborate side-by-side with generative AI agents that sit either upstream or downstream of a human in a business workflow. Then there’s the software engineers, or those who will be charged with creating or fine-tuning generative AI agents.

Ultimately, each company will have to assess which new roles will be required (i.e. prompt engineers) and which ones will change materially (i.e., software developer). They’ll have to train each employee on how to use the technology — even if that training is at a basic level.

Generative AI and the energy sector

There are already growing use cases where generative AI is making an impact in energy and, as energy consumption increases, those use cases will expand.

For example, generative AI is currently playing a key role in safety procedures at various energy companies around the world. Historically, before any operator at an energy company begins a job, they’d receive a standard, but often generic, safety briefing. Traditionally, the safety analysis has been completed manually, which can leave out a more comprehensive view of all the necessary safety measures.

With a generative AI agent trained on the right safety data, operators will have access to insights on near misses, extensive safety records, weather conditions, etc. Operators can receive briefings that are specific to their role, job site and team.

Generative AI is also accelerating the rate at which energy employees can access data. With a generative-AI powered enterprise search, enterprises now allow their employees to find pertinent data as soon as they start a job. Through retrieval augmented generation, the generative-AI agent will learn which data is most relevant to the right staff members as they search. This will allow employees to access the right data such as log data, geographical data, information on local culture and much more.

For the energy sector to reap these benefits they’ll need to apply sound, repeatable upskilling practices at the right scale and to the right employees.

Have you read?
How AI and advanced analytics will be key for the grid of tomorrow
Robot dog Spot to transform into Sparky with AI enhancements

Upskilling talent — Who? How? Why?

Like other industries, the energy sector is competing for talent that can match their plans for generative AI implementation. This is why external hiring of data scientists isn’t occurring at the rate energy executives would like to see. Also, the energy sector requires a specific set of expertise, which further commodifies generative AI-related roles at energy companies such as data scientists, prompt engineers and software developers.

Since finding data scientists and other roles with the right expertise hasn’t been easy, certain energy companies are instead looking to the experts already within their ranks. This translates to upskilling initiatives for as much talent as possible in generative AI, which helps close the gap in external hiring. Some of the upskilling will be for roles such as data scientists, enterprise architects and data engineers.

There are already examples of energy companies taking intentional approaches to upskilling. For example, as Duke Energy continues its cloud journey, it has built a framework that allows many of its employees to access relevant training content and engage in learning that aligns with Duke Energy’s cloud computing and clean energy goals.

Other avenues are available to energy companies who want to upskill their talent on generative AI. Some companies may choose to turn to cloud and foundation model providers to support internal employee training through formal class or online learning. This is another reason why it’s important to develop relationships with the partners who are developing the generative AI technology that companies are trying to use.

Other upskilling approaches include providing free sources of consumable training content through sites such as deeplearning.ai. Further, there are some enterprises that are creating opportunities for experiential learning through proof of concepts, hackathons and workshops. These experiential opportunities in particular are great ways to train talent on scenarios that extend past technical skills.

One energy company AWS worked with recently leaned into an experimental upskilling initiative to better leverage radio communication transcripts. The radio communications team and edge team worked together to develop a generative AI agent that combines radio communication transcripts with asset IoT data to produce daily job status reports. The radio communications and edge teams did not typically work together. However, joining forces to create the prototype helped them develop the required relationships to take generative AI to the next level.

Breaking silos and bringing different departments together — like the example above — is a major reason to invest in the right generative AI training. However, getting buy-in from boards of directors and participating in responsible AI practices are also good reasons to practice upskilling.

Upskilling promotes responsible AI

Despite some of the benefits generative AI brings, there are still many leaders, particularly in the energy sector, that have concerns about the introduction of generative AI into their companies. For example, many energy/utility companies have access to customer information and confidential internal data that can be introduced to foundational models. Board members and c-suite leaders want to be sure this information remains secure. From a financial standpoint, today’s enterprise leaders want to make sure investing in generative AI issues an adequate return on investment.

In each scenario, training all members of an organisation on responsible AI practices should be a part of any upskilling approach. This includes understanding responsible AI tenets such as fairness, explainability, robustness, privacy and security, governance, and transparency. With proper responsible AI training, enterprises can safely power innovation, mitigate stakeholder concerns and see continued ROI.

Keeping pace with innovation

The current hiring landscape suggests that energy companies won’t be able to hire generative AI talent at the expected (and necessary) pace of innovation.

This talent and recruitment landscape likely points to a world where energy companies will not only have to begin investment in upskilling their own talent, but possibly double and triple down on investment initiatives.

With energy consumption on the rise, organisations will have to place greater focus on empowering the talent they already have to train generative AI models, analyse subsequent data and leverage that data to create the solutions necessary for the future.

About the Author
Joseph Santamaria is director of WW Energy and Utilities Solution Architecture at AWS.

In his role, he works with the largest utilities, oil and gas and energy producers in the world to utilise the cloud to solve the most complex problems in the energy transition and operations.

ChatGrid, the brainchild of Pacific Northwest National Laboratory (PNNL) optimisation and grid modelling researcher Shrirang Abhyankar, was conceived to exploit the question-and-answer approach of generative AI tools to support grid operators in their decision making.

With this, the user can then ask a question such as: “What is the generation capacity of the top five wind power generators in the Western Interconnection?” with the response of a visualisation showing the desired information.

Users can ask questions about generation capacity, voltage, power flow and more, while customising the visualization to show different information layers.

Have you read?
Tech talk | On the grid edge
Europe’s grid action plan: a step in the right direction, but is it enough?

Abhyankar says the aim is to simplify the experience for grid operators who have to make many decisions as they monitor the grid in real-time.

“We’re envisioning a new way to look at data through questions. ChatGrid allows someone to query the data – in a literal sense – and get an instantaneous answer.”

ChatGrid runs on a publicly available large language model, with the input data the synthesised data from the Exascale Grid Optimisation (ExaGO) model, which was developed to take advantage of the power of supercomputing to simulate the nation’s power grid in real time.

Moreover, to further protect grid security, the model was not trained on the data itself.

Instead, the data was compiled in an internal database in columns with headings such as ‘capacity’ and ‘location’ of power plants and the model used to produce a ‘structured query language’ (SQL) that allows ChatGrid to search this database for its answers.

Work in progress

For Abhyankar, ChatGrid remains very much a work in progress.

He hopes that once grid operators start using ChatGrid and providing feedback, a better version can be built that they can then safely use in their control rooms with real-life data.

For that to work, ExaGO’s developers need the data to be useful on regular computers as well, however.

Further, while ChatGrid is available for download on GitHub, the process takes a few steps and once the feedback starts rolling in, the development of a one-step download process is anticipated.

Users also are invited to play around with the phrasing prompts and questions to assess how to produce the best answers.

Active in over 40 countries and five continents, MYTILINEOS’ activities on the energy side of the business span across grids, power plants, thermal technologies and renewable energy sources (RES), all contributing to a sustainable and vibrant energy future.

On the Metals side, MYTILINEOS is the largest bauxite producer in Europe, operating the sole bauxite to aluminum integrated unit in the European Union, with aluminium recycling making up about a quarter of overall production in 2023

Grids driving the green revolution

Managing an extensive portfolio of 30 ongoing power projects across 10 countries, MYTILINEOS M Power Projects segment showcases the kind of global reach and impact that transcends all segments.

With a thermal project portfolio exceeding 16GW for third parties worldwide, the company is actively involved in constructing natural gas-fired power plants in the UK and Poland, illustrating its commitment to expanding its international operational footprint.

MYTILINEOS recognises the pivotal role that grids play in shaping the future of our energy landscape, paralleling the significance of renewable energy sources. Beyond being instrumental in the green transition, grids open up exciting avenues for growth and collaboration.

According to the European Union, a substantial €584 billion (US$634 billion) investment is needed in new networks and the upgrading of existing infrastructure, setting the stage for a sustainable energy evolution.

Recently, MYTILINEOS as awarded a £1 billion (US$1.3 billion) contract to construct the UK’s first high-capacity East Coast subsea link in collaboration with GE Vernova, benefitting Scottish Power and the UK’s National Grid, enabling the transmission of renewable green energy to power more than two million homes across the UK.

Based on track record, MYTILINEOS has completed among others a significant 130km interconnection line between Maritsa East 1 (BG) and Nea Santa (EL), enhancing transfer capacity and ensuring safe integration of renewable energy in northeast Greece and Bulgaria.

Expertise in designing and building high voltage lines, like the DISTOMO-High Voltage Centre AGIOS NIKOLAOS I & II transmission line, another of the Company’s major projects, is crucial for safe distribution and supporting increased power flows.

WATCH: Avokado is breaking new ground in Energy AI

Cutting-edge power generation: the energy trilemma

In the realm of natural gas, MYTILINEOS is a standout player in the Southeastern Europe market, engaging in extensive trading and supplying operations.

Seven state-of-the-art industrial thermal (gas-fired) power plants showcase MYTILINEOS’s commitment to innovation and energy security, boasting cutting-edge technology that enables an annual power generation exceeding 5TWh. These plants not only signify technological prowess but also underline the company’s dedication to meeting the surging global demand for energy.

Countries worldwide grapple with the energy ‘trilemma’, balancing accessibility, affordability and sustainability. Recent crises have spotlighted vulnerabilities in existing energy infrastructure, highlighting the need for a transition towards more sustainable and integrated solutions.

Global impact: portfolio, expansion and commitment

Founded in Greece in 1990, MYTILINEOS has evolved into a global player with a firm commitment to the communities it serves. As a publicly listed company on the Athens Stock Exchange, boasting a consolidated turnover of €5.5 billion and an EBITDA of €1 billion, MYTILINEOS possesses the financial strength to invest in cutting-edge technologies and projects that contribute to sustainable energy solutions globally.

Moreover, the company is a leader in renewable energy projects across Europe, Chile, Australia, the Americas, and Asia. With a capacity of 14GW in different stages of development, these initiatives underscore MYTILINEOS’s commitment to shaping a cleaner and more sustainable energy landscape.

Shaping the energy transition future

MYTILINEOS is not just an energy company; it’s an energy transition powerhouse. As it pioneers advancements in grids, power plants, thermal technologies, customer solutions and renewable energy, MYTILINEOS remains dedicated to a future where energy is not just accessible and affordable, but most importantly, sustainable.

With innovation as its driving force, MYTILINEOS continues to empower the future of energy, contributing to a world where sustainable solutions thrive.

About MYTILINEOS

MYTILINEOS Energy & Metals, founded in Greece in 1990, is an industrial and energy multinational company, listed on the Athens Stock Exchange, with a consolidated turnover of €5.5 billion and EBITDA of €1 billion with activities across 40 countries and 5 continents. Through the energy sector, the company is strategically positioned at the forefront of the energy transition as an integrated utility of the future, while through the metallurgy sector the company is establishing as a benchmark for competitive ‘green’ metallurgy in the European landscape. Focused on sustainability, it has set a target to reduce CO2 emissions by at least 30% by 2030 and achieve by 2050 net zero carbon footprint in all its operations in accordance with the criteria for Environment, Society and Governance (ESG).

Though the ‘edge’ has been talked about for years, it is increasingly taking central stage as more and more homes and businesses take up solar and battery systems, switch to electric vehicles ((EVs) and heat pumps and instal the smart appliances that are advertised as bringing more convenience to life.

In broad terms the edge is where the utility and customer meet and is effectively represented by the meter – the utility side in front of the meter and the customer side behind the meter.

With this growth of decentralised resources and the increasingly complex and unpredictable power flows, some of the risks include the likely emergence of hyper-local capacity constraints and that ageing infrastructure can be put at risk.

Have you read?
Generative AI solutions for utilities on the rise
‘We need to think smart and fast’ to future-proof the grid

But there has been what Itron has termed a ‘control gap’, with the challenge that whereas a typical SCADA manages approximately 1,000 assets per million customers and a typical advanced distribution management systems 10,000 assets, that to the point of service is a further two orders of magnitude greater at around 1 million points.

But that is changing, with the evolution of IT and other technologies opening the way for a variety of new products and services to provide visibility and control to address the challenges of the evolving grid.

Itron’s grid edge intelligence portfolio

A pioneer of edge intelligence in the energy sector, Itron has consolidated its offerings into a cloud-based edge intelligence portfolio combining connectivity, analytics and applications with intelligence for AMI operations and optimisers for the low and medium voltage grid, DERs and EVs, coupled to a central datahub.

To simplify the process the Itron Enterprise Edition has been made available in the Microsoft Azure marketplace, also opening the way for integrating the Azure OpenAI generative AI solution for users to expedite and improve visibility on data and operations.

Among the new solutions launched are Active Transformer Load and Voltage Monitoring (ATLM/ATVM) applications to enable visibility on transformer loading and voltage statistics in real-time along with configurable threshold-based alarms.

Key for broader uptake of the solutions is partnerships with other providers with these opening the way for Itron’s grid edge intelligence solutions to be integrated into Schneider Electric’s digital grid solutions and to GE Vernova’s new GridOS Data Fabric alongside the GridOS apps.

A further partnership is with the Mobility House as part of its Fast & Flexible Interconnect (FIX) programme for charging of EV fleets in constrained distribution systems.

Don Reeves, senior VP of Outcomes at Itron, reports that customers have advised that the company’s Grid Edge Intelligence portfolio can enhance grid capacity by approximately 20% through the optimisation of existing grid assets.

“Utilities are operating in a more complex environment than ever before and there is a real sense of urgency that change is needed to ensure grid reliability, resiliency and sustainability and improve the customer experience.”

Landis+Gyr and Span partnership

Landis+Gyr has announced a partnership with home electrification technology developer Span, with the first joint product combining their respective solutions to deliver a grid edge solution with circuit-level billing-grade metering, DER visibility and controls.

Describing the co-innovated solution as “a whole-home multi-asset virtual power plant (VPP)”, Werner Lieberherr, CEO of Landis+Gyr, says: “The partnership not only expands our flexibility management platform but also helps [utilities] reduce costly grid infrastructure investments required for electrification. We’re particularly excited to bring SPAN’s service upgrade avoidance capabilities and intuitive app experience … to drive energy efficiency and flexibility.”

While full details of the solution are still to be released, the companies promise to evaluate it in pilots with US utilities starting later in the year.

Siemens Gridscale X

Siemens has launched Gridscale X as a modular software to scale grid capacity and handle the complexity of DERs.

A key component of Gridscale X is DER Insights which is designed to unlock visibility over the distribution grid, with features including the location and behaviour of DERs, grid impact identification and digital grid mapping and modelling.

“With the electrification of everything and the exponential growth of DERs, there is an urgent need for increasing grid capacity fast,” says Sabine Erlinghagen, CEO Siemens Grid Software, pointing to the use of such software as enabling utilities to focus on critical infrastructure upgrades and reducing the impact and occurrence of grid equipment failure, outages and technical debt.

Users of these or similar softwares are invited to contact us with case studies.

Jonathan Spencer Jones

Specialist writer
Smart Energy International

Follow me on Linkedin

Pacific Gas & Electric (PG&E), the largest utility in California, is partnering up with energy software business Kaluza and EV charging company Wallbox to pilot the smart charging and Vehicle to Everything (V2X) technology.

Through $1.5 million in phase one funding from the California Energy Commission (CEC) REDWDS grant, the partners will develop new technologies to incorporate dynamic price signals for both one-way ‘V1G’ and bidirectional ‘V2X’ charging.

The project will allow drivers to ‘set and forget’ their EV charging: using Kaluza’s algorithms, a smart EV charger, driver preferences, live grid data and dynamic pricing structures, vehicles will charge optimally to reduce grid pressures during public safety power shutoff events.

The programme will comprise 330 vehicles, with a commitment to deploy at least 50% of these assets in low-income communities.

Some of these assets will be connected to Wallbox’s bidirectional charger, Quasar 2, enabling users to charge their EVs and export power back to their homes or offer emergency back-up power when the grid is down. EVs store around 70kWh in their battery – sufficient to power an average home for three days, longer than most stationary batteries.

Have you read:
Is V2X energy transition’s missing piece of the puzzle?
How to Scale V2X: Findings from INFLEXION

Project progression

If the project is successful, additional CEC funding of up to $4 million will be made available through a second phase to continue deploying managed charging and bidirectional solutions in California.

Mike Delaney, vice president of Utility Partnerships and Innovation at PG&E, commented on the V2X partnership in a release: “Our work to prepare the grid to power and support millions more EVs over the next decade includes creating the most robust vehicle-grid-integration portfolio in the world.

“To that end, we are collaborating with the best and the brightest to integrate new bidirectional charging capabilities and to provide the platform, expertise, and cross-industry leadership to enable our customers with a range of options that unleash the full potential of their EVs.”

Phase 1 of the three-year pilot kicks off this year, with customer enrolment expected at the end of 2024. The programme operation and data collection will extend through September 2026.

PG&E provides natural gas and electric services to approximately 16 million customer, with 600,000 operating EVs throughout the utility’s Northern and Central California service area.

In a release, the partners cite high initial costs and the reliance of low-income individuals on their vehicles for work, posing challenges for these communities in transitioning to EVs. The project partners will further collaborate to lower the upfront costs of switching to an EV and showcase the efficiency of managed charging programmes in ensuring affordable charging and constant vehicle readiness for customers.

Additional partners in the initiative include community-owned electricity provider Sonoma Clean Power and Valley Clean Air Now (CAN). The former aims to make EV charging more accessible for low-income communities and the will support customers in learning about options to make use of second hand EVs.

Jonathan Levy, US managing director at Kaluza, commented: “We are thrilled to be selected for up to $6.2 million in funding from the California Energy Commission, enabling Kaluza to accelerate our work in the United States.

“With California rapidly approaching 2 million cumulative EV sales, managed charging with software solutions like Kaluza means everyone’s a winner – including EV drivers, utilities like PG&E, the grid and the planet.”

The scientists developed a model that simulates storm damages to the Texas power grid and studied 10,000 realisations of potential damages for each of seven historical tropical cyclones, including the major hurricanes Harvey (2017) and Ike (2008). Their approach allowed them to reproduce observed supply failures.

The Texas electric power system was chosen due to its high frequency of exposure to hurricanes and weaker tropical storms, providing the perfect context to study these complex effects and potential resilience adaptation options in depth.

The researchers, who published their findings in Increasing the resilience of the Texas power grid against extreme storms by hardening critical lines, find that large-scale power outages caused by tropical cyclones can be prevented almost entirely if small but critical sets of power lines are protected against storm damages.

Study author and PIK scientist Christian Otto commented in a release on their analysis: “We found that the failures of certain lines can trigger large-scale outages affecting whole regions or cities. Regions or cities fail in one major cascade, rather than gradually.

“Our research shows that such cascades can be avoided almost entirely if less than 1% of the overall grid – this is 20 lines in the case of the Texas power grid – is protected against storm damages, for example by reinforcing transmission towers or using underground cables. This way, the risk of outages in major population centres can be significantly reduced. Notably, protecting the same small set of relevant lines works for all seven historical hurricanes considered.”

Have you read:
Extreme weather preparedness a top concern for US utilities, Wi-SUN finds
DISTRIBUTECH: Merging data streams for updated transmission planning

Modelling grid to storms

Based on a model of the Texas power grid, the scientists coupled a model of the evolution of tropical clones’ wind fields with a dynamic model of the Texas power grid in a spatio-temporal approach, allowing it to describe the evolution of storm-induced cascading power outages.

“For the first time, our analysis shows how an electric network reacts to evolving storms. By simulating the co-evolution of wind-induced failures of high-voltage transmission lines and the resulting cascading power outages, we discovered which parts of the electricity network are most critical as their failures have cascading impacts leading to major power outages,” said PIK scientist and study author Frank Hellmann.

“This appears to be a property of the network itself, rather than the storm’s precise path.”

“This is a challenging task, as the time scales at which storms and power outages evolve can be very different,” added scientist Mehrnaz Anvari, who conducted the research at PIK and is now group leader of Network Evaluation Technologies at the Fraunhofer Institute for Algorithms and Scientific Computing.

“By combining PIK expertise on the event-based modelling of tropical storms and power grids, we managed to identify the critical lines, whose failure can trigger large blackouts.”

“Tropical cyclones are one of the most destructive category of extreme weather events,” said Katja Frieler, scientist and head of the Research Department, Transformation Pathways, at PIK.

“As peak wind speeds of the most intense storms are projected to increase with global warming, the damage caused by these storms is likely to increase unless we adapt accordingly. Our new method gives grid operators a crucial tool to identify effective adaptation options and can help make our infrastructure networks fit for a new climate reality.”

The company has been piloting the software 1Streetworks, which provides traffic management plans, with the finding that the average time taken to connect new or altered power connections was reduced by a quarter across approximately 300 Surrey roadworks sites where it was used.

Based on this outcome UK Power Networks is now planning to roll out the technology in a larger one-year trial in Kent to test its use in other workstreams across the company.

“Planning streetworks to the high standards we expect takes time and few have tried to revolutionise the process during my 23 years in the sector,” says Paul Dooley, streetworks performance manager at UK Power Networks.

“So, I’m excited about the potential of 1Streetworks to streamline complex traffic management plans, enable better communication with customers and highway authorities and improve the speed and accuracy of streetworks plans.”

Have you read?
Why a UK consortium is bidding on geospatial planning for net zero
Mapping the future of utility networks

Traditionally a streetwork design plan for a smaller power connection, overhead line or underground cable repair usually needs a surveyor to assess the site, take measurements then plot signage on a CAD system – a process that can take hours of work, with the need to maintain high levels of safety and accuracy and to meet industry regulations.

The cloud-based 1Streetworks from the Cambridge headquartered location and geospatial data specialist 1Spatial is stated able to produce similar plans on-site in under two minutes.

Once the user plots the location of the work on a map, the software instantaneously plans site-specific traffic management, integrating layers of maps with main roads, bus stops, lane rental and streetworks rules.

Claire Milverton, CEO of 1Spatial, said the pilot has been a key milestone for the company and a culmination of many years of work and investment.

“We are delighted that our innovative 1Streetworks application has delivered such fantastic results for UK Power Networks and its customers. We look forward to roll out the software further across the network over the coming months.”

UK Power Networks has 190,000km of cables and delivers thousands of streetworks every year across London, the southeast and east of England.

On average there are over 4 million low-speed road works undertaken in the UK each year.

1Streetworks was developed initially with GB gas network operator Northern Gas Networks for expediting works on its underground pipelines.

The increasing complexity of power grids with high levels of inverter-based variable renewables and unpredictable electric vehicle charging patterns has brought with it challenges for power grid operation and the need for real-time control as key for maintaining voltage stability.

Based on deep reinforcement learning – a subset of machine learning – the new algorithms are designed to solve this challenge by delivering intelligence to power converters in the grid utilising what the researchers describe as a novel data synchronisation strategy to optimise the large-scale coordination of energy sources safely under fast fluctuations without real-time communication.

“Centralised control is not cost-efficient or fast under continuous fluctuations of renewable energy and electric vehicles,” says Qianwen Xu, one of the researchers involved in the project.

Have you read?
It’s time for a new era of low voltage grid management
How digitalisation can solve grid challenges for TSOs

“Our purpose is to improve control strategies for power converters, by making them more adaptive and intelligent in order to stabilise complex and changing power grids.”

The research, which was demonstrated in KTH’s smart microgrid hardware platform and published in the IEEE Transactions on Sustainable Energy, proposes a projection-embedded deep reinforcement learning algorithm to achieve decentralised optimal control with guaranteed 100% safety.

This is intended to overcome the challenge of existing deep reinforcement learning methods in power system applications of not being able to achieve optimal performance and guarantee safe operation at the same time.

In essence, the approach of the researchers is to formulate the grid control problem as a deep reinforcement learning problem with hard physical constraints and then based on this to project a multi-agent algorithm onto a set of constraints characterised by the physics of the distribution system.

With this, the proposed method can achieve the optimal control of the distribution system in a decentralised manner without real-time communication while guaranteeing the physical constraints of the system all the time. As such, it is thus flexible for scalability and practical deployment.

The research formed part of KTH’s Digital Futures Centre which collaborates with researchers from the Universities of California, Berkeley and Stockholm University.

Deep reinforcement learning combines deep learning and reinforcement learning and has been developed for application in complex, unpredictable systems.

The first radio site successfully started operation at E.DIS north of Berlin in late 2023, with the first use case for smart metering.

With this E.DIS is no longer dependent on the availability of public mobile networks and intends to gradually transition its smart grid applications to the 450MHz network as the buildout in Germany grows towards expected completion in 2025.

Dr Alexander Montebaur, CEO of E.DIS Netz parent group E.DIS AG in turn part of the E.ON group and Deputy Chairman of the Supervisory Board of 450connect, who played a leading role in the developments around the 450MHz network in the group, commented that E.DIS subsidiary e.discom Telekommunikation was involved in the first pilot tests of the 450MHz network.

Have you read?
450MHz network to be built out for critical infrastructure in Germany
Is Germany’s grid renewables ready?

“The introduction of the 450MHz network is an important milestone for us in order to ensure and improve communication in the energy sector in a crisis-proof manner under the constantly growing requirements such as e-mobility and the connection of numerous renewable energy plants and to drive digitalisation forward,” he said.

“We are convinced that this technology will help us to successfully meet the challenges of the energy transition.”

The 450MHz band – formerly known as the C band – has gained growing interest for military and other critical applications with characteristics such as strong signal penetration and suitability for large scale IoT applications.

While interest in the band is widespread globally, in Germany its use has been awarded to the energy and water sector backed 450connect, an organisations with equal shareholdings by Alliander, E.ON, the 450MHz consortium of regional energy suppliers and the Utility Alliance 450 of small energy and water supply companies.

The German network is being deployed by Nokia, which also is contracted for other services including maintenance until 2040.

Other key features include a dual-use role with normal operation being monitoring and control of critical infrastructures and in times of crisis for communication and other critical control measures and being backed up with a 72-hour emergency power supply in the event of power outages and enabling information exchange for speedy service restoration.

E.DIS Netz is one of the largest regional energy grid operators in Germany and operates a power grid of around 79,000km in Brandenburg and Mecklenburg-Western Pomerania.

Understanding that the energy market is complex and costly due to many stakeholders, Nikolopoulos notes that artificial intelligence is the key to enabling a green transition for all stakeholders.

“Artificial intelligence together with machine learning, and advanced algorithms, come into play to simplify and orchestrate all these stakeholders towards a common goal.”

He adds that AI will accelerate the transition towards a green sustainable goal.

Avokado Energy AI goes beyond conventional energy efficiency offerings by providing a comprehensive portfolio of AI offerings that accelerate the green energy transition of cities, businesses, and households.

It combines key Energy AI ingredients, such as Machine Learning for Energy, Geolocation AI and Generative AI, into ready-to-run Energy AI offerings for energy optimisation.

Key offerings include:

• AVOS™, a universal Operating System inside energy storage batteries
• Avokado AI™, the Energy API suite that enables flexibility in markets
• AVOX™, the Digital Experience platform that combines Energy AI, Location AI and Internet of Energy

Avokado offerings use patented proprietary ML models and scientific algorithms.

Watch the full video interview below with Vassilis Nikolopoulos, co-founder and CTO of Avokado.

This interview was filmed in November 2023 at Enlit Europe in Paris, France.

You might be interested in:
Mytilineos: Decision-making will define utilities of the future

Generative AI appears to be attracting as much interest in the energy sector as it is concerned.

New data from IBM, unveiled at DISTRIBUTECH International, indicate that almost three-quarters of energy and utility companies surveyed have implemented or are exploring using AI in their operations.

Moreover, in an earlier survey two-thirds of energy and resource CEOs felt they are more likely than their global peers to expect to realise value in the next three years from generative AI and automation.

However, an almost similar percentage expressed concerns about the sources of data used in generative AI.

Have you read?
Siemens brings generative AI to predictive maintenance
The EU Projects Zone Podcast: Using AI to boost the grid and renewables

As the latest iteration of AI, generative AI is attracting much interest in the energy sector, as elsewhere, with tentative steps being taken as utilities investigate use cases where it can add value.

Itron integrates Microsoft Azure OpenAI

So far few energy solution providers have incorporated generative AI into their offerings and among the frontrunners is Itron, which ahead of DISTRIBUTECH 2024 announced what should prove a significant innovation for the sector with its integration of the Microsoft Azure OpenAI service.

Initially, the integration of the OpenAI service – which is based on the same model as ChatGPT – is with the Itron Enterprise Edition Meter Data Management system, distributed intelligence applications and Itron’s cloud-based DataHub platform, which is intended as the common access point for all data from the company’s portfolio.

This includes data created by Itron as well as that from third-party DI applications, such as load disaggregation, transformer connectivity and loading data.

With the OpenAI solution users should be enabled to get answers to questions, perform tasks, access data across the MDM and on the DataHub and for example use plain language queries to generate charts and reports as well as receive suggestions and feedback to improve data quality, accuracy and analysis.

“Through this collaboration [with Microsoft], we will enable utilities and cities to leverage the power of generative AI to boost efficiency, unlock creativity and enhance data management,” said Don Reeves, Senior Vice President of Outcomes at Itron.

IBM’s watsonx governance

While IBM’s watsonx generative AI and data platform for utilities and other enterprises was announced in May 2023, the latest addition to it is the governance toolkit that is designed to allow users to direct, manage and monitor their AI.

In particular, it is aimed to strengthen a company’s ability to detect and mitigate risks, manage changing regulatory requirements and address ethical concerns for both generative AI and machine learning models.

Casey Werth, IBM Global Energy Industry General Manager, says that as energy and utility CEOs manage their ongoing transformation efforts, they can also capitalise on the opportunities of generative AI and foundation models.

“In doing so they need to remember to focus on their own data, how it is gathered, accessed and used within their workflows along with the governance that should be baked into their tools and processes.”

i-DE is testing the technology on its distribution network in Vizcaya province near Bilbao in the Basque region of Spain, where Iberdrola is headquartered, throughout 2024.

If the trial’s outcome shows improvement in i-DE’s processes, including supporting its vegetation management strategy, enhancing network reliability and aiding wildfire prevention, the technology could be further rolled across the company’s network areas.

The LiveEO Treeline satellite software solution is designed to improve vegetation risk assessments, including modelling and predicting vegetation growth as well auditing previous work.

Have you read?
Space data increasingly important for smart grid – EUSPA
Harnessing the power of the EU’s Space Programme for renewable energy

The AI-based package is designed to identify and evaluate all forms of vegetation risks based on satellite data that is processed on a near real-time basis, to enable identification and response to emerging risks as they occur.

LiveEO, regularly named among the top 100 geospatial companies, states its Treeline solution can deliver results including a 15% reduction in vegetation-related outages, a 20% reduction in contractor cost per km and a one-year return on investment.

Other utilities that have deployed the solution include Iberdrola subsidiary Avangrid, Dominion Energy and Liberty Utilities in the US and E.DIS in Germany.

Data from earth observation satellites is becoming an increasingly important element of utility datasets, with vegetation management being a key use case and others including planning and design of new renewables projects, while other space-based data is available for positioning and timing use cases.

Graphene is often described as the ‘wonder material’ and it has a name for it but that is for applications such as energy storage.

But another candidate for the moniker is the less high-tech sounding perovskite that is expected to bring the next step change for solar photovoltaics, with new levels of efficiency and cost-effectiveness.

Perovskite, which is named after the Russian mineralogist Lev Perovski following its discovery in Russia’s Ural Mountains in 1839, is a naturally occurring mineral of calcium titanium oxide (CaTiO3).

Have you read?
Tech Talk | Space-based solar energy advances
Harnessing the power of the EU’s Space Programme for renewable energy

Despite being so long known it is only in this century that perovskites, i.e. not only perovskite itself but also other materials with a similar chemical structure that occur both naturally and can be synthesised in the lab, have been found to have a range of unusual physical properties such as superconductivity and ferroelectricity.

This makes them suitable for a range of applications, of which solar cells have emerged as the most prominent, with the potential to offer a low-cost, high-efficiency product – around at least 20% more than that of traditional silicon cells – that could boost the global renewables revolution.

But that potential has also come with challenges, in particular the stability of perovskites to the day-to-day environmental factors to which they must be subject, such as moisture, light and temperature.

No surprise then that the development of perovskites has seen, and is seeing, considerable investment and research interest along with the entry of new startups with the prospect of a major market opportunity.

Commercialising perovskite solar cells

Though they have yet to become fully commercialised, that day is not far off with Oxford PV, a spin-off from the University of Oxford in the UK, at the forefront after over a decade of developing the technology.

Oxford PV, founded in 2010 to advance solar PV but only latterly focussing exclusively on perovskites has pioneered the ‘tandem cell’ approach in which perovskite is added on top of conventional silicon solar cells to enhance their performance while maintaining the standard cell footprint.

In May 2023 Oxford PV recorded a record 28.6% cell conversion efficiency and in January 2024 a record panel efficiency of 25% compared with the averages for standard silicon cells and panels around 22 to 23%.

Moreover, Oxford PV’s theoretical maximum efficiency for its tandem cell approach is more than 40% compared with less than 30% for the standard cells.

“This new world record is a crucial milestone for Oxford PV, proving that our tandem solar cells can deliver record-breaking performance when assembled into solar panels,” said David Ward, CEO of Oxford PV, commenting in the January announcement that it is a first step in what should be a “transformative 2024”.

While R&D is continuing to improve the efficiency of the technology with a roadmap to go well beyond 30%, Oxford PV has reported starting production of its tandem cells at its Brandenburg-an-der-Havel site near Berlin in Germany – an acquisition of a former production site from Bosch Solar.

These are then expected to start coming to the market later in 2024, not directly but through their integration into modules of manufacturers in the market.

At the same time, Oxford PV is searching for a new high-volume manufacturing site with a particular eye on the US, where a subsidiary has been registered.

Perovskites in space

Just as perovskites are expected to become the solar PV product of choice for the next generation rooftop and utility-scale deployments, so too they are being eyed for use in space as an alternative to the go-to gallium arsenide cells.

Solar PV is essential in space for providing on-board power to orbiting satellites and for example the International Space Station. Gallium arsenide cells have become the technology of choice for their high absorption but more importantly, their ability to withstand the harsh space environment.

However, the main challenge with their use is the manufacturing costs primarily resulting from the scarcity of gallium and the more complex manufacturing process.

That is where perovskites are expected to have the potential to come in, because of their simpler manufacturing. Another key benefit is their versatility for diverse applications, from lightweight to bendable solar panels – a key factor for the proposed kilometre-scale satellites proposed to deliver solar energy to the Earth from space.

An understanding of the behaviour of perovskites in space is still ongoing, however.

In the Caltech space-based solar demonstrator which ran for most of 2023, the perovskite cells were found to exhibit marked variability in performance, whereas the low cost manufactured gallium arsenide cells had consistently performed well overall.

An earlier 10-month demonstration on the International Space Station also revealed some unusual properties about their absorption characteristics with varying temperature, with both a ‘self healing’ quality and enhanced light absorption that could make them particularly suitable for long-duration missions.

“A lot of people doubted that these materials could ever be strong enough to deal with the harsh environment of space,” said NASA research engineer Dr Lyndsey McMillon-Brown announcing the findings in May 2023, adding: “Not only do they survive, but in some ways, they thrived.”

With space technology developments often spinning off to Earth-based applications, this is a space to also keep watching.

And if you are involved in the development of perovskites, be sure to keep us updated with your findings.

Jonathan Spencer Jones

Specialist writer
Smart Energy International

Follow me on Linkedin

The study, Online Detection of Winding Deformations in Large Power Transformers, aims to validate a detector prototype that can digitally and continuously monitor transformer voltage and current.

Already proven effective in a university setting, the transformer monitoring technique has been validated by computer simulation and bench testing on small transformers.

It will now be tested in the Power Authority’s Advanced Grid Innovations Laboratory for Energy (AGILe), which helps develop new technologies and demonstrate new solutions for energy systems.

If the NYPA-NYU project is successful, future phases could focus on field demonstration and commercialisation.

Transformer monitoring

AGILe simulates portions of New York State’s transmission grid and tests the impact of technologies and systems such as DERs, EVs, energy storage, cybersecurity, sensors and automation. The study will build 3D models for large power transformers and simulate deformations of winding disks.

According to the NYPA, the idea behind the detector is to continuously monitor online the voltage and currents of the transformer, and accurately calculate the leakage impedance of the transformer based on those measurements.

The proposed platform will then send an alarm to the operator when the transformer leakage reactance has changed more than the recommended 3% by Institute of Electrical and Electronics Engineers (IEEE) standards. This enables early detection of deformation in transformer windings due to forces and stresses from the short circuit events.

Normally, transformers need to be taken out of service for a Frequency Response Analysis (FRA) test to be performed. The proposed winding deformation detection technique would avoid disrupting the system operation, which is an expensive process.

Have you read:
Enedis instals new transformer with Paris Olympic Games on the horizon
Hitachi Energy expands German power transformer facility to address demand

If successfully implemented, this new technology would avoid the cost of taking transformers offline to perform diagnostics to detect winding deformation, saving approximately $15,000 per day as well as preventing the cost of larger equipment failures that can cost up to $1.5 million per incident.

“Large power transformers are the backbone of electricity systems, designed to operate for decades,” said Francisco de Leon, NYU Tandon professor of electrical and computer engineering and member of NYU Tandon Power Lab.

“But unchecked accumulated mechanical deformations triggered by short circuits elsewhere in the system cause expensive repairs, lengthy downtime and even fire hazards. This collaboration with NYPA continues NYU Tandon Power Lab’s tradition of working in real world applications, in this case by creating technological safeguards to help identify when transformers need critical maintenance.”

NYSERDA-supported

The research is being supported by a nearly $190,000 grant from the New York State Energy Research and Development Authority (NYSERDA).

NYSERDA’s Electric Power Transmission and Distribution Future Grid Challenge programme supported the project with funding from the Clean Energy Fund.

Projects awarded under this initiative help establish a pathway for products and services to gain market entry by addressing existing technical and economic barriers within a specific challenge area associated with creating a high-performing, future grid.

Doreen M. Harris, president and CEO of NYSERDA said, “Modernising the state’s electric grid infrastructure is essential to ensuring the necessary capacity and transmission capabilities for continued reliability and resiliency.

“NYSERDA is pleased to support our sister agency in testing and advancing technology that can proactively identify potential issues with transformer operation without incurring costly maintenance outages as we transition to a dynamically managed zero-emission electric grid for New York State.”

The NYPA is the largest state public power organisation in the US, operating 16 generating facilities and more than 1,400 circuit miles of transmission lines.

More than 80% of the electricity NYPA produces is clean renewable hydropower. NYPA finances its operations with revenues earned in large part through sales of electricity.

The new robot – known as EXTRM MK4.1 – has been developed by tech company Ross Robotics and is being used in electricity high-voltage converter stations to help monitor and inspect electrical components, identifying any faults or future maintenance requirements.

The roll-out of the robot follows on from a successful two-week trial at SSEN Transmission’s Noss Head Switching Station in Wick in 2023, which allowed project teams to run a series of tests and programmes for the new robot.  The robot’s new home in SSEN Transmission’s HVDC converter station in Blackhillock, near Keith, marks the first time such technology has been used on the electricity transmission network in Scotland.

HVDC converter stations operate at an extremely high voltage level of electricity, meaning service personnel cannot access many of the electrical environments when energised and in operation.

At present, SSEN Transmission’s HVDC converter stations are monitored using remote systems and static CCTV cameras to check for any issues, however, they do not provide full visibility of the electrical equipment and its condition.   

Instead, scheduled planned outages are put in place where the systems are shut down and isolated to allow engineers to conduct close inspections of the electrical components.

Despite the high reliability of HVDC stations, unplanned outages are possible which can cause disruption across the transmission network in the north of Scotland, and it is hoped that the robot can help mitigate the risk of such disruptions occurring.

Have you read:
Elia deploys first autonomous robot for HVDC substation inspection
Robot dog Spot to transform into Sparky with AI enhancements

EXTRM MK4.1

Ross Robotics’ EXTRM MK4.1 autonomous robot is built to withstand the extreme high-voltage electricity systems and is fitted with a series of cameras and sensors including state-of-the-art visual imaging, thermal imaging and acoustic imaging to find abnormalities which enable valuable data to be collected.  The data is collated to allow the asset operators to make informed decisions in relation to any future maintenance.

The autonomous robot has four all-terrain wheels and weighs around 25kg, meaning it is small enough to roam the high-voltage halls unassisted while ensuring it gathers key data. Once it has finished its pre-programmed route of the building, the robot returns to its charging port in the hall.

The project is part of SSEN Transmission’s Network Innovation Allowance (NIA) AIM High project, which aims to find innovative ways to help ensure the transmission network in the north of Scotland continues to operate safely and efficiently.

Deploying the new EXTRM MK4.1 robot into the Blackhillock HVDC converter station follows on from months of close working with teams and engineers from SSEN Transmission and Ross Robotics.

Tania Shaw, SSEN Transmission Innovation project manager, said in a release:

“Deploying the EXTRM MK4.1 means we can check the condition of our electrical equipment and assets in real-time in the HVDC halls, meaning we can establish and identify any areas which require maintenance quickly to include within planned outages.

“Engineers cannot enter the halls when they are energised, and any innovation which can help us mitigate against unplanned outages, efficiently monitor our equipment in real-time while is a huge advantage to the north of Scotland transmission network.”

Added Dominic Cusk, managing director of Ross Robotics: “We’re very excited to be part of this important project with SSEN Transmission. The deployment of our robot at Blackhillock HVDC Converter hall will deliver a new level of monitoring for this type of critical asset and the data captured will support the transition towards predictive maintenance, with all the operational, availability and commercial benefits it brings.” 

GridOS Data Fabric, claimed a first for grid orchestration, uses data federation to access the decentralised data, enabling multiple datasets to be combined and then virtualised to create a centralised view across the grid ecosystem, from transmission to distribution and the edge and across information technology and operational technology applications.

With this grid operators should be able to discover, govern and utilise large volumes of highly distributed data from multiple sources for improved and more rapid decision making while orchestrating the grid in real time.

“Energy data plays a key role in delivering a more efficient grid. Utilities will need to connect energy data from across the grid ecosystem to effectively automate grid operations, orchestrating more intelligent, secure and resilient grid that is ready and built for future electrification needs,” says Mahesh Sudhakaran, General Manager at GE Vernova’s Grid Software business.

Have you read?
How AI and advanced analytics will be key for the grid of tomorrow
‘We need to think smart and fast’ to future-proof the grid

“By leveraging energy data, AI and machine learning powered technologies, utilities can move at speed to meet demand while addressing renewables management and electrification challenges.”

The GridOS strategy is centred around a modular, composable, data-driven software portfolio designed to orchestrate a more sustainable energy grid and help utilities keep pace with the energy transition, a GE Vernova statement says.

The announcement of GridOS Data Fabric, which follows GE Vernova’s acquisition of Greenbird Integration Technology and is the first major addition since the launch of GridOS a year ago, also includes GridOS Connect.

GridOS Connect is an energy data integration engine as a key component for the federated grid data fabric that feeds continuously updated data sets into the system – information that traditionally has been difficult for utilities to compile and analyse.

Itron collaboration

With the release, GE Vernova also has announced a collaboration with Itron, which intends to leverage GridOS Data Fabric to connect grid operations and grid edge data from sources such as residential solar, electric vehicles and more.

Don Reeves, Senior Vice President of Outcomes at Itron, says that a key component of the GridOS Data Fabric software is its ability to connect and integrate data to make more accurate real-time decisions to enable a reliable and resilient grid.

“The data to be exchanged with Itron’s grid edge intelligence solutions can provide new insights to promote grid stability and to train and power AI and machine learning applications that help automate key aspects of the grid operation.”

The recommendations, based on published sources and the practical experiences of CurrENT members, are aimed to provide guidance to overcome a key challenge experienced by DSOs of the limited resources to consider the specifics of technologies and their deployment and related issues such as standards, regulations and business models.

Alongside general deployment issues including network studies, procurement and tenders, the cost benefit analysis and installation and testing, specific technologies considered – categorised as ‘grid optimising technologies’ – are advanced conductors, digital twin technologies, dynamic line rating, modular power flow control and monitoring sensors.

These technologies are innovative in maximising the use of the electricity grid and are mature and commercially available but are not yet standardised for many companies.

Have you read?
How the biggest US grid operator could add 6.6GW without rebuilding lines
Iberdrola’s Elena León Muñoz reveals how to break the grid bottleneck

“We know that an extraordinary amount of renewable energy will need to be connected to the DSO grid in the coming decades’ says Layla Sawyer, secretary general of CurrENT,

“Yet it is still a big challenge for many DSOs to be aware and make use of the full range of new technologies being developed. In part, this is because the technical assurance and procurement of new technologies is done differently at the DSO level than at the TSO level, and there is less manpower available for these kinds of studies.”

The paper Recommendations for the deployment of DSO projects, finds that the application of these grid technologies to the distribution network and its operators can ensure faster, lower cost, more flexible, beneficial and seamlessly integrated solutions.

Digitalisation of the energy system is targeted and essential, with universally recognised major benefits to stakeholders and network operators alike.

“It is advantageous not to wait, but start the evaluation through to deployment process to avail of these benefits early,” states the document.

Thus for example a recommendation is for the use of trial projects or limited use first deployments of the technologies to be eliminated in favour of first deployments into full active use in the network as the benefits should far outweigh any risks of stranding assets.

Another is that the technologies cannot only be applied standalone and should be considered in combination, with guidance from suppliers to address the individual use case.

Further recommendations include minimising technical assurance to only the areas of a new technology where the technology performance is truly essential and the introduction by regulators of incentives for innovation.

CurrENT also reports presently advocating for a ‘distribution technopedia’ at national and/or European level – a concept implemented by ENTSO-E – to provide DSOs with a list of commercial ready technologies in order to minimise their effort in identifying and learning how to appraise the often new alternatives.

With the technologies continually evolving CurrENT also anticipates providing future updates to the recommendations and potentially expanding the technologies reviewed.

The roadmap is built around two pillars that are considered key, i.e. developing a power system fit for a carbon-neutral Europe while at the same time managing a secure and efficient power system for the region.

Or put another way this corresponds to ‘preparing the future’ while ‘managing the present’, to which the TSOs commit, stating: “This will require the continuous deployment of operational excellence, implementing efficient and operational market mechanisms, increasing regional coordination, and making the best use of information and communication technologies.”

Developing the power system

Starting with the power system for a carbon-neutral Europe pillar, the roadmap identifies five main areas where change is necessary to deliver on that.

Have you read?
Europe’s offshore network development plans set out
Energy Transitions Podcast: Redefining resilience for a modern power system

● Energy system flexibility: An accurate assessment of flexibility needs and potential is needed at national and European levels, as is a comprehensive ‘system of systems’ approach involving TSOs, DSOs and other sectors such as hydrogen to coordinate the deployment and use of the most efficient flexibility resources.

● Operating future grids: In a ‘system of systems’ approach, new approaches are needed, including enhanced real-time grid visibility, forecasting capabilities and controllability. Automation and AI will support operators in handling grid complexity while the electrification of end uses and sector coupling will require new risk-based methodologies, cybersecurity and new concepts for the coordination of operators.

● Infrastructure and investments: To accelerate the delivery of grid infrastructure both onshore and offshore coordinated planning will be required across the ‘system of systems’, as will massive investments in the transmission networks. Other requirements include reforming regulatory frameworks, ensuring fit-for-purpose financing mechanisms, developing seamless supply chains to overcome bottlenecks and enhancing engagement with local communities.

● Market design: Electricity markets will need to evolve, with strong long-term signals to enable investments in renewables, flexibility and grids, short-term markets to encourage efficient resource use and carbon-neutral flexibility and with incentives aligned with system capabilities and security, while other important aspects are transparency tools for a carbon-neutral system and potential changes to transmission tariff principles.

● Innovation development and uptake: While the TSOs are making breakthroughs in new strategic technologies by implementing ENTSO-E’s RD&I roadmap and the deployment of solutions, new measures regarding the adaptation of regulatory frameworks, the de-risking of first-of-a-kind projects, demonstrators and corresponding stakeholder engagement should be pursued.

Managing the power system

In the secure and efficient power system pillar, four main areas are identified in which the TSOs, with support and coordination by ENTSO-E, are playing multiple roles.

● Operational excellence, with support to TSOs to deliver efficient, resilient and secure system operation.

● Market development and operation, with the implementation of market mechanisms to efficiently operate the system and optimise social welfare for consumers.

● Regional coordination of national and regional actors.

● Information and communication technology, with support for the design and development of the ICT tools to manage the power system.

The roadmap document concludes that while planning and delivering the future power system, Europe needs to continue to rely on a strong, secure and efficient electricity supply.

“To ensure the balance between these two dimensions, ENTSO-E will need to manage intertwined and sometimes challenging approaches or activities while fulfilling these dual strategic goals. The strategic roadmap will focus its activities, resources and the stakeholder engagement of ENTSO-E on [these] twofold objectives.”

According to the US-based research institute and consultancy, GETs, which are hardware and software solutions deployed within the transmission system, would help increase the capacity, flexibility and efficiency of the current grid.

The study, GETting Interconnected in PJM, finds that although GETs – including dynamic line ratings (DLRs), advanced power flow controls (PFCs) and topology optimisation (TO) – are becoming more widely studied and deployed in the US and internationally, they are not yet routinely considered in planning paradigms such as grid operators’ interconnection studies.

By freeing up additional transmission capacity for clean energy, 95 GETs projects considered in RMI’s analysis would generate approximately $1 billion in production cost savings per year for PJM, a regional transmission organisation (RTO).

“With growing demand for electricity to power our lives and an influx of clean energy projects under development, the US grid needs to expand, fast,” said Katie Siegner, an electric sector expert at RMI.

“Grid-enhancing technologies can be deployed in a matter of months and offer a multi-faceted solution – they unlock greater efficiency on the grid, keep electricity rates down, and enhance reliability throughout the energy transition.”

Interconnecting 6.6GW of projects by 2027

According to RMI’s study, GETs could facilitate the interconnection of 6.6GW of new wind, solar and storage generation across Illinois, Indiana, Ohio, Pennsylvania and Virginia that otherwise might have required prohibitively high-cost or time-consuming network upgrades.

For comparison, they add that in these five states, just over 2GW was connected to PJM’s grid in 2023.

Additionally, they state, that evaluating and deploying GETs as network upgrades would allow for faster and cheaper integration of large volumes of new generation. Traditional network upgrade costs have increased significantly in recent years — in PJM and elsewhere — as less and less hosting capacity is available on regional grids and more expensive upgrades are required.

RMI states in the study that transmission owners are now commonly identifying reconductoring or rebuilding affected transmission lines as such upgrades to address overloads triggered by interconnecting projects. However, GETs costs range from $272 to $523 million less than these types of network upgrades.

In addition to the cost savings, GETs significantly reduce the time required to connect new generation; reconductoring or rebuilding lines can take up to three years or more, adds RMI, while transmission owners can deploy GETs in months.

RMI adds that their analysis revealed significant savings that would flow to electricity consumers in the PJM region.

Specifically, within their production cost modelling analysis, RMI found that GETs-enabled new generators and reduced congestion would reduce energy production costs by just under $1 billion in 2027, ramping up to over $1 billion in savings per year by 2030.

Driven by lower OPEX of new renewable and storage resources, as well as the broader congestion relief that GETs provide, additional lower-cost generation would thus be enabled on PJM’s grid.

Recommendations

RMI comments in the study that, to further realise the potential of GETs, PJM should institute robust evaluation of the technologies across its interconnection and transmission planning practices and ensure its staff has the requisite training and modelling tools.

Transmission owners, they add, should build their internal capacity on GETs through studies and deployments, developers should propose and support GETs evaluation as network upgrades and state regulators should provide oversight and guidance to spur GETs adoption by their jurisdictional utilities.

Additionally, RMI states that the Federal Energy Regulatory Commission (FERC) should take additional steps to provide a comprehensive national regulatory framework that supports GETs adoption.

Have you read:
Ofgem policy to push ‘zombie projects’ out of grid connection queue
Action plan for Europe’s grids launched

Filings for GETs

According to the WATT (Working for Advanced Transmission Technologies) Coalition, RMI’s findings follow a filing from the PJM Interconnection to FERC on January 17, 2024, emphasising the value of DLR deployments during Winter Storm Elliot:

“The DLR ratings on this line during the storm proved higher than the ambient adjusted ratings PJM would have operated to otherwise. Had PJM not had the higher dynamic line ratings, PJM would have had to take action to re-dispatch the system to maintain reliability. Such action would have been very difficult under the critical operating conditions.”

PJM reaffirmed their support, states WATT, for a requirement for utilities to deploy DLR on all thermally constrained lines that lead to significant congestion and noted the need for application guides to facilitate utility adoption.

PPL Electric Utilities followed with their own filing to FERC on February 9, 2024, reporting that their DLR deployments have operated successfully since deployment – in one case eliminating congestion which was $12 million in summer 2022, and reducing congestion on another line from approximately $66 million to $1.6 million.

According to WATT, PPL Electric Utilities reported that they plan to install DLR on five more lines by the end of June this year.

Commenting in a release, Julia Selker, executive director of the WATT Coalition, said:

“It is very encouraging to see a system operator and utility sharing new information with FERC about the value of Dynamic Line Ratings. These comments show the substantial cost-saving and reliability benefits of DLR.

“The RMI study reminds us that it’s crucial to integrate all Grid Enhancing Technologies into utility practices to achieve the lowest-cost electricity system.

“I look forward to seeing compliance filings this spring in response to FERC’s Order 2023 on generator interconnection, which requires advanced power flow control and topology optimisation to be studied in interconnection processes and left DLR to the operator’s discretion.”

PJM Interconnection coordinates the movement of wholesale electricity in all or parts of Delaware, Illinois, Indiana, Kentucky, Maryland, Michigan, New Jersey, North Carolina, Ohio, Pennsylvania, Tennessee, Virginia, West Virginia and the District of Columbia.

GETting interconnected was funded by Amazon and based on analysis conducted by Quanta Technologies.

Sentient Energy announced the solution, which they say is specifically designed to identify ground faults using autonomous line sensors. The feature significantly improves the accuracy of fault location, setting a new standard in outage management procedures, claims the Texas-based company, which develops grid solutions and services.

The new capability, announced as a major upgrade to the tech company’s Ample Analytics Platform, was initially developed with Alabama Power and implemented in a pilot programme.

Alabama Power has deployed over 2,000 intelligent line sensors and integrated sensor data into its Advanced Distribution Management System (ADMS) to refine distance-to-fault calculations.

By strategically placing three autonomous sensors at a location and utilising the Ample platform to create a virtual three-phase device, Alabama Power can now accurately identify ground faults, exceeding its target accuracy of 85%, says Sentient in a release. This has enabled Alabama Power to improve its response and restoration times.

Also of interest:
Grid resilience lessons from the frontline of climate change
US lab testing new model for investigating grid faults

“Until now, line sensing technology was unable to accurately identify ground faults, creating potential errors in distance-to-fault calculations that depended on fault data. Our successful pilot programme with Alabama Power is a perfect example of how advanced analytics and sensor data improve the reliability and safety of power distribution,” stated Bob Karschnia, CEO of Sentient Energy.

“We are thrilled with the success of this pilot and look forward to implementing these technologies on a broader scale to continue improving the reliability and safety of our power grids.”

According to Sentient Energy, their Ample Analytics Platform predicts and prevents outages, detects faults, reports fault magnitudes and now distinguishes ground faults.

This enhanced fault detection and location capability is a vital component of the fault location, isolation, and service restoration (FLISR) application, they add, providing a swift solution that reduces System Average Interruption Duration Index (SAIDI) and Customer Minutes Interrupted (CMI), improving customer experience during outages.

Alabama Power, a subsidiary of Atlanta-based Southern Company, manages over 83,000 miles (133,575.55km) of power lines, providing electricity to 1.5 million customers across the state.

With the phase 2 plan, AES Ohio is proposing to continue the modernisation of its grid, which has been underway in the first phase, with a focus on the ongoing rollout of smart technologies to improve system stability and performance and the backbone communication capabilities.

At the foundation of the smart grid is smart meters and AES Ohio expects to have deployed these to 95% of customers by June 2025.

The smart grid phase 2 plan has three principal components – automation of distribution operations, advanced grid intelligence and telecommunications and cybersecurity.

Have you read?
Managing power grid complexity: The 5 biggest priorities for utilities in 2024
European energy bosses join IEA’s call for grid action

“We have a commitment to our customers and community to ensure the reliability and resiliency of our grid by making needed modernisation investments,” says Ken Zagzebski, President and CEO of AES Utilities.

“With the successful deployment of smart meters and mid-line reclosers in phase 1, customers are benefitting from fewer outages and decreased restoration times. The Smart Grid 2 plan is a critical step to an integrated grid and creating meaningful capability improvements that add value to our customers.”

The plan filings point to a number of challenges and opportunities that have driven the phase 2 vision.

These include fundamental changes in the energy industry that have created unprecedented strain on the nation’s power grid such as the rise of decarbonisation, the installation of utility-scale storage and renewables projects and the rapid adoption of customer-owned distributed resources.

In addition localised changes including more volatile weather, increasing adoption of EVs and growth from new industrial, commercial and residential customers have further increased the need for grid modernisation.

To achieve improved operational insights, AES Ohio is proposing investments in areas including dynamic network model optimisation, distributed energy resource management, the distribution performance monitoring and analytics centre and grid edge intelligence.

Regarding grid technology deployment, AES plans to continue to make investments in a self-healing grid, with a particular focus on grid automation, volt/var optimisation/conservation voltage reduction, an advanced distribution management system and field crew management.

To support the connectivity needs of the new technologies, such as the new substation and distribution devices, upgrades and expansion of the existing communication networks also are proposed, along with a strengthening of cybersecurity measures and optimising advanced threat readiness.

Positive benefits

In the filing, AES Ohio estimates a 3.6 to 1 NPV benefits-to-cost ratio of the investments over 20 years, with most indirect in the form of reduced CO2 emissions and economic impact but almost a third direct, including avoided or deferred capital spend, operations and maintenance and energy and demand savings and enhanced reliability.

AES Ohio has requested an order on the plan in Q1 of 2025 to enable smooth transition between the two phases but also in the anticipation of maintaining on-site the same contractors working on the phase 1 investments.

AES Ohio serves more than 527,000 customer accounts in west central Ohio.

The proposition is to use LiDAR data along with other geospatial data and imagery to map the networks with a high degree of accuracy down to the level of individual infrastructures including poles and towers and the conductors between them to create a digital twin.

This is then proposed to be used to identify and evaluate risks across the networks, which span some 7,500km, particularly in the face of increasingly more extreme weather events and the growing risk of such weather-related power outages.

“This partnership marks a pivotal moment in climate-proofing our energy supply. Preparing for more violent weather events in advance will be central to keeping communities safe and connected as the climate crisis escalates,” says Taco Engelaar, Senior Vice President of Sydney-headquartered Neara.

Have you read?
TwinEU to create European electricity grid digital twin
Using digitalisation to achieve net zero infrastructure in power and renewables

“Proactively managing the hazards that cause distress for families and businesses, like falling trees, is the first step on an exciting road to strengthening our infrastructure. It’s extremely encouraging to see utilities like ESB Networks leading the charge by innovating and exploring new ways of assessing and predicting climate-related risks.”

Neara’s technology draws on AI and digital modelling combining multiple datasets to create digital twins.

The company states that its digital models take around two weeks to provide detailed insights, compared to an average of three to four months for manual reporting, enabling much faster identification and addressing of risks.

ESB Networks is using the platform to address one of the central causes of power outages during extreme weather, namely falling trees and vegetation near power lines.

With the digital twin ESB Networks can identify high-risk areas where these hazards might cause power lines to fail enabling vegetation management activities to be prioritised accordingly.

In the future, ESB Networks is set to use the technology to optimise the use of existing infrastructure by identifying latent capacity where more renewable energy could be run.

It also could be used for other use cases including enhancing network design and construction and automating further management processes to optimise performance and strengthen vital infrastructure.

Indeed the title of the session, the Energy Innovation Forum, gives it away.

But what is innovation? I and daresay many others tend to think first of advances in technologies, but ultimately it is much more than that and there is the need for innovation across multiple fronts – policy and funding to name some, in addition to technology – to be able to achieve the various climate targets as set out to culminate in net zero by 2050.

Just as the social sciences started becoming part of science policy in the 1990s so too they are now becoming part of innovation with more than one speaker highlighting the need for the human aspect to be placed at its centre.

Have you read?
Statnett to tap CERN for grid innovation
New Managing Director of Siemens Energy France shares her vision for the energy transition

“It is important to recognise innovation in all its forms. It’s exciting to hear about some of the key technological breakthroughs but that is just one part of the equation and it’s good and necessary but not enough,” said David Turk, US Deputy Secretary of Energy, in his summing up.

“The human piece is incredibly important throughout … It’s not just human behaviour for the technologies that are consumer-facing but it has to work for the businesses, the incumbents, the other parts of the system as well,” he continued.

“We should be working for the betterment of fellow citizens around the world,” he said.

Another aspect of innovation that he highlighted as a takeaway from the discussions is the need to consider the full innovation cycle with the need to move from pilot to scale up but with what appears today a limited focus on the demonstration phase.

Turk suggested that AI and machine learning could play a role in shrinking the innovation cycle.

A third is “connecting the dots” between all the parties in the sector and the fourth related to this is knowledge sharing on at least a real-time basis and the tracking of progress.

“The IEA’s tracking of clean energy progress last year found that only three of the 50 technologies and sectors were on target and those are impressive but we need that across the board.”

Innovation looking ahead

Part of the focus of the meeting was to get input on areas that the IEA should focus on to advance energy innovation in the years ahead.

In her summing up, Amanda Wilson, Director-General of the Office of R&D at National Resources Canada and chair of the IEA’s energy research committee, pointed to technology priorities that arose in the discussions including needs around products and software such as AI, batteries for storage and electrolysis for hydrogen and large scale processes including industry decarbonisation, carbon capture and storage and nuclear.

The needs of emerging economies also arose as a key topic, particularly around energy access, clean cooking and digital skills.

Then on top of those inputs, numerous more were from participants in an hour long session with the general sentiment among the specifics being the need for the IEA to draw on its expertise and for example its tracking and analytical skills to address all the facets of innovation and to advise on and support the acceleration of the energy transition.

Technology advisory body

A notable aspect of the IEA’s work over the years is the broadening of its scope as reflected in the breadth of its reports, covering countries and technologies and not least the net zero pathway that forms the baseline for its future work.

In their communique from the meeting, and taking into account the input from participants, the ministers said they reiterate their commitment to support energy RD&D to reach the 2050 objectives, including through the IEA’s technology collaboration programmes.

The ministers also indicated support for further discussion towards the establishment of a technology advisory body of innovators, investors and industry and to foster synergies between international initiatives such as the IEA TCPs – of which the International Smart Grid Action Network is one – the Clean Energy Ministerial and Mission Innovation.

As these occur we will continue to report on but in the meantime let us know the innovations you are working on.

Jonathan Spencer Jones

Specialist writer
Smart Energy International

Follow me on Linkedin

Avangrid, which owns and operates eight electric and natural gas utilities, serving more than 3.3 million customers in New York and New England, said in a release that the project will deploy the robot dog to complete visual and thermal inspections at two substations of its Connecticut subsidiary, United Illuminating (UI).

The project will take place at UI’s Singer and East Shore substations and test a variety of AI models, developed by Levatas, to read analogue gauges, record thermal images and detect damaged equipment.

To do so, the robot dog—nicknamed Sparky by the Avangrid team—is outfitted with a camera that has a 30 times optical zoom and an infrared camera capable of taking thermal readings to compare the transformer and breaker phases.

There is also an option to attach an acoustic sensor that can detect, locate and visualise changes in sound signatures, malfunctioning equipment and other noise anomalies in real time. The robot also has a core processor to enhance autonomous navigation and communications.

At the Singer substation, the project will test how quickly and accurately the robot can detect and read several of the substation’s analogue gauges. At East Shore substation, the project will test the robot’s ability to inspect transformers, circuit breakers and capacitor banks.

Have you read:
Spot the robotic dog sniffs out faults in National Grid’s interconnectors
High voltage birdspotting: Elia uses drones for collision prevention

Initially, the robot will be controlled by an onsite operator using a tablet, which can be used to both drive the robot and create autonomous missions. Avangrid is also working to install software that would allow for remote operation as well.

“We’re very proud to once again be among the utility industry pioneers pushing the boundaries of technology,” said Pedro Azagra, Avangrid CEO.

“Last year, we announced the establishment of an in-house team to build unique machine learning models to increase reliability. With this pilot project, we are now exploring using AI in another aspect of our business where there is great potential to bring high value to our customers and stakeholders. This type of innovation will help us be more efficient, target our investments and increase reliability for our customers.”

“It’s amazing to see this technology, which was inconceivable a few years ago, in our hands bringing value and benefits to our customers,” added Catherine Stempien, Avangrid Networks President and CEO.

“While there will be many benefits, most important is that we expect Sparky will increase the frequency of our substation inspections so that we can see how our equipment is functioning during different seasons, times of the day and energy loads. With this increased amount of data, we will have the potential to proactively identify unknown issues and trends before they cause outages that impact our customers. This is a great example of innovation and technology helping us do more.”

From Spot to Sparky

According to a spokesperson from Avangrid, Sparky improves on Spot in that it will be trained to live and operate within an energised substation environment and will be taught to identify abnormal conditions within that space.

Using machine learning algorithms, Avangrid has collaborated with Levatas to create an insulator inspection model that will use one of Sparky’s cameras to look for, identify and report insulator anomalies.

It will have the ability to digitise analogue gauges to keep track of important equipment health indicators and create alarms and notifications.

Sparky also has a thermal camera that it will use to inspect for thermal hotspots on substation equipment, giving operations personnel the opportunity to manage those issues promptly and efficiently.

The spokesperson added that, as with AI models, they expect the machine learning algorithms to improve with time, making the solution more valuable.

“The gauge reading model, for example, has been successful in flagging health indicators out of pre-defined thresholds and acceptable range. We are pleased with the results so far and are excited to continue with Sparky’s integration into our day-to-day operations and maintenance programs.

“Currently, we do not have a specific timeline for deployment of Sparky. At this time, we are focused on developing its application model, including its operational space, data management and communication protocols.”