In 2024 and beyond, explains Joseph Santamaria of AWS, the energy sector will find combining generative AI with proper upskilling to be extremely valuable.
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.
