AI Revolution Could Drive Clean Energy Future

Artificial intelligence (AI) is becoming a ubiquitous part of our lives, impacting much of what we do at work and home. AI’s growth trajectory is expected to skyrocket, with new potentials identified to help address and solve today’s challenges and tomorrow’s opportunities. AI advances have been remarkable, but so far relatively little attention has been paid to the game-changing opportunities that these technologies could bring to the energy and environment sectors.

For more than a decade, EPRI has been studying AI and its potential impacts on the ecosystem. As an independent, non-profit energy research and development (R&D) institute, we help identify innovative ways to drive an affordable, reliable, and equitable clean energy future. As I plan to tell a U.S. House Energy and Commerce Subcommittee this week, AI certainly has the potential to play a key role as part of our collective clean energy transformation.

For example, more extreme weather and climate, combined with aging infrastructure, are causing reliability concerns for power to our homes and businesses. Energy companies are already using AI for a wide variety of applications, such as automated analysis of transmission and distribution asset inspections. In recent years, the development and deployment of drones have provided energy companies with a step change in the amount of inspection data available to them for ensuring grid reliability. With drones providing more images to energy companies, some are starting to turn to AI to assist with inspection analysis.

AI can also be used for proactive management of grid assets using satellite imagery to identify dead and distressed trees that are near utility poles. This would allow crews to preemptively remove trees that are likely to fall on power lines without having to conduct manual surveys. Meanwhile, field crews are often using augmented reality for training.

Additionally, there is potential for AI to monitor and provide real-time data for electric grid management. The U.S. power grid has often been described as the most complex machine in the world due to the exponentially increasing complexity of grid-connected components in a network. As new technologies come online as energy companies continue to decarbonize—especially highly variable generation sources like solar and wind—AI can serve a role in continuing to keep the lights on by balancing demand and generation.

This load-balancing activity will become increasingly complicated as an ever-increasing number of grid-connected components are installed, and as two-way power flows into and out of houses from solar panels and battery storage devices, which are becoming commonplace. For example, during periods of high demand, energy companies could pay homeowners to utilize energy stored in their electric vehicles (EVs) to meet grid demand, as well as reduce consumption by dimming smart TVs or temporarily turning off heating, ventilation, and air conditioning (HVAC) units. Conversely, during periods of high generation and low demand, consumers could charge EVs at reduced rates and energy companies could charge grid-scale battery storage devices or ramp up high-load facilities such as hydrogen production or desalination plants to utilize excess generation. AI can help grid operators understand the data, and in turn, keep the lights on.

AI can also help with energy usage. Buildings consume nearly half of the world’s energy needs. Collaborating with various stakeholders, EPRI has been working on technologies to optimize energy management in buildings by controlling how and when HVAC and other energy-intensive systems are used based on time of day, building occupancy, cost of energy, and other factors. AI technologies offer the potential to reduce overall energy use in buildings by 20% to 40%. If these systems were implemented at scale, more than 10% of global energy usage could be reduced, having an even more dramatic effect on their carbon footprints and accelerating the clean energy transition.

Are machines going to replace people? Probably not. It’s more likely they can enhance the work we’re doing to increase economic activity. Using AI will enable computers to do what they do best (rapid, accurate calculations) and allow people to do what we do best (strategy, creative thinking, and implementation). Concerning proactive tree removal, for example, energy companies will still be required to send out crews to do the manual work, but using AI will allow the workforce to be more efficient in planning the right scope for maximum benefit, helping to keep the power on.

AI offers great promise in the energy sector’s efforts to decarbonize toward a net-zero economy. These technologies can improve the efficiency of existing assets, optimize energy usage, and reduce wasted energy. As the AI revolution continues, collaboration will be key for society to see benefits as part of a reliable, affordable, equitable clean energy future.

—Jeremy Renshaw is senior technical executive with EPRI.