U.S. Department of Energy
08/16/2024 | News release | Archived content
How AI Can Help Clean Energy Meet Growing Electricity Demand
Reports across the United States highlight a rapid increase in projected electricity demand, partly driven by growth from artificial intelligence (AI) and data center energy use. This load growth is not historically unprecedented and presents an economic opportunity. In fact, DOE has more solutions and technologies available today than it did during previous decades of load growth to help meet growing demand. However, deploying these solutions in the near-term is incumbent on our ability to permit and build clean energy infrastructure.
Foundational models such as large language models (LLMs) as well as other AI models, have the potential to make substantial improvements in siting and permitting processes. Models can be fine-tuned to the relevant contexts for these processes that can be used to build tools for developers, government reviewers, and the public that can improve the design of projects, bring efficiencies to siting and permitting reviews, and improve public engagement. AI can also be a driver for innovation in clean energy and grid operations, accelerating clean energy deployment to provide a safer, cleaner, more efficient, and more secure power grid capable of meeting load growth.
In April 2024, DOE released a report outlining how AI can accelerate the development of a 100% clean electricity system. Key opportunities include:
- Improving grid planning: Utilizing high-resolution climate data sets developed by the National Renewable Energy Laboratory with advanced generative machine learning to accommodate more variable renewable generation.
- Enhancing grid resilience: AI's ability to rapidly process massive amounts of data and detect subtle patterns can assist grid operators in diagnosing and responding to (or avoiding) disruptions in electricity delivery.
- Discovering new materials: Quickly identifying new materials for clean energy technologies, such as for batteries requiring less lithium, novel solar-active materials, or improved catalysts to increase hydrogen production.
Recognizing the need to build clean energy projects at speed and scale, DOE is currently developing AI tools to improve the way such projects are sited and permitted at the Federal, state, and local levels. This includes tools to put decades of previously inaccessible environmental data in the hands of scientists and government reviewers to identify opportunities to improve community engagement, utilize data to drive better social and environmental outcomes, and accelerate decisions. By developing AI tools that assist government as well as public sector staff in environmental report reviews and permitting, subject matter experts can focus more on complex problem-solving and engaging with affected communities. This is part of the Department's recently launched voltAIc Initiative, which will allow DOE to work with leading computer scientists, organizations, academia, private sector, and other stakeholders to address the growing need for efficient siting and permitting of clean energy to address the climate crisis.
Since the voltAIc Initiative's announcement, its anchor project, PolicyAI, hosted at Pacific Northwest National Laboratory, has shown early successes. Achievements include:
- NEPATEC1.0 release: The first public, comprehensive text data setfrom all Federal Agency Environmental Impact Statements from late 2012 through 2023, that can be used by researchers and private AI companies to develop tools to improve future environmental reviews.
- Generative AI testbed: Providing a searchable database of information from thousands of past environmental reviews to testers across 13 federal agencies to expedite AI development for environmental and permitting reviews.
- Public comment sorting: Demonstrating the effectiveness of Large Language Models in sorting public comments for projects, potentially saving months of manual work. This can improve agency efficiency to allow staff to focus on comment analysis and response drafting.
Additional use cases for AI in NEPA and the permitting process can also be found in the Council on Environmental Quality's report on potential for online and digital technologies to address delays in reviews and improve public accessibility and transparency.
Beyond Federal efforts, the voltAIc Initiative aims to drive AI tool development and deployment at the state and local levels. As a large portion of clean energy infrastructure, including utility-scale wind and solar projects, electric vehicle chargers, rooftop solar and home-battery backups, heat pumps, and even most transmission lines will be sited and permitted locally. AI-powered tools can assist understaffed local permitting departments with new and unfamiliar project types.
AI can be a key technology to support clean energy innovation and deployment.