Energy / Power and gas utility
Duke Energy: Automating the grid interconnection study workflow
- Company
- Duke Energy
- Country
- United States
- Adoption stage
- Limited operation
- Source published
- Date basis
- The date the source was published. It can differ from the date adoption started.
- How the source was checked
- Read the full source text
The work problem
US utilities must complete interconnection studies before new generation, storage or large loads can connect to the grid. As industry context, the AWS press release cites Lawrence Berkeley National Laboratory data showing that more than 2,000 GW of generation and storage was seeking US interconnection at the end of 2025, and that projects entering operation that year had spent a median of more than five years in the process. The same release says large load connection requests to ERCOT, the Texas grid operator, reached about 410 GW in March 2026, and that demand for studies is outpacing the number of qualified engineers. These figures describe the whole industry, not Duke Energy alone. John Pressley, who leads digital strategy and engineering at Duke Energy, said the company maintains one of the largest utility grids in the United States and that its engineers must complete a higher volume of increasingly complex studies.
Technology and data
According to the release, AWS worked closely with Duke Energy engineers to build Agentic Grid Planning on AWS, and Duke Energy contributed transmission planning expertise and ongoing feedback. The AI agents carry out study workflows using the physics-based simulation software, grid models, scripts and engineering standards that utility teams already use and trust. The simulation software performs the deterministic modelling and analysis, while the agents handle data preparation, analysis runs and workflow coordination. The work is kept as a versioned, reviewable record. Pressley said engineers lead the work and make all final engineering decisions.
Results
According to the release, Duke Energy has seen data preparation tasks go from two weeks of manual work to hours with the agents. Duke Energy aims to increase planners' capacity and improve efficiency across the interconnection process. The two companies are also working to extend these capabilities to large load planning workflows and to lay the foundation for load and generation studies. AWS says the service is available to qualified utilities and grid operators.
Limits and open questions
The source is an AWS press release and gives no figures beyond data preparation time, such as the number of studies, total study duration or accuracy. Duke Energy is automating key components of the study process first, and the scope is still being expanded.
Sources
- AWS Launches Agentic Grid Planning Program to Accelerate Interconnection Studiespress.aboutamazon.com, Accessed
Compiled from public sources. These are not results from ATF Works customers.