Texas team uses AI to prevent power outages

Researchers at the University of Texas at Dallas have developed an AI model that could help prevent power outages by rerouting electricity in milliseconds.

Adobe Stock

Published in Nature Communications, the study describes “self-healing grid” technology that uses AI to detect and repair outages autonomously and without human intervention. Using various scenarios in a test network, the Texas team demonstrated that their solution could automatically identify alternative routes for electricity before an outage occurs. According to the researchers, AI can reroute grid power in microseconds, while current human-controlled processes could take anywhere from minutes to hours.

“In this interdisciplinary project, by leveraging our team expertise in power systems, mathematics and machine learning, we explored how we can systematically describe various interdependencies in the distribution systems using graph abstractions,” said study co-author  Dr Yulia Gel, professor of mathematical sciences at the University of Texas.

“We then investigated how the underlying network topology, integrated into the reinforcement learning framework, can be used for more efficient outage management in the power distribution system.”

Dr. Yulia Gel, Dr. Jie Zhang and electrical engineering doctoral student Roshni Anna Jacob demonstrated that their artificial intelligence system can automatically identify alternative power routes and then transfer electricity to users within microseconds before an outage occurs. - The University of Texas at Dallas

The approach relies on reinforcement learning that makes the best decisions to achieve optimal results. If electricity is blocked due to line faults, the system can reconfigure using switches and draw power from available sources in close proximity, such as from large-scale solar panels or batteries on a university campus or business. After focusing on preventing outages, the researchers will aim to develop similar technology to repair and restore the grid after a power disruption.

“Our goal is to find the optimal path to send power to the majority of users as quickly as possible,” said Dr Jie Zhang, associate professor of mechanical engineering at the university’s Erik Jonsson School of Engineering and Computer Science.

“But more research is needed before this system can be implemented.”