Researchers from the University of Texas at Dallas (UT Dallas) have developed an artificial intelligence (AI) model aimed to help electrical grids prevent power outages.
The AI would accomplish this by automatically rerouting electricity in milliseconds.
Researchers said the technology is an example of “self-healing grid” technology that uses AI to detect and repair problems such as outages autonomously and without human intervention when issues occur — like storm-damaged power lines or periods of high heat or frigid cold.
While testing the method, researchers found the AI was able to identify alternative routes to transfer electricity to users before an outage occurs. AI can reroute electrical flows in milliseconds compared to human-controlled processes that find alternative paths in minutes to hours, the researchers said.
“Our goal is to find the optimal path to send power to the majority of users as quickly as possible,” said Jie Zhang, associate professor of mechanical engineering in the Erik Jonsson School of Engineering and Computer Science at UT Dallas. “But more research is needed before this system can be implemented.”
How they did it
The team used technology that applies machine learning to graphs in order to map relationships between entities that make up the power distribution network. The AI learns the topology, various components of the network and how they are arranged in relation to each other and how electricity moves through the system.
“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 Yulia Gel, professor of mathematical sciences in the School of Natural Sciences and Mathematics at UT Dallas. “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.”
For example, if electricity is blocked due to line faults, the system reconfigures the network using switches and draws power from available sources in proximity like large-scale solar panels or batteries on a university campus or business.
The next steps are to develop similar technology to repair and restore the grid after a power disruption.
The full research can be found in the journal Nature Communications.
