University of Texas and University at Buffalo team up to develop AI model to prevent power outages

Researchers at the University of Texas at Dallas have developed an artificial intelligence (AI) model to help power grids prevent power outages by automatically redirecting electricity within milliseconds.

The UT Dallas researchers, working with engineers from the University at Buffalo in New York, demonstrated the automated system in a study published online in Nature Communications. The work was supported by the U.S. Office of Naval Research and the National Science Foundation.

The study leverages self-healing grid technology, which uses AI to detect and repair problems such as outages autonomously and without human intervention when problems arise, such as power lines damaged by a storm. The researchers demonstrated that their solution is able to automatically identify alternative paths to transfer electricity to users before an outage occurs.

While AI can automatically reroute electrical flow in milliseconds, current human-controlled processes for determining alternative paths take longer.

Dr. Jie Zhang, associate professor of mechanical engineering in the Erik Jonsson School of Engineering and Computer Science, and colleagues used technology that applies machine learning to graphs to map the complex relationships between entities that make up an energy distribution network.

Graph machine learning involves describing the topology of a network, how different components are arranged in relation to each other, and the movement of electricity through the system.

According to Dr. Yulia Gel, professor of mathematical sciences in the School of Natural Sciences and Mathematics, network topology is also important in applying AI to solving problems in other complex systems, such as critical infrastructure and ecosystems.

Led by Dr. Souma Chowdhury, co-corresponding author and associate professor of mechanical and aerospace engineering, the University at Buffalo researchers focused on the reinforcement learning aspect of the project.

Roshni Anna Jacob, a doctoral student in electrical engineering at UTD and co-first author of the paper, said the system is capable of reconfiguring itself using switches and drawing power from nearby available sources , such as large-scale solar panels or university batteries. campus or business, if electricity is blocked due to line faults.

Researchers will also aim to develop similar technology to repair and restore the network after a power outage.