Arizona State University has announced that a team of electrical engineering researchers and a doctoral student have used machine learning known as deep-Q learning to determine the best power grid cyber-defense strategies to counter cyberattacks.
The team’s research paper, “Defending smart electrical power grids against cyberattacks with deep Q-learning,” was recently published in PRX Energy, a highly selective and new open-access journal of the American Physical Society focusing on modern energy issues.
Mohammadamin Moradi, an electrical engineering doctoral student, used artificial intelligence to analyze the most damaging attacks and best defenses possible. His work was guided by two faculty members in the School of Electrical, Computer and Energy Engineering, part of the Ira A. Fulton Schools of Engineering at Arizona State University: Ying-Cheng Lai, a Regents Professor of electrical engineering and advisor for Moradi’s doctoral degree, and Yang Weng, an assistant professor of electrical engineering.
This research was funded by the U.S. Department of Energy and the Israeli Ministry of Energy through the Israel-United States Binational Industrial Research and Development Foundation, or BIRD Foundation, to help both countries increase their cybersecurity defenses.
Moradi, Lai and Weng worked with a type of machine learning known as deep-Q reinforcement learning, combined with stochastic game theory, to simulate what cyberattacks could cause the most damage to a power grid and the best countermeasures to keep the grid operating in the face of such attacks.
“Power grid security has a substantial impact on Americans’ lives,” Moradi says. “Last year in Texas, there were power outages and people were freezing in winter. A well-planned, well-informed attacker can cause a lot of disasters, and we as defenders should be ready to act accordingly.”
The research team says they are looking to further refine their work with future simulations, taking into account factors such as limited financial and human resources for defending the power grid.
Weng, whose research focuses on power systems, machine learning and cyberphysical systems among other areas, says he anticipates that the research can be used for real-life cybersecurity.
“Being part of this project helped me appreciate the great idea of using this model to understand a physical system theoretically using AI solutions,” he says. “This will ensure that the work will transition to the real world, which is the core reason for this research.”
Read the full story here.
The U.S. Army Corps of Engineers has been tasked with…
Brown and Caldwell, a leading environmental engineering and construction firm,…
Humboldt State University, one of four campuses within the California…
