Carnegie Mellon University

Hamerschlag Hall

February 07, 2024

Qu Receives Top Recognition in IEEE Journal

Guannan Qu and team have received recognition for their paper, “Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges,” in the IEEE Transactions on Smart Grid. Their paper has been selected as the 3rd paper out of the top five papers chosen among over a thousand articles published in the IEEE Transactions on Smart Grid (TSG) in the past three years.

The IEEE Transactions on Smart Grid is a cross disciplinary journal aimed at disseminating results of research on and development of the smart grid, which encompasses energy networks where prosumers, electric transportation, distributed energy resources, and communications are integral and interactive components, as in the case of microgrids and active distribution networks interfaced with transmission systems. The journal publishes original research on theories and principles of smart grid technologies and systems, used in demand response, Advance Metering Infrastructure, cyber-physical systems, multi-energy systems, transactive energy, data analytics, and EV integration.

With large-scale integration of renewable generation and distributed energy resources, modern power systems are confronted with new operational challenges, such as growing complexity, increasing uncertainty, and aggravating volatility. Meanwhile, more and more data are becoming available owing to the widespread deployment of smart meters, smart sensors, and upgraded communication networks. As a result, data-driven control techniques, especially reinforcement learning (RL), have attracted surging attention in recent years. This paper provides a comprehensive review of various RL techniques and how they can be applied to decision-making and control in power systems. In particular, we select three key applications, i.e., frequency regulation, voltage control, and energy management, as examples to illustrate RL-based models and solutions. We then present the critical issues in the application of RL, i.e., safety, robustness, scalability, and data. Several potential future directions are discussed as well.