A Graph Policy Network Approach for Volt-Var Control in Power Distribution Systems
Date
2022-06-20
Authors
Major Professor
Advisor
Committee Member
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Volt-var control (VVC) is the problem of operating power distribution systems within healthy regimes by controlling actuators in power systems. Existing works have mostly adopted the conventional routine of representing the power systems (a graph with tree topology) as vectors to train deep reinforcement learning (RL) policies. We propose a framework that combines RL with graph neural networks and study the benefits and limitations of graph-based policy in the VVC setting. Our results show that graph-based policies converge to the same rewards asymptotically however at a slower rate when compared to vector representation counterpart. We conduct further analysis on the impact of both observations and actions: on the observation end, we examine the robustness of graph-based policy on two typical data acquisition errors in power systems, namely sensor communication failure and measurement misalignment. On the action end, we show that actuators have various impacts on the system, thus using a graph representation induced by power systems topology may not be the optimal choice. In the end, we conduct a case study to demonstrate that the choice of readout function architecture and graph augmentation can further improve training performance and robustness.
Series Number
Journal Issue
Is Version Of
Versions
Series
Academic or Administrative Unit
Type
Preprint
Comments
This is a preprint from Lee, Xian Yeow, Soumik Sarkar, and Yubo Wang. "A Graph Policy Network Approach for Volt-Var Control in Power Distribution Systems." arXiv preprint arXiv:2109.12073 (2021).
doi: https://doi.org/10.48550/arXiv.2109.12073. Published as Lee, Xian Yeow, Soumik Sarkar, and Yubo Wang. "A graph policy network approach for volt-var control in power distribution systems." Applied Energy 323 (2022): 119530. doi: https://doi.org/10.1016/j.apenergy.2022.119530.
Rights Statement
This preprint is licensed as CC BY.