期刊
IEEE TRANSACTIONS ON POWER SYSTEMS
卷 37, 期 6, 页码 4168-4178出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TPWRS.2022.3155117
关键词
Training; Power system stability; Task analysis; Adaptation models; Uncertainty; Power system dynamics; Power grids; Deep reinforcement learning; emergency control; meta-learning; strategy optimization; load shedding; voltage stability
资金
- DOE ARPA-E OPEN 2018 Program
- U.S. Department of Energy (DOE) [DE-AC0576RL01830]
With the transformation of power systems and the increasing risk of outages, enhancing grid emergency control is imperative. This paper proposes a novel deep meta-reinforcement learning (DMRL) algorithm to overcome the limitations of existing DRL-based solutions, achieving superior performance in real-world applications.
As power systems are undergoing a significant transformation with more uncertainties, less inertia and closer to operation limits, there is increasing risk of large outages. Thus, there is an imperative need to enhance grid emergency control to maintain system reliability and security. Towards this end, great progress has been made in developing deep reinforcement learning (DRL) based grid control solutions in recent years. However, existing DRL-based solutions have two main limitations: 1) they cannot handle well with a wide range of grid operation conditions, system parameters, and contingencies; 2) they generally lack the ability to fast adapt to new grid operation conditions, system parameters, and contingencies, limiting their applicability for real-world applications. In this paper, we mitigate these limitations by developing a novel deep meta-reinforcement learning (DMRL) algorithm. The DMRL combines the meta strategy optimization together with DRL, and trains policies modulated by a latent space that can quickly adapt to new scenarios. We test the developed DMRL algorithm on the IEEE 300-bus system. We demonstrate fast adaptation of the meta-trained DRL polices with latent variables to new operating conditions and scenarios using the proposed method, which achieves superior performance compared to the state-of-the-art DRL and model predictive control (MPC) methods.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据