期刊
IEEE TRANSACTIONS ON POWER SYSTEMS
卷 36, 期 3, 页码 2733-2736出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TPWRS.2021.3057523
关键词
Training; Deep learning; Security; Power system dynamics; Transient analysis; Generators; Stability criteria; Total transfer capability; artificial intelligence; deep learning; deep reinforcement learning; distributed proximal policy optimization; power system dynamics
资金
- National Nature Science Foundation of China [51977133]
This study proposes a data-driven hybrid method based on deep learning and deep reinforcement learning for dynamic total transfer capability control. The experimental results demonstrate its advantages in handling unknown and insecure scenarios.
This letter proposes a data-driven hybrid deep learning method for dynamic total transfer capability (TTC) control. It leverages deep learning (DL) to achieve fast prediction of TTC and reduce the problem complexity, while the deep reinforcement learning (DRL) method, e.g., proximal policy optimization (PPO), is enhanced by competitive learning (CL) to obtain a better generalization of the DRL agents. This also allows us to deal with system stochasticity. Comparison results with other model-based alternatives on the IEEE 39-bus system highlight the advantages of the proposed method for variable unseen and insecure scenarios.
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