Self-Attention Generative Adversarial Network Enhanced Learning Method for Resilient Defense of Networked Microgrids Against Sequential Events

• Published in: IEEE transactions on power systems Vol. 38; no. 5; pp. 4369 - 4380
• Main Authors: Zhao, Jin, Li, Fangxing, Sun, Haoyuan, Zhang, Qiwei, Shuai, Hang
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.09.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptation models; Data models; Deep learning; deep reinforcement learning (DRL); Distributed generation; distributed generator (DG); generative adversarial network (GAN); Generative adversarial networks; Generators; Hurricanes; Load modeling; Markov processes; microgrids (MGs); Reconfiguration; Resilience; Self-attention; Survival; Tornadoes; Training
• ISSN: 0885-8950; 1558-0679
• DOI: 10.1109/TPWRS.2022.3215510

The resilient responses of networked microgrids (MGs) can greatly improve the survival of critical loads during extreme events. In order to efficiently handle the scarce data issue as well as improve the adaptability of deep reinforcement learning (DRL) methods for complex sequential extreme events (SEEs) such as hurricanes and tornadoes, a new learning-based method is proposed for the survival of critical loads in MGs during SEEs. A generative adversarial network (GAN) is applied to generate a sufficient extreme event-related database in a model-free way. Specifically, a self-attention GAN (SA-GAN) is developed to capture sequential features of the SEE process. Then, the SA-GAN is integrated into a DRL framework, and the corresponding Markov decision process (MDP) and the environment are designed to realize adaptive networked MG reconfiguration for the survival of critical loads. Faced with uncertain distributed generator (DG) output and sequential line damage, the SA-GAN-DRL method provides an adaptive model-free solution to continuously supply critical loads during SEEs. The effectiveness of the proposed method is validated using a 7-bus test system and the IEEE 123-bus system, and the results demonstrate both a strong learning ability with limited practice data, and robustness and adaptability for highly changeable SEE processes.