Online Power System Event Detection via Bidirectional Generative Adversarial Networks

Journal Article · 24 February 2022 · IEEE Transactions on Power Systems

DOI: https://doi.org/10.1109/tpwrs.2022.3153591 · OSTI ID:1867798

Cheng, Yuanbin ^[1]; Yu, Nanpeng ^[2]; Foggo, Brandon ^[2]; Yamashita, Koji ^[2]

---

1. UCR, Riverside, CA (United States); University of California, Riverside
2. Univ. of California, Riverside, CA (United States)

Accurate and speedy detection of power system events is critical to enhancing the reliability and resiliency of power systems. Although supervised deep learning algorithms show great promise in identifying power system events, they require a large volume of high-quality event labels for training. This paper develops a bidirectional anomaly generative adversarial network (GAN)-based algorithm to detect power system events using streaming PMU data, which does not rely on a huge amount of event labels. By introducing conditional entropy constraint in the objective function of GAN and graph signal processing-based PMU sorting technique, our proposed algorithm significantly outperforms state-of-the-art event detection algorithms in terms of accuracy. To facilitate the adoption of the proposed algorithm, a prototype online platform is also developed using Apache Hadoop, Kafka, and Spark to enable real-time event detection. Here, the accuracy and computational efficiency of the proposed algorithm are validated using a large-scale real-world PMU dataset from the Eastern Interconnection of the United States.

• Research Organization: Univ. of California, Riverside, CA (United States)
• Sponsoring Organization: USDOE
• Grant/Contract Number: OE0000916
• OSTI ID: 1867798
• Journal Information: IEEE Transactions on Power Systems, Journal Name: IEEE Transactions on Power Systems Journal Issue: 6 Vol. 37; ISSN 0885-8950
• Publisher: IEEECopyright Statement
• Country of Publication: United States
• Language: English