A Method for Anomaly Detection in Power Time Series Data within Energy Big Data Based on Generative Adversarial Networks

Anomaly detection in power time series data plays a crucial role in ensuring the stability and security of energy systems. In this study, a novel approach based on Generative Adversarial Networks (GANs) is proposed to tackle this problem. Firstly, the power time series data are preprocessed to remove noise and outliers. Then, a GAN model is constructed for generating synthetic power data that follow the same statistical properties as the original data. By comparing the real and synthetic data, anomalies can be identified based on their deviations. Experimental results on a real-world power dataset demonstrate the effectiveness and robustness of the proposed method. Experimental results show that the anomaly detection model has strong performance in judging data with large differences from the original data Moreover, the proposed method shows promising potential for application in other domains beyond power systems.