Lei, X.Li, Z.Jiang, H.Yu, S.S.Chen, Y.Liu, B.Shi, P.2025-07-172025-07-172025Expert Systems with Applications, 2025; 292:128586-1-128586-110957-41741873-6793https://hdl.handle.net/2440/146083Available online 14 June 2025Phasor measurement units (PMUs) are vital for power grid monitoring, yet their high cost restricts widespread adoption. PMU measurement data is also crucial for fault analysis in power systems. However, existing research seldom explores the interplay between optimal PMU placement (OPP) and fault analysis, impeding advancements in grid economy and security. This study introduces a perception-driven, deep learning-based optimization approach that integrates OPP, multi-task learning, and fault data augmentation. First, deep reinforcement learning optimizes PMU placement, balancing cost-effectiveness with observability requirements. Next, multi-task learning, enhanced by Bayesian optimization, improves fault classification efficiency using PMU data. Finally, pretrained models paired with 𝑘-means clustering augment fault data, boosting classification accuracy. Extensive simulations across four IEEE standard test systems validate the proposed method’s effectiveness.en© 2025 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.Data augmentation; Deep reinforcement learning; Multi-task learning; Optimal PMU placement; Phase measurement unit; Power system fault classificationJournal article10.1016/j.eswa.2025.128586743465Shi, P. [0000-0001-6295-0405] [0000-0001-8218-586X] [0000-0002-0864-552X] [0000-0002-1358-2367] [0000-0002-5312-5435]