Gradient-Complementary Asynchronous Federated Learning for Multi-Task Anomaly Detection in Smart Grid
TL;DR
A gradient-complementary asynchronous federated learning framework, which explicitly models gradient complementarity as a distributed intelligence fusion mechanism for multi-task anomaly detection and validate the effectiveness of gradient complementarity as a general computational intelligence principle for distributed anomaly detection.
Abstract
The increasing deployment of heterogeneous IoT devices has transformed smart grids into large-scale distributed cyber–physical systems, where anomaly detection becomes a critical yet challenging computational intelligence problem. In such environments, anomaly knowledge is sparse, fragmented, and highly non-independent across users, while device participation is asynchronous and communication-constrained. This paper proposes a gradient-complementary asynchronous federated learning (GC-AFL) framework, which explicitly models gradient complementarity as a distributed intelligence fusion mechanism for multi-task anomaly detection. Unlike conventional federated aggregation that suppresses heterogeneity, GC-AFL exploits dissimilar gradient information to preserve task-specific anomaly knowledge. The framework further integrates a communication-aware collaboration strategy and a staleness-compensated aggregation scheme to ensure efficiency and long-term fairness under asynchronous updates. Extensive experiments demonstrate that GC-AFL consistently outperforms state-of-the-art synchronous and asynchronous federated learning methods in terms of detection accuracy, robustness to Non-IID data, anomaly recall, and communication efficiency. The results validate the effectiveness of gradient complementarity as a general computational intelligence principle for distributed anomaly detection.