Heterogeneity-Aware Federated Learning for Device Anomaly Detection in Industrial loT

With the popularity and application of the Industrial Internet of Things (1IoT), device anomaly detection is considered as one of the important challenges in IloT implementation. However, the privacy sensitivity of device data and the high heterogeneity of IloT devices make it impossible for traditional schemes to achieve efficient, accurate, and privacy-protected device anomaly detection in IloT networks. In this study, we propose an intelligent anomaly detection architecture for IloT networks based on federated optimization algorithms and deep learning (DL). In particular, an online, adaptive, and semi-supervised device anomaly detection model is designed, and a heterogeneity-aware federated learning algorithm, called Clustered-FedProx, is presented. The Clustered-FedProx algorithm considers the differences in computational power and data statistical distribution among IloT devices, whereby multiple devices can be coordinated to train a global DL model in highly heterogeneous networks. Simulation results show that the proposed scheme can achieve more stable and accurate performance than conventional schemes.