Detection of Global Anomalies on Distributed IoT Edges with Device-to-Device Communication
This addresses the problem of efficient anomaly detection in distributed IoT environments where cloud processing is impractical, though it appears incremental as it builds on federated learning and autoencoder concepts.
The paper tackles collaborative anomaly detection across distributed IoT devices by proposing WAFL-Autoencoder, a fully distributed scheme using device-to-device communication to detect global anomalies that are rare across all devices. The result shows the scheme trained anomaly detectors perfectly across devices and achieved high true positive rates with low false positive rates for global anomaly detection.
Anomaly detection is an important function in IoT applications for finding outliers caused by abnormal events. Anomaly detection sometimes comes with high-frequency data sampling which should be carried out at Edge devices rather than Cloud. In this paper, we consider the case that multiple IoT devices are installed in a single remote site and that they collaboratively detect anomalies from the observations with device-to-device communications. For this, we propose a fully distributed collaborative scheme for training distributed anomaly detectors with Wireless Ad Hoc Federated Learning, namely "WAFL-Autoencoder". We introduce the concept of Global Anomaly which sample is not only rare to the local device but rare to all the devices in the target domain. We also propose a distributed threshold-finding algorithm for Global Anomaly detection. With our standard benchmark-based evaluation, we have confirmed that our scheme trained anomaly detectors perfectly across the devices. We have also confirmed that the devices collaboratively found thresholds for Global Anomaly detection with low false positive rates while achieving high true positive rates with few exceptions.