Edge Computing and Federated Learning for Real-Time Anomaly Detection in Industrial Internet of Things (IIoT)
Shivkumar V Haldikar, Omer Farook Mohideen Abdul Kader, Roop Kumar Yekollu
Abstract
This entire study has focused on the integration of edge computing and federated learning in order to increase real-time anomaly detection in the Industrial Internet of Things (IIoT) environment. Edge computing significantly enabled overall processing and analysis of data closer to the source, minimized latency and improved responsiveness. A decentralized machine learning approach, federated learning enables collaborative model training throughout distributed edge devices without any centralized sensitive data. However, the synergy of these technologies significantly addresses the challenges of real-time anomaly detection in IIoT, which critically ensures timely identification and addressing potential disruption in industrial processes. This study has found that this approach not only increases the effectiveness of anomaly detection but also significantly preserves data privacy and security.