Decentralized Federated Anomaly Detection in Smart Grids: A P2P Gossip Approach

TL;DR

This paper proposes a decentralized federated anomaly detection method for smart grids using gossip protocols, improving detection accuracy, training time, and privacy preservation over traditional federated learning approaches.

Contribution

Introduces a novel decentralized federated learning scheme based on gossip protocols, addressing FL limitations in privacy, communication, and robustness within smart grid security.

Findings

Random Walk protocol outperforms Epidemic in detection accuracy

Achieved 35% faster training time than conventional federated learning

Demonstrated superior attack detection on industrial control datasets

Abstract

The increasing security and privacy concerns in the Smart Grid sector have led to a significant demand for robust intrusion detection systems within critical smart grid infrastructure. To address the challenges posed by privacy preservation and decentralized power system zones with distinct data ownership, Federated Learning (FL) has emerged as a promising privacy-preserving solution which facilitates collaborative training of attack detection models without necessitating the sharing of raw data. However, FL presents several implementation limitations in the power system domain due to its heavy reliance on a centralized aggregator and the risks of privacy leakage during model update transmission. To overcome these technical bottlenecks, this paper introduces a novel decentralized federated anomaly detection scheme based on two main gossip protocols namely Random Walk and Epidemic. Our findings indicate that the Random Walk protocol exhibits superior performance compared to the Epidemic protocol, highlighting its efficacy in decentralized federated learning environments. Experimental validation of the proposed framework utilizing publicly available industrial control systems datasets demonstrates superior attack detection accuracy while safeguarding data confidentiality and mitigating the impact of communication latency and stragglers. Furthermore, our approach yields a notable 35% improvement in training time compared to conventional FL, underscoring the efficacy and robustness of our decentralized learning method.