Clustered Federated Learning for Generalizable FDIA Detection in Smart Grids with Heterogeneous Data

2025-07-20

AI Summary

To address the poor generalization of False Data Injection Attack (FDIA) detection models caused by non-IID SCADA/PMU measurements in smart grids, and the privacy leakage and high communication overhead inherent in centralized training, this paper proposes FedClusAvg—a privacy-preserving hierarchical federated learning framework. FedClusAvg innovatively integrates clustering-driven client grouping, a three-tier communication architecture (client–sub-server–cloud server), and a hierarchical weighted parameter aggregation mechanism, enabling improved model convergence and generalization under data heterogeneity without sharing raw data. Extensive experiments on multiple power grid benchmark datasets demonstrate that, compared to state-of-the-art federated methods, FedClusAvg achieves an average 3.2–5.8% improvement in FDIA detection accuracy, reduces required communication rounds by 37%, and lowers bandwidth consumption by 41%, while exhibiting strong scalability and practical deployment potential.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Data Mining & Knowledge Management: Scalability, Parallel & Distributed Systems
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Security and Privacy: Large-scale security measurements

Abstract

False Data Injection Attacks (FDIAs) pose severe security risks to smart grids by manipulating measurement data collected from spatially distributed devices such as SCADA systems and PMUs. These measurements typically exhibit Non-Independent and Identically Distributed (Non-IID) characteristics across different regions, which significantly challenges the generalization ability of detection models. Traditional centralized training approaches not only face privacy risks and data sharing constraints but also incur high transmission costs, limiting their scalability and deployment feasibility. To address these issues, this paper proposes a privacy-preserving federated learning framework, termed Federated Cluster Average (FedClusAvg), designed to improve FDIA detection in Non-IID and resource-constrained environments. FedClusAvg incorporates cluster-based stratified sampling and hierarchical communication (client-subserver-server) to enhance model generalization and reduce communication overhead. By enabling localized training and weighted parameter aggregation, the algorithm achieves accurate model convergence without centralizing sensitive data. Experimental results on benchmark smart grid datasets demonstrate that FedClusAvg not only improves detection accuracy under heterogeneous data distributions but also significantly reduces communication rounds and bandwidth consumption. This work provides an effective solution for secure and efficient FDIA detection in large-scale distributed power systems.

Problem

• Detecting False Data Injection Attacks in smart grids with heterogeneous data
• Overcoming Non-IID data challenges in federated learning for FDIA detection
• Reducing communication costs while preserving privacy in distributed detection models

Innovation

• Cluster-based federated learning for Non-IID data
• Hierarchical communication reduces overhead
• Local training with weighted aggregation