Automated Byzantine-Resilient Clustered Decentralized Federated Learning for Battery Intelligence in Connected EVs

TL;DR

This paper introduces ABC-DFL, a blockchain-based decentralized federated learning framework for EV battery data, featuring Byzantine resilience, trust enhancement, and incentive mechanisms, validated through extensive experiments.

Contribution

It proposes a novel decentralized federated learning system with blockchain, Byzantine fault tolerance, and adaptive clustering, improving security and trust in EV data management.

Findings

FLECA matches FedProx convergence in benign scenarios.

FLECA significantly reduces attack impact scores below 0.10.

Experimental results validate the system's effectiveness and practicality.

Abstract

Federated learning (FL) has emerged as a promising paradigm for managing electric vehicle (EV) battery data in intelligent transportation systems (ITS), enabling privacy-preserving tasks such as anomaly detection and capacity estimation. However, most existing frameworks rely on centralized aggregation schemes, which pose critical limitations in terms of security and trust. To address these challenges, we propose ABC-DFL, an automated Byzantine-resilient clustered decentralized federated learning (C-DFL) framework for connected EVs. The proposed incentive-driven C-DFL system replaces the central server with an open-permissioned blockchain, featuring a new dynamic Quorum Byzantine Fault Tolerance (QBFT) protocol and an oracle-based aggregation layer, to enhance trust, security, and automation. At the core of ABC-DFL lies FLECA (Filtered Layered Enhanced Clustering Aggregation), a robust hierarchical aggregation protocol that mitigates Byzantine attacks by having each EV filter malicious updates using an adaptive threshold based on deviations from its reference model update. Oracle nodes, responsible for inter-group aggregation, employ robust clustering to isolate and aggregate model updates from trustworthy EV groups. Comprehensive experimental evaluations demonstrate that FLECA matches FedProx convergence under benign conditions and significantly outperforms existing defenses with attack impact scores below 0.10 in adaptive adversarial scenarios. Furthermore, several learning experiments with multitask models confirm the effectiveness and fairness of the incentive mechanism. Finally, on-chain and off-chain benchmarks validate the practicality of ABC-DFL.