Automated Byzantine-Resilient Clustered Decentralized Federated Learning for Battery Intelligence in Connected EVs
arXiv:2605.21115v1 Announce Type: cross 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 propose
The proliferation of connected electric vehicles and the increasing reliance on massive datasets for battery management necessitate robust, decentralized, and secure AI frameworks.
Decentralized and Byzantine-resilient federated learning is critical for scaling AI in sensitive, distributed environments like intelligent transportation, ensuring data integrity and operational reliability without compromising privacy.
This research outlines a method to move beyond centralized aggregation in federated learning for EVs, enhancing security and trust while enabling broader data utilization.
- · Electric Vehicle Manufacturers
- · Intelligent Transportation Systems
- · Cybersecurity Providers
- · AI/ML Platform Developers
- · Centralized Cloud Service Providers (for specific FL tasks)
- · Less secure federated learning approaches
Improved battery longevity and performance prediction in EVs through secure data collaboration.
Accelerated development of autonomous features and smart grid integration for EVs due to more reliable and private data sharing.
Enhanced trust in AI systems deployed across critical infrastructure, paving the way for broader adoption in other distributed applications.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG