Enhanced Battery Capacity Estimation in Data-Limited Scenarios through Swarm Learning

2025-04-16

AI Summary

To address the challenges of electric vehicle battery capacity estimation under data scarcity—including limited sample size, insufficient feature representation, poor data quality, and distributional shift—while ensuring privacy preservation and fault tolerance, this paper proposes the first privacy-preserving swarm learning framework tailored for battery management. The method integrates distributed federated training with a credibility-weighted model aggregation mechanism, enabling decentralized, dynamic model fusion without reliance on large-scale centralized datasets or raw data sharing. Evaluated on a multi-condition cycling dataset comprising 66 commercial LiNiCoAlO₂ battery cells, the framework significantly reduces capacity estimation error across four distinct data-scarce scenarios. Its accuracy matches that of centralized training, while simultaneously providing strong privacy guarantees and robust system-level fault tolerance.

Technology Category

• Machine Learning: Privacy
• Intelligent Robots: State Estimation
• Search and Optimization: Learning to Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Security and Privacy: Large-scale security measurements

Abstract

Data-driven methods have shown potential in electric-vehicle battery management tasks such as capacity estimation, but their deployment is bottlenecked by poor performance in data-limited scenarios. Sharing battery data among algorithm developers can enable accurate and generalizable data-driven models. However, an effective battery management framework that simultaneously ensures data privacy and fault tolerance is still lacking. This paper proposes a swarm battery management system that unites a decentralized swarm learning (SL) framework and credibility weight-based model merging mechanism to enhance battery capacity estimation in data-limited scenarios while ensuring data privacy and security. The effectiveness of the SL framework is validated on a dataset comprising 66 commercial LiNiCoAlO2 cells cycled under various operating conditions. Specifically, the capacity estimation performance is validated in four cases, including data-balanced, volume-biased, feature-biased, and quality-biased scenarios. Our results show that SL can enhance the estimation accuracy in all data-limited cases and achieve a similar level of accuracy with central learning where large amounts of data are available.

Problem

• Improving battery capacity estimation with limited data
• Ensuring data privacy in battery management systems
• Enhancing accuracy in biased and data-scarce scenarios

Innovation

• Decentralized swarm learning for battery management
• Credibility weight-based model merging mechanism
• Enhanced capacity estimation in data-limited scenarios