Enhanced Battery Capacity Estimation in Data-Limited Scenarios through Swarm Learning
This addresses a bottleneck in deploying data-driven methods for battery management in electric vehicles, offering a privacy-preserving and fault-tolerant solution, though it is incremental as it builds on existing swarm learning concepts.
The paper tackles the problem of poor performance in data-driven battery capacity estimation for electric vehicles when data is limited, by proposing a swarm learning framework that enhances accuracy across various data-limited scenarios while ensuring data privacy and security, achieving similar accuracy to central learning with large datasets.
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.