TimeSeries2Report prompting enables adaptive large language model management of lithium-ion batteries

This paper introduces TimeSeries2Report (TS2R), a prompting framework that converts raw lithium-ion battery operational time-series into structured, semantically enriched reports. This enables large language models (LLMs) to reason, predict, and make decisions in Battery Energy Storage System (BESS) management. TS2R improves LLM performance in accuracy, robustness, and explainability for tasks like anomaly detection and state-of-charge prediction.