Sunwoda Electronic Co., Ltd, and Tsinghua Berkeley Shenzhen Institute (TBSI) generate the TBSI Sunwoda Battery Dataset. We open-source this dataset to inspire more data-driven novel material verification, battery management research and applications.

Battery charging schedule optimization to minimize lithium-ion battery degradation.

The project analyzes battery cycling data to predict degradation patterns and performance metrics using both deep learning (LSTM) and traditional machine learning (XGBoost) approaches. The implementation enables accurate estimation of battery health, which is crucial for battery management systems in various applications.

🔋 Optimize battery dispatch using a rainflow-aware DQN that tracks degradation and enhances performance with advanced features for reliable results.

Rainflow‑aware DQN for battery dispatch (arbitrage + FR/reserves): Gymnasium env with safety layer, exact cycle‑based degradation, time features & stacked observations; SB3 training.

Machine learning analysis of lithium-ion battery degradation using CALCE CS2 dataset, including DVA/ICA electrochemical insights, statistical testing, and RUL prediction.

DQN-based battery dispatch with exact rainflow degradation tracking, cyclic time encodings, and observation stacking for superior energy arbitrage and load-following performance