The carbon neutrality consensus of human beings requires deep penetration of renewable energy. Lithium-ion battery is one of the most important energy storage components in the energy storage systems and its performance is always monitored by the battery management system (BMS). With the development of machine learning methods and GPUs, data-driven methods have become more popular and efficient for SOC and SOH estimation. This digest makes an overview of machine learning-enabled battery state estimation methods, and makes a comparison between different methods to draw a general conclusion. The future direction is also prospected.
