Joint Estimation of SOC and SOE for Energy Storage Lithium-ion Batteries Based on KNN Algorithm

In the battery management system, State of Charge (SOC) and State of Energy (SOE) are important parameters to guarantee the safe, reliable and efficient operation of lithium-ion batteries, and their accurate estimation plays a decisive role in the stable operation of the whole battery system. In practice, complex and variable conditions significantly affect battery characteristics and the accuracy of the state of charge (SOC) and state of energy (SOE), so accurate estimation of SOC and SOE is critical. To solve this problem, a joint SOC-SOE estimation method based on KNN algorithm is proposed in this paper. Firstly, the strong correlation correspondence between SOC-SOE was explored using the KNN algorithm. Secondly, the search method is used to determine the optimal hyperparameter values of the KNN, and finally the SOE values are corrected by combining the maximum energy obtained from the extended Kalman filtering algorithm. The experimental results show that the method can accurately estimate the SOE value with strong robustness.