Estimation of State of Charge of a Lead Acid Battery Using Support Vector Regression

Abstract

Abstract Estimation of State of Charge (SOC) of batteries plays a vital role in Battery Management Systems(BMS). It is important to enhance the lifetime of a battery and give the user an accurate estimation of available runtime. This study aims to estimate the battery SOC based on current through and voltage across a battery using Support Vector Regression (SVR). Tests are run on SIMULINK using a 6 V, 4.5 Ah Lead Acid battery. Hyper parameters that decide the accuracy of SVR are estimated using Grid Search and Particle Swarm Optimization (PSO). The SVR maintains a high level of accuracy, with a Mean Squared Error (MSE) of 0.45% for PSO and 0.95% for GS.