부산대학교 도서관

The charging demand of electric vehicles may change at any time. Therefore, the SOC balancing control algorithm needs to be able to quickly respond to these changes and dynamically adjust the charging strategy. Therefore, a SOC balancing control method for electric vehicle charging stations based on ensemble learning is proposed. Establish an energy storage battery model, apply Stacking ensemble learning method, and preprocess the SOC of electric vehicle charging stations. Stacking ensemble learning methods can adapt to changes in data through training, which helps to handle dynamic changes in charging demands. Estimate the State of Charge (SOC) of electric vehicle charging stations based on Kalman filtering. Based on this, design SOC control steps for charging stations that consider balance characteristics. The experimental results show that the research method is more accurate in estimating the SOC of electric vehicle charging stations, with a network loss rate consistently below 0.3% and shorter time consumption.