Residential Electric Vehicle Charging Load Prediction Method Based on DBO-ELM

In recent years, the rapid development of the electric vehicle (EV) industry in China has significantly increased the pressure on the power grid due to the rising demand for EV charging. Accurate prediction of EV charging load is crucial for effective power grid planning and management. This paper presents a novel approach for predicting residential EV charging load by utilizing the Dung Beetle Optimized Extreme Learning Machine (DBO-ELM). The study identifies key factors influencing charging behavior, including battery State of Charge (SOC), time-of-use tariffs, and charging time, and constructs mathematical models for each. The DBO algorithm is employed to optimize the input weights and hidden layer biases of the ELM model, resulting in improved prediction accuracy. Experimental results demonstrate that the DBO-ELM model outperforms traditional ELM models in terms of prediction accuracy, making it a valuable tool for addressing the uncertainties and fluctuations in residential EV charging load.