Short Term Load Forecasting and Early Warning of Charging Station Based on PSO-SVM

摘要

In this paper, a short-term load forecasting model and a load early warning model for charging station based on PSO-SVM are proposed. Particle swarm optimization (PSO) is used to optimize the parameters of support vector machine (SVM) model, and the PSO-SVM load forecasting model for the optimal nuclear parameters of charging station is established according to the normalized root mean square error (NRMS). On the basis of it, a load warning model of charging station is established and verified by an example. Experiments show that the short-term load forecasting model based on PSO-SVM and the load forecasting model of charging station meet the requirements of forecasting and forecasting accuracy.