Electricity Consumption Prediction based on Data Mining Techniques with Particle Swarm Optimization

Accurate forecasting of electric load has always been the most important issues in the electricity industry, particularly for developing countries. Due to the various influences, electric load forecasting reveals highly nonlinear characteristics. The SVR model with Particle Swarm Optimization and Cross Validation is proposed according to the characteristics of the nonlinear electricity consumption data which are new Data Mining Techniques (DMT). In this model, PSO-CV method is used to the parameter determination. Then PSO-CV-SVR model is applied to the electricity consumption prediction of Jiangsu province. The result shows better than the ANNs method and improves the accuracy of the prediction.