The new hybrid approaches to forecasting short-term electricity load

Abstract

Electric load forecasting has a great impact on dispatching work and production scheme of power system. And accurate forecasting is helpful to the security and stability of power system. This paper proposes a hybrid model based on ensemble empirical mode decomposition (EEMD), random forest (RF), support vector regression (SVR) and ridge regression (RR) algorithm, namely EEMD-RF- SVR-RR model. EEMD is employed to solve the problem of data fluctuation. RF, SVR, and RR make the model have strong anti-noise ability, nonlinear mapping and stability. Numerical experiments were carried out with New South Wales(NSW, Australia). The results have showed that the forecasting accuracy of the model for different types in this paper is better than other models. So the feasibility and effectiveness of this method in short-term load forecasting are verified.