The Optimization Selection of Correlative Factors for Long-Term Power Load Forecasting

Abstract

In order to reflect the influence of each element on the load forecasting result, an Artificial Neural Network (ANN) Based approach for long-term load forecasting is investigated. Based on the theory of artificial neural network, a three-layer back propagation(BP) network is proposed. The idea is to forecast medium and long term load using the ability of ANN to nonlinear system. Seven factors are selected as inputs for the proposed ANN. The factors include GDP, heavy industry production, light industry production, agriculture production, primary industry, secondary industry, tertiary industry. Elimination method is used for the optimization selection of correlative factors, and forecasting accuracy is discussed. Simulation results show that predicting precision is elevated notably. after using elimination method, So the method brought forward is feasible and effective.