Affiliations: [a]
School of Economic and Management Administration, North China Electric Power University, Beinong Load, Beijing, China
| [b]
School of Economics and Business Administration, Beijing Information Science and Technology University, Xiaoying East Load, Beijing, China
Correspondence:
[*]
Corresponding author. Wang Jianjun, School of Economic and Management Administration, North China Electric Power University, Beinong Load 2, Beijing, China. Tel./Fax: +86 10 61773123; E-mail: [email protected].
Abstract: Long-term load forecasting is an important issue for a country’s power suppliers to determine the future electric system plan, investment and operation. This paper presents a novel hybrid long-term forecasting method with support vector regression(SVR) and backtracking search algorithm(BSA) optimization algorithm, which is used to obtain the parameters of the SVR. The practical case of China’s annual electricity demand is used to evaluate the effectiveness of the proposed method. According to the results, the performance of the proposed method is better than the SVR model with default parameters, back propagation artificial neural network (BPNN) and regression forecasting models in annual load forecasting.
