The research on electric load forecasting based on nonlinear gray bernoulli model optimized by cosine operator and particle swarm optimization

Article type: Research Article

Authors: Li, Wei^{a; b; *} | Lu, Can^a | Liu, Shuai^a

Affiliations: [a] Department of Business Administration, North China Electric Power University, Baoding, China | [b] Energy Economic Development Strategy Research Base, Soft Science Research Base of Hebei Province, Baoding, China

Correspondence: [*] Corresponding author. Wei Li. Tel.: +86 18713286966; Fax: +86 0312 7525108; E-mail: [email protected].

Abstract: According to the characteristics of the power system with nonlinear operation, this paper analyzed the application limitations of traditional gray model. This study processed original data sequence with Cosine function, which could weaken the influence of outliers, improve the smoothness of the sequence and reduce reduction error. The particle swarm optimization algorithm was employed to optimize the parameter r and the background value structure coefficient α in nonlinear gray bernoulli model with the purpose of searching for the optimal parameters of the model, which could make up for the insufficient caused by given the parameters on experience. Finally, this paper discussed the implementation process of the optimized model. The history load data of Beijing grid was applied to inspect the forecasting effect of the optimized model. The numerical results and error analysis illustrated that the model has a favorable prediction effect and wide applications.

Keywords: Electric load forecasting, nonlinear gray bernoulli model, cosine operator, particle swarm optimization

DOI: 10.3233/IFS-162112

Journal: Journal of Intelligent & Fuzzy Systems, vol. 30, no. 6, pp. 3665-3673, 2016