期刊
APPLIED MATHEMATICAL MODELLING
卷 37, 期 23, 页码 9643-9651出版社
ELSEVIER SCIENCE INC
DOI: 10.1016/j.apm.2013.05.016
关键词
Support vector regression (SVR); Seasonal mechanism; Chaotic gravitational search algorithm (CGSA); Electricity forecasting
资金
- National Science Council, Taiwan [NSC 100-2628-H-161-001-MY4]
Hybridization chaotic mapping functions with optimization algorithms into a support vector regression model has been shown its efficient potential to avoid converging prematurely. It is deserved to explore more possibility by hybridizing with other optimization algorithms. Electricity demand sometimes demonstrates a seasonal tendency due to complicate economic activities or climate cyclic nature. This investigation presents a SVR-based electricity forecasting model which applied a novel hybrid algorithm, namely chaotic gravitational search algorithm (CGSA), to improve the forecasting performance. The proposed CGSA employs the chaotic local search by logistic chaotic mapping function in the iteration of the original GSA to search and refine the current best solution. In addition, seasonal mechanism is also applied to deal with seasonal electricity tendency. A numerical example from an existed reference is used to illustrate the forecasting performance of the proposed SSVRCGSA model. The forecasting results indicate that the proposed model yields more accurate forecasting results than ARIMA and TF-epsilon-SVR-SA models. (C) 2013 Elsevier Inc. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据