可再生能源2017，Vol.35Issue(11)：1699-1705,7.
IGSA优化LSSVM的短期风电功率预测研究
Short-term wind power prediction based on LSSVM optimized by IGSA
摘要
Abstract
This paper proposes a short-term wind power forecasting method based on Improved Gravitational Search Algorithm (IGSA) to optimize LSSVM. The gravitational search algorithm utilizes chaos mapping learning strategy to initialize position;the global memory strategy is used to improve the velocity and enhance the optimal solution quality;the Gaussian mutation operator and the greedy strategy are used to update the optimal solution position by the chaotic map learning strategy initializing the population position. In order to compare the effects of different kernel functions on the performance of LSSVM prediction model,four commonly used kernel functions (RBF,Sigmoid,Poly and Linear)are constructed to construct LSSVM prediction model,and the model is optimized by IGSA. Taking the measured data of a wind farm in Anhui as an example,the simulation results show that the IGSA-LSSVM model with RBF kernel function is better than other kernel functions. At the same time IGSA optimizes LSSVM has better stability and higher accuracy for short-term wind power prediction compared with BPNN and GA,PSO, GSA-LSSVM.关键词
短期风电功率预测/引力搜索算法/最小二乘支持向量机/改进引力搜索算法Key words
short-term wind power prediction/gravitational search algorithm/least squares support vector machine/improved gravitational search algorithm分类
能源科技引用本文复制引用
凤志民,田丽,吴道林,李从飞..IGSA优化LSSVM的短期风电功率预测研究[J].可再生能源,2017,35(11):1699-1705,7.基金项目
安徽省自然基金(1508085ME74) （1508085ME74）
安徽省教育厅自然科学研究重点项目(KJ2014A282). （KJ2014A282）
