Parameter Optimization of SVM Based on Improved PSO and Its Application in Wind Speed Predictions

doi:10.11930/j.issn.1004-9649.2013.11.105.3

Abstract

Abstract: For accurate prediction of short-term wind speeds in a wind farm, a new SVM (support vector machine) predicting method based on improved PSO(particle swarm optimization) is proposed, which is designed to improve the self-learning ability and social learning ability of the particle swarm algorithm by bettering its learning factors, consequently making the PSO more conducive to converge to the global optimal solution and to find a better and more accurate parameter values to minimize the error of support vector machine prediction. The testing results show that compared with the conventional PSO-SVM and SVM prediction, the improved PSO-SVM method is more accurate in prediction result and has lower errors.

Key words: improved PSO, SVM, parameter selection, wind speed forecasting

CLC Number:

TM614

ZHU Xiao-yan, ZHANG Jin-hui, FU Shi-peng, ZHU Xiao-xun. Parameter Optimization of SVM Based on Improved PSO and Its Application in Wind Speed Predictions[J]. Electric Power, 2013, 46(11): 105-108.

Add to citation manager EndNote|Ris|BibTeX

URL: https://www.electricpower.com.cn/EN/10.11930/j.issn.1004-9649.2013.11.105.3

https://www.electricpower.com.cn/EN/Y2013/V46/I11/105

References

[1] 袁铁江,晁勤,李义岩,等. 基于风电极限穿透功率的经济调度优化模型研究[J]. 电力系统保护与控制, 2011,39（1）：15-22.
YUAN Tie-jiang, CHAO Qin, LI Yi-yan, et al . The optimization model of economic dispatch based on wind power penetration limit [J]. Power System Protection and Control, 2011, 39(1): 15-22.
[2] 栗然,王粤,肖进永. 基于经验模式分解的风电场短期风速预测[J]. 中国电力,2009,42（9）：77-80.
LI Ran, WANG Yue, XIAO Jin-yong. Short-term wind speed forecasting for wind farms based on empirical mode decomposition model [J]. Electric Power, 2009, 42(9): 77-80.
[3] 杨秀媛,肖洋,陈树勇. 风电场风速和发电功率预测研究[J]. 中国电机工程学报,2005,25（11）：1-5.
YANG Xiu-yuan, XIAO Yang, CHEN Shu-yong. The forecasting of wind speed and power generation [J]. Proceedings of the CSEE, 2005, 25(11): 1-5.
[4] HIPPERT H S, PEDREIRA C E, SOUZA R C. Neural networks for short-term load forecasting: A review and evaluation[J]. IEEE Trans on Power Systems, 2001, 16(1): 44-55.
[5] 刘涛,彭世蕤. 改进BP神经网络在航空弹药预测中的应用[J].探测与控制学报,2009,31（5）：52-55.
LIU Tao, PENG Shi-rui. The application of improved BP neural network in the aviation ordnance prediction[J]. Journal of Detection & Control, 2009, 31(5): 52-55.
[6] 杨建国,翁善勇,赵虹,等. 采用遗传算法优化的煤粉着火特性BP神经网络预测模型[J]. 动力工程,2006,26（1）,81-83,115.
YANG Jian-guo, WENG Shan-yong, ZHAO Hong, et al . An optimized BP network model using genetic algorithm for predicting the ignition-stability index of pulverized coal[J]. Journal of Power Engineering, 2006, 26(1): 81-83, 115.
[7] 石彦辉,高蒙,邸建红,等. 基于小波神经网络的非线性负载功率预测[J]. 电测与仪表,2008,45（12）：8-11.
SHI Yan-hui, GAO Meng, DI Jian-hong, et al . Forecasting for non-linear load power based on wavelet and ANN[J]. Electrical Measurement & Instrumentation, 2008, 45(12): 8-11.
[8] 孙相文,王美玉,惠璟. 电力市场中基于混沌理论的电价预测研究[J]. 东北电力大学学报：自然科学版,2009,29（2）：52-55.
SUN Xiang-wen, WANG Mei-yu, HUI Jing. The study of price forecasting based on chaos theory in electricity market [J]. Journal of Northeast Dianli University: Natural Science Edition,2008, 45(12): 8-11.
[9] 鲍永胜,吴振升. 基于SVM的时间序列短期风速预测[J]. 中国电力,2011,44（9）：61-64.
BAO Yong-sheng, WU Zhen-sheng. The short-term wind speed prediction of time series based SVM [J]. Electric Power, 2011, 44(9): 61-64.
[10] 祝海龙,屈梁生,张海军. 基于小波变换和支持向量机的人脸检测系统[J]. 西安交通大学学报,2002,36（9）：947-950.
ZHU Hai-long, QU Liang-sheng, ZHAG Hai-jun. Face detection based on wavelet transform and support vector machine[J]. Journal of Xi’an Jiaotong University, 2002, 36(9): 947-950.
[11] 邓乃扬,田英杰. 数据挖掘中的新方法—支持向量机[M]. 北京：科学出版社,2004.
[12] 谢宏,魏江平,刘鹤立. 短期负荷预测中支持向量机模型的参数选取和优化方法[J]. 中国电机工程学报,2006,26（22）：17-22.
XIE Hong, WEI Jiang-ping, LIU He-li. Parameter selection and optimization method of SVM model for short-term load forecasting[J]. Proceedings of the CSEE, 2006, 26(22): 17-22.
[13] 许磊,张凤鸣,程军. 基于PSO神经网络的故障诊断方法研究[J]. 计算机工程与设计,2007,28（15）：3640-3643.
XU Lei, ZHANG Feng-ming, CHENG Jun. Research on fault diagnosis method based on PSO neural network[J]. Computer Engineering and Design, 2007, 28(15):3640-3643.
[14] 张春晓,张涛. 基于最小二乘支持向量机和粒子群算法的两相流含油率软测量方法[J]. 中国电机工程学报,2010,30（2）：86-91.
ZHANG Chun-xiao, ZHANG Tao. Soft measurement method for oil holdup of two phase flow based on least squares support vector machine and particle swarm optimization [J]. Proceedings of the CSEE, 2010, 30(2): 86-91.
[15] 杜颖,卢继平,李青,等. 基于最小二乘支持向量机的风电场短期风速预测[J]. 电网技术,2008,32（15）：62-66.
DU Ying, LU Ji-ping, LI Qing, et al . Short-term wind speed forecasting of wind farm based on least square-support vector machine [J]. Power System Technology, 2008, 32(15): 62-66.