Research of Short Term Load Forecasting based on CA-SVM

被引：0

作者：

Chen, Tao ^{[1
]}

机构：

[1] Shaanxi Univ Technol, Apartment Math, Hanzhong, Shaanxi, Peoples R China

来源：

2011 AASRI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND INDUSTRY APPLICATION (AASRI-AIIA 2011), VOL 2 | 2011年

关键词：

short term load forecasting; support vector machine (SVM); cultural algorithm (CA); parameters optimization;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper presented a forecasting model based on CA-SVM to improve effects of short term load forecasting.Optimal rule is the least mean square error of samples, and the parameters of SVM are optimized by CA, Short-term load is forecasted by using SVM.The simulation results show that parameters selection based on CA can accelerate the pace of the search parameters and improve generalization ability of SVM. CA-SVM can improve forecasting accuracy, and it is feasible and effective in the short term load forecasting.

引用

页码：245 / 248

页数：4

共 11 条

[1] Choosing multiple parameters for support vector machines
Chapelle, O
Vapnik, V
Bousquet, O
Mukherjee, S
[J]. MACHINE LEARNING, 2002, 46 (1-3) : 131 - 159
[2] Chung C, 1997, P 1996 1 AS PAC C SI, P17
[3] Liang Zhishan, 1998, CONTROL DECISION, V13, P87
[4] Ping Z., 1998, P EPSA, V10, P45
[5] Qi Liang, 2008, SYSTEM SIMULATION TE, V11, P34
[6] Sanchez A D, 2003, NEUROCOMPUTING, V55, P15
[7] Shao Xin-Guang, 2006, Control Theory & Applications, V23, P740
[8] Yang Jingyan, 2004, TECHNIQUES AUTOMATIO, V23, P14
[9] Ye Guiyun, 2002, HEILONGJIANG ELECT T, V7, P74
[10] Zhao Hongwei, 1997, CHINESE SOC ELECT EN, V17, P347

← 1 2 →