Short-Term Load Forecasting Using Support Vector Regression-Based Local Predictor

被引:0
作者
Li, M. S. [1 ]
Wu, J. L. [1 ]
Ji, T. Y. [1 ]
Wu, Q. H. [1 ]
Zhu, L. [2 ]
机构
[1] S China Univ Technol, Sch Elect Power Engn, Guangzhou 510641, Guangdong, Peoples R China
[2] Univ Liverpool, Dept Elect Engn & Elect, Liverpool L69 3GJ, Merseyside, England
来源
2015 IEEE POWER & ENERGY SOCIETY GENERAL MEETING | 2015年
关键词
Load demand forecast; support vector regression; local predictor; NEURAL-NETWORK;
D O I
暂无
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
This paper introduced a novel forecasting method, Support Vector Regression with Local Predictor (SVRLP), which aims to forecast the short-term load distribution function. To increase the forecast accuracy, the conventional Support Vector Regression (SVR) is combined with a phase space reconstruction technique, called local predictor. This proposed forecast method can be applied to forecast the load demand using smaller training samples and overcome the local optimal solution problem. Therefore, the SVRLP is able to provide more reliable forecast results to the system operators. In the experimental studies, the SVRLP is evaluated on the load data of collect from Guangzhou on the China Southern Grid (CSG), and is compared with the predictors based on conventional SVR, the Auto-Regressive Moving Average (ARMA) and the Artificial Neural Network (ANN), respectively. The results demonstrate that the proposed method can achieve a better performance than the other methods.
引用
收藏
页数:5
相关论文
共 16 条
[1]   An adaptive fuzzy combination model based on self-organizing map and support vector regression for electric load forecasting [J].
Che, Jinxing ;
Wang, Jianzhou ;
Wang, Guangfu .
ENERGY, 2012, 37 (01) :657-664
[2]   Least squares support vector machines with tuning based on chaotic differential evolution approach applied to the identification of a thermal process [J].
dos Santos, Glauber Souto ;
Justi Luvizotto, Luiz Guilherme ;
Mariani, Viviana Cocco ;
Coelho, Leandro dos Santos .
EXPERT SYSTEMS WITH APPLICATIONS, 2012, 39 (05) :4805-4812
[3]   Short-Term Load Forecasting Based on a Semi-Parametric Additive Model [J].
Fan, Shu ;
Hyndman, Rob J. .
IEEE TRANSACTIONS ON POWER SYSTEMS, 2012, 27 (01) :134-141
[4]   INDEPENDENT COORDINATES FOR STRANGE ATTRACTORS FROM MUTUAL INFORMATION [J].
FRASER, AM ;
SWINNEY, HL .
PHYSICAL REVIEW A, 1986, 33 (02) :1134-1140
[5]   Short-term load forecasting using SVR (support vector regression)-based radial basis function neural network with dual extended Kalman filter [J].
Ko, Chia-Nan ;
Lee, Cheng-Ming .
ENERGY, 2013, 49 :413-422
[6]   Local prediction of non-linear time series using support vector regression [J].
Lau, K. W. ;
Wu, Q. H. .
PATTERN RECOGNITION, 2008, 41 (05) :1539-1547
[7]   Application of a hybrid quantized Elman neural network in short-term load forecasting [J].
Li, Penghua ;
Li, Yinguo ;
Xiong, Qingyu ;
Chai, Yi ;
Zhang, Yi .
INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS, 2014, 55 :749-759
[8]   A Fast Luminance Inspector for Backlight Modules Based on Multiple Kernel Support Vector Regression [J].
Lin, Wu-Ja ;
Jhuo, Sin-Sin .
IEEE TRANSACTIONS ON COMPONENTS PACKAGING AND MANUFACTURING TECHNOLOGY, 2014, 4 (08) :1391-1401
[9]   Application of Artificial Neural Network for Reducing Random Coincidences in PET [J].
Oliver, Josep F. ;
Fuster-Garcia, Elies ;
Cabello, Jorge ;
Tortajada, Salvador ;
Rafecas, Magdalena .
IEEE TRANSACTIONS ON NUCLEAR SCIENCE, 2013, 60 (05) :3399-3409
[10]  
Pang Qingle, 2010, Proceedings of the 2010 International Conference on Intelligent Computation Technology and Automation (ICICTA 2010), P1132, DOI 10.1109/ICICTA.2010.38