Support vector machines for wind speed prediction

被引：618

作者：

Mohandes, MA ^{[1
]}

Halawani, TO ^{[1
]}

Rehman, S ^{[1
]}

Hussain, AA ^{[1
]}

机构：

[1] King Fahd Univ Petr & Minerals, Dept Elect Engn, Engn Res Ctr, Dhahran 31261, Saudi Arabia

来源：

RENEWABLE ENERGY | 2004年 / 29卷 / 06期

关键词：

wind speed prediction; neural networks; multilayer perceptron; support vector machines;

D O I：

10.1016/j.renene.2003.11.009

中图分类号：

X [环境科学、安全科学];

学科分类号：

08 ; 0830 ;

摘要：

This paper introduces support vector machines (SVM), the latest neural network algorithm, to wind speed prediction and compares their performance with the multilayer perceptron (MLP) neural networks. Mean daily wind speed data from Madina city, Saudi Arabia, is used for building and testing both models. Results indicate that SVM compare favorably with the MLP model based on the root mean square errors between the actual and the predicted data. These results are confirmed for a system with order 1 to system with order 11. (C) 2004 Elsevier Ltd. All rights reserved.

引用

页码：939 / 947

页数：9

共 13 条

[1]

Bakhsh H., 1985, Sol. Wind Technol., V2, P59, DOI DOI 10.1016/0741-983X(85)90027-X

[2]

Collobert R, 2000, IDIAPRR0017

[3]

CRISTIANI N, 1999, SUPPORT VCTOR MACH O, P243

[4]

Haykin S., 1994, Neural networks: a comprehensive foundation

[5] Estimation of global solar radiation using artificial neural networks [J].

Mohandes, M ;

Rehman, S ;

Halawani, TO .

RENEWABLE ENERGY, 1998, 14 (1-4) :179-184

[6] A neural networks approach for wind speed prediction [J].

Mohandes, MA ;

Rehman, S ;

Halawani, TO .

RENEWABLE ENERGY, 1998, 13 (03) :345-354

[7]

MUKHERJEE S, 1997, 7 P 1997 IEEE WORKSH, P511, DOI DOI 10.1109/NNSP.1997.622433

[8]

MULLER KR, 1999, PREDICTING TIME SERI, P243

[9] STATISTICAL CHARACTERISTICS OF WIND IN SAUDI-ARABIA [J].

REHMAN, S ;

HALAWANI, TO .

RENEWABLE ENERGY, 1994, 4 (08) :949-956

[10]

RUMELHART E, 1986, RES GROUP PATALLEL D

← 1 2 →