基于小波分解和最小二乘支持向量机的短期风速预测  

Short-Term Wind Speed Forecasting Based on Wavelet Decomposition and Least Square Support Vector Machine

作　　者：王晓兰[1] 王明伟[1] 

机构地区：[1]兰州理工大学电气工程与信息工程学院,甘肃省兰州市730050

出　　处：《电网技术》2010年第1期179-184,共6页Power System Technology

基　　金：甘肃省自然科学基金资助项目(0710RJZA054)

摘　　要：短期风速预测对并网风力发电系统的运行有重要意义。对风速进行较准确地预测,可以有效减轻或避免风电场对电力系统的不利影响,同时提高风电场在电力市场中的竞争能力。简述了短期风速预测的价值和方法,提出了基于小波分解(wavelet decomposition,WD)和最小二乘支持向量机(least square support vector machine,LS-SVM)的短期风速预测方法,分别以香港和河西走廊地区风电场为例,建立了上述2个地区风速预测的WD-LSSVM模型,根据上述地区的数据进行实例验证,结果表明文中的方法显著提高了超前一步预测的精度。Short-term wind speed forecasting is of significance for the operation of grid-connected wind power generation systems. A more accurate wind speed forecasting can effectively reduce or avoid the adverse effect of wind farm on power grid; meanwhile strengthens competition ability of wind farm in electricity market. In this paper the value and methods of wind speed forecasting are briefly introduced, and a short-term wind speed forecasting method based on wavelet decomposition （WD） and least square support vector machine （LSSVM） is proposed. Serving wind farms in Hong Kong region and the Hexi Corridor in Northwest China as examples respectively, two WD-LSSVM models for above-mentioned two regions are built and according to the data from these two regions the case verification is performed. Verification results show that the proposed method can improve the accuracy of one-step ahead wind speed forecasting.

关 键 词：风速预测 风力发电 风电场 小波分解 最小二乘支持向量机 

分 类 号：TM615[电气工程—电力系统及自动化] TM744