基于WRF模式和PSO-LSSVM的风电场短期风速订正

风速预测是风电场风电功率预测的基础与前提,以数值天气预报（WRF模式）为基础进行风速预测,为了提高WRF模式预测的准确性,采用最小二乘支持向量机（Least Squares Support Vector Machine,LSSVM）对WRF模式输出的风速进行订正。同时,为提高LSSVM算法的精确度和减小拟合过程的复杂度,采用粒子群优化算法（Particle Swarm Optimization,PSO）对其参数进行优化。试验结果表明：采用LSSVM订正可以进一步减小WRF模式预测风速的误差,再经过PSO优化后,相对均方根误差和相对平均绝对误差降低了5%～10%,均方根误差下降了0.5 m/s。...

Full description

Saved in:
Bibliographic Details
Published in电力系统保护与控制 Vol. 45; no. 22; pp. 48 - 54
Main Author 叶小岭;顾荣;邓华;陈浩;杨星
Format Journal Article
LanguageChinese
Published 南京信息工程大学信息与控制学院,江苏 南京 210044 2017
南京信息工程大学气象灾害预报预警与 评估协同创新中心,江苏 南京 210044%南京信息工程大学信息与控制学院,江苏 南京,210044
Subjects
PSO-LSSVM
WRF模式
预测效果
风力发电
风速订正
预测效果
WRF model
PSO-LSSVM
wind power
wind speed correction
WRF模式
风速订正
风力发电
forecast effect
Online AccessGet full text
ISSN1674-3415
DOI10.7667/PSPC161827

Cover

More Information
Summary:风速预测是风电场风电功率预测的基础与前提,以数值天气预报（WRF模式）为基础进行风速预测,为了提高WRF模式预测的准确性,采用最小二乘支持向量机（Least Squares Support Vector Machine,LSSVM）对WRF模式输出的风速进行订正。同时,为提高LSSVM算法的精确度和减小拟合过程的复杂度,采用粒子群优化算法（Particle Swarm Optimization,PSO）对其参数进行优化。试验结果表明：采用LSSVM订正可以进一步减小WRF模式预测风速的误差,再经过PSO优化后,相对均方根误差和相对平均绝对误差降低了5%～10%,均方根误差下降了0.5 m/s。与未经优化的LSSVM以及极限学习机（ELM）算法对比分析后得出,粒子群优化最小二乘支持向量机（PSO-LSSVM）对WRF模式预测的风速有较好的订正效果,能进一步提高风速预测的准确性。
Bibliography:YE Xiaoling1,2, GU Rong1, DENG Hua1,2, CHEN Hao1, YANG Xing1 （1. School of Information and Control, Nanjing University of Information Science ＆ Technology, Nanjing 210044, China; 2. Collaborative Innovation Center on Forecast and Evaluation of Meteorological Disasters, Nanjing University of Information Science ＆ Technology, Nanjing 210044, China）
wind power; wind speed correction; WRF model; PSO-LSSVM; forecast effect
41-1401/TM
Wind speed forecasting is the base and precondition of wind power prediction of wind farm. The Numerical Weather Prediction （WRF） model is used to predict wind speed. In order to improve the accuracy of WRF model, the Least Square Support Vector Machine （LSSVM） is used to correct the wind speed of the output of the WRF model. At the same time, in order to improve the accuracy of the LSSVM model and reduce the complexity of the fitting process, Particle Swarm Algorithm （PSO） is used to optimize the parameters. Experimental results show that the LSSVM can further reduce the error of WRF mo
ISSN:1674-3415
DOI:10.7667/PSPC161827