摘要
风电功率预测的关键是预测模型的选择和模型性能的优化。选择最小二乘支持向量机(least squares support vector machine,LSSVM)作为风电功率预测模型,使用改进的粒子群算法(improved particle swarm optimization algorithm,IPSO)对影响最小二乘支持向量机回归性能的参数进行优化。在建立了改进的粒子群算法优化最小二乘支持向量机(LSSVM)的风电功率预测模型后,运用该模型对广西某风电场进行了仿真研究。为了对比研究,同时使用前馈(back propagation,BP)神经网络模型和支持向量机(support vector machine,SVM)模型进行了预测。最后采用多种误差指标对三种模型的预测结果进行综合分析。结果表明,使用改进的粒子群算法优化最小二乘向量机(IPSO-LSSVM)的风电功率预测模型具有较高的预测精度。
The keys of wind power forecasting are the forecasting model selection and model optimization. The least squares support vector machine (LSSVM) is chosen as the wind power prediction model. Improved particle swarm optimization algorithm (IPSO) is used to optimize the most important parameters which influence the least squares support vector machine (LSSVM) regression model First, the wind power prediction model based on IPSO-LSSVM is built, which is used to predict the short-term (3 hours) wind power. For comparative study, Back Propagation (BP) neural network model and the traditional support vector machine (SVM) model are used for forecasting. Several error indicators are selected to analyze the results of the three models. Prediction analysis results show that compared with back-propagation artificial neural networks and support vector machine, the IPSO-LSSVM model can achieve higher prediction accuracy.
出处
《电力系统保护与控制》
EI
CSCD
北大核心
2012年第24期107-112,共6页
Power System Protection and Control
基金
国家自然科学基金项目(61074101)
博士点基金项目(20110141110032)
教育部中央高校基本科研业务费专项资金资助(20112072020008)~~
关键词
风电功率预测
改进粒子群算法
最小二乘支持向量机
IPSO-LSSVM
误差分析
wind power prediction
improved particle swarm optimization (IPSO)
least squares support vector machine (LSSVM)
IPSO-LSSVM
error analysis