文章基本信息

标题：Hybrid WT-PSO based Neural Networks for Single Step-Ahead Wind Power Prediction for Ontario Electricity Market
本地全文：下载
作者：Saroha ; Sanjeev Kumar Aggarwal
期刊名称：International Journal on Electrical Engineering and Informatics
印刷版ISSN：2085-6830
出版年度：2015
卷号：7
期号：2
DOI：10.15676/ijeei.2015.7.2.6
出版社：School of Electrical Engineering and Informatics
摘要：Wind Power forecasting is an important subject of concern for reliableoperations of grid and it has been studied from different points of views of bothaccuracy and reliability. So with an aim of improvement in prediction accuracy thispaper presents a hybrid wind power prediction machine for Ontario Electricity Market(OEM) on single step ahead basis in which Wavelet Transform (WT) is used for preprocessingof input wind power data, then the pre-processed data is trained by neuralnetworks. In this initially, the parameters of neural networks (biases & weights) areinitialized as random &then at second stage are optimized by Particle SwarmOptimization (PSO) base training algorithm. The varying time series input training datapatterns are used in order to remove the overtraining & over-fitting problem so that themaximum accuracy is achieved. The results of proposed method are compared withNaive Predictor, Feed Forward Neural Networks (FFNN) & Particle SwarmOptimization based Neural Network (PSONN) and is presented in the form ofcomparative tables on Mean absolute error (MAE) & mean absolute percentage error(MAPE) scale with emphasis on weekly as well as monthly predictions. The data usedby proposed model for estimation is collected from Ontario Electricity Market for theyear 2009-12 and tested for such a long period of one year on single step ahead basis. Itis found that the accuracy of proposed model is far better than the other models.
关键词：Particle Swarm Optimization; wavelet transform; neural networks; time;series; wind power