Electrical Engineering  2016, Vol. 17 Issue (7): 41-47    DOI:
Research & Development Current Issue| Next Issue| Archive| Adv Search |
The Combination Forecasting Model for Wind Farm Power based on PCA
Wu Jinhao, Yang Xiuyuan, Sun Jun
Beijing Information Science and Technology University, Beijing 100192

Download: PDF (9877 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  Intermittency and uncertainty is the inherent characteristics of the wind power and in the rapid development of wind power generation background the importance of wind power forecasting is becoming more and more obvious. In order to reduce the error of the single model and are improve the prediction accuracy and relative error rate of the whole forecasting method, the paper combine two basic models of BP neural network and support vector machine(SVM), and introduce the particle swarm and cross validation to optimize the parameters. The original data are preprocessed by principal component analysis (PCA). In the premise of little reducing the accuracy of prediction, the original data is reduced to the dimension of the original data to improve the operation efficiency. The results show that the NMAE and NRMSE of the combined forecasting model meet the domestic current index. And the accuracy of the model is improved, and the relative error is more stable. This method can effectively reduce the appearance of large errors. In the final, these prove the feasibility of the combination forecasting model for wind farm power based on PCA.
Key wordswind power forecast      principal components analysis (PCA)      BP neural network      particle swarm      support vector machine (SVM)      forecast combination     
Published: 27 July 2016
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
Wu Jinhao
Yang Xiuyuan
Sun Jun
Cite this article:   
Wu Jinhao,Yang Xiuyuan,Sun Jun. The Combination Forecasting Model for Wind Farm Power based on PCA[J]. Electrical Engineering, 2016, 17(7): 41-47.
URL:  
https://dqjs.cesmedia.cn/EN/Y2016/V17/I7/41
Copyright © Electrical Engineering
Supported by: Beijing Magtech