基于主成分分析法的风电功率短期组合预测

Abstract
Figure/Table
References
Related Citation (15)

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 words： wind 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:

http://dqjs.cesmedia.cn/EN/Y2016/V17/I7/41

[1] 何东, 刘瑞叶. 基于主成分分析的神经网络动态集成风功率超短期预测[J]. 电力系统保护与控制, 2013, 4(4): 50-54.
[2] 周松林, 茆美琴, 苏建徽. 基于主成分分析与人工神经网络的风电功率预测[J]. 电网技术, 2011, 35(9): 128-132.
[3] 杨秀媛, 肖洋, 陈树勇. 风电场风速和发电功率预测研究[J]. 中国电机工程学报, 2005, 25(11): 1-5.
[4] 范高锋, 王伟胜, 刘纯. 基于人工神经网络的风电功率短期预测系统[J]. 电网技术, 2008(22): 72-76.
[5] 杨志凌, 刘永前. 应用粒子群优化算法的短期风电功率预测[J]. 电网技术, 2011, 05(5): 159-164.
[6] 陈宁, 沙倩, 汤奕, 等. 基于交叉熵理论的风电功率组合预测方法[J]. 中国电机工程学报, 2012(4): 29-34, 22.
[7] 孟安波, 陈育成. 基于虚拟预测与小波包变换的风电功率组合预测[J]. 电力系统保护与控制, 2014, 3(3): 71-76.
[8] 罗毅, 刘峰, 刘向杰. 基于主成分—遗传神经网络的短期风电功率预测[J]. 电力系统保护与控制, 2012(23): 47-53.
[9] 王丽婕, 冬雷, 高爽. 基于多位置NWP与主成分分析的风电功率短期预测[J]. 电工技术学报, 2015, 5(5): 79-84.
[10] 王丽婕, 冬雷, 廖晓钟, 等. 基于小波分析的风电场短期发电功率预测[J]. 中国电机工程学报, 2009(28): 30-33.
[11] 范高锋, 王伟胜, 刘纯, 等. 基于人工神经网络的风电功率预测[J]. 中国电机工程学报, 2008(34): 118-123.
[12] 王贺, 胡志坚, 仉梦林. 基于模糊信息粒化和最小二乘支持向量机的风电功率波动范围组合预测模型[J]. 电工技术学报, 2014(12): 218-224.
[13] Ernst B, Oakleaf B, Ahlstrom ML, et al. Predicting the wind[J]. Power and Energy Magazine, IEEE, 2007, 5(6): 78-89.
[14] Peiyuan C, Pedersen T, Bak-Jensen B, et al. ARIMA-based time series model of stochastic wind power Generation[J]. IEEE Transactions on Power Systems, 2010, 25(2): 667-676.
[15] Chen Xia, Dong Zhaoyang, Meng Ke, et al. Electricity price forecasting with extreme learning machine and bootstrapping[J]. IEEE Transactions on Power Systems, 2012, 27(4): 2055-2062.
[16] 刘纯, 范高锋, 王伟胜, 等. 风电场输出功率的组合预测模型[J]. 电网技术, 2009(13): 74-79.
[17] Rodrigues AB, Da Silva MD. Confidence intervals estimation for reliability data of power distribution equipments using bootstrap[J]. IEEE Transactions on Power Systems, 2013, 28(3): 3283-3291.
[18] Khosravi A, Nahavandi S, Creighton D. Prediction intervals for Short-Term wind farm power Generation forecasts[J]. IEEE Transactions on Sustainable Energy, 2013, 4(3): 602-610.
[19] 风电场功率预测预报管理暂行办法[S]. 北京: 国家能源局, 2011
[20] 风电功率预测功能规范[S]. 北京: 国家电网公司, 2011.