黄勇东,陈冬沣,肖建华,林艺城,董朕
HUANG Yondong,CHEN Dongfeng,XIAO Jianhua,LIN Yicheng,DONG Zhen

• 1:广东电网有限责任公司揭阳供电局
• 2:广东工业大学自动化学院

摘要(Abstract)：

风速预测在风电场的智能管理和安全并网中起着至关重要的作用,针对风速预测固有的波动性、间歇性和非线性等特点,以及常规BP神经网络和差分算法神经网络均存在容易陷入局部最优导致收敛过早、泛化能力不足等缺陷,提出一种综合WPD和IDE算法的短期风速预测神经网络方法。该方法首先利用WPD将风速的时间序列分解成多种不同频率的子序列,然后采用IDE算法优化后的神经网络对小波包分解后的每个不同频率的子序列进行单步预测,最后将预测后的各个子序列进行叠加,得出最终预测结果。为验证所提方法的有效性,将其分别与采用混合小波分解的BP神经网络风速预测方法和混合小波分解的差分算法风速预测神经网络方法进行对比,对某地区的实际风速数据进行实验仿真,结果表明,所提方法的预测精度明显优于其他算法。
Wind speed forecasting is of great importance for intelligent wind farm management power system integration safety. Wind speed forecast is characterized by inherent volatility, intermittence and nonlinearity;in addition, the conventional back propagation(BP) neural network and differential evolution(DE) neural network tend to fall into local optimal which leads to premature convergence and weak generalization ability. The paper presents a short-term wind speed forecast method based on neural network, which combines wavelet packet decomposition(WPD) with improved differential evolution(IDE). Firstly, WPD is employed to decompose the wind speed time series into sub-series with different frequencies. Secondly, the IDE optimized neural is used for single-step prediction of the sub-series. The eventual predicted results are obtained through sub-series aggregation. To verify the proposed method, it is respectively compared with the wind speed forecasting method based on neural networks that adopts hybrid WPD and wind speed forecasting method based on DE that adopts hybrid WPD. Experimental simulation is conducted on actual wind speed data in a specific area,which demonstrates that forecast accuracy of the proposed method is comparatively higher.

关键词(KeyWords)： 差分算法;小波包分解;风速预测;神经网络
differential evolution;wavelet packet decomposition;wind speed forecasting;neural network

Abstract:

Keywords:

基金项目(Foundation): 广东省科技计划项目(2016A010104016);; 广东电网公司科技项目(GDKJQQ20152066)

作者(Author): 黄勇东,陈冬沣,肖建华,林艺城,董朕
HUANG Yondong,CHEN Dongfeng,XIAO Jianhua,LIN Yicheng,DONG Zhen

DOI: 10.19585/j.zjdl.201706001

参考文献(References)：

• [1]王德明,王莉,张广明.基于遗传BP神经网络的短期风速预测模型[J].浙江大学学报(工学版).2012,46(5):837-841.
• [2]全球风力发电市场前景乐观各国竞相开发风能资源[J].浙江电力,2006,25(4):46.
• [3]黄文杰,傅砾,肖盛.采用改进模糊层次分析法的风速预测模型[J].电网技术,2010,34(7):164-168.
• [4]王韶,杨江平,李逢兵,等.基于经验模式分解和神经网络的短期风速组合预测[J].电力系统保护与控制,2012,40(10):6-11.
• [5]CHEN N,QIAN Z,NABNEY I T,et al.Wind Power Forecasts Using Gaussian Processes and Numerical Weather Prediction[J].IEEE Transactions on Power Systems,2014,29(2):656-665.
• [6]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.
• [7]孙斌,姚海涛,刘婷.基于高斯过程回归的短期风速预测[J].中国电机工程学报,2012,32(29):104-109.
• [8]邰能灵,侯志俭,李涛,等.基于小波分析的电力系统短期负荷预测方法[J].中国电机工程学报,2003,23(1):45-50.
• [9]BASHIR Z A,El-Hawary M E.Applying Wavelets to Short-Term Load Forecasting Using PSO-Based Neural Networks[J].IEEE Transactions on Power Systems 2009,24(1):20-27.
• [10]KHAJEH M,HEZARYAN S.Combination of ACO-artificial neural network method for modeling of manganese and cobalt extraction onto nanometer Si O2from water samples[J].Journal of Industrial and Engineering Chemistry,2013,19(6):2100-2107.
• [11]陈海燕,蔡嗣经,郑明贵.中国能源可持续发展的遗传神经网络评价[J].太阳能学报,2010,31(9):1220-1224.
• [12]ZHUO L,ZHANG J,DONG P,et al.An SA-GA-BP neural network-based color correction algorithm for TCMtongue images[J].Neurocomputing,2014,134(9):111-116.
• [13]郑一鸣,孙淑莲,孙翔,等.基于自适应小波分析的在线油色谱数据预处理方法[J].浙江电力,2016,35(11):1-6.
• [14]戈剑武,祁荣宾,钱锋,等.一种改进的自适应差分进化算法[J].华东理工大学学报,2009,35(4):600-605.
• [15]孟安波,卢海明,胡函武,等.混合小波包与纵横交叉算法的风电预测神经网络模型[J].太阳能学报,2015,36(7):1645-1651.
• [16]杨锡运,孙宝君,张新房,等.基于相似数据的支持向量机短期风速预测仿真研究[J].中国电机工程学报,2012,32(4):35-41.
• [17]CADENAS E,RIVERA W.Wind speed forecasting in three different regions of Mexico,using a hybrid ARIMA-ANN model[J].Renewable Energy,2010,35(12):2732-2738.