基于相空间重构的风电场日有功功率组合预测Combined Prediction of Daily Active Power in Wind Farm Based on Phase Space Reconstruction
陈伟;赵庆堂;郭建鹏;王维州;肖骏;
摘要(Abstract)：
风力发电具有波动性、随机性和间歇性,因此准确预测风电场的日有功功率对风电场与电力系统的稳定运行具有重要的意义。利用C-C法对风电场的日有功功率时间序列进行相空间重构,并通过计算其最大Lyapunov指数,验证了此功率时间序列具有混沌属性。在此基础上,用相空间重构建立了RBF神经网络和最小二乘支持向量机预测模型,对预测结果采用协方差优选确定权重,进行组合预测。通过对甘肃省酒泉地区某风电场的实测数据进行仿真,证明了该组合模型的有效性和可行性,并有效提高了预测精度。
关键词(KeyWords)： 风力发电;相空间重构;RBF神经网络;最小二乘支持向量机;组合预测
基金项目(Foundation): 国家自然科学基金资助项目(51267012);; 甘肃省电网公司科技项目(2010406029);; 甘肃省高等学校基本科研业务费专项资金项目(1103ZTC141)
作者(Authors): 陈伟;赵庆堂;郭建鹏;王维州;肖骏;
参考文献(References)：
- [1]丁明,吴义纯,张立军(Ding Ming,Wu Yichun,Zhang Lijun).风电场风速概率分布参数计算方法的研究(Study on the algorithm to the probabilistic distribution parameters of wind speed in wind farms)[J].中国电机工程学报(Proceedings of the CSEE),2005,25(10):107-110.
- [2]Damousis I G,Alexiadis M C,Theocharis J B,et al.A fuzzy model for wind speed prediction and power generation in wind parks using spatial correlation[J].IEEE Trans on Energy Conversion,2004,19(2):352-361.
- [3]Ernst B,Oakleaf B,Ahlstrom M L,et al.Predicting the wind[J].IEEE Power&Energy Magazine,2007,5(6):79-89.
- [4]王丽捷,廖晓钟,高阳,等(Wang Lijie,Liao Xiaozhong,Gao Yang,et al).风电场发电功率的建模和预测研究综述(Summarization of modeling and prediction of wind power generation)[J].电力系统保护与控制(Power System Protection and Control),2009,37(13):118-121.
- [5]马轶东,何怡刚,王桓(Ma Yidong,He Yigang,Wang Huan).运用BP神经网络的电力负荷混沌多步预测(Chaotic multi-step forecasting of power load applying BP neural network)[J].电力系统及其自动化学报(Proceedings of the CSU-EPSA),2010,22(4):81-84.
- [6]武小梅,白银明,文福拴(Wu Xiaomei,Bai Yinming,Wen Fushuan).基于RBF神经元网络的风电功率短期预测(Short-term wind power forecast based on the radial basis function neural network)[J].电力系统保护与控制(Power System Protection and Control),2011,39(15):80-83.
- [7]蔡凯,谭伦农,李春林,等(Cai Kai,Tan Lunnong,Li Chunlin,et al).时间序列与神经网络法相结合的短期风速预测(Short-term wind speed forecasting combing time series and neural network method)[J].电网技术(Power System Technology),2008,32(8):82-85,90.
- [8]金群,李欣然(Jin Qun,Li Xinran).遗传算法参数设置及其在负荷建模中应用(GA parameter setting and its application in load modeling)[J].电力自动化设备(Electric Power Automation Equipment),2006,26(5):23-27.
- [9]孟思齐,杨洪耕(Meng Siqi,Yang Honggeng).基于灰色生成的卡尔曼滤波短期负荷预测(Short-term load forecasting using Kalman filter based on grey generation)[J].电力系统及其自动化学报(Proceedings of the CSU-EPSA),2008,20(6):78-82.
- [10]戚双斌,王维庆,张新燕(Qi Shuangbin,Wang Weiqing,Zhang Xinyan).基于支持向量机的风速与风功率预测方法研究(Wind speed and wind power prediction based on SVM)[J].华北电力(East China Electric Power),2009,37(9):1600-1603.
- [11]肖先勇,葛嘉,何德胜(Xiao Xianyong,Ge Jia,He Desheng).基于支持向量机的中长期电力负荷组合预测(Combination method of mid-long term load forecasting based on support vector machine)[J].电力系统及其自动化学报(Proceedings of the CSU-EPSA),2008,20(1):84-88.
- [12]牛晨光,刘丛(Niu Chenguang,Liu Cong).基于相空间重构的神经网络短期风电预测模型(Neural network model for short-term wind power prediction based on phases space reconstruction)[J].中国电力(Electric Power),2011,44(11):73-77.
- [13]吕涛,唐巍,所丽(LüTao,Tang Wei,Suo Li).基于混沌相空间重构理论的风电场短期风速预测(Prediction of short-term wind speed in wind farm based on chaotic phase space reconstruction theory)[J].电力系统保护与控制(Power System Protection and Control),2010,38(21):113-117.
- [14]吕金虎,陆君安,陈士华.混沌时间序列分析及其应用[M].武汉:武汉大学出版社,2002.