发布时间 : 星期四 文章2011年电工杯数学建模全国一等奖论文更新完毕开始阅读
七、参考文献
【1】Bailey B, Brower MC, Zack J. Short-term wind forecasting[C] . European Wind Energy Conference, Nice France, 1999:1062-1065
【2】www.cwpc.cn/cwpc/zh-cn/system
【3】M.Alexiadis, P.Dokopoulos, H.Sahsamanoglou, I.Manousaridos.Short term forecasting of wind speed and related electrical power. Solar Energy.1998,63(1)
【4】邓自立,卡尔曼滤波与维纳滤波[M],哈尔滨:哈尔滨工业大学出版社,2001
【5】丁明,张立军,吴义纯,基于时间序列分析的风电场风速预测模型[J],电力自动化设备,2008,8(25):32,34
【6】时庆华,高山,基于ARMA和神经网络的风电场短期风速预测,2009 【7】时庆华,高山,基于ARMA和卡尔曼滤波的风电场风电功率预测研究,第25届全国高校电力系统及其自动化专业学术年会,2009
【8】蒋宗礼,人工神经网络导论[M],北京:高等教育出版社,2001:97-106 【9】魏晓霞,我国风电发展存在的问题和应对措施[J],电力技术经济,2009,21(6):23-26
【10】韩爽,风电场功率预测方法研究[D],华北电力大学,2008
【11】Pinson P,Kariniotakis G N.Wind Power Forecasting Using Fuzzy Neural Networks Enhanced with On-line Prediction Risk Assessment[A]. in: Power Tech Conference Proceedings 2003 IEEE[C]. Bologna: 2003. 【12】Damousis I G, Dokopoulos P. A Fuzzy Expert System for the Forecasting of Wind Speed and Power Generation in Wind Farms[J]. Power Industry Computer Applications,2001,(4):63-69.
【13】Wang P , Billinton R . Time-sequential Simulation Technique for Rural Distribution System Reliability Cost/worth Evaluation Including Wind Generation as Alternative Supply[J].IEEE Proceedings on Gener, Transm,andDistrib, 2001,148(4):355-360.
【14】 Li S.Wind Power Prediction Using Recurrent Multilayer Perceptron Neural Networks[A]. in: Power Engineering Society General Meeting, IEEE[C].2003.2325-2330.
【15】CAO Lei,LI Ran.Short-Term Wind Speed Forecasting Model for Wind Farm Based on Wavelet Decomposition[J].IEEE Trans on DRPT,2008:2525-2529
【16】LI Shu-hui,Wunsch D,O'Hair E,et al.Using Neural Networks to Estimate Wind Turbine Power Generation[A]. in: Power Engineering Society Winter Meeting[C].2001.977.
39
【17】楼顺天,施阳, 基于Matlab 的系统分析与设计——神经网络[M]. 西 安:西安电子科技大学出版社,2000.
40
附录:
%遗传神经网络主函数 input_train=input'; output_train=output'; input_test=input_test';
[inputn,inputps]=mapminmax(input_train); [outputn,outputps]=mapminmax(output_train);
net=newff(inputn,outputn,12);
net.trainParam.epochs=30; net.trainParam.lr=0.001; net.trainParam.goal=0.0000004;
net=train(net,inputn,outputn);
inputn_test=mapminmax('apply',input_test,inputps);
an=sim(net,inputn_test);
BPoutput=mapminmax('reverse',an,outputps);
[~,in]=size(BPoutput);
BPoutput(1:in-1)=BPoutput(2:in); BPoutput(in)=output_test(in); figure(1)
plot(BPoutput,'-og') holdon
plot(output_test,'-*');
41
legend('预测值','实际值','fontsize',12) title('·风力电机功率预测曲线图','fontsize',12) [xx,~]=size(BPoutput);
plot(1:xx,BPoutput,1:xx,output_test) xlabel('样本点','fontsize',12) ylabel('输出功率','fontsize',12) print-dtiff-r6004-3 %?¤2a?ó2?
error=BPoutput-output_test;
figure(2) plot(error,'-*') title('神经网络预测误差')
figure(3)
plot((output_test-BPoutput)./BPoutput,'-*');title('神经网络预测误差百分比')
errorsum=sum(abs(error));
%遗传主函数
inputnum=4; hiddennum=8; outputnum=1;
input_train=input'; input_test=output';
42