全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...
电网技术  2015 

基于混沌时间序列GA-VNN模型的超短期风功率多步预测

DOI: 10.13335/j.1000-3673.pst.2015.08.015, PP. 2160-2166

Keywords: 混沌时间序列,BP神经网络,GA算法,Volterra泛函模型,风功率超短期多步预测

Full-Text   Cite this paper   Add to My Lib

Abstract:

随着风电在电力系统中的渗透水平不断提高,能准确、可靠地进行风功率预测至关重要。为提高风功率超短期预测精度,利用风功率时间序列的混沌特性,推导分析了Volterra泛函模型和3层前馈(backpropagation,BP)神经网络在结构上的一致性,提出混沌时间序列遗传算法-Volterra神经网络(geneticalgorithm-Volterraneuralnetwork,GA-VNN)模型,对超短期风功率进行多步预测。该模型将实用的Volterra泛函模型和BP神经网络结合起来,解决了求解Volterra泛函模型高阶核函数的问题。同时设计了一种混沌时间序列GA-VNN模型的学习算法,在算法中利用GA全局寻优能力来优化BP神经网络,获得最优的初始权值和阀值。将上述方法应用于某风电场风功率超短期多步预测中,结果验证了所提模型的多步预测性能明显优于Volterra预测滤波器和BP神经网络。

References

[1]  林少伯,韩民晓,赵国鹏,等.基于随机误差的分布式光伏配网储能系统容量配置方法[J].中国电机工程学报,2013,33(4):25-33.Lin Shaobo,Han Minxiao,Zhao Guopeng,et al.Capacity allocation of energy storage in distributed photovoltaic power system based on stochastic prediction error[J].Proceedings of the CSEE,2013,33(4):25-33(in Chinese).
[2]  范高峰,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,2008,28(34):118-123.Fan Gaofeng,Wang Weisheng,Liu Chun,et al.Wind power prediction based on artificial neural network[J].Proceedings of the CSEE,2008,28(34):118-123(in Chinese).
[3]  冬雷,王丽婕,郝颖,等.基于自回归滑动平均模型的风力发电容量预测[J].太阳能学报,2011,32(5):617-622.Dong lei,Wang Lijie,HaoYing,et al.Prediction of wind power generation based on autoregressive moving average model[J].Acta Energiae Solaris Sinica,2011,32(5):617-622(in Chinese).
[4]  Bossanyi E A.Short-term wind prediction using Kalman filter[J].Wind Engineering,1985,9(1):1-8.
[5]  刘瑞叶,黄磊.基于动态神经网络的风电场输出功率预测[J].电力系统自动化,2012,36(11):19-37.Liu Ruiye,Huang Lei.Wind power forecasting based on dynamic neural networks[J].Automation of Electric Power Systems,2012,36(11):19-37(in Chinese).
[6]  Barbounis T G,Theocharis J B.Locally recurrent neural networks for wind speed prediction using spatial correlation[J].Information Sciences,2007,177(24):5775-5797.
[7]  王贺,胡志坚,陈珍,等.基于集合经验模态分解和小波神经网络的短期风功率组合预测[J].电工技术学报,2013,29(9):137-144.Wang He,Hu Zhijian,Chen Zhen,et al.A hybrid model for wind power forecasting based on ensemble empirical mode decomposition and wavelet neural networks[J].Transactions of China Electrotechnical Society ,2013,28(9):137-144(in Chinese).
[8]  叶林,刘鹏.基于经验模态分解和支持向量机的短期风电功率组合预测模型[J].中国电机工程学报,2011,31(31):102-108.Ye Lin,Liu Peng.Combined model based on EMD-SVM for short-term wind power prediction[J].Proceedings of the CESS,2011,31(31):102-108(in Chinese).
[9]  王丽婕,廖晓钟,高爽,等.并网型大型风电场风力发电功率-时间序列的混沌属性分析[J].北京理工大学学报,2007,27(12):1077-1080.Wang Lijie,Liao Xiaozhong,Gao Shuang,et al.Chaos characteristics analysis of wind power generation time series for a grid connecting wind farm[J].Transactions of Beijing Institute of Technology,2007,27(12):1077-1080(in Chinese).
[10]  张家树,肖先赐.混沌时间序列的Volterra自适应预测[J].物理学报,2000,49(3):404-408.Zhang Jiashu,Xiao Xianci.Prediction low-dimensional chaotic time series using Volterra adaptive filers[J].Acta Physica Sinica,2000,49(3):404-408(in Chinese).
[11]  Chatterjee A.Parameter estimation of Duffing oscillator using Volterra series and multi-tone excitation[J].Neural Networks,2009,22(1):343-347.
[12]  张雪清,梁军.风电功率时间序列混沌特性分析及预测模型研究[J].物理学报,2012,61(19):70-81.Zhang Xueqing,Liang Jun.Chaotic characteristics analysis and prediction model study on wind power time series[J].Acta Physica Sinica,2012,61(19):70-81(in Chinese).
[13]  王松岩,李碧君,于继来,等.风速与风电功率预测误差概率分布的时变特性分析[J].电网技术,2013,37(4):967-973.Wang Songyan,Li Bijun,Yu Jilai,et al.Analysis on time-varying characteristics of probability error in forecast of wind speed and wind power[J].Power System Technology,2013,37(4):967-973(in Chinese).
[14]  殷礼胜,何怡刚,董学平,等.交通流量VNNTF神经网络模型多步预测研究[J].自动化学报,2014,40(9):2066-2072.Yin Lisheng,He Yigang,Dong Xueping,et al.Research on the multi-step prediction of Volterra neural network for traffic flow[J].Acta Automatica Sinica,2014,40(9):2066-2072(in Chinese).
[15]  Li Shuhui,Wunsch Donald C,O'Hair Edgar A,et al.Using neural network to estimate wind turbine power generation[J].IEEE Transactions on Energy Conversion,2004,16(3):523-536.
[16]  Yu Jiali,Zhang Yi,Zhou Jiliu.Continuous attractors of Lotka-Volterra recurrent neural networks with infinite neurons[J].IEEE Transactions on Neural Networks,2010,21(10):1690 -1695.
[17]  孟洋洋,卢继平,孙华利,等.基于相似日和人工神经网络的风电功率短期预测[[J].电网技术,2010,34(12):163-167.Meng Yangyang,Lu Jiping,Sun Huali,et al.Short-term wind power forecasting based on similar days and artificial neural network[J].Power System Technology,2010,34(12):163-167(in Chinese).
[18]  门志国,彭秀艳,王兴梅,等.基于GA优化BP神经网络辨识的Volterra级数核估计算法[J].南京理工大学学报,2012,36(6):962-967.Meng Zhiguo,Peng Xiuyan,Wang Xingmei,et al.Volterra series kernels estimation algorithm based on GA optimized BP neural network identification[J].Journal of Nanjing University of Science and Technology,2012,36(6):962-967(in Chinese).
[19]  程洪亮,张国贤,包海昆.基于GA神经网络的自适应预测控制的设计与仿真[J].系统仿真学报,2003,15(5):718-721.Cheng Hongliang,Zhang Guoxian,Bao Haikun.The design and simulation of a self-tuning predictive control based on neural network optimized by genetic algorithm[J].Journal of System Simulation,2003,15(5):718-721(in Chinese).

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133