摘要
为提高风电功率预测精度,将混沌时间序列分析应用于风电序列,研究风电数据混沌特性以及混沌时间序列加权一阶局域多步预测法(AOLMM).针对高维相空间中相点间的相关性大小不能被欧式距离精确反映的问题,利用灰色关联度和相点间的距离确定邻近点的权重大小,同时将中心点与邻近点延迟矢量最后一个分量的强相关性考虑在内,改进了预测方法.对风电功率预测分析可见,改进的方法具有较好的适应能力和预测精度.
To improve the accuracy of wind power time series short-term forecasting, the chaotic time series analysis is applied to wind power sequence; the chaotic characteristic of wind power time series and weighted one rank local multi-steps forecasting model(AOLMM) is discussed. The correlation of phase point is not reflected by the Euclid in high embedding dimension phase space, an improved weighted one rank local forecasting model is presented. The weights of grey relational degree and Euclidean distance for phase points are weighted and applied to chaotic local forecasting model; the strongest correlation of center point and the last component of neighborhood are taken into consideration. Through the analysis of the wind power time series prediction, the results show the model has better adaptability and prediction accuracy.
引文
[1] 张庆阳,郭家康.世界风能强国发展风电的经验与对策[J].中外能源,2015,20(6):25-34.Zhang Qingyang,Guo Jiakang.Major wind power using countries’ experience and countermeasures in developing wind energy[J].Sino-Global Energy,2015,20(6):25-34.
[2] 杨茂,季本明.基于局域一阶加权法的风电功率超短期预测研究[J].东北电力大学学报,2015,35(5):6-10.Yang Mao,Ji Benming.The ultra-short-term forecasting of wind power based on local one-order weighted method[J].Journal of Northeast Electric Power University,2015,35(5):6-10.
[3] 黄慧杰,刘华伟.从世界发展趋势展望我国风力发展前景[J].科技创新与应用,2015,(6):115.Huang Huijie,Liu Huawei.Prospect of wind power development in China from the perspective of world development[J].Journal of Electric Power Technology,2015,(6):115.
[4] Zhong Qingchang.Control of Power Inverters in Renewable Energy and Smart Grid Integration[M].IEEE Press,2012.
[5] 段学伟,王瑞琪,王昭鑫,等.风速及风电功率预测研究综述[J].山东电力技术,2015,42(7):26-32.Duan Xuewei,Wang Ruiqi,Wang Zhaoxin,et al.Review of wind speed and wind power prediction methods[J].Shandong Electric Power,2015,42(7):26-32.
[6] 孙佳龙,郭金运,郭淑艳.基于夹角余弦的电离层ETC混沌预测[J].测绘通报,2013,(5):8-11.Sun Jialong,Guo Jinyun,Guo Shuyan.Analysis of chaotic properties and prediction of inonspheric total electron content based on cosine of the angle[J].Bulletin of Surveying and Mapping,2013,(5):8-11.
[7] 廖荣华,兰时勇,刘正熙.基于混沌时间序列局域法的短时交通流量预测[J].计算机技术与发展,2015,25(1):1-5.Liao Ronghua,Lan Shiyong,Liu Zhengxi.Short-term traffic flow forecasting based on local prediction method in chaotic time series[J].Computer Technology and Development,2015,25(1):1-5.
[8] 邓聚龙.灰理论基础[M].武汉:华中科技大学出版社,1992.Deng Julong.Grey Theory Basis[M].Wuhan:Huazhong University of Science and Technology Press,1992.
[9] Takens T.Determing strange attractors in turbulence[J].Lectutr Notes in Mathematics,1981,898:366-381.
[10] 张淑清,贾健,高敏,等.混沌时间序列重构相空间参数选取研究[J].物理学报,2010,59(3):1576-1582.Zhang Shuqing,Jia Jian,Gao Min,et al.Study on the parameters determination for reconstructing phase-space in chaos time series[J].Acta Physica Sinica,2010,59(3):1576-1582.
[11] 雷兴刚,邓君明,麦康森.灰色关联度分析法评价蛋白质营养价值的可行性探讨[J].云南农业大学学报(自然科学版),2010,25(4):545-550.Lei Xinggang,Deng Junming,Mai Kangsen.Research on the feasibility of gray relation analysis in nutritional evaluation of protein[J].Journal of Yunnan Agricultural University (Natural Science),2010,25(4):545-550.
[12] 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.Lü Jinhu,Lu Junan,Chen Shihua.Chaotic Time Series Analysis and Application[M].Wuhan:Wuhan University Press,2002.
[13] Zhong Shihong,Wang Hongqing,Han Hoongwei,et al.Chaotic analysis and adding-weight local-region multi-step forecasting model for wind power time series[J].Journal of Information and Computational Science,2015,12(12):4615-4623.
[14] Fan Xinghua,Li Shasha,Tian Lixin.Chaotic characteristic identification for carbon price and an multi-layer perceptron network prediction model[J].Expert Systems with Applications,2015,42:3945-3952.
[15] De Oliveira F A,Nobre C N,Zarate L E.Applying artifical neural networks to prediction of stock price and improvement of the directional prediction index—Case study of PETR4,Petrobras,Brazil[J].Expert Systems with Applications,2013,40:7596-7606.
[16] Yu Lean,Wang Shuoyang,Lai Kinkeung,et al.A multi scale neural network learning paradigm for financial crisis forecasting[J].Neurocomputing,2010,73:716-725.
[17] Zhu Bangzhu,Wei Yinming.Carbon price forecasting with a novel hybrid arima and least squares support vector machines methodology[J].Omegq-International Journal of Management Science,2013,41:517-524.