程泽;刘冲;刘力;

• 1:天津大学电气工程与自动化学院
• 2:天津内燃机研究所

摘要(Abstract)：

针对光伏发电可预测性低的问题,提出了一种综合使用通径分析(path analysis,PA)、k近邻算法(k-Nearest Neighbor,KNN)、神经网络分位数回归(quantile regression neural network,QRNN)和核密度估计(kernel density estimator,KDE)的光伏出力概率分布估计方法,构造出未来1 d任意时刻的光伏出力概率密度函数,可以得到比点预测和区间预测更多的有用信息。首先由通径分析对气象因素进行约减,在降低模型输入维数的基础上减小变量间的耦合作用。然后通过K-means算法按天气类型对历史样本进行聚类,进一步提高相似样本的筛选效果。最后利用神经网络分位数回归和核密度估计对光伏出力的概率分布进行估计。实验结果表明,相比于核密度估计和传统的正态分布估计方法,采用所提方法估计出的概率分布的可靠性和锐度更高。

关键词(KeyWords)： 神经网络分位数回归;通径分析;核密度估计;光伏发电;概率分布

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金项目(61374122)~~

作者(Author): 程泽;刘冲;刘力;

Email:

DOI: 10.13335/j.1000-3673.pst.2016.0958

参考文献(References)：

• [1]北极星太阳能光伏网.2016年中国光伏产业发展形势展[EB/OL].2016-01-15[2016-02-27].http://guangfu.bjx.com.cn/news/20160115//701651/701651.shtml.
• [2]梅生伟,朱建全.智能电网中的若干数学与控制科学问题及其展望[J].自动化学报,2013,39(2):119-131.Mei Shengwei,Zhu Jianquan.Mathematical and control scientific issues of smart grid and its prospects[J].Acta Automatica Sinica,2013,39(2):119-131(in Chinese).
• [3]江岳春,张丙江,邢方方,等.基于混沌时间序列GA-VNN模型的超短期风功率多步预测[J].电网技术,2015,39(8):2160-2166.Jiang Yunchun,Zhang Bingjiang,Xing Fangfang,et al.Super-shortterm multi-step prediction of wind power based on GA-VNN model of chaotic time series[J].Power System Technology,2015,39(8):2160-2166(in Chinese).
• [4]陈昌松,段善旭,殷进军.基于神经网络的光伏阵列发电预测模型的设计[J].电工技术学报,2009,24(9):153-158.Chen Changsong,Duan Shanxu,Yin Jinjun.Design of photovoltaic array power forecasting model based on neutral network[J].Transactions of China Electrotechnical Society,2009,24(9):153-158(in Chinese).
• [5]李育强,晁勤,索南加乐.基于线性回归算法光伏电站短期功率预报模型研究[J].可再生能源,2013,31(1):25-28.Li Yuqiang,Chao Qin,Suonan Jiale.Research on photovoltaic power station short-term power forecast model based on the linear regression algorithm[J].Renewable Energy Resource,2013,31(1):25-28(in Chinese).
• [6]刘达.基于误差校正的中长期负荷预测模型[J].电网技术,2012,36(8):243-247.Liu Da.A model for medium-and long-term power load forecasting based on error correction[J].Power System Technology,2012,36(8):243-247(in Chinese).
• [7]Kaplani E,Kaplanis S.A stochastic simulation model for reliable PV system sizing providing for solar radiation fluctuation[J].Applied Energy,2012,97(1):970-981.
• [8]王守相,张娜.基于灰色神经网络组合模型的光伏短期出力预测[J].电力系统自动化,2012,36(19):37-41.Wang Shouxiang,Zhang Na.Short-term output power forecast of photovoltaic based on a grey and neural network hybrid model[J].Automation of Electric Power Systems,2012,36(19):37-41(in Chinese).
• [9]栗然,李光敏.基于支持向量机回归的光伏发电出力预测[J].中国电力,2008,41(2):74-78.Li Ran,Li Guangmin.Photovoltaic power generation output forecasting based on support vector machine regression technique[J].Electric Power,2008,41(2):74-78(in Chinese).
• [10]丁明,鲍玉莹,毕锐.应用改进马尔科夫链的光伏出力时间序列模拟[J].电网技术,2016,40(2):459-464.Ding Ming,Bao Yuying,Bi Rui.Simulation of PV output time series used improved Markov chain[J].Power System Technology,2016,40(2):459-464(in Chinese).
• [11]Huang C M,Chen S J,Yang S P,Kuo C J.One-day-ahead hourly forecasting for photovoltaic power generation using an intelligent method with weather-based forecasting models[J].IET Generation,Transmission&Distribution,2015,14(9):1874-1882.
• [12]Al Hakeem D,Mandal P,Haque A U.A new strategy to quantify uncertainties of wavelet-GRNN-PSO based solar PV power forecasts using bootstrap confidence intervals[C]//Power&Energy Society General Meeting.Denver,CO:IEEE,2015:1-5.
• [13]Joao Gari da Silva Fonseca Jun,Takashi Oozeki.On the use of maximum likelihood and input data similarity to obtain prediction intervals for forecasts of photovoltaic power generation[J].Journal of Electrical Engineering&Technology,2015,10(3):1342-1348.
• [14]赵维嘉,张宁,康重庆,等.光伏发电出力的条件预测误差概率分布估计方法[J].电力系统自动化,2015,39(16):8-15.Zhao Weijia,Zhang Ning,Kang Chongqing,et al.A method of probabilistic distribution estimation of conditional forecast error for photovoltaic power generation[J].Automation of Electric Power Systems,2015,39(16):8-15(in Chinese).
• [15]Zhang Yao,Wang Jianxue.GEFCom2014 probabilistic solar power forecasting based on k-Nearest neighbor and kernel density estimator[C]//Power&Energy Society General Meeting.Denver,CO:IEEE,2015:1-5.
• [16]Golestaneh F,Pinson P,Gooi H B.Very short-term non-parametric probabilistic forecasting of renewable energy generation-with application to solar energy[J].IEEE Transactions on Power Systems,2007,PP(99):1-14.
• [17]Global energy forecasting competition 2014[EB/OL].2014-08-15[2016-01-27].http://www.crowdanalytix.com/contests/global-energyforecasting-competition-2014-probabilistic-solar-power-forecasting.
• [18]Hong T,Pinson P,Fan S.Global energy forecasting competition2012[J].International Journal of Forecasting,2014,30(2):357-363.
• [19]Taylor J W.A quantile regression neural network approach to estimating the conditional density of multiperiod returns[J].Journal of Forecasting,2000,19(4):299-311.
• [20]Donaldson R G,Kamstra M.Forecast combining with neural networks[J],Journal of Forecasting,1996,15(1):49-61.
• [21]Wand P,Jones C.Kernel smoothing[M].London:Chapman&Hall,1994:58-86.