摘要
为了保障电力系统的稳定运行和合理的调度分配,提高预测系统的预测精度,提出一种自主学习建立气象模型库的光伏功率预测方法。介绍该方法的实现过程,并通过实例分析该方法的预测结果。
In order to ensure the stable operation of power system and reasonable dispatch and distribution,aphotovoltaic power prediction method based on self-learning and building meteorological model library was proposed.The implementation process of the method was introduced,and the prediction results of the method were analyzed by an example.
引文
[1]龚莺飞,鲁宗相,乔颖,等.光伏功率预测技术[J].电力系统自动化,2016(04):140-151.
[2]2016年光伏发电统计信息[EB/OL].[2017-02-04].http://www.nea.gov.cn/2017-02/04/c_136030860.htm.
[3]吕双辉,蔡声霞,王守相.分布式光伏-储能系统的经济性评估及发展建议[J].中国电力,2015(02):139-144.
[4]YONA A,SENJYU T,FUNABASHI T,et al.Application of neural network to one-day-ahead 24hours generating power forecasting for photovoltaic system[J].Intelligent Systems Applications to Power Systems,2007:1-6.
[5]Jianhong Xie.Time Series Prediction Based on Recurrent LSSVM with Mixed Kernel[J].Asia-Pacific Conference on Information Processing.2009(01):113-116.
[6]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(11):19-22.
[7]朱永强,田军.最小二乘支持向量机在光伏功率预测中的应用[J].电网技术,2011(07):54-59.
[8]刘长良,吴家佳.基于核极端学习机的短期风电功率预测研究[J].热能动力工程,2017(01):95-100.
[9]Almonacid F,P.J.Pérez-Higueras,EduardoF.Fernández,et al.A methodology based on dynamic artificial neural network for short-term forecasting of the power output of a PV generator[J].Energy Conversion and Management,2014,85(9):389-398.