高阳;张碧玲;毛京丽;刘勇;

• 1:北京邮电大学网络教育学院

摘要(Abstract)：

由于当前国内对太阳辐射强度和云量信息的预报能力较低,气象数据的引入对光伏直接预测法的预测精度提高有限。为解决此问题,基于历史出力数据自身特征的挖掘来提高预测精度,提出一种具有自适应能力的光伏超短期出力预测模型。该模型首先利用已有历史出力数据的小波分析和特征分析结果训练支持向量机(support vector machine,SVM)分类器,通过已建立的SVM分类器利用前30 min的光伏出力数据预测之后15 min的出力曲线类型,最后结合曲线类型从自回归与滑动平均模型(auto-regressive and moving average model,ARMA)和神经网络模型(artificial neural network mode,ANN)中选取出合适的方法对光伏出力进行预测。对ARMA、ANN和自适应模型进行了对比实验,结果表明:所提的自适应预测模型在均方根误差(root mean square error,RMSE)、平均绝对百分比误差(mean absolute percentage error,MAPE)和希尔不等系数(Theil inequality coefficient,TIC)上性能最好。

关键词(KeyWords)： 自适应预测;自回归和滑动平均模型;神经网络;小波分析;超短期光伏出力预测

Abstract:

Keywords:

基金项目(Foundation): 北京邮电大学青年科研创新计划专项(2013RC100)

作者(Author): 高阳;张碧玲;毛京丽;刘勇;

Email:

DOI: 10.13335/j.1000-3673.pst.2015.02.002

参考文献(References)：

• [1]汪海瑛,白晓民,马纲.并网光伏电站的发电可靠性评估[J].电网技术,2012,36(10):1-5.Wang Haiying,Bai Xiaomin,Ma Gang.Reliability assessment of gridintegrated solar photovoltaic system[J].Power System Technology,2012,36(10):1-5(in Chinese).
• [2]艾欣,韩晓楠,孙英云.大型光伏电站并网特性及其低碳运行与控制技术[J].电网技术,2013,37(1):15-23.Ai Xin,Han Xiaonan,Sun Yingyun.Grid-connection characteristics of large-scale photovoltaic power station and its low-carbon operation and control technology[J].Power System Technology,2013,37(1):15-23(in Chinese).
• [3]沈瑶,罗安,陈燕东,等.基于功率前馈的光伏并网控制方法及稳定性分析[J].电网技术,2014,38(9):2449-2454.Shen Yao,Luo An,Chen Yandong,et al.A power feedforward-based control approach for grid-connection of photovoltaic generation and its stability analysis[J].Power System Technology,2014,38(9):2449-2454(in Chinese).
• [4]Shi Jie,Lee Weijei,Liu Yongqian,et al.Forecasting power output of photovoltaic systems based on weather classification and support vector machines[J].IEEE Transactions on Industry Applications,2012,48(3):1064-1069
• [5]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 oil a grey and neural network hybrid model[J].Automation of Electric Power Systems,2012,36(19):37-41(in Chinese).
• [6]代倩,段善旭,蔡涛,等.基于天气类型聚类识别的光伏系统短期无辐照度发电预测模型研究[J].中国电机工程学报,2011,31(34):28-35.Dai Qian,Duan Shanxu,Cai Tao,et al.Short-term PV generation system forecasting model without irradiation based on weather type clustering[J].Proceedings of the CSEE,2011,31(34):28-35.
• [7]Selmin Ener Rusen,Annette Hammer,Akinoglu B G.Coupling satellite images with surface measurements of bright sunshine hours to estimate daily solar irradiation on horizontal surface[J].Renewable Energy,2013,55(7):212-219.
• [8]Ricardo Marquez,Hugo T.C.Pedro,Carlos F.M.Coimbra.Hybrid solar forecasting method uses satellite imaging and ground telemetry as inputs to ANNs[J].Solar Energy,2013,92(6):176-188.
• [9]Liu Yongqian,Shi Jie,Yang Yongping,et al.Short-term wind-power prediction based on wavelet transform-support vector machine and statistic characteristics analysis[J].IEEE Transactions on Industry Applications,2012,48(4):1136-1141.
• [10]冯垛生,宋金莲,等.太阳能发电原理与应用[M].北京:人民邮电出版社,2007:55.
• [11]Cyril Voyant,Marc Muselli,Christophe Paoli,et al.Hybrid methodology for hourly global radiation forecasting in Mediterranean area[J].Renewable Energy,2013,53(5):1-11.
• [12]郑凌蔚,刘士荣,谢小高.基于改进小波神经网络的光伏发电系统非线性模型辨识[J].电网技术,2011,35(10):159-164.Zheng Lingwei,Liu Shirong,Xie Xiaogao.Modified wavelet neural network based nonlinear model identification for photovoltaic generation system[J].Power System Technology,2011,35(10):159-164(in Chinese).
• [13]李如琦,苏浩益,王宗耀,等.应用启发式最小二乘支持向量机的中长期电力负荷预测[J].电网技术,2011,35(11):195-199.Li Ruqi,Su Haoyi,Wang Zongyao,et al.Medium-and long-term load forecasting based on heuristic least square support vector machine[J].Power System Technology,2011,35(11):195-199(in Chinese).
• [14]郭旭阳,谢开贵,胡博,等.计入光伏发电的电力系统分时段随机生产模拟[J].电网技术,2013,37(6):1499-1505.Guo Xuyang,Xie Kaigui,Hu Bo,et al.A time-interval based probabilistic production simulation of power system with gridconnected photovoitaic generation[J].Power System Technology,2013,37(6):1499-1505(in Chinese).
• [15]王元章,李智华,吴春华,等.基于BP神经网络的光伏组件在线故障诊断[J].电网技术,2013,37(8):2094-2100.Wang Yuanzhang,Li Zhihua,Wu Chunhua,et al.A survey of online fault diagnosis for PV module based on BP neural network[J].Power System Technology,2013,37(8):2094-2100(in Chinese).
• [16]Hartman E J,Keeler J D,Kowalski J M.Layered neural networks with Gaussian hidden units as universal approximations[J].Neural Computation,1990,2(2):210-215.
• [17]Alfredo Fernandez-Jimenez L,Alberto Falces,Montserrat MendozaVillena,et al.Short-term power forecasting system for photovoltaic plants[J].Renewable Energy,2012,44(8):311-317.
• [18]Ying Chen,Luh Peter B,Friedland Peter B,et al.Short-term load forecasting:similar day-based wavelet neural networks[J].IEEE Transactions on Power Systems,2010,25(1):322-330.
• [19]易丹辉.数据分析与EViews应用[M].北京:中国人民大学出版社,2008:47.