基于非线性自回归神经网络的GHI预测
|
摘要
针对水平面总辐照度(global horizontal irradiation,GHI)短期预测问题,提出一种基于非线性自回归神经网络的短期水平面太阳总辐照度预测模型。首先,提出一种并联结构训练样本,以保证训练样本内部的时间耦合性。其次,通过对9项气象参数共511种组合作为输入的模型预测精度进行分析,确定模型最优输入组合。最后,利用4种典型气象条件下GHI时延神经网络预测模型,非线性自回归动态神经网络预测模型预测标准均方根误差均降低。
This paper proposes a short-term GHI forecast model based on nonlinear autoregressive dynamic neural network. At first,this paper proposes a kind of training sample in parallel structure to guarantee the time correlation within training sample. Secondly,by comparing the forecast accuracy of 511 combinations of 9 meteorological parameters,as model inputs,the best input combination is identified. Finally,this paper tests model's adaptiveness to four different typical weather conditions. By comparing with forecast results of the traditional forecast model based on focus time delay neural network,the forecast model based on nonlinear autoregressive neural network can effectively reduce the normalized root mean squared error.
This paper proposes a short-term GHI forecast model based on nonlinear autoregressive dynamic neural network. At first,this paper proposes a kind of training sample in parallel structure to guarantee the time correlation within training sample. Secondly,by comparing the forecast accuracy of 511 combinations of 9 meteorological parameters,as model inputs,the best input combination is identified. Finally,this paper tests model's adaptiveness to four different typical weather conditions. By comparing with forecast results of the traditional forecast model based on focus time delay neural network,the forecast model based on nonlinear autoregressive neural network can effectively reduce the normalized root mean squared error.
引文
[1]Wu Ji,Keong Chanchee.Prediction of hourly solar radiation using a novel hybrid model of ARMA and TDNN[J].Solar Energy,2011,85(5):808-817.
[2]Sun Huaiwei,Yan Dong,Zhao Na,et al.Empirical investigation on modeling solar radiation series with ARMA-GARCH models[J].Energy Conversing and Management,2015,92:385-395.
[3]David M,Ramahatana F,Trombe P J,et al.Probabilistic forecasting of the solar irradiance with recursive ARMA and GARCH models[J].Solar Energy,2016,133:55-72.
[4]Yang Dazhi,Sharma V,Ye Zhen,et al.Forecasting of global horizontal irradiance by exponential smoothing,using decompositions[J].Energy,2015,81:111-119.
[5]Dong Zibo,Yang Dazhi,Reindl T,et al.Short-term solar irradiance forecastingusing exponential smoothing state space model[J].Energy,2013,55:1104-1113.
[6]Aguiar J,Collares-Perrira M,Conde S.Simple procedure for generating of dailyradiation values using a library of Markov transition matrices[J].Solar Energy,1988,40(3):269-279.
[7]王建平,谢云林,朱程辉,等.基于相空间重构小波神经网络的太阳逐日辐射能量预测[J].太阳能学报,2013,34(9):1651-1655.[7]Wang Jianping,Xie Yunlin,Zhu Chenghui,et al.Daily solar radiation prediction based on phase space reconstruction of wavelet neural network[J].Acta Energiae Solaris Sinica,2013,34(9):1651-1655.
[8]米增强,王飞,杨光,等.光伏电站辐照度ANN预测及其两维变尺度修正方法[J].太阳能学报,2013,34(2):251-259.[8]Mi Zengqiang,Wang Fei,Yang Guang,et al.ANNbased irradiance forecast of photovoltaic power plant and two dimensions variable scale modification method for the forecast value[J].Acta Energiae Solaris Sinica,2013,34(2):251-259.
[9]曹双华,曹家枞.太阳逐时总辐射混沌优化神经网络预测模型研究[J].太阳能学报,2006,27(2):164-169.[9]Cao Shuanghua,Cao Jiacong.Study of chaos optimization neural networks for the forecast of hourly total solar irradiation[J].Acta Energiae Solaris Sinica,2006,27(2):164-169.
[10]Marquez R,Pedro H T C.Hybrid solar forecasting method uses satellite imaging and ground telemetry as inputs to ANNs[J].Solar Energy,2013,92(4):176-188.
[11]Dong Zibo,Yang Dazhi,Reindl T,et al.Satellite image analysis and a hybrid ESSS/ANN model to forecast solar irradiance in the tropics[J].Energy Conversion and Management,2014,79(3):66-73.
[12]Lima F J L,Martins F R,Pereira E B,et al.Forecast for surface solar irradiance at the Brazilian Northeastern region using NWP model and artificial neural networks[J].Renewable Energy,2016,87:807-818.
[13]Lauret P,Diagne M,David M.A neural network post-processing approach to improving NWP solar radiation forecast[J].Energy Procedia,2014,57:1044-1052.
[14]Lorenz E,Heinemann D.Prediction of solar irradiation and photovoltaic power[J].Comprehensive Renewable Energy Amsterdam,2012,1:239-292.
[15]Chen Changsong,Duan Shanxu,Cai Tao,et al.Online24-h solar power forecasting based on weather type classification using artificial neural network[J].Solar Energy,2011,85(11):2856-2870.
[16]Cornaro C,Pierro M,Bucci F.Master optimization process based on neural networks ensemble for 24h solar irradiance forecast[J].Solar Energy,2015,111:297-312.
[17]Aguiar L M,Pereira B,David M,et al.Use of satellite data to improve solar radiation forecasting with Bayesian artificial neural networks[J].Solar Energy,2015,122:1309-1324.
[18]Cao Jiacong,Lin Xingchun.Study of hourly and daily solar irradiation forecast using diagonal recurrent wavelet neural networks[J].Energy Conversion and Management,2008,49(6):1396-1406.
[19]王炳忠.太阳辐射计算讲座(第一讲)太阳能中天文参数的计算[J].太阳能,1999,(2):8-10.[19]Wang Bingzhong.Solar irradiation calculation lecture,(Section 1):Astronomical parameters calculations in solar energy[J].Solar Energy,1992,(2):8-10.
[20]王炳忠.太阳辐射计算讲座第二讲相对于斜面的太阳位置计算[J].太阳能,1999,(3):8-9.[20]Wang Bingzhong.Solar irradiation calculation lecture,(Section 2):Sun position calculations relative to inclined plane[J].Solar Energy,1992,(3):8-9.
[21]王炳忠.太阳辐射计算讲座(第三讲)地外水平面辐射量的计算[J].太阳能,1999,(4):12-13.[21]Wang Bingzhong.Solar irradiation calculation lecture(Section 3)extraterrestrial horizontal irradiation calculation[J].Solar Energy,1992,(2):8-10.
[22]Kasten F,Young A.Revised optical air mass tables and approximation formula[J].Applied Optics,1989,28(22):4735-4738.
[2]Sun Huaiwei,Yan Dong,Zhao Na,et al.Empirical investigation on modeling solar radiation series with ARMA-GARCH models[J].Energy Conversing and Management,2015,92:385-395.
[3]David M,Ramahatana F,Trombe P J,et al.Probabilistic forecasting of the solar irradiance with recursive ARMA and GARCH models[J].Solar Energy,2016,133:55-72.
[4]Yang Dazhi,Sharma V,Ye Zhen,et al.Forecasting of global horizontal irradiance by exponential smoothing,using decompositions[J].Energy,2015,81:111-119.
[5]Dong Zibo,Yang Dazhi,Reindl T,et al.Short-term solar irradiance forecastingusing exponential smoothing state space model[J].Energy,2013,55:1104-1113.
[6]Aguiar J,Collares-Perrira M,Conde S.Simple procedure for generating of dailyradiation values using a library of Markov transition matrices[J].Solar Energy,1988,40(3):269-279.
[7]王建平,谢云林,朱程辉,等.基于相空间重构小波神经网络的太阳逐日辐射能量预测[J].太阳能学报,2013,34(9):1651-1655.[7]Wang Jianping,Xie Yunlin,Zhu Chenghui,et al.Daily solar radiation prediction based on phase space reconstruction of wavelet neural network[J].Acta Energiae Solaris Sinica,2013,34(9):1651-1655.
[8]米增强,王飞,杨光,等.光伏电站辐照度ANN预测及其两维变尺度修正方法[J].太阳能学报,2013,34(2):251-259.[8]Mi Zengqiang,Wang Fei,Yang Guang,et al.ANNbased irradiance forecast of photovoltaic power plant and two dimensions variable scale modification method for the forecast value[J].Acta Energiae Solaris Sinica,2013,34(2):251-259.
[9]曹双华,曹家枞.太阳逐时总辐射混沌优化神经网络预测模型研究[J].太阳能学报,2006,27(2):164-169.[9]Cao Shuanghua,Cao Jiacong.Study of chaos optimization neural networks for the forecast of hourly total solar irradiation[J].Acta Energiae Solaris Sinica,2006,27(2):164-169.
[10]Marquez R,Pedro H T C.Hybrid solar forecasting method uses satellite imaging and ground telemetry as inputs to ANNs[J].Solar Energy,2013,92(4):176-188.
[11]Dong Zibo,Yang Dazhi,Reindl T,et al.Satellite image analysis and a hybrid ESSS/ANN model to forecast solar irradiance in the tropics[J].Energy Conversion and Management,2014,79(3):66-73.
[12]Lima F J L,Martins F R,Pereira E B,et al.Forecast for surface solar irradiance at the Brazilian Northeastern region using NWP model and artificial neural networks[J].Renewable Energy,2016,87:807-818.
[13]Lauret P,Diagne M,David M.A neural network post-processing approach to improving NWP solar radiation forecast[J].Energy Procedia,2014,57:1044-1052.
[14]Lorenz E,Heinemann D.Prediction of solar irradiation and photovoltaic power[J].Comprehensive Renewable Energy Amsterdam,2012,1:239-292.
[15]Chen Changsong,Duan Shanxu,Cai Tao,et al.Online24-h solar power forecasting based on weather type classification using artificial neural network[J].Solar Energy,2011,85(11):2856-2870.
[16]Cornaro C,Pierro M,Bucci F.Master optimization process based on neural networks ensemble for 24h solar irradiance forecast[J].Solar Energy,2015,111:297-312.
[17]Aguiar L M,Pereira B,David M,et al.Use of satellite data to improve solar radiation forecasting with Bayesian artificial neural networks[J].Solar Energy,2015,122:1309-1324.
[18]Cao Jiacong,Lin Xingchun.Study of hourly and daily solar irradiation forecast using diagonal recurrent wavelet neural networks[J].Energy Conversion and Management,2008,49(6):1396-1406.
[19]王炳忠.太阳辐射计算讲座(第一讲)太阳能中天文参数的计算[J].太阳能,1999,(2):8-10.[19]Wang Bingzhong.Solar irradiation calculation lecture,(Section 1):Astronomical parameters calculations in solar energy[J].Solar Energy,1992,(2):8-10.
[20]王炳忠.太阳辐射计算讲座第二讲相对于斜面的太阳位置计算[J].太阳能,1999,(3):8-9.[20]Wang Bingzhong.Solar irradiation calculation lecture,(Section 2):Sun position calculations relative to inclined plane[J].Solar Energy,1992,(3):8-9.
[21]王炳忠.太阳辐射计算讲座(第三讲)地外水平面辐射量的计算[J].太阳能,1999,(4):12-13.[21]Wang Bingzhong.Solar irradiation calculation lecture(Section 3)extraterrestrial horizontal irradiation calculation[J].Solar Energy,1992,(2):8-10.
[22]Kasten F,Young A.Revised optical air mass tables and approximation formula[J].Applied Optics,1989,28(22):4735-4738.