云图纹理分析结合SVM的地表太阳辐射预测
|
摘要
太阳能资源的间歇性与不稳定性为地表太阳辐射的准确预测带来很大的挑战.本研究通过对全天空图像进行纹理特征分析,并结合支持向量机模型,实现了对地表太阳辐射的预测.首先,基于全天空图像,利用数字图像处理技术提取与太阳辐射相关的图像纹理特征,包括反差、熵、灰度相关与能量;然后,结合图像特征与辐射衰减系数建立回归模型;最后,基于支持向量机模型实现地表太阳辐射的预测.实验结果表明:本文算法的预测精度明显优于基于统计的传统算法,同时优于基于云团遮挡预测的算法,为准确预测复杂天气条件下的地表太阳能辐射提供重要的参考依据.
The intermittency and instability of the solar energy resource brings great challenge to the accurate forecasting of the surface solar irradiation.In this work,based on texture characteristics analysis of sky image collected by TSI combined with SVM model,a new methods for the forecasting of ground solar radiation was presented.First,the texture characteristics related to solar irradiation were extracted from sky images through image processing technologies,including contrast,entropy,grayscale and energy.Second regression model was built between image characteristics and irradiation reduction coefficient.And finally,the SVM model was used to forecasting ground solar radiation.The experiment results indicated that:the forecasting accuracy of the method based on texture characteristics tends to provide better a performance than traditional forecasting method and forecasting method based on cloud block movement prediction.It can provide important reference for the accurate forecasting of surface solar irradiation on complex climate conditions.
The intermittency and instability of the solar energy resource brings great challenge to the accurate forecasting of the surface solar irradiation.In this work,based on texture characteristics analysis of sky image collected by TSI combined with SVM model,a new methods for the forecasting of ground solar radiation was presented.First,the texture characteristics related to solar irradiation were extracted from sky images through image processing technologies,including contrast,entropy,grayscale and energy.Second regression model was built between image characteristics and irradiation reduction coefficient.And finally,the SVM model was used to forecasting ground solar radiation.The experiment results indicated that:the forecasting accuracy of the method based on texture characteristics tends to provide better a performance than traditional forecasting method and forecasting method based on cloud block movement prediction.It can provide important reference for the accurate forecasting of surface solar irradiation on complex climate conditions.
引文
[1]KASSIANOV E,LONG C N,OVTCHINNIKOV M.Cloud Sky Cover Versus Cloud Fraction:Whole-Sky Simulations and Observations[J].Journal of Applied Meteorology,2005,44(1):86-98.
[2]PFISTER G,MCKENZIE R L,LILEY J B,et al.Cloud Coverage Based on All-Sky Imaging and Its Impact on Surface Solar Irradiance[J].Journal of Applied Meteorology,2003,42(10):1421-1434.
[3]饶瑞中.现代大气光学[M].北京:科学出版社,2012:80-86.
[4]TANIGUCHI H,OTANI K,KUROKAWA K.Hourly Forecast of Global Irradiation Using GMS Satellite Images[J].Solar Energy Materials&Solar Cells,2001,67(1):551-557.
[5]HAMMER A,HEINEMANN D,LORENZ E,et al.Short-Term Forecasting of Solar Radiation:A Statistical Approach Using Satellite Data[J].Solar Energy,1999,67(1-3):139-150.
[6]CALBO J,SABBURG J.Feature Extraction from Whole-Sky Ground-Based Images for Cloud-Type Recognition[J].Journal of Atmospheric and Oceanic Technology,2008,25(1):3-14.
[7]LONG C N,SLATER D W,TOOMAN T.Total Sky Imager Model 880Status and Testing Results[R].Washington DC:Office of Scientific&Technical Information Technical Reports,2001.
[8]GENKOVA I,LONG C N,BESNARD T,et al.Assessing Cloud Spatial and Vertical Distribution with Infrared Cloud Radiometer CIR-7[C]//Fourteenth ARM Science Team Meeting Proceedings.Albuquerque,New Mexico:SPIE,2004:5571.
[9]周文君,牛生杰,许潇锋.全天空成像仪云量计算方法的改进[J].大气科学学报,2014,37(3):289-296.
[10]苏适,李红萍,杨洋,等.基于最大类间方差法的天空图像云空识别模型[J].华北电力大学学报(自然科学版),2016,43(5):36-42.
[11]MARQUEZ R,COIMBRA C F M.Forecasting of Global and Direct Solar Irradiance Using Stochastic Learning Methods,Ground Experiments and the NWS Database[J].Solar Energy,2011,85(5):746-756.
[12]MELLIT A,PAVAN A M.A 24-h Forecast of Solar Irradiance Using Artificial Neural Network:Application for Performance Prediction of a Grid-Connected PV Plant at Trieste,Italy[J].Solar Energy,2010,84(5):807-821.
[13]陈志宝,丁杰,周海,等.地基云图结合径向基函数人工神经网络的光伏功率超短期预测模型[J].中国电机工程学报,2015,35(3):561-567.
[14]丁宇宇,丁杰,周海,等.基于全天空成像仪的光伏电站水平面总辐射预报[J].中国电机工程学报,2014,34(1):50-56.
[15]MARTINEZ-CHICO M,BATLLES F J,BOSCH J L.Cloud Classification in a Mediterranean Location Using Radiation Data and Sky Images[J].Energy,2011,36(7):4055-4062.
[16]刘丽,匡纲要.图像纹理特征提取方法综述[J].中国图象图形学报,2009,14(4):622-635.
[17]王小平,李柳柏.基于AdaBoost算法的图像自动标注[J].西南大学学报(自然科学版),2015,37(7):174-180.
[18]杨金焕,于化丛,葛亮.太阳能光伏发电应用技术[M].北京:电子工业出版社,2009:21-24.
[19]CRISTIANINI N,SHAWE-TAYLOR J.支持向量机导论[M].李国正,王猛,曾华军,译.北京:电子工业出版社,2004:82-84.
[20]吴娟.基于图像特征和GA-SVM的烤烟烘烤阶段识别研究[J].西南师范大学学报(自然科学版),2016,41(9):100-106.
[2]PFISTER G,MCKENZIE R L,LILEY J B,et al.Cloud Coverage Based on All-Sky Imaging and Its Impact on Surface Solar Irradiance[J].Journal of Applied Meteorology,2003,42(10):1421-1434.
[3]饶瑞中.现代大气光学[M].北京:科学出版社,2012:80-86.
[4]TANIGUCHI H,OTANI K,KUROKAWA K.Hourly Forecast of Global Irradiation Using GMS Satellite Images[J].Solar Energy Materials&Solar Cells,2001,67(1):551-557.
[5]HAMMER A,HEINEMANN D,LORENZ E,et al.Short-Term Forecasting of Solar Radiation:A Statistical Approach Using Satellite Data[J].Solar Energy,1999,67(1-3):139-150.
[6]CALBO J,SABBURG J.Feature Extraction from Whole-Sky Ground-Based Images for Cloud-Type Recognition[J].Journal of Atmospheric and Oceanic Technology,2008,25(1):3-14.
[7]LONG C N,SLATER D W,TOOMAN T.Total Sky Imager Model 880Status and Testing Results[R].Washington DC:Office of Scientific&Technical Information Technical Reports,2001.
[8]GENKOVA I,LONG C N,BESNARD T,et al.Assessing Cloud Spatial and Vertical Distribution with Infrared Cloud Radiometer CIR-7[C]//Fourteenth ARM Science Team Meeting Proceedings.Albuquerque,New Mexico:SPIE,2004:5571.
[9]周文君,牛生杰,许潇锋.全天空成像仪云量计算方法的改进[J].大气科学学报,2014,37(3):289-296.
[10]苏适,李红萍,杨洋,等.基于最大类间方差法的天空图像云空识别模型[J].华北电力大学学报(自然科学版),2016,43(5):36-42.
[11]MARQUEZ R,COIMBRA C F M.Forecasting of Global and Direct Solar Irradiance Using Stochastic Learning Methods,Ground Experiments and the NWS Database[J].Solar Energy,2011,85(5):746-756.
[12]MELLIT A,PAVAN A M.A 24-h Forecast of Solar Irradiance Using Artificial Neural Network:Application for Performance Prediction of a Grid-Connected PV Plant at Trieste,Italy[J].Solar Energy,2010,84(5):807-821.
[13]陈志宝,丁杰,周海,等.地基云图结合径向基函数人工神经网络的光伏功率超短期预测模型[J].中国电机工程学报,2015,35(3):561-567.
[14]丁宇宇,丁杰,周海,等.基于全天空成像仪的光伏电站水平面总辐射预报[J].中国电机工程学报,2014,34(1):50-56.
[15]MARTINEZ-CHICO M,BATLLES F J,BOSCH J L.Cloud Classification in a Mediterranean Location Using Radiation Data and Sky Images[J].Energy,2011,36(7):4055-4062.
[16]刘丽,匡纲要.图像纹理特征提取方法综述[J].中国图象图形学报,2009,14(4):622-635.
[17]王小平,李柳柏.基于AdaBoost算法的图像自动标注[J].西南大学学报(自然科学版),2015,37(7):174-180.
[18]杨金焕,于化丛,葛亮.太阳能光伏发电应用技术[M].北京:电子工业出版社,2009:21-24.
[19]CRISTIANINI N,SHAWE-TAYLOR J.支持向量机导论[M].李国正,王猛,曾华军,译.北京:电子工业出版社,2004:82-84.
[20]吴娟.基于图像特征和GA-SVM的烤烟烘烤阶段识别研究[J].西南师范大学学报(自然科学版),2016,41(9):100-106.