基于相似日和分位数回归森林的光伏发电功率概率密度预测
|
摘要
为提高光伏发电功率预测精度及可靠性,提出一种基于相似日和分位数回归森林(QRF)的光伏发电功率概率密度预测模型。选取某光伏电站实测数据为研究对象,在将光伏发电功率原始数据按不同天气类型进行分类的基础上,通过温度和风速2个特征向量选取相似日,并对相似日历史数据建立BP神经网络(BPNN)、支持向量机(SVM)和QRF预测模型。结果表明:晴天时,不同模型预测值均能较好跟踪真实值变化趋势,在13:00—16:00光伏发电功率下降时间段,QRF模型更接近真实值;多云或阴天时,在9:00—12:00,3种模型预测误差均较大;雨天时,在14:00—16:00光伏发电功率突变时间段,BPNN模型预测误差最大,SVM预测值相对于QRF模型更接近真实值,而在10:00—12:00,SVM模型预测误差增大。对不同模型不同天气类型下的预测误差,QRF模型预测性能更佳。
In order to improve the forecasting accuracy and reliability of photovoltaic power generation, a photovoltaic power generation probability density forecasting model based on similar day and quantile regression forests(QRF) is proposed. The measured data of a photovoltaic power station are selected as the research object. On the basis of classifying the original data of the photovoltaic power generation according to different weather types, similar days are selected by two eigenvectors(temperature and wind speed). Moreover, the BP neural network(BPNN) model, support vector machine(SVM) model and QRF forecasting model are established for the historical data of similar days. The results show that, on sunny days, the forecasting results of different models can better track the change trend of true values, and the QRF model's result is closer to the true value during the period of photovoltaic power reduction from 13:00 to 16:00. On cloudy days, the forecasting errors of the above three models are relatively large from 9:00 to 12:00. In rainy days, during the sudden change of photovoltaic power generation from 14:00 to 16:00, the BPNN model has the largest forecasting error, and the SVM model's forecasting result is closer to the true value than the QRF model, but the forecasting error of the SVM model increases from 10:00 to 12:00. The QRF model has better prediction performance for different weather types among different models.
In order to improve the forecasting accuracy and reliability of photovoltaic power generation, a photovoltaic power generation probability density forecasting model based on similar day and quantile regression forests(QRF) is proposed. The measured data of a photovoltaic power station are selected as the research object. On the basis of classifying the original data of the photovoltaic power generation according to different weather types, similar days are selected by two eigenvectors(temperature and wind speed). Moreover, the BP neural network(BPNN) model, support vector machine(SVM) model and QRF forecasting model are established for the historical data of similar days. The results show that, on sunny days, the forecasting results of different models can better track the change trend of true values, and the QRF model's result is closer to the true value during the period of photovoltaic power reduction from 13:00 to 16:00. On cloudy days, the forecasting errors of the above three models are relatively large from 9:00 to 12:00. In rainy days, during the sudden change of photovoltaic power generation from 14:00 to 16:00, the BPNN model has the largest forecasting error, and the SVM model's forecasting result is closer to the true value than the QRF model, but the forecasting error of the SVM model increases from 10:00 to 12:00. The QRF model has better prediction performance for different weather types among different models.
引文
[1] PIERRO M, BUCCI F, DE FELICE M, et al. Multi-model ensemble for day ahead prediction of photovoltaic power generation[J]. Solar Energy, 2016, 134:132-146.
[2]刘琳.光伏电站有功功率优化分配[J].热力发电,2015, 44(11):104-108.LIU Lin. Active power control in photovoltaic power plants[J]. Thermal Power Generation, 2015, 44(11):104-108.
[3]成珂,郭黎明,王亚昆.聚类分析在光伏发电量预测中的应用研究[J].可再生能源, 2017, 35(5):68-73.CHENG Ke, GUO Liming, WANG Yakun. Application of cluster analysis in forecasting photovoltaic power generation[J]. Renewable Energy Resources, 2017,35(5):68-73.
[4]张玉,黄睿,张振涛,等.基于克里格模型的光伏发电量预测[J].热力发电, 2017, 46(4):27-32.ZHANG Yu, HUANG Rui, ZHANG Zhentao, et al.Photovoltaic power generation prediction based on Krige model[J]. Thermal Power Generation, 2017, 46(4):27-32.
[5] GUO H P, WU S H, WANG Z Q, et al. Linear regression for forecasting photovoltaic power generation[J]. Applied Mechanics&Materials, 2014, 494:1771-1774.
[6]李芬,宋启军,蔡涛,等.基于PCA-BPNN的并网光伏电站发电量预测模型研究[J].可再生能源, 2017,35(5):61-67.LI Fen, SONG Qijun, CAI Tao, et al. Based on principal component analysis and the BP neural network in the application of grid-connected photovoltaic power energy prediction[J]. Renewable Energy Resources, 2017, 35(5):61-67.
[7]张玉,莫寒,张烈平.基于模糊支持向量机的光伏发电量预测[J].热力发电, 2017, 46(1):116-120.ZHANG Yu, MO Han, ZHANG Lieping. Photovoltaic power prediction based on fuzzy support vector machine[J].Thermal Power Generation, 2017, 46(1):116-120.
[8]张雨金,杨凌帆,葛双冶,等.基于Kmeans-SVM的短期光伏发电功率预测[J].电力系统保护与控制, 2018,46(21):118-124.ZHANG Yujin, YANG Lingfan, GE Shuangye, et al.Short-term photovoltaic power forecasting based on Kmeans algorithm and support vector machine[J]. Power System Protection and Control, 2018, 46(21):118-124.
[9]傅美平,马红伟,毛建容.基于相似日和最小二乘支持向量机的光伏发电短期预测[J].电力系统保护与控制, 2012, 40(16):65-69.FU Meiping, MA Hongwei, MAO Jianrong. Short-term photovoltaic power forecasting based on similar days and least square support vector machine[J]. Power System Protection and Control, 2012, 40(16):65-69.
[10]单英浩,付青,耿炫,等.基于改进BP-SVM-ELM与粒子化SOM-LSF的微电网光伏发电组合预测方法[J].中国电机工程学报, 2016, 36(12):3334-3342.SHAN Yinghao, FU Qing, GENG Xuan, et al. Combined forecasting of photovoltaic power generation in microgrid based on the improved BP-SVM-ELM and SOM-LSF with particlization[J]. Proceedings of the CSEE, 2016,36(12):3334-3342.
[11] YANG X, JIE R, HONG Y. Photovoltaic power forecasting with a rough set combination method[C]//2016 UKACC 11th International Conference on Control(CONTROL), Belfast, 2016:1-6.
[12] LI Q, SUN Y, YU Y, et al. Short-term photovoltaic power forecasting for photovoltaic power station based on EWT-KMPMR[J]. Transactions of the Chinese Society of Agricultural Engineering, 2017, 33(20):265-273.
[13]李多,董海鹰,杨立霞.基于EMD与ELM的光伏电站短期功率预测[J].可再生能源, 2016, 34(2):173-177.LI Duo, DONG Haiying, YANG Lixia. The short-term power forecasting of photovoltaic plant based on EMD-ELM[J]. Renewable Energy Resources, 2016,34(2):173-177.
[14]张立影,刘智昱,孟令甲,等.基于小波变换和神经网络的光伏功率预测[J].可再生能源, 2015, 33(2):171-176.ZHANG Liying, LIU Zhiyu, MENG Lingjia, et al.Photovoltaic output power prediction approach based on wavelet transform and neural network[J]. Renewable Energy Resources, 2015, 33(2):171-176.
[15]路志英,任一墨,葛路琨.基于样条估计分位数回归的光伏功率回归模型[J].湖南大学学报(自然科学版),2017, 44(10):96-103.LU Zhiying, REN Yimo, GE Lukun. Photovoltaic power regression model based on spline estimation and quantile regression[J]. Journal of Hunan University(Natural Sciences), 2017, 44(10):96-103.
[16]陈云龙,殷豪,孟安波,等.基于模糊信息粒化的光伏出力区间预测[J].电测与仪表, 2018, 55(14):63-68.CHEN Yunlong, YIN Hao, MENG Anbo, et al. PV power interval prediction based on fuzzy information granulation[J].Electrical Measurement&Instrumentation, 2018, 55(14):63-68.
[17]程泽,刘冲,刘力.基于相似时刻的光伏出力概率分布估计方法[J].电网技术, 2017, 41(2):117-124.CHENG Ze, LIU Chong, LIU Li. A method of probabilistic distribution estimation of PV generation based on similar time of day[J]. Power System Technology,2017, 41(2):117-124.
[18]杨锡运,刘欢,张彬,等.组合权重相似日选取方法及光伏输出功率预测[J].电力自动化设备, 2014, 34(9):118-122.YANG Xiyun, LIU Huan, ZHANG Bin, et al. Similar day selection based on combined weight and photovoltaic power output forecasting[J]. Electric Power Automation Equipment, 2014, 34(9):118-122.
[19]李芬,李春阳,糜强,等.基于GRA-BPNN时变权重的光伏短期出力组合预测[J].可再生能源, 2018,36(11):1605-1611.LI Fen, LI Chunyang, MI Qiang, et al. The time-varying weight ensemble forecasting of short-term photovoltaic power based on GRA-BPNN[J]. Renewable Energy Resources, 2018, 36(11):1605-1611.
[20] NICOLAI M. Quantile regression forests[J]. Journal of Machine Learning Research, 2006, 7(2):983-999.
[21] TRAPERO J R. Calculation of solar irradiation prediction intervals combining volatility and kernel density estimates[J]. Energy, 2016, 114:266-274.
[2]刘琳.光伏电站有功功率优化分配[J].热力发电,2015, 44(11):104-108.LIU Lin. Active power control in photovoltaic power plants[J]. Thermal Power Generation, 2015, 44(11):104-108.
[3]成珂,郭黎明,王亚昆.聚类分析在光伏发电量预测中的应用研究[J].可再生能源, 2017, 35(5):68-73.CHENG Ke, GUO Liming, WANG Yakun. Application of cluster analysis in forecasting photovoltaic power generation[J]. Renewable Energy Resources, 2017,35(5):68-73.
[4]张玉,黄睿,张振涛,等.基于克里格模型的光伏发电量预测[J].热力发电, 2017, 46(4):27-32.ZHANG Yu, HUANG Rui, ZHANG Zhentao, et al.Photovoltaic power generation prediction based on Krige model[J]. Thermal Power Generation, 2017, 46(4):27-32.
[5] GUO H P, WU S H, WANG Z Q, et al. Linear regression for forecasting photovoltaic power generation[J]. Applied Mechanics&Materials, 2014, 494:1771-1774.
[6]李芬,宋启军,蔡涛,等.基于PCA-BPNN的并网光伏电站发电量预测模型研究[J].可再生能源, 2017,35(5):61-67.LI Fen, SONG Qijun, CAI Tao, et al. Based on principal component analysis and the BP neural network in the application of grid-connected photovoltaic power energy prediction[J]. Renewable Energy Resources, 2017, 35(5):61-67.
[7]张玉,莫寒,张烈平.基于模糊支持向量机的光伏发电量预测[J].热力发电, 2017, 46(1):116-120.ZHANG Yu, MO Han, ZHANG Lieping. Photovoltaic power prediction based on fuzzy support vector machine[J].Thermal Power Generation, 2017, 46(1):116-120.
[8]张雨金,杨凌帆,葛双冶,等.基于Kmeans-SVM的短期光伏发电功率预测[J].电力系统保护与控制, 2018,46(21):118-124.ZHANG Yujin, YANG Lingfan, GE Shuangye, et al.Short-term photovoltaic power forecasting based on Kmeans algorithm and support vector machine[J]. Power System Protection and Control, 2018, 46(21):118-124.
[9]傅美平,马红伟,毛建容.基于相似日和最小二乘支持向量机的光伏发电短期预测[J].电力系统保护与控制, 2012, 40(16):65-69.FU Meiping, MA Hongwei, MAO Jianrong. Short-term photovoltaic power forecasting based on similar days and least square support vector machine[J]. Power System Protection and Control, 2012, 40(16):65-69.
[10]单英浩,付青,耿炫,等.基于改进BP-SVM-ELM与粒子化SOM-LSF的微电网光伏发电组合预测方法[J].中国电机工程学报, 2016, 36(12):3334-3342.SHAN Yinghao, FU Qing, GENG Xuan, et al. Combined forecasting of photovoltaic power generation in microgrid based on the improved BP-SVM-ELM and SOM-LSF with particlization[J]. Proceedings of the CSEE, 2016,36(12):3334-3342.
[11] YANG X, JIE R, HONG Y. Photovoltaic power forecasting with a rough set combination method[C]//2016 UKACC 11th International Conference on Control(CONTROL), Belfast, 2016:1-6.
[12] LI Q, SUN Y, YU Y, et al. Short-term photovoltaic power forecasting for photovoltaic power station based on EWT-KMPMR[J]. Transactions of the Chinese Society of Agricultural Engineering, 2017, 33(20):265-273.
[13]李多,董海鹰,杨立霞.基于EMD与ELM的光伏电站短期功率预测[J].可再生能源, 2016, 34(2):173-177.LI Duo, DONG Haiying, YANG Lixia. The short-term power forecasting of photovoltaic plant based on EMD-ELM[J]. Renewable Energy Resources, 2016,34(2):173-177.
[14]张立影,刘智昱,孟令甲,等.基于小波变换和神经网络的光伏功率预测[J].可再生能源, 2015, 33(2):171-176.ZHANG Liying, LIU Zhiyu, MENG Lingjia, et al.Photovoltaic output power prediction approach based on wavelet transform and neural network[J]. Renewable Energy Resources, 2015, 33(2):171-176.
[15]路志英,任一墨,葛路琨.基于样条估计分位数回归的光伏功率回归模型[J].湖南大学学报(自然科学版),2017, 44(10):96-103.LU Zhiying, REN Yimo, GE Lukun. Photovoltaic power regression model based on spline estimation and quantile regression[J]. Journal of Hunan University(Natural Sciences), 2017, 44(10):96-103.
[16]陈云龙,殷豪,孟安波,等.基于模糊信息粒化的光伏出力区间预测[J].电测与仪表, 2018, 55(14):63-68.CHEN Yunlong, YIN Hao, MENG Anbo, et al. PV power interval prediction based on fuzzy information granulation[J].Electrical Measurement&Instrumentation, 2018, 55(14):63-68.
[17]程泽,刘冲,刘力.基于相似时刻的光伏出力概率分布估计方法[J].电网技术, 2017, 41(2):117-124.CHENG Ze, LIU Chong, LIU Li. A method of probabilistic distribution estimation of PV generation based on similar time of day[J]. Power System Technology,2017, 41(2):117-124.
[18]杨锡运,刘欢,张彬,等.组合权重相似日选取方法及光伏输出功率预测[J].电力自动化设备, 2014, 34(9):118-122.YANG Xiyun, LIU Huan, ZHANG Bin, et al. Similar day selection based on combined weight and photovoltaic power output forecasting[J]. Electric Power Automation Equipment, 2014, 34(9):118-122.
[19]李芬,李春阳,糜强,等.基于GRA-BPNN时变权重的光伏短期出力组合预测[J].可再生能源, 2018,36(11):1605-1611.LI Fen, LI Chunyang, MI Qiang, et al. The time-varying weight ensemble forecasting of short-term photovoltaic power based on GRA-BPNN[J]. Renewable Energy Resources, 2018, 36(11):1605-1611.
[20] NICOLAI M. Quantile regression forests[J]. Journal of Machine Learning Research, 2006, 7(2):983-999.
[21] TRAPERO J R. Calculation of solar irradiation prediction intervals combining volatility and kernel density estimates[J]. Energy, 2016, 114:266-274.