基于日类型及融合理论的BP网络光伏功率预测
|
摘要
针对光伏发电受到外界环境的制约、发电功率波动较大、很难保证高比率接入等对电网的安全运行和调度造成一定影响的问题,提出一种基于日类型及融合理论的BP网络预测方法,将不同的天气大体分为3种日类型即晴天、多云天、雨天,并进行分类预测,充分考虑制约光伏发电的5个最主要因素即光照强度、环境温度、组件温度、风速和相对湿度,找出其与发电功率之间的相关系数,通过信息融合理念将其融合成1个综合影响因子λ。以BP神经网络模型为构架进行功率预测,通过动态变换隐含层层数提高预测精度,并利用改进的粒子群算法对其参数进行优化,同时通过光伏历史功率输出波动特性对预测误差进行修正,最后在某县光伏电站进行实际验证。研究结果表明:该网络预测方法可行有效,且精度较高。
Considering that photovoltaic power generation is constrained by the external environment, and the fluctuations in power generation is large, and it is difficult to ensure high-rate access, which affect the safe operation and dispatch of the power grid, a BP network prediction method was proposed based on daily types and fusion theory. It divided different weathers into three daily types, and classification predictions were made for the three daily types. Five most important factors that restricted photovoltaic power generation were fully considered, and the correlation coefficient between the factors and power generation was found out, and information was integrated into a comprehensive influencing factor λ. The power forecast was made based on the BP neural network model. and the prediction accuracy is improved by dynamically changing the number of hidden layers. The parameters were optimized based on particle swarm algorithm and the prediction error is corrected by the historical power output fluctuation characteristics of the photovoltaic. Finally, the method was verified at a photovoltaic power station.The results show that the network prediction method is feasible and effective, and the accuracy is high.
Considering that photovoltaic power generation is constrained by the external environment, and the fluctuations in power generation is large, and it is difficult to ensure high-rate access, which affect the safe operation and dispatch of the power grid, a BP network prediction method was proposed based on daily types and fusion theory. It divided different weathers into three daily types, and classification predictions were made for the three daily types. Five most important factors that restricted photovoltaic power generation were fully considered, and the correlation coefficient between the factors and power generation was found out, and information was integrated into a comprehensive influencing factor λ. The power forecast was made based on the BP neural network model. and the prediction accuracy is improved by dynamically changing the number of hidden layers. The parameters were optimized based on particle swarm algorithm and the prediction error is corrected by the historical power output fluctuation characteristics of the photovoltaic. Finally, the method was verified at a photovoltaic power station.The results show that the network prediction method is feasible and effective, and the accuracy is high.
引文
[1]张贵涛,龚芬,夏向阳,等.光伏并网逆变器电能质量控制策略[J].电力科学与技术学报,2017,32(4):50-56.ZHANG Guitao,GONG Fen,XIA Xiangyang,et al.Power quality control strategy of photovoltaic grid-connected inverter[J].Journal of Electric Power Science and Technology,2017,32(4):50-56.
[2]易浩民,夏向阳,李经野,等.基于无功功率和储能平衡的配网馈线电压控制[J].中南大学学报(自然科学版),2017,48(11):2972-2978.YI Haomin,XIA Xiangyang,LI Jingye,et al.Feeder voltage control in distribution network based on reactive power and energy storage balance[J].Journal of Central South University(Science and Technology),2017,48(11):2972-2978.
[3]夏向阳,易浩民,邱欣,等.双重功率优化控制的规模化光伏并网电压越限研究[J].中国电机工程学报,2016,36(19):5164-5171,5397.XIA Xiangyang,YI Haomin,QIU Xin,et al.Research on dual power optimal control for scaled photovoltaic grid-connected voltage[J].China Journal of Electrical Engineering,2016,36(19):5164-5171,5397.
[4]贾晋峰,易浩民,夏向阳,等.分布式能源接入电力系统的新型计量系统[J].电力系统保护与控制,2017,45(3):118-124.JIA Jinfeng,YI Haomin,Xiayang,et al.Distributed energy power system access new metering system[J].Power System Protection and Control,2017,45(3):118-124.
[5]夏向阳,王锦泷,易浩民,等.光伏并网发电系统最大功率输出控制研究[J].中南大学学报(自然科学版),2016,47(7):2296-2303.XIA Xiangyang,WANG Jinlong,YI Haomin,et al.Research on the maximum power output control of photovoltaic generation system[J].Journal of Central South University(Science and Technology),2016,47(7):2296-2303.
[6]叶林,陈政,赵永宁,等.基于遗传算法-模糊径向基神经网络的光伏发电功率预测模型[J].电力系统自动化,2015,39(16):16-22.YE Lin,CHEN Zheng,ZHAO Yongning,et al.Photovoltaic power forecasting model based on genetic algorithm and fuzzy radial basis function neural network[J].Automation of Power System,2015,39(16):16-22.
[7]NORDIN N.Prediction of AC power output in grid-connectedphotovoltaic system using Artificial Neural Network with multi-variable inputs 2016 IEEE Conference on Systems[C]//Process and Control(ICSPC),2016:192-195.
[8]于群,朴在林,胡博.基于EEMD和BP神经网络的短期光伏功率预测模型[J].电网与清洁能源,2016,32(7):132-137YU Qun,PU Zailin,HU Bo.A hybrid model for short-term photovoltaic power forecasting based on eemd-bp combined method[J].Power System and Clean Energy,2016,32(7):132-137.
[9]嵇灵,牛东晓,汪鹏.基于相似日聚类和贝叶斯神经网络的光伏发电功率预测研究[J].中国管理科学,2015,23(3):118-122.JI Lin,NIU Xiaodong,WANG Peng.Photovoltaic load forecasting based on the similar day and bayesian neural network[J].Chinese Journal of Management Science,2015,23(3):118-122.
[10]史佳琪,张建华.基于深度学习的超短期光伏精细化预测模型研究[J].电力建设,2017,38(6):28-35.SHI Jiaqi,ZHANG Jianhua.Ultra short-term photovoltaic refined forecasting model based on deep learning[J].Electric Power Construction,2017,38(6):28-35.
[11]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 PVgeneration system forecasting model without irradiation based on weather type clustering[J].China Journal of Electrical Engineering,2011,31(34):28-35.
[12]李春来,张海宁,杨立滨,等.基于无迹卡尔曼滤波神经网络的光伏发电预测[J].重庆大学学报,2017,40(4):54-61.LI Chunlai,ZHANG Haining,YANG Libing,et al.Photovoltaic power forecasting based on unscented Kalman filtering neural network[J].Journal of Chongqing University,2017,40(4):54-61.
[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.CHEN Zhibao,DING Jie,ZHOU Hai,et al.A model of very short-term photovoltaic power forecasting based on ground-based cloud images and rbf neural network[J].China Journal of Electrical Engineering,2015,35(3):561-567.
[14]MANDAL P,MADHIRA S T S,MENG J,et al.Forecasting power output of solar photovoltaic system using wavelet transform and artificial intelligence techniques[J].Procedia Computer Science,2012,12:332-337.
[15]姜运,彭红海,曾祥君,等.配电网故障行波定位动模实验平台[J].电力科学与技术学报,2017,32(3):81-85.JIANG Yun,PENG Honghai,ZENG Xiangjun,et al.Dynamic simulation experimental platform for traveling-wave-based fault location in distribution network[J].Journal of Electric Power Science and Technology,2017,32(3):81-85.
[16]YONA A,SENJYU T,FUNABASHI T.Application of recurrent neural network to short-term-ahead generating power forecasting for photovoltaic system[C]//IEEE Power Engineering Society General Meeting.Tampa,FLORIDA,USA:Institute of Electrical and Electronics Engineers,2007:1-6.
[17]唐俊熙,何迪,郭创新.基于模糊综合评估的电网人因可靠性分析[J].电力科学与技术学报,2017,32(3):63-68.TANG Junxi,HE Di,GUO Chuangxin.Analysis of human reliability in power grid based on fuzzy synthetic evaluation[J].Journal of Electric Power Science and Technology,2017,32(3):63-68.
[18]张世丰.影响太阳能光伏发电的气象因子分析[J].农业与技术,2014,34(7):194-201.ZHANG Shifeng.Analysis of meteorological factors affecting solar photovoltaic power generation[J].Agriculture and Technology,2014,34(7):194-201.
[19]宫娅宁,苏舒,林湘宁,等.独立光伏发电储能系统能量管理与经济调度研究[J].电力科学与技术学报,2017,32(2):3-9,30.GONG Yaning,SU Shu,LIN Xiangning,et al.Study on energy management and economic dispatch of stand-alone photovoltaic generation system with hybrid energy storage[J].Journal of Electric Power Science and Technology,2017,32(2):3-9,30.
[20]刘雪飞,田启东,焦昊,等.考虑多风险因素的电网调度操作风险评估[J].电力科学与技术学报,2016,31(4):109-115.LIU Xuefei,TIAN Qidong,JIAO Hao,et al.Power grid risk assessment of dispatching operation considering multi-risk elements[J].Journal of Electric Power Science and Technology,2016,31(4):109-115.
[21]龙海超,欧阳森,张华赢.基于BP神经网络的电网电压暂降源定位方法[J].电力科学与技术学报,2017,32(2):62-69.LONG Haichao,OUYANG Sen,ZHANG Huaying.A novel location method of power grid voltage sag source with BP neural network[J].Journal of Electric Power Science and Technology,2017,32(2):62-69.
[22]刘晓楠,周介圭,贾宏杰,等.基于非参数核密度估计与数值天气预报的风速预测修正方法[J].电力自动化设备,2017,37(10):15-20.LIU Xiaolan,ZHOU Jiewa,JIA Hongjie,et al.Correction method of wind speed prediction based on non-parametric kernel density estimation and numerical weather prediction[J].Power Automation Equipment,2017,37(10):15-20.
[23]解玖霞.基于粒子群算法的主动配电网经济优化调度[J].电气技术,2017(9):15-18.XIE Jiuxia.Economic optimization scheduling of active power distribution[J].Electrical Technology,2017(9):15-18.
[24]陈深,肖俊阳,黄玉程,等.基于改进量子粒子群算法的微网多目标优化调度[J].电力科学与技术学报,2015,30(2):41-47.CHEN Shen,XIAO Junyang,HUANG Yucheng,et al.Multi-objective optimal dispatching of micro-grid with improved quantum-behaved particle swarm algorithm[J].Journal of Electric Power Science and Technology,2015,30(2):41-47.
[25]乔颖,鲁宗相,闵勇.提高风电功率预测精度的方法[J].电网技术,2017,41(10):3261-3269.QIAO Ying,LU Zongxiang,MIN Yong,et al.Research&application of raising wind power prediction accuracy[J].Power Grid Technology,2017,41(10):3261-3269.
[26]史常凯,闫文棋,张筱慧,等.基于BP网络和灰色模型的春节配变重过载预测[J].电力科学与技术学报,2016,31(3):140-145.SHI Changkai,YAN Wenqi,ZHANG Xiaohui,et al.Heavy overload forecasting of distribution festival based on BP network transformer during the spring and grey model[J].Journal of Electric Power Science and Technology,2016,31(3):140-145.
[2]易浩民,夏向阳,李经野,等.基于无功功率和储能平衡的配网馈线电压控制[J].中南大学学报(自然科学版),2017,48(11):2972-2978.YI Haomin,XIA Xiangyang,LI Jingye,et al.Feeder voltage control in distribution network based on reactive power and energy storage balance[J].Journal of Central South University(Science and Technology),2017,48(11):2972-2978.
[3]夏向阳,易浩民,邱欣,等.双重功率优化控制的规模化光伏并网电压越限研究[J].中国电机工程学报,2016,36(19):5164-5171,5397.XIA Xiangyang,YI Haomin,QIU Xin,et al.Research on dual power optimal control for scaled photovoltaic grid-connected voltage[J].China Journal of Electrical Engineering,2016,36(19):5164-5171,5397.
[4]贾晋峰,易浩民,夏向阳,等.分布式能源接入电力系统的新型计量系统[J].电力系统保护与控制,2017,45(3):118-124.JIA Jinfeng,YI Haomin,Xiayang,et al.Distributed energy power system access new metering system[J].Power System Protection and Control,2017,45(3):118-124.
[5]夏向阳,王锦泷,易浩民,等.光伏并网发电系统最大功率输出控制研究[J].中南大学学报(自然科学版),2016,47(7):2296-2303.XIA Xiangyang,WANG Jinlong,YI Haomin,et al.Research on the maximum power output control of photovoltaic generation system[J].Journal of Central South University(Science and Technology),2016,47(7):2296-2303.
[6]叶林,陈政,赵永宁,等.基于遗传算法-模糊径向基神经网络的光伏发电功率预测模型[J].电力系统自动化,2015,39(16):16-22.YE Lin,CHEN Zheng,ZHAO Yongning,et al.Photovoltaic power forecasting model based on genetic algorithm and fuzzy radial basis function neural network[J].Automation of Power System,2015,39(16):16-22.
[7]NORDIN N.Prediction of AC power output in grid-connectedphotovoltaic system using Artificial Neural Network with multi-variable inputs 2016 IEEE Conference on Systems[C]//Process and Control(ICSPC),2016:192-195.
[8]于群,朴在林,胡博.基于EEMD和BP神经网络的短期光伏功率预测模型[J].电网与清洁能源,2016,32(7):132-137YU Qun,PU Zailin,HU Bo.A hybrid model for short-term photovoltaic power forecasting based on eemd-bp combined method[J].Power System and Clean Energy,2016,32(7):132-137.
[9]嵇灵,牛东晓,汪鹏.基于相似日聚类和贝叶斯神经网络的光伏发电功率预测研究[J].中国管理科学,2015,23(3):118-122.JI Lin,NIU Xiaodong,WANG Peng.Photovoltaic load forecasting based on the similar day and bayesian neural network[J].Chinese Journal of Management Science,2015,23(3):118-122.
[10]史佳琪,张建华.基于深度学习的超短期光伏精细化预测模型研究[J].电力建设,2017,38(6):28-35.SHI Jiaqi,ZHANG Jianhua.Ultra short-term photovoltaic refined forecasting model based on deep learning[J].Electric Power Construction,2017,38(6):28-35.
[11]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 PVgeneration system forecasting model without irradiation based on weather type clustering[J].China Journal of Electrical Engineering,2011,31(34):28-35.
[12]李春来,张海宁,杨立滨,等.基于无迹卡尔曼滤波神经网络的光伏发电预测[J].重庆大学学报,2017,40(4):54-61.LI Chunlai,ZHANG Haining,YANG Libing,et al.Photovoltaic power forecasting based on unscented Kalman filtering neural network[J].Journal of Chongqing University,2017,40(4):54-61.
[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.CHEN Zhibao,DING Jie,ZHOU Hai,et al.A model of very short-term photovoltaic power forecasting based on ground-based cloud images and rbf neural network[J].China Journal of Electrical Engineering,2015,35(3):561-567.
[14]MANDAL P,MADHIRA S T S,MENG J,et al.Forecasting power output of solar photovoltaic system using wavelet transform and artificial intelligence techniques[J].Procedia Computer Science,2012,12:332-337.
[15]姜运,彭红海,曾祥君,等.配电网故障行波定位动模实验平台[J].电力科学与技术学报,2017,32(3):81-85.JIANG Yun,PENG Honghai,ZENG Xiangjun,et al.Dynamic simulation experimental platform for traveling-wave-based fault location in distribution network[J].Journal of Electric Power Science and Technology,2017,32(3):81-85.
[16]YONA A,SENJYU T,FUNABASHI T.Application of recurrent neural network to short-term-ahead generating power forecasting for photovoltaic system[C]//IEEE Power Engineering Society General Meeting.Tampa,FLORIDA,USA:Institute of Electrical and Electronics Engineers,2007:1-6.
[17]唐俊熙,何迪,郭创新.基于模糊综合评估的电网人因可靠性分析[J].电力科学与技术学报,2017,32(3):63-68.TANG Junxi,HE Di,GUO Chuangxin.Analysis of human reliability in power grid based on fuzzy synthetic evaluation[J].Journal of Electric Power Science and Technology,2017,32(3):63-68.
[18]张世丰.影响太阳能光伏发电的气象因子分析[J].农业与技术,2014,34(7):194-201.ZHANG Shifeng.Analysis of meteorological factors affecting solar photovoltaic power generation[J].Agriculture and Technology,2014,34(7):194-201.
[19]宫娅宁,苏舒,林湘宁,等.独立光伏发电储能系统能量管理与经济调度研究[J].电力科学与技术学报,2017,32(2):3-9,30.GONG Yaning,SU Shu,LIN Xiangning,et al.Study on energy management and economic dispatch of stand-alone photovoltaic generation system with hybrid energy storage[J].Journal of Electric Power Science and Technology,2017,32(2):3-9,30.
[20]刘雪飞,田启东,焦昊,等.考虑多风险因素的电网调度操作风险评估[J].电力科学与技术学报,2016,31(4):109-115.LIU Xuefei,TIAN Qidong,JIAO Hao,et al.Power grid risk assessment of dispatching operation considering multi-risk elements[J].Journal of Electric Power Science and Technology,2016,31(4):109-115.
[21]龙海超,欧阳森,张华赢.基于BP神经网络的电网电压暂降源定位方法[J].电力科学与技术学报,2017,32(2):62-69.LONG Haichao,OUYANG Sen,ZHANG Huaying.A novel location method of power grid voltage sag source with BP neural network[J].Journal of Electric Power Science and Technology,2017,32(2):62-69.
[22]刘晓楠,周介圭,贾宏杰,等.基于非参数核密度估计与数值天气预报的风速预测修正方法[J].电力自动化设备,2017,37(10):15-20.LIU Xiaolan,ZHOU Jiewa,JIA Hongjie,et al.Correction method of wind speed prediction based on non-parametric kernel density estimation and numerical weather prediction[J].Power Automation Equipment,2017,37(10):15-20.
[23]解玖霞.基于粒子群算法的主动配电网经济优化调度[J].电气技术,2017(9):15-18.XIE Jiuxia.Economic optimization scheduling of active power distribution[J].Electrical Technology,2017(9):15-18.
[24]陈深,肖俊阳,黄玉程,等.基于改进量子粒子群算法的微网多目标优化调度[J].电力科学与技术学报,2015,30(2):41-47.CHEN Shen,XIAO Junyang,HUANG Yucheng,et al.Multi-objective optimal dispatching of micro-grid with improved quantum-behaved particle swarm algorithm[J].Journal of Electric Power Science and Technology,2015,30(2):41-47.
[25]乔颖,鲁宗相,闵勇.提高风电功率预测精度的方法[J].电网技术,2017,41(10):3261-3269.QIAO Ying,LU Zongxiang,MIN Yong,et al.Research&application of raising wind power prediction accuracy[J].Power Grid Technology,2017,41(10):3261-3269.
[26]史常凯,闫文棋,张筱慧,等.基于BP网络和灰色模型的春节配变重过载预测[J].电力科学与技术学报,2016,31(3):140-145.SHI Changkai,YAN Wenqi,ZHANG Xiaohui,et al.Heavy overload forecasting of distribution festival based on BP network transformer during the spring and grey model[J].Journal of Electric Power Science and Technology,2016,31(3):140-145.