基于双维度顺序填补框架与改进Kohonen天气聚类的光伏发电短期预测
|
摘要
为提高部分数据缺失情况下智能电网光伏发电功率预测精度,提出一种基于双维度顺序填补框架与改进Kohonen天气聚类的光伏发电功率预测模型。采用双维度顺序填补方法补齐缺失数据,基于完整数据分析光伏发电功率影响因素,建立改进Kohonen天气聚类模型,并利用S-Kohonen实现预测日天气类型识别,将聚类历史日数据与预测日气象数据作为输入,采用多种群果蝇优化广义回归神经网络(MFOA-GRNN)模型对预测日光伏发电功率进行预测。仿真结果表明,所提方法能有效提高预测精度,为实现数据缺失情况下智能电网光伏发电功率的精准预测提供了一种思路。
To improve the accuracy of smart grid photovoltaic power forecasting in the absence of partial data,a forecasting method based on double-dimensional sequential imputation framework and improved Kohonen clustering is proposed. Firstly,using double-dimensional sequential imputation method to complement missing data,analyzing the influential factors of photovoltaic power based on the complete data,an improved Kohonen weather clustering model is established. Secondly,the weather type of the forecasting day is identified using S-Kohonen method. Finally,the MFOA-GRNN( Multi-swarm Fruit fly Optimization Algorithm and Generalized Regression Neural Network) model is used to forecast the daily photovoltaic power using the meteorological data of clustering historical day and forecasting day as input. The results show that the proposed method can effectively improve the forecasting accuracy and provide a way to accurately forecast the smart grid photovoltaic power under the condition of missing data.
To improve the accuracy of smart grid photovoltaic power forecasting in the absence of partial data,a forecasting method based on double-dimensional sequential imputation framework and improved Kohonen clustering is proposed. Firstly,using double-dimensional sequential imputation method to complement missing data,analyzing the influential factors of photovoltaic power based on the complete data,an improved Kohonen weather clustering model is established. Secondly,the weather type of the forecasting day is identified using S-Kohonen method. Finally,the MFOA-GRNN( Multi-swarm Fruit fly Optimization Algorithm and Generalized Regression Neural Network) model is used to forecast the daily photovoltaic power using the meteorological data of clustering historical day and forecasting day as input. The results show that the proposed method can effectively improve the forecasting accuracy and provide a way to accurately forecast the smart grid photovoltaic power under the condition of missing data.
引文
[1]鞠平,周孝信,陈维江,等.“智能电网+”研究综述[J].电力自动化设备,2018,38(5):2-11.JU Ping,ZHOU Xiaoxin,CHEN Weijiang,et al.“Smart grid plus”research overview[J]. Electric Power Automation Equipment,2018,38(5):2-11.
[2]孙丰杰,王承民,谢宁.面向智能电网大数据关联规则挖掘的频繁模式网络模型[J].电力自动化设备,2018,38(5):110-116.SUN Fengjie,WANG Chengmin,XIE Ning. Frequent pattern network model for association rule mining of big data in smart grid[J]. Electric Power Automation Equipment,2018,38(5):110-116.
[3]HU C,TAN B,YAO X. Research voltage stability of photovoltaic power generation system[C]∥2016 IEEE Electronic and Automation Control Conference(IMCEC). Xi'an,China:IEEE,2016:1491-1494.
[4]贾祺,严干贵,李泳霖,等.新型多端输入光伏并网系统运行控制策略[J].电力自动化设备,2017,37(10):43-48.JIA Qi,YAN Gangui,LI Yonglin,et al. Operation control strategy of novel multi-input grid-connected PV system[J]. Electric Power Automation Equipment,2017,37(10):43-48.
[5]李升,卫志农,孙国强,等.大规模光伏发电并网系统电压稳定分岔研究[J].电力自动化设备,2016,36(1):17-23.LI Sheng,WEI Zhinong,SUN Guoqiang,et al. Voltage stability bifurcation of large-scale grid-connected PV system[J]. Electric Power Automation Equipment,2016,36(1):17-23.
[6]王继东,庞文杰. Fisher判别分类法在光伏并网系统稳态电能质量评估中的应用[J].电力自动化设备,2017,37(3):50-54.WANG Jidong,PANG Wenjie. Application of Fisher discriminant analysis in steady-state power quality evaluation of grid-connected photovoltaic system[J]. Electric Power Automation Equipment,2017,37(3):50-54.
[7]龚莺飞,鲁宗相,乔颖,等.光伏功率预测技术[J].电力系统自动化,2016,40(4):140-151.GONG Yingfei,LU Zongxiang,QIAO Ying,et al. An overview of photovoltaic energy system output forecasting technology[J]. Automation of Electric Power Systems,2016,40(4):140-151.
[8]黎静华,赖昌伟.考虑气象因素的短期光伏出力预测的奇异谱分析方法[J].电力自动化设备,2018,38(5):50-57,76.LI Jinghua,LAI Changwei. Singular spectrum analysis method for short-term photovoltaic output prediction considering meteorological factors[J]. Electric Power Automation Equipment,2018,38(5):50-57,76.
[9]王飞,米增强,甄钊,等.基于天气状态模式识别的光伏电站发电功率分类预测方法[J].中国电机工程学报,2013,33(34):75-82.WANG Fei,MI Zengqiang,ZHEN Zhao,et al. A classified forecasting approach of power generation for photovoltaic plants based on weather condition pattern recognition[J]. Proceedings of the CSEE,2013,33(34):75-82.
[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]郭一飞,高厚磊,田佳.引入聚类分析的光伏出力建模及其在可靠性评估中的应用[J].电力系统自动化,2016,40(23):93-100.GUO Yifei,GAO Houlei,TIAN Jia. Photovoltaic output modeling by introducing clustering analysis and its application in reliability evaluation[J]. Automation of Electric Power Systems,2016,40(23):93-100.
[12]赵文清,郭丙旭,李刚,等.基于智能水滴算法优化Elman神经网络的光伏电站输出功率预测[J].太阳能学报,2017,38(6):1553-1559.ZHAO Wenqing,GUO Bingxu,LI Gang,et al. Output power forecast of plant based on Elman neural network drop algorithm[J]. Acta Energiae Solaris Sinica,2017,38(6):1553-1559.
[13]王昕,黄柯,郑益慧,等.基于PNN/PCA/SS-SVR的光伏发电功率短期预测方法[J].电力系统自动化,2016,40(17):156-162.WANG Qi,HUANG Ke,ZHENG Yihui,et al. Short-term forecasting method of photovoltaic output power based on PNN/PCA/SS-SVR[J]. Automation of Electric Power Systems,2016,40(17):156-162.
[14]TASCIKARAOGLU A,SANANDAJI B M,CHICCO G,et al. A shortterm spatio-temporal approach for photovoltaic power forecasting[C]∥2016 IEEE Power Systems Computation Conference(PSCC). Genoa,Italy:IEEE,2016:1-7.
[15]马茜,谷峪,李芳芳,等.顺序敏感的多源感知数据填补技术[J].软件学报,2016,27(9):2332-2347.MA Qian,GU Yu,LI Fangfang,et al. Order-sensitive missing value imputation technology for multi-source sensory data[J]. Journal of Software,2016,27(9):2332-2347.
[16]马小慧,阳育德,龚利武.基于Kohonen聚类和SVM组合算法的电网日最大负荷预测[J].电网与清洁能源,2014,30(2):7-11.MA Xiaohui,YANG Yude,GONG Liwu. Forecasting of the daily maximum load based on a combined model of Kohonen custering and SVM[J]. Power System and Clean Energy,2014,30(2):7-11.
[17]方浩,王艳红.改进的Kohonen神经网络航迹关联算法[J].计算机应用,2013,33(5):1476-1480.FANG Hao,WANG Yanhong. Track correlation algorithm based on modified Kohonen neural network[J]. Journal of Computer Applications,2013,33(5):1476-1480.
[18]郭欣,王蕾,宣伯凯,等.基于有监督Kohonen神经网络的步态识别[J].自动化学报,2017,43(3):430-438.GUO Xin,WANG Lei,XUAN Bokai,et al. Gait recognition based on supervised Kohonen neural network[J]. Acta Automatica Sinica,2017,43(3):430-438.
[19]姚李孝,刘学琴,伍利,等.基于广义回归神经网络的电力系统中长期负荷预测[J].电力自动化设备,2007,27(8):26-29.YAO Lixiao,LIU Xueqin,WU Li,et al. Mid-&long-term load forecast based on GRNN[J]. Electric Power Automation Equipment,2007,27(8):26-29.
[20]ANDREEV P G,YURKOV N K,ANDREEVA T V. Artificial neural networks of GRNN type in prediction problems[C]∥2017 IEEE Soft Computing and Measurements(SCM). Petersburg,Russia:IEEE,2017:458-460.
[21]李冬辉,尹海燕,郑博文.基于MFOA-GRNN模型的年电力负荷预测[J].电网技术,2018,42(2):585-590.LI Donghui,YIN Haiyan,ZHENG Bowen. An annual load forecasting model based on generalized regression neural network with multiswarm fruit fly optimization algorithm[J]. Power System Technology,2018,42(2):585-590.
[2]孙丰杰,王承民,谢宁.面向智能电网大数据关联规则挖掘的频繁模式网络模型[J].电力自动化设备,2018,38(5):110-116.SUN Fengjie,WANG Chengmin,XIE Ning. Frequent pattern network model for association rule mining of big data in smart grid[J]. Electric Power Automation Equipment,2018,38(5):110-116.
[3]HU C,TAN B,YAO X. Research voltage stability of photovoltaic power generation system[C]∥2016 IEEE Electronic and Automation Control Conference(IMCEC). Xi'an,China:IEEE,2016:1491-1494.
[4]贾祺,严干贵,李泳霖,等.新型多端输入光伏并网系统运行控制策略[J].电力自动化设备,2017,37(10):43-48.JIA Qi,YAN Gangui,LI Yonglin,et al. Operation control strategy of novel multi-input grid-connected PV system[J]. Electric Power Automation Equipment,2017,37(10):43-48.
[5]李升,卫志农,孙国强,等.大规模光伏发电并网系统电压稳定分岔研究[J].电力自动化设备,2016,36(1):17-23.LI Sheng,WEI Zhinong,SUN Guoqiang,et al. Voltage stability bifurcation of large-scale grid-connected PV system[J]. Electric Power Automation Equipment,2016,36(1):17-23.
[6]王继东,庞文杰. Fisher判别分类法在光伏并网系统稳态电能质量评估中的应用[J].电力自动化设备,2017,37(3):50-54.WANG Jidong,PANG Wenjie. Application of Fisher discriminant analysis in steady-state power quality evaluation of grid-connected photovoltaic system[J]. Electric Power Automation Equipment,2017,37(3):50-54.
[7]龚莺飞,鲁宗相,乔颖,等.光伏功率预测技术[J].电力系统自动化,2016,40(4):140-151.GONG Yingfei,LU Zongxiang,QIAO Ying,et al. An overview of photovoltaic energy system output forecasting technology[J]. Automation of Electric Power Systems,2016,40(4):140-151.
[8]黎静华,赖昌伟.考虑气象因素的短期光伏出力预测的奇异谱分析方法[J].电力自动化设备,2018,38(5):50-57,76.LI Jinghua,LAI Changwei. Singular spectrum analysis method for short-term photovoltaic output prediction considering meteorological factors[J]. Electric Power Automation Equipment,2018,38(5):50-57,76.
[9]王飞,米增强,甄钊,等.基于天气状态模式识别的光伏电站发电功率分类预测方法[J].中国电机工程学报,2013,33(34):75-82.WANG Fei,MI Zengqiang,ZHEN Zhao,et al. A classified forecasting approach of power generation for photovoltaic plants based on weather condition pattern recognition[J]. Proceedings of the CSEE,2013,33(34):75-82.
[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]郭一飞,高厚磊,田佳.引入聚类分析的光伏出力建模及其在可靠性评估中的应用[J].电力系统自动化,2016,40(23):93-100.GUO Yifei,GAO Houlei,TIAN Jia. Photovoltaic output modeling by introducing clustering analysis and its application in reliability evaluation[J]. Automation of Electric Power Systems,2016,40(23):93-100.
[12]赵文清,郭丙旭,李刚,等.基于智能水滴算法优化Elman神经网络的光伏电站输出功率预测[J].太阳能学报,2017,38(6):1553-1559.ZHAO Wenqing,GUO Bingxu,LI Gang,et al. Output power forecast of plant based on Elman neural network drop algorithm[J]. Acta Energiae Solaris Sinica,2017,38(6):1553-1559.
[13]王昕,黄柯,郑益慧,等.基于PNN/PCA/SS-SVR的光伏发电功率短期预测方法[J].电力系统自动化,2016,40(17):156-162.WANG Qi,HUANG Ke,ZHENG Yihui,et al. Short-term forecasting method of photovoltaic output power based on PNN/PCA/SS-SVR[J]. Automation of Electric Power Systems,2016,40(17):156-162.
[14]TASCIKARAOGLU A,SANANDAJI B M,CHICCO G,et al. A shortterm spatio-temporal approach for photovoltaic power forecasting[C]∥2016 IEEE Power Systems Computation Conference(PSCC). Genoa,Italy:IEEE,2016:1-7.
[15]马茜,谷峪,李芳芳,等.顺序敏感的多源感知数据填补技术[J].软件学报,2016,27(9):2332-2347.MA Qian,GU Yu,LI Fangfang,et al. Order-sensitive missing value imputation technology for multi-source sensory data[J]. Journal of Software,2016,27(9):2332-2347.
[16]马小慧,阳育德,龚利武.基于Kohonen聚类和SVM组合算法的电网日最大负荷预测[J].电网与清洁能源,2014,30(2):7-11.MA Xiaohui,YANG Yude,GONG Liwu. Forecasting of the daily maximum load based on a combined model of Kohonen custering and SVM[J]. Power System and Clean Energy,2014,30(2):7-11.
[17]方浩,王艳红.改进的Kohonen神经网络航迹关联算法[J].计算机应用,2013,33(5):1476-1480.FANG Hao,WANG Yanhong. Track correlation algorithm based on modified Kohonen neural network[J]. Journal of Computer Applications,2013,33(5):1476-1480.
[18]郭欣,王蕾,宣伯凯,等.基于有监督Kohonen神经网络的步态识别[J].自动化学报,2017,43(3):430-438.GUO Xin,WANG Lei,XUAN Bokai,et al. Gait recognition based on supervised Kohonen neural network[J]. Acta Automatica Sinica,2017,43(3):430-438.
[19]姚李孝,刘学琴,伍利,等.基于广义回归神经网络的电力系统中长期负荷预测[J].电力自动化设备,2007,27(8):26-29.YAO Lixiao,LIU Xueqin,WU Li,et al. Mid-&long-term load forecast based on GRNN[J]. Electric Power Automation Equipment,2007,27(8):26-29.
[20]ANDREEV P G,YURKOV N K,ANDREEVA T V. Artificial neural networks of GRNN type in prediction problems[C]∥2017 IEEE Soft Computing and Measurements(SCM). Petersburg,Russia:IEEE,2017:458-460.
[21]李冬辉,尹海燕,郑博文.基于MFOA-GRNN模型的年电力负荷预测[J].电网技术,2018,42(2):585-590.LI Donghui,YIN Haiyan,ZHENG Bowen. An annual load forecasting model based on generalized regression neural network with multiswarm fruit fly optimization algorithm[J]. Power System Technology,2018,42(2):585-590.