考虑数据新鲜度和交叉熵的电动汽车短期充电负荷预测模型
|
摘要
研究了公交车充电站短期负荷预测方法,提出了一种基于数据新鲜度和交叉熵的组合预测模型。首先,对公交车充电站的负荷特性进行分析,发现日充电负荷具有波动大、周期性、与气象条件(温度、降雨等)密切相关的特点。其次,对组合预测模型在累积历史预测误差的过程中作了如下改进:1考虑充电负荷样本数据的时间特征和波动性特征,给出了基于灰色关联度的相似日选取方法;2考虑单一模型在预测过程中的精度和稳定度,基于交叉熵和正态分布概率密度函数建立组合预测模型,动态地调整权重系数;3充分考虑数据源的时间有效性,提出新鲜度函数的概念,改善了单一预测方法的概率密度分布函数,进而优化组合预测的权重系数,进一步提高组合模型预测精度。基于北京市某公交车充电站的历史充电数据构建训练样本和测试样本,通过与单一预测模型和其他组合模型的预测结果进行比较,证明了所提组合预测模型的有效性。
Short-term load forecasting methods for the bus charging station are studied prior to proposing a combined forecasting model based on data freshness and cross entropy.First,the load characteristics are analyzed to show the daily charging load has the features of large fluctuation,periodicity,and being closely related to meteorological conditions(including temperature and rainfall).Secondly,in the accumulation process of historical prediction errors,the combined forecasting model is improved in the following aspects:1Considering the time characteristics and fluctuating characteristics of the charging load sample data,the selecting method of similar days based on grey relational degree is proposed;2Considering the precision and stability of a single method,a combined forecasting model based on cross entropy and normal distribution probability density function is developed to dynamically adjust the weight coefficients;3Considering the time effectiveness of the data source,the concept of freshness function is put forward,which improves the probability density distribution function of the single forecasting method to further optimize the weight coefficients of the combined forecasting model,improving the accuracy of the model.Finally,the training samples and test samples based on the historical data of a Beijing bus charging station are developed.Compared with single models and other combined forecasting methods,the validity of the combined forecasting model proposed is proved.
Short-term load forecasting methods for the bus charging station are studied prior to proposing a combined forecasting model based on data freshness and cross entropy.First,the load characteristics are analyzed to show the daily charging load has the features of large fluctuation,periodicity,and being closely related to meteorological conditions(including temperature and rainfall).Secondly,in the accumulation process of historical prediction errors,the combined forecasting model is improved in the following aspects:1Considering the time characteristics and fluctuating characteristics of the charging load sample data,the selecting method of similar days based on grey relational degree is proposed;2Considering the precision and stability of a single method,a combined forecasting model based on cross entropy and normal distribution probability density function is developed to dynamically adjust the weight coefficients;3Considering the time effectiveness of the data source,the concept of freshness function is put forward,which improves the probability density distribution function of the single forecasting method to further optimize the weight coefficients of the combined forecasting model,improving the accuracy of the model.Finally,the training samples and test samples based on the historical data of a Beijing bus charging station are developed.Compared with single models and other combined forecasting methods,the validity of the combined forecasting model proposed is proved.
引文
[1]Electric Vehicles Initiative(EVI).Globe EV outlook:understanding the electric vehicle landscape to 2020[R].2013.
[2]Energy saving and new energy automobile industry planning[EB/OL].[2015-04-25].http://www.gov.cn/zwgk/2012-07/09/content_2179032.htm.
[3]RAZEGHI G,ZHANG L,BROWN T,et al.Impacts of plug-in hybrid electric vehicles on a residential transformer using stochastic and empirical analysis[J].Journal of Power Sources,2014,252:277-285.
[4]CLEMENT K,HAESEN E,DRIESEN J,et al.The impact of charging plug-in hybrid electric vehicle on a residential distribution grid[J].IEEE Trans on Power Systems,2010,25(1):371-380.
[5]陈丽丹,张尧.电动汽车充电负荷预测系统研究[J].电力科学与技术学报,2014,29(1):29-34.CHEN Lidan,ZHANG Yao.Load forecasting system of electric vehicle charging[J].Journal of Electric Power Science and Technology,2014,29(1):29-34.
[6]MASOUM A S,DEILAMI S,MOSES P S,et al.Smart load management of plug-in electric vehicles in distribution and residential networks with charging stations for peak shaving and loss minimisation considering voltage regulation[J].IET Generation,Transmission&Distribution,2011,5(8):877-888.
[7]刘青,戚中译.基于蒙特卡洛法的电动汽车负荷预测建模[J].电力科学与工程,2014,30(10):14-21.LIU Qing,QI Zhongyi.Electric vehicles load forecasting model based on Monte Carlo simulation[J].Electric Power Science and Engineering,2014,30(10):14-21.
[8]袁正平,周伟,王文斌.电动汽车充电负荷预测方法研究[J].华东电力,2013,41(12):2657-2665.YUAN Zhengping,ZHOU Wei,WANG Wenbin.Charging load forecasting method for electric vehicles[J].East China Electric Power,2013,41(12):2657-2665.
[9]刘青,戚中译.考虑空间运动特性的规模化电动汽车接入电网负荷预测模型[J].现代电力,2015,32(1):76-87.LIU Qing,QI Zhongyi.The load forecast model for power grid with the accessing of large-scale electric vehicles by considering spatial motion characteristics[J].Modern Electric Power,2015,32(1):76-87.
[10]张洪财,胡泽春,宋永华,等.考虑时空分布的电动汽车充电负荷预测方法[J].电力系统自动化,2014,38(1):13-20.DOI:10.7500/AEPS20130613009.ZHANG Hongcai,HU Zechun,SONG Yonghua,et al.A prediction method for electric vehicle charging load considering spatial and temporal distribution[J].Automation of Electric Power Systems,2014,38(1):13-20.DOI:10.7500/AEPS20130613009.
[11]ASHTARI A,BIBEAU E,SHAHIDINEJAD S,et al.PEV charging profile prediction and analysis based on vehicle usage data[J].IEEE Trans on Smart Grid,2012,3(1):341-350.
[12]常德政,任杰,赵建伟,等.基于RBF-NN的电动汽车充电站短期负荷预测研究[J].青岛大学学报(工程技术版),2014,29(4):45-51.CHANG Dezheng,REN Jie,ZHAO Jianwei,et al.Research of short-term load forecasting model for electrical vehicle charging station based on RBF-NN[J].Journal of Qingdao University(Engineering&Technology Edition),2014,29(4):45-51.
[13]刘文霞,徐晓波,周樨.基于支持向量机的纯电动公交车充/换电站日负荷预测[J].电力系统自动化设备,2014,34(11):41-48.LIU Wenxia,XU Xiaobo,ZHOU Xi.Daily load forecasting based on SVM for electric bus charging station[J].Electric Power Automation Equipment,2014,34(11):41-48.
[14]TASCIKARAOGLU A,UZUNOGLU M.A review of combined approaches for prediction of short-term wind speed and power[J].Renewable and Sustainable Energy Reviews,2014,34:243-254.
[15]ZHANG W Y,HONG W C,DONG Y C,et al.Application of SVR with chaotic GASA algorithm in cyclic electric load forecasting[J].Energy,2012,45(1):850-858.
[16]周湶,孙威,任海军,等.基于最小二乘支持向量机和负荷密度指标法的配电网空间负荷预测[J].电网技术,2011,35(1):66-70.ZHOU Quan,SUN Wei,REN Haijun,et al.Spatial load forecasting of distribution network based on least squares support vector machine and load density index system[J].Power System Technology,2011,35(1):66-70.
[17]肖白,聂鹏,穆钢,等.基于多级聚类分析和支持向量机的空间负荷预测方法[J].电力系统自动化,2015,39(12):56-61.DOI:10.7500/AEPS20140520001.XIAO Bai,NIE Peng,MU Gang,et al.A spatial load forecasting method based on multilevel clustering analysis and support vector machine[J].Automation of Electric Power Systems,2015,39(12):56-61.DOI:10.7500/AEPS20140520001.
[18]VAPNIK V,GOLOWICH S,SMOLA A.Support vector machine for function approximation,regression estimation and signal processing[C]//Advances in Neural Information Processing Systems,December 2-5,1996,Denver,USA:281-287.
[19]HINOJOSA V H,HOESE A.Short-term load forecasting using fuzzy inductive reasoning and evolutionary algorithms[J].IEEE Trans on Power Systems,2010,25(1):565-574.
[20]BATES J,GRANGER C.The combination of forecast[J].Operations Research Quarterly,1969,20(4):451-468.
[21]陈华友.组合预测方法有效性理论及其应用[M].北京:科学出版社,2008:40-98,113-125,224-237.
[22]FAN S,CHEN L,LEE W J.Short-term load forecasting using comprehensive combination based on multimeteorological information[J].IEEE Trans on Industry Applications,2009,45(4):1460-1466.
[23]VELSQUEZ J D,ZAMBRANO C,FRANCO C J.Forecast combining using ageneralized single multiplicative neuron[J].IEEE Latin America Transactions,2014,12(4):713-717.
[24]苏小红.基于人工神经网络的燃气短期负荷预测研究[D].重庆:重庆大学,2005.
[25]尹星露,肖先勇,孙晓璐.基于预测有效度和马尔科夫-云模型的母线负荷预测模型筛选与变权重组合预测[J].电力自动化设备,2015,35(7):114-120.YIN Xinglu,XIAO Xianyong,SUN Xiaolu.Bus load forecasting model selection and variable weights combination forecasting based on forecasting effectiveness and Markov chain-cloud model[J].Electric Power Automation Equipment,2015,35(7):114-120.
[26]高尚,梅亮.基于支持向量机的电价组合预测模型[J].电力自动化设备,2008,28(11):50-55.GAO Shang,MEI Liang.Combined forecasting model of electricity price based on support vector machine[J].Electric Power Automation Equipment,2008,28(11):50-55.
[27]赵文清,朱永利,张小奇.应用支持向量机的变压器故障组合预测[J].中国电机工程学报,2008,28(9):14-21.ZHAO Wenqing,ZHU Yongli,ZHANG Xiaoqi.Combinational forecast for transformer faults based on support vector machine[J].Proceedings of the CSEE,2008,28(9):14-21.
[28]栗然,刘会兰,卢云,等.基于交叉熵理论的配电变压器寿命组合预测方法[J].电力系统保护与控制,2014,42(2):97-101.LI Ran,LIU Huilan,LU Yun,et al.A combination method for distribution transformer life prediction based on cross entropy theory[J].Power System Protection and Control,2014,42(2):97-101.
[29]陈宁,沙倩,汤奕,等.基于交叉熵理论的风电功率组合预测方法[J].中国电机工程学报,2012,32(4):29-34.CHEN Ning,SHA Qian,TANG Yi,et al.A combination method for wind power predication based on cross entropy theory[J].Proceedings of the CSEE,2012,32(4):29-34.
[30]孙广强,姚建刚,谢宇翔,等.基于新鲜度函数和预测有效度的模糊自适应变权重中长期电力负荷组合预测[J].电网技术,2009,33(9):103-108.SUN Guangqiang,YAO Jiangang,XIE Yuxiang,et al.Combination forecast of medium-and long-term load using fuzzy adaptive variable weight based on fresh degree function and forecasting availability[J].Power System Technology,2009,33(9):103-108.
[2]Energy saving and new energy automobile industry planning[EB/OL].[2015-04-25].http://www.gov.cn/zwgk/2012-07/09/content_2179032.htm.
[3]RAZEGHI G,ZHANG L,BROWN T,et al.Impacts of plug-in hybrid electric vehicles on a residential transformer using stochastic and empirical analysis[J].Journal of Power Sources,2014,252:277-285.
[4]CLEMENT K,HAESEN E,DRIESEN J,et al.The impact of charging plug-in hybrid electric vehicle on a residential distribution grid[J].IEEE Trans on Power Systems,2010,25(1):371-380.
[5]陈丽丹,张尧.电动汽车充电负荷预测系统研究[J].电力科学与技术学报,2014,29(1):29-34.CHEN Lidan,ZHANG Yao.Load forecasting system of electric vehicle charging[J].Journal of Electric Power Science and Technology,2014,29(1):29-34.
[6]MASOUM A S,DEILAMI S,MOSES P S,et al.Smart load management of plug-in electric vehicles in distribution and residential networks with charging stations for peak shaving and loss minimisation considering voltage regulation[J].IET Generation,Transmission&Distribution,2011,5(8):877-888.
[7]刘青,戚中译.基于蒙特卡洛法的电动汽车负荷预测建模[J].电力科学与工程,2014,30(10):14-21.LIU Qing,QI Zhongyi.Electric vehicles load forecasting model based on Monte Carlo simulation[J].Electric Power Science and Engineering,2014,30(10):14-21.
[8]袁正平,周伟,王文斌.电动汽车充电负荷预测方法研究[J].华东电力,2013,41(12):2657-2665.YUAN Zhengping,ZHOU Wei,WANG Wenbin.Charging load forecasting method for electric vehicles[J].East China Electric Power,2013,41(12):2657-2665.
[9]刘青,戚中译.考虑空间运动特性的规模化电动汽车接入电网负荷预测模型[J].现代电力,2015,32(1):76-87.LIU Qing,QI Zhongyi.The load forecast model for power grid with the accessing of large-scale electric vehicles by considering spatial motion characteristics[J].Modern Electric Power,2015,32(1):76-87.
[10]张洪财,胡泽春,宋永华,等.考虑时空分布的电动汽车充电负荷预测方法[J].电力系统自动化,2014,38(1):13-20.DOI:10.7500/AEPS20130613009.ZHANG Hongcai,HU Zechun,SONG Yonghua,et al.A prediction method for electric vehicle charging load considering spatial and temporal distribution[J].Automation of Electric Power Systems,2014,38(1):13-20.DOI:10.7500/AEPS20130613009.
[11]ASHTARI A,BIBEAU E,SHAHIDINEJAD S,et al.PEV charging profile prediction and analysis based on vehicle usage data[J].IEEE Trans on Smart Grid,2012,3(1):341-350.
[12]常德政,任杰,赵建伟,等.基于RBF-NN的电动汽车充电站短期负荷预测研究[J].青岛大学学报(工程技术版),2014,29(4):45-51.CHANG Dezheng,REN Jie,ZHAO Jianwei,et al.Research of short-term load forecasting model for electrical vehicle charging station based on RBF-NN[J].Journal of Qingdao University(Engineering&Technology Edition),2014,29(4):45-51.
[13]刘文霞,徐晓波,周樨.基于支持向量机的纯电动公交车充/换电站日负荷预测[J].电力系统自动化设备,2014,34(11):41-48.LIU Wenxia,XU Xiaobo,ZHOU Xi.Daily load forecasting based on SVM for electric bus charging station[J].Electric Power Automation Equipment,2014,34(11):41-48.
[14]TASCIKARAOGLU A,UZUNOGLU M.A review of combined approaches for prediction of short-term wind speed and power[J].Renewable and Sustainable Energy Reviews,2014,34:243-254.
[15]ZHANG W Y,HONG W C,DONG Y C,et al.Application of SVR with chaotic GASA algorithm in cyclic electric load forecasting[J].Energy,2012,45(1):850-858.
[16]周湶,孙威,任海军,等.基于最小二乘支持向量机和负荷密度指标法的配电网空间负荷预测[J].电网技术,2011,35(1):66-70.ZHOU Quan,SUN Wei,REN Haijun,et al.Spatial load forecasting of distribution network based on least squares support vector machine and load density index system[J].Power System Technology,2011,35(1):66-70.
[17]肖白,聂鹏,穆钢,等.基于多级聚类分析和支持向量机的空间负荷预测方法[J].电力系统自动化,2015,39(12):56-61.DOI:10.7500/AEPS20140520001.XIAO Bai,NIE Peng,MU Gang,et al.A spatial load forecasting method based on multilevel clustering analysis and support vector machine[J].Automation of Electric Power Systems,2015,39(12):56-61.DOI:10.7500/AEPS20140520001.
[18]VAPNIK V,GOLOWICH S,SMOLA A.Support vector machine for function approximation,regression estimation and signal processing[C]//Advances in Neural Information Processing Systems,December 2-5,1996,Denver,USA:281-287.
[19]HINOJOSA V H,HOESE A.Short-term load forecasting using fuzzy inductive reasoning and evolutionary algorithms[J].IEEE Trans on Power Systems,2010,25(1):565-574.
[20]BATES J,GRANGER C.The combination of forecast[J].Operations Research Quarterly,1969,20(4):451-468.
[21]陈华友.组合预测方法有效性理论及其应用[M].北京:科学出版社,2008:40-98,113-125,224-237.
[22]FAN S,CHEN L,LEE W J.Short-term load forecasting using comprehensive combination based on multimeteorological information[J].IEEE Trans on Industry Applications,2009,45(4):1460-1466.
[23]VELSQUEZ J D,ZAMBRANO C,FRANCO C J.Forecast combining using ageneralized single multiplicative neuron[J].IEEE Latin America Transactions,2014,12(4):713-717.
[24]苏小红.基于人工神经网络的燃气短期负荷预测研究[D].重庆:重庆大学,2005.
[25]尹星露,肖先勇,孙晓璐.基于预测有效度和马尔科夫-云模型的母线负荷预测模型筛选与变权重组合预测[J].电力自动化设备,2015,35(7):114-120.YIN Xinglu,XIAO Xianyong,SUN Xiaolu.Bus load forecasting model selection and variable weights combination forecasting based on forecasting effectiveness and Markov chain-cloud model[J].Electric Power Automation Equipment,2015,35(7):114-120.
[26]高尚,梅亮.基于支持向量机的电价组合预测模型[J].电力自动化设备,2008,28(11):50-55.GAO Shang,MEI Liang.Combined forecasting model of electricity price based on support vector machine[J].Electric Power Automation Equipment,2008,28(11):50-55.
[27]赵文清,朱永利,张小奇.应用支持向量机的变压器故障组合预测[J].中国电机工程学报,2008,28(9):14-21.ZHAO Wenqing,ZHU Yongli,ZHANG Xiaoqi.Combinational forecast for transformer faults based on support vector machine[J].Proceedings of the CSEE,2008,28(9):14-21.
[28]栗然,刘会兰,卢云,等.基于交叉熵理论的配电变压器寿命组合预测方法[J].电力系统保护与控制,2014,42(2):97-101.LI Ran,LIU Huilan,LU Yun,et al.A combination method for distribution transformer life prediction based on cross entropy theory[J].Power System Protection and Control,2014,42(2):97-101.
[29]陈宁,沙倩,汤奕,等.基于交叉熵理论的风电功率组合预测方法[J].中国电机工程学报,2012,32(4):29-34.CHEN Ning,SHA Qian,TANG Yi,et al.A combination method for wind power predication based on cross entropy theory[J].Proceedings of the CSEE,2012,32(4):29-34.
[30]孙广强,姚建刚,谢宇翔,等.基于新鲜度函数和预测有效度的模糊自适应变权重中长期电力负荷组合预测[J].电网技术,2009,33(9):103-108.SUN Guangqiang,YAO Jiangang,XIE Yuxiang,et al.Combination forecast of medium-and long-term load using fuzzy adaptive variable weight based on fresh degree function and forecasting availability[J].Power System Technology,2009,33(9):103-108.