考虑光伏发电出力不确定性的年度最大负荷概率预测
|
摘要
为了在年度最大负荷预测中计及光伏、气象等因素的不确定性,提出了一种基于概率理论的年度最大负荷概率预测方法。首先,针对各影响因素的不同影响方式,利用传统预测法结合贝叶斯网络(Bayesian network,BN)加以气象修正预测,得到全社会最大负荷的概率分布;其次,利用BN理论基于历史数据建立光伏发电出力概率预测模型,提出了扩容后光伏发电出力概率预测的方法,利用联合概率分布理论实现了光伏发电出力的概率预测。最后,利用概率理论将全社会最大负荷"减"去光伏发电总出力得到年度最大负荷的概率分布预测结果。通过某地市一个配电公司的案例研究证明了这种方法的可行性。
This paper presents a probabilistic forecasting method for the annual peak load taking into account uncertainties of photovoltaic,weather and other factors.First,this paper combines the traditional prediction method with Bayesian network(BN)as well as meteorologic correction to obtain probability distribution of the maximum load of the whole society.Second,this paper applies BN theory to establish the probabilistic forecasting model for photovoltaic generation output using historical data.The joint probability distribution theory is then applied to develop probability prediction functions on expanded photovoltaic generation.Finally,the probability distribution of the annual peak load of the whole society minus the probabilistic distribution of total photovoltaic generation output to obtain the annual peak load provided by power grid.Case study on a local distribution company has proved feasibility of this approach.
This paper presents a probabilistic forecasting method for the annual peak load taking into account uncertainties of photovoltaic,weather and other factors.First,this paper combines the traditional prediction method with Bayesian network(BN)as well as meteorologic correction to obtain probability distribution of the maximum load of the whole society.Second,this paper applies BN theory to establish the probabilistic forecasting model for photovoltaic generation output using historical data.The joint probability distribution theory is then applied to develop probability prediction functions on expanded photovoltaic generation.Finally,the probability distribution of the annual peak load of the whole society minus the probabilistic distribution of total photovoltaic generation output to obtain the annual peak load provided by power grid.Case study on a local distribution company has proved feasibility of this approach.
引文
[1]郭林,江登笠,刘宇,等.基于自适应权重缓冲灰色理论的中长期负荷预测方法研究[J].陕西电力,2016,44(7):33-37.GUO Lin,JIANG Dengli,LIU Yu,et al.Medium and longterm load forecasting based on adaptive weight buffer gray theory[J].Shaanxi Electric Power,2016,44(7):33-37.
[2]王守相,韩亮.DG出力不确定性对配电网影响力分析的复仿射数学方法[J].中国电机工程学报,2014,34(31):5507-5515.WANG Shouxiang,HAN Liang.Complex affine arithmetic based method for the analyses of DG’s uncertainty influence on distribution network[J].Proceedings of the CSEE,2014,34(31):5507-5515.
[3]唐平舟,陈镝.结合熵值法和极端学习机的短期光伏发电量预测[J].广东电力,2015,28(10):15-19.TANG Pingzhou,CHEN Di.Prediction on short-term photovoltaic generating capacity based on entropy method combining with extreme learning machine[J].Guangdong Electric Power,2015,28(10):15-19.
[4]肖建华,刘滨涛,姜彬.区域电网年最大负荷概率预测[J].吉林电力,2008(6):13-16.XIAO Jianhua,LIU Bintao,JIANG Bin.Research on annual maximum load probability of regional power grid[J].Jilin Electric Power,2008(6):13-16.
[5]李辉.改进残差GM(1,1)模型在中长期负荷预测中的应用[J].广东电力,2017,30(9):81-85.LI Hui.Application of improved residual error GM(1,1)model in medium and long term load forecasting[J].Guangdong Electric Power,2017,30(9):81-85.
[6]卫志农,滕俊,王丹,等.电力系统年最大负荷概率预测[J].电力系统及其自动化学报,2004(6):64-67.WEI Zhinong,,TENG Jun,WANG Dan,et al.Power system annual maximum load probability prediction[J].Journal of Power System and Automation,2004(6):64-67.
[7]吴丹,程浩忠,奚珣,等.基于模糊层次分析法的年最大电力负荷预测[J].电力系统及其自动化学报,2007(1):55-58,67.WU Dan,CHENG Haozhong,XI Xun,et al.An annual maximum power load forecasting based on fuzzy analytic hierarchy process[J].Journal of Electric Power Systems and Automation,2007(1):55-58,67.
[8]葛斐,荣秀婷,石雪梅,等.基于经济、气象因素的安徽省年最大负荷预测方法研究[J].中国电力,2015(3):84-87.GE Fei,RONG Xiuting,SHI Xuemei,et al.Research on the annual maximum load forecasting method based on economic meteorological factors in Anhui province[J].Electric Power,2015(3):84-87.
[9]张柏林,拜润卿,智勇,等.基于空间相关性的分布式光伏超短期预测技术研究[J].陕西电力,2017,45(5):22-26.ZHANG Bolin,BAI Runqing,ZHI Yong,et al.Distributed PV ultra-short term power forecast technology based on spetial correlation[J].Shaanxi Electric Power,2017,45(5):22-26.
[10]贾逸伦,龚庆武,雷杨,等.基于灰色关联与量子粒子群寻优的光伏短期预测[J].电网与清洁能源,2016,32(2):109-115.JIA Yilun,GONG Qingwu,LEI Yang,et al.Photovoltaic power short-term prediction based on grey related analysis and QPSO-SVM[J].Power System and Clean Energy,2016,32(2):109-115.
[11]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,2017,448-454.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,2017,448-454.
[12]杨慧霞,邓迎君,刘志斌,等.含有历史不良数据的电力负荷预测研究[J].电力系统保护与控制,2017(15):62-68.YANG Huixia,DENG Yingjun,LIU Zhibin,et al.Study on electric load forecasting with historical bad data[J].Power System Protection and Control,2017(15):62-68.
[13]赵唯嘉,张宁,康重庆,等.光伏发电出力的条件预测误差概率分布估计方法[J].电力系统自动化,2015,39(16):8-14.ZHAO Weijia,ZHANG Ning,KANG Chongqing,et al.A method of probabilistic distribution estimation of conditional forecast error for photovoltaic power generation[J].Automation of Electric Power Systems,2015,39(16):8-14.
[14]牛东晓,刘卫东,黄雅莉,等.基于贝叶斯推理的ANFIS电网发展水平评估[J].电网与清洁能源,2017,33(3):8-16.NIU Dongxiao,LIU Weidong,HUANG Yali,et al.Evaluation of power network developmental level based on ANFIS improved by Bayesian inference[J].Power System and Clean Energy,2017,33(3):8-16.
[15]边莉,边晨源.电网故障诊断的智能方法综述[J].电力系统保护与控制,2014(3):146-153.BIAN Li,BIAN Chenyuan.Review on intelligence fault diagnosis in power networks[J].Power System Protection and Control,2014(3):146-153.
[16]YONA A,SENJYU T,FUNABASHI T.Application of recur-rent neural network to short-term-ahead generating power fore-casting for photovoltaic system[C]//IEEE Power Engineering SocietyGeneralMeeting. Piscataway:IEEE Press,2007.
[2]王守相,韩亮.DG出力不确定性对配电网影响力分析的复仿射数学方法[J].中国电机工程学报,2014,34(31):5507-5515.WANG Shouxiang,HAN Liang.Complex affine arithmetic based method for the analyses of DG’s uncertainty influence on distribution network[J].Proceedings of the CSEE,2014,34(31):5507-5515.
[3]唐平舟,陈镝.结合熵值法和极端学习机的短期光伏发电量预测[J].广东电力,2015,28(10):15-19.TANG Pingzhou,CHEN Di.Prediction on short-term photovoltaic generating capacity based on entropy method combining with extreme learning machine[J].Guangdong Electric Power,2015,28(10):15-19.
[4]肖建华,刘滨涛,姜彬.区域电网年最大负荷概率预测[J].吉林电力,2008(6):13-16.XIAO Jianhua,LIU Bintao,JIANG Bin.Research on annual maximum load probability of regional power grid[J].Jilin Electric Power,2008(6):13-16.
[5]李辉.改进残差GM(1,1)模型在中长期负荷预测中的应用[J].广东电力,2017,30(9):81-85.LI Hui.Application of improved residual error GM(1,1)model in medium and long term load forecasting[J].Guangdong Electric Power,2017,30(9):81-85.
[6]卫志农,滕俊,王丹,等.电力系统年最大负荷概率预测[J].电力系统及其自动化学报,2004(6):64-67.WEI Zhinong,,TENG Jun,WANG Dan,et al.Power system annual maximum load probability prediction[J].Journal of Power System and Automation,2004(6):64-67.
[7]吴丹,程浩忠,奚珣,等.基于模糊层次分析法的年最大电力负荷预测[J].电力系统及其自动化学报,2007(1):55-58,67.WU Dan,CHENG Haozhong,XI Xun,et al.An annual maximum power load forecasting based on fuzzy analytic hierarchy process[J].Journal of Electric Power Systems and Automation,2007(1):55-58,67.
[8]葛斐,荣秀婷,石雪梅,等.基于经济、气象因素的安徽省年最大负荷预测方法研究[J].中国电力,2015(3):84-87.GE Fei,RONG Xiuting,SHI Xuemei,et al.Research on the annual maximum load forecasting method based on economic meteorological factors in Anhui province[J].Electric Power,2015(3):84-87.
[9]张柏林,拜润卿,智勇,等.基于空间相关性的分布式光伏超短期预测技术研究[J].陕西电力,2017,45(5):22-26.ZHANG Bolin,BAI Runqing,ZHI Yong,et al.Distributed PV ultra-short term power forecast technology based on spetial correlation[J].Shaanxi Electric Power,2017,45(5):22-26.
[10]贾逸伦,龚庆武,雷杨,等.基于灰色关联与量子粒子群寻优的光伏短期预测[J].电网与清洁能源,2016,32(2):109-115.JIA Yilun,GONG Qingwu,LEI Yang,et al.Photovoltaic power short-term prediction based on grey related analysis and QPSO-SVM[J].Power System and Clean Energy,2016,32(2):109-115.
[11]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,2017,448-454.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,2017,448-454.
[12]杨慧霞,邓迎君,刘志斌,等.含有历史不良数据的电力负荷预测研究[J].电力系统保护与控制,2017(15):62-68.YANG Huixia,DENG Yingjun,LIU Zhibin,et al.Study on electric load forecasting with historical bad data[J].Power System Protection and Control,2017(15):62-68.
[13]赵唯嘉,张宁,康重庆,等.光伏发电出力的条件预测误差概率分布估计方法[J].电力系统自动化,2015,39(16):8-14.ZHAO Weijia,ZHANG Ning,KANG Chongqing,et al.A method of probabilistic distribution estimation of conditional forecast error for photovoltaic power generation[J].Automation of Electric Power Systems,2015,39(16):8-14.
[14]牛东晓,刘卫东,黄雅莉,等.基于贝叶斯推理的ANFIS电网发展水平评估[J].电网与清洁能源,2017,33(3):8-16.NIU Dongxiao,LIU Weidong,HUANG Yali,et al.Evaluation of power network developmental level based on ANFIS improved by Bayesian inference[J].Power System and Clean Energy,2017,33(3):8-16.
[15]边莉,边晨源.电网故障诊断的智能方法综述[J].电力系统保护与控制,2014(3):146-153.BIAN Li,BIAN Chenyuan.Review on intelligence fault diagnosis in power networks[J].Power System Protection and Control,2014(3):146-153.
[16]YONA A,SENJYU T,FUNABASHI T.Application of recur-rent neural network to short-term-ahead generating power fore-casting for photovoltaic system[C]//IEEE Power Engineering SocietyGeneralMeeting. Piscataway:IEEE Press,2007.