基于决策树自标识的主动配电网状态估计算法
|
摘要
为解决目前配电网前端数据数量大、缺省多、分析复杂等问题,本文提出一种适用于主动配电网的状态估计算法来管理分析前端数据。采用了基于决策树自标识的主动配电网状态估计算法,通过估计前预处理数据,对数据进行分类以及修正,使输入状态估计模型中的数据有更好的相容性。同时,本文针对分布式能源配套量测装置少的问题,建立了考虑分布式电源的状态估计模型,对分布式能源缺省数据进行补全修正,提高输入数据的质量。该方法运用到实际算例中可以看出,对比传统的状态估计,基于决策树自标识的主动配电网状态估计算法有更好的估计效果以及更快的迭代速度。因此本文提出的算法能有效的运用到当前大规模分布式能源接入的配电网状态估计中。
In order to solve the problems of large number of front-end data,many defaults and complex analysis in distribution network,a state estimation algorithm suitable for active distribution network is proposed to manage and analyze front-end data. An active distribution network state estimation algorithm based on self-identification of decision tree is adopted. By pre-processing data before estimation,data are classified and corrected to make the data in the input state estimation model more compatible. At the same time,aiming at the problem of fewer measurement devices for distributed energy,a state estimation model considering distributed generation is established to correct the default data of distributed energy and improve the quality of input data. Compared with the traditional state estimation,the method based on self-identification of decision tree has better estimation effect and faster iteration speed. Therefore,the proposed algorithm can be effectively applied to the current large-scale distributed energy access distribution network state estimation.
In order to solve the problems of large number of front-end data,many defaults and complex analysis in distribution network,a state estimation algorithm suitable for active distribution network is proposed to manage and analyze front-end data. An active distribution network state estimation algorithm based on self-identification of decision tree is adopted. By pre-processing data before estimation,data are classified and corrected to make the data in the input state estimation model more compatible. At the same time,aiming at the problem of fewer measurement devices for distributed energy,a state estimation model considering distributed generation is established to correct the default data of distributed energy and improve the quality of input data. Compared with the traditional state estimation,the method based on self-identification of decision tree has better estimation effect and faster iteration speed. Therefore,the proposed algorithm can be effectively applied to the current large-scale distributed energy access distribution network state estimation.
引文
[1]赵波,王财胜,周金辉,等.主动配电网现状与未来发展[J].电力系统自动化,2014,38(18):125-135.ZHAO Bo,WANG Caisheng,ZHOU Jinhui,et al.Present and future development trend of active distribution network[J].Automation of Electric Power Systems,2014,38(18):125-135.
[2]马钊,梁惠施,苏剑.主动配电系统规划和运行中的重要问题[J].电网技术,2015,39(06):1499-1503.MA Zhao,LIANG Huishi,SU Jian.Important issues in planning and operation of active distribution system[J].Power System Technology,2015,39(06):1499-1503.
[3]LIU Y,NING P,REITER M K.False data injection attacks against state estimation in electric power grids[J].ACM Transactions on Information and System Security,2011,14(01):1-12.
[4]SODHI R,SRIVASTAVA S C,SINGH S N.Optimal PMU placement method for complete topological and numerical observability of power system[J].Electric Power Systems Research,2010,80(09):1154-1159.
[5]GOMEZ EXPOSITO A,ABUR A,et al.A multilevel state estimation paradigm for smart grids[J].Proceedings of the IEEE,2011,99(06):952-976.
[6]CHEN P,PEDERSEN T,BAK-JENSEN B,et al.ARIMA based time series model of stochastic wind power generation[J].IEEETransactions on Power Systems,2010,25(02):667-676.
[7]GHAHREMANI E,KAMWA I.Dynamic state estimation in power system by applying the extended Kalman filter with unknown inputs to phasor measurements[J].IEEE Transactions on Power Systems,2011,26(04):2556-2566.
[8]赵洪山,田甜.基于自适应无迹卡尔曼滤波的电力系统动态状态估计[J].电网技术,2014,38(01):188-192.ZHAO Hongshan,TIAN Tian.Dynamic state estimation for power system based on an adaptive unscented Kalman filter[J].Power System Tecnology,2014,38(01):188-192.
[9]孙国强,黄蔓云,卫志农,等.基于无迹变换强跟踪滤波的发电机动态状态估计[J].中国电机工程学报,2016,36(03):615-623.SUN Guoqiang,HUANG Manyun,WEI Zhinong,et al.Dynamic state estimation for synchronous machines based on unscented transformation of strong tracking filter[J].Proceedings of the CSEE,2016,36(03):615-623.
[10]厉超,卫志农,倪明,等.基于变量代换内点法的加权最小绝对值抗差状态估计[J].电力系统自动化,2015,39(06):48-52.LI Chao,WEI Zhinong,NI Ming,et al.WLAV robust stateestimation based on variable substitution interior point method[J].Automation of Electric Power Systems,2015,39(06):48-52.
[11]姚诸香,郭烨,郭玉金,等.含指数型目标函数的电力系统抗差状态估计方法在江西电网中的应用[J].中国电机工程学报,2012,36(04):155-159.YAO Zhuxiang,GUO Ye,GUO Jinyu,et al.Application of a robust state estimator based on maximum exponential square in Jiangxi power system[J].Proceedings of the CSEE,2012,36(04):155-159.
[12]YANG WENG,ROHIT NEGI,MARIJA D.ILI'C.Probabilistic joint state estimation for operational planning[J].IEEE Transactions on Smart Grid,2019,10(01):601-612.
[13]WANG S,GAO W,MELIOPOULOS A P S.An alternative method for power system dynamic state estimation based on unscented transform[J].IEEE Transactions on Power Systems,2012,27(02):942-950.
[14]KORRES G N.Observability analysis based on echelon form of a reduced dimensional Jacobian matrix[J].IEEE Transactions on Power Systems,2011,26(04):2572-2573.
[15]李滨,杜孟远,祝云,等.基于准实时数据的智能配电网状态估计[J].电工技术学报,2016,31(01):34-44.LI Bin,DU Mengyuan,ZHU Yun,et al.A state estimator for smart distribution networks with quasi-real time data[J].Transactions of China Electro technical Society,2016,31(01):34-44.
[16]李梦宇,张泽亚,张知,等.基于CART算法的电能表故障概率决策树分析[J].电力大数据,2017,20(10):7-10+60.LI Mengyu,ZHANG Zeya,ZHANG Ming,et al.Analysis of decision tree for power meter fault probability based on CART algorithm[J].Power Systems and Big Data,2017,20(10):7-10+60.
[17]印然.基于IGG抗差最小二乘法的三相配电网谐波状态估计[J].电力大数据,2018,21(04):69-72.YIN Ran.Harmonic state estimation of three-phase distribution network based on IGG differential least square method[J].Power Systems and Big Data,2018,21(04):69-72.
[18]蒋煜,丁晓群,郑程拓,等.管志成含电动汽车的主动配电网分布式电源规划[J].广东电力,2017,30(7):1-6.JIANG Yu,DING Xiaoqun,ZHENG Chengtuo,et al.Distributed generation planning for active distribution network with electric vehicle[J].Guangdong Electric Power,2017,30(07):1-6.
[19]刘学军,俞伟,何颋,等.基于大数据的配电网运行状态评估与预警[J]浙江电力.2017,36(12):75-80.LIU Xuejun,YU Wei,HE Ting,et al.Operation state evaluation and early warning of distribution network based on big data[J].Zhejiang Electric Power,2017,36(12):75-80.
[2]马钊,梁惠施,苏剑.主动配电系统规划和运行中的重要问题[J].电网技术,2015,39(06):1499-1503.MA Zhao,LIANG Huishi,SU Jian.Important issues in planning and operation of active distribution system[J].Power System Technology,2015,39(06):1499-1503.
[3]LIU Y,NING P,REITER M K.False data injection attacks against state estimation in electric power grids[J].ACM Transactions on Information and System Security,2011,14(01):1-12.
[4]SODHI R,SRIVASTAVA S C,SINGH S N.Optimal PMU placement method for complete topological and numerical observability of power system[J].Electric Power Systems Research,2010,80(09):1154-1159.
[5]GOMEZ EXPOSITO A,ABUR A,et al.A multilevel state estimation paradigm for smart grids[J].Proceedings of the IEEE,2011,99(06):952-976.
[6]CHEN P,PEDERSEN T,BAK-JENSEN B,et al.ARIMA based time series model of stochastic wind power generation[J].IEEETransactions on Power Systems,2010,25(02):667-676.
[7]GHAHREMANI E,KAMWA I.Dynamic state estimation in power system by applying the extended Kalman filter with unknown inputs to phasor measurements[J].IEEE Transactions on Power Systems,2011,26(04):2556-2566.
[8]赵洪山,田甜.基于自适应无迹卡尔曼滤波的电力系统动态状态估计[J].电网技术,2014,38(01):188-192.ZHAO Hongshan,TIAN Tian.Dynamic state estimation for power system based on an adaptive unscented Kalman filter[J].Power System Tecnology,2014,38(01):188-192.
[9]孙国强,黄蔓云,卫志农,等.基于无迹变换强跟踪滤波的发电机动态状态估计[J].中国电机工程学报,2016,36(03):615-623.SUN Guoqiang,HUANG Manyun,WEI Zhinong,et al.Dynamic state estimation for synchronous machines based on unscented transformation of strong tracking filter[J].Proceedings of the CSEE,2016,36(03):615-623.
[10]厉超,卫志农,倪明,等.基于变量代换内点法的加权最小绝对值抗差状态估计[J].电力系统自动化,2015,39(06):48-52.LI Chao,WEI Zhinong,NI Ming,et al.WLAV robust stateestimation based on variable substitution interior point method[J].Automation of Electric Power Systems,2015,39(06):48-52.
[11]姚诸香,郭烨,郭玉金,等.含指数型目标函数的电力系统抗差状态估计方法在江西电网中的应用[J].中国电机工程学报,2012,36(04):155-159.YAO Zhuxiang,GUO Ye,GUO Jinyu,et al.Application of a robust state estimator based on maximum exponential square in Jiangxi power system[J].Proceedings of the CSEE,2012,36(04):155-159.
[12]YANG WENG,ROHIT NEGI,MARIJA D.ILI'C.Probabilistic joint state estimation for operational planning[J].IEEE Transactions on Smart Grid,2019,10(01):601-612.
[13]WANG S,GAO W,MELIOPOULOS A P S.An alternative method for power system dynamic state estimation based on unscented transform[J].IEEE Transactions on Power Systems,2012,27(02):942-950.
[14]KORRES G N.Observability analysis based on echelon form of a reduced dimensional Jacobian matrix[J].IEEE Transactions on Power Systems,2011,26(04):2572-2573.
[15]李滨,杜孟远,祝云,等.基于准实时数据的智能配电网状态估计[J].电工技术学报,2016,31(01):34-44.LI Bin,DU Mengyuan,ZHU Yun,et al.A state estimator for smart distribution networks with quasi-real time data[J].Transactions of China Electro technical Society,2016,31(01):34-44.
[16]李梦宇,张泽亚,张知,等.基于CART算法的电能表故障概率决策树分析[J].电力大数据,2017,20(10):7-10+60.LI Mengyu,ZHANG Zeya,ZHANG Ming,et al.Analysis of decision tree for power meter fault probability based on CART algorithm[J].Power Systems and Big Data,2017,20(10):7-10+60.
[17]印然.基于IGG抗差最小二乘法的三相配电网谐波状态估计[J].电力大数据,2018,21(04):69-72.YIN Ran.Harmonic state estimation of three-phase distribution network based on IGG differential least square method[J].Power Systems and Big Data,2018,21(04):69-72.
[18]蒋煜,丁晓群,郑程拓,等.管志成含电动汽车的主动配电网分布式电源规划[J].广东电力,2017,30(7):1-6.JIANG Yu,DING Xiaoqun,ZHENG Chengtuo,et al.Distributed generation planning for active distribution network with electric vehicle[J].Guangdong Electric Power,2017,30(07):1-6.
[19]刘学军,俞伟,何颋,等.基于大数据的配电网运行状态评估与预警[J]浙江电力.2017,36(12):75-80.LIU Xuejun,YU Wei,HE Ting,et al.Operation state evaluation and early warning of distribution network based on big data[J].Zhejiang Electric Power,2017,36(12):75-80.