基于GRA-LSSVM的配电网空间负荷预测方法研究
|
摘要
针对配电网空间负荷预测实际应用中容易存在可用信息和数据散杂且经常匮乏的问题,提出了一种基于最小二乘支持向量机的新型配电网空间负荷密度预测算法,以解决预测方法中样本有限、不易识别等问题。同时引入灰色关联分析改善最小二乘支持向量机的样本筛选,并采用混沌粒子群算法完善最小二乘支持向量机的参数选择,提高算法的空间负荷密度预测的精度。在介绍算法原理基础上,详细设计了配电网空间负荷预测方法的实现流程。对该算法的性能进行实例分析表明,所提方法可以有效地提高负荷密度预测的精度。
In the practical application of spatial load forecasting of distribution network, the available information and data are often scattered and poor. In this paper, a novel spatial load density prediction algorithm based on the Least Squares Support Vector Machine(LSSVM) is proposed to solve the problems of limited samples and difficulty in identification. In this algorithm, Grey Relational Analysis(GRA) is introduced to improve the sample selection of the Least Squares Support Vector Machine(LSSVM), and Chaos Particle Swarm Optimization(CPSO) algorithm is adopted to consummate the parameter selection of the least squares support vector machine, which improves the accuracy of spatial load density prediction of the algorithm. Based on the principle of algorithm, this paper designs a detailed implementation process for the spatial load prediction method of distribution network. The performance of this algorithm is analyzed with an example. The example calculation shows that the proposed method can effectively improve the precision of load density prediction.
In the practical application of spatial load forecasting of distribution network, the available information and data are often scattered and poor. In this paper, a novel spatial load density prediction algorithm based on the Least Squares Support Vector Machine(LSSVM) is proposed to solve the problems of limited samples and difficulty in identification. In this algorithm, Grey Relational Analysis(GRA) is introduced to improve the sample selection of the Least Squares Support Vector Machine(LSSVM), and Chaos Particle Swarm Optimization(CPSO) algorithm is adopted to consummate the parameter selection of the least squares support vector machine, which improves the accuracy of spatial load density prediction of the algorithm. Based on the principle of algorithm, this paper designs a detailed implementation process for the spatial load prediction method of distribution network. The performance of this algorithm is analyzed with an example. The example calculation shows that the proposed method can effectively improve the precision of load density prediction.
引文
[1]肖峻,崔艳妍,王建民,等.配电网规划的综合评价指标体系与方法[J].电力系统自动化,2008,32(15):36-40.XIAOJun,CUIYanyan,WANGJianmin,etal.Comprehensiveevaluationindexsystemandmethodof distribution network planning[J]. Automation of Electric Power Systems, 2008, 32(15):36-40.
[2]解大琴.基于多目标的配电网规划研究[D].南京:河海大学, 2007.XIEDaqin.Studyonmulti-objectivedistributionnetwork planning[D]. Nanjing:Hohai University, 2007.
[3]杨慢慢,王金凤,李燕青.改进的空间负荷预测法及其应用[J].电力科学与工程, 2011, 27(11):35-38.YANGManman,WANGJinfeng,LIYanqing.The improved spatial load forecasting and it's application[J].ElectricPowerScienceandEngineering,2011,27(11):35-38.
[4]肖白,周潮,穆钢.空间电力负荷预测方法综述与展望[J].中国电机工程学报, 2013, 33(25):78-92.XIAOBai,ZHOUChao,MUGang.Reviewand prospectofthespatialloadforecastingmethods[J].Proceedings of the CSEE, 2013, 33(25):78-92.
[5]WILLIS H L. Spatial electric load forecasting[M]. New York:Marcel Dekker, 2002.
[6]余贻鑫,张崇见,张鸿鹏.空间电力负荷预测元胞用地分析(一):模糊推理新方法和元胞用地分析原理[J].电力系统自动化, 2001, 25(6):23-26.YUYixin,ZHANGChongjian,ZHANGHongpeng.Spatial electric load forecasting district land branch(I)[J].AutomationofElectricPowerSystems,2001,25(6):23-26.
[7]程其云,张晓星,周湶,等.基于粗糙集数据挖掘的配电网小区空间负荷预测方法研究[J].电工技术学报,2005, 20(5):98-102.CHENG Qiyun, ZHANG Xiaoxing, ZHOU Quan, et al.Spatial load forecasting method for distribution net based onroughsetdataminingapproach[J].Transactionsof China Electrotechnical Society, 2005, 20(5):98-102.
[8]熊浩,李卫国,黄彦浩,等.基于模糊粗糙集理论的综合数据挖掘方法在空间负荷预测中的应用[J].电网技术, 2007, 31(14):36-40.XIONGHao,LIWeiguo,HUANGYanhao,etal.Application of comprehensive data mining method based on fuzzy rough spatial load forecasting[J]. Power System Technology, 2007, 31(14):36-40.
[9]刘自发,庞诚诚,魏建炜,等.基于IAHP和TOPSIS方法的负荷密度指标计算[J].电力系统自动化,2012,36(13):56-59.LIU Zifa, PANG Chengcheng, WEI Jianwei, et al. Index calculation of load density based on IAHP and TOPSIS methods[J]. Automation of Electric Power Systems, 2012,36(13):56-59.
[10]刘宝英,杨仁刚.基于主成分分析的最小二乘支持向量机短期负荷预测模型[J].电力自动化设备,2008,28(11):13-16.LIU Baoying, YANG Rengang. Short term load forecasting modelbasedonLSSVMwithPCA[J].ElectricPower Automation Equipment, 2008, 28(11):13-16.
[11]罗毅,李星龙.基于熵权法和灰色关联分析法的输电网规划方案综合决策[J].电网技术, 2013, 37(1):77-81.LUO Yi, LI Yulong. Comprehensive decision-making of transmission network planning based on entropy weight and grey relational analysis[J]. Power System Technology,2013, 37(1):77-81.
[12]李金超,牛东晓,李金颖,等.基于负荷细分与SVM技术的电力负荷空间分布预测[J].电工电能新技术,2008, 27(1):40-43.LI Jinchao, NIU Dongxiao, LI Jinying, et al. Forecasting based on load decomposition and support vector machine[J].Advanced Technology of Electrical Engineering and Energy,2008, 27(1):40-43.
[13]张宪,苑津莎,杨薛明.基于混沌粒子群算法的配电网规划[J].华北电力大学学报, 2006, 33(3):14-18.ZHANGXian,YUANJinsha,YANGXueming.Distributionnetworkplanningbasedonparticleswarm optimization[J].JournalofNorthChinaElectricPower University, 2006, 33(3):14-18.
[14]苗增强,姚建刚,李婷,等.改进的多目标遗传算法在配电网规划中的应用[J].电力系统及其自动化学报,2009, 21(5):63-67.MIAOZengqiang,YAOJiangang,LITing,etal.Applicationofimprovedmulti-objectivegeneticalgorithm indistributionnetworkplanning[J].Proceedingsofthe CSU-EPSA, 2009, 21(5):63-67.
[15]钟庆,吴捷,伍力,等.基于系统动力学的分区负荷预测[J].电网技术, 2001, 25(3):51-55.ZHONGQing,WUJie,WULi,etal.Subareaload forecasting based on system dynamics[J]. Power System Technology, 2001, 25(3):51-55.
[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):66-71.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):66-71.
[17]肖白,李科,田春筝,等.空间负荷预测中确定元胞负荷合理最大值的主成分分析法[J].电测与仪表,2017,54(14):112-116.XIAOBai,LIKe,TIANChunzheng,etal.APCA method for ascertaining maximal value of cellular load in spatialloadforecasting[J].ElectricalMeasurement&Instrumentation, 2017, 54(14):112-116.
[2]解大琴.基于多目标的配电网规划研究[D].南京:河海大学, 2007.XIEDaqin.Studyonmulti-objectivedistributionnetwork planning[D]. Nanjing:Hohai University, 2007.
[3]杨慢慢,王金凤,李燕青.改进的空间负荷预测法及其应用[J].电力科学与工程, 2011, 27(11):35-38.YANGManman,WANGJinfeng,LIYanqing.The improved spatial load forecasting and it's application[J].ElectricPowerScienceandEngineering,2011,27(11):35-38.
[4]肖白,周潮,穆钢.空间电力负荷预测方法综述与展望[J].中国电机工程学报, 2013, 33(25):78-92.XIAOBai,ZHOUChao,MUGang.Reviewand prospectofthespatialloadforecastingmethods[J].Proceedings of the CSEE, 2013, 33(25):78-92.
[5]WILLIS H L. Spatial electric load forecasting[M]. New York:Marcel Dekker, 2002.
[6]余贻鑫,张崇见,张鸿鹏.空间电力负荷预测元胞用地分析(一):模糊推理新方法和元胞用地分析原理[J].电力系统自动化, 2001, 25(6):23-26.YUYixin,ZHANGChongjian,ZHANGHongpeng.Spatial electric load forecasting district land branch(I)[J].AutomationofElectricPowerSystems,2001,25(6):23-26.
[7]程其云,张晓星,周湶,等.基于粗糙集数据挖掘的配电网小区空间负荷预测方法研究[J].电工技术学报,2005, 20(5):98-102.CHENG Qiyun, ZHANG Xiaoxing, ZHOU Quan, et al.Spatial load forecasting method for distribution net based onroughsetdataminingapproach[J].Transactionsof China Electrotechnical Society, 2005, 20(5):98-102.
[8]熊浩,李卫国,黄彦浩,等.基于模糊粗糙集理论的综合数据挖掘方法在空间负荷预测中的应用[J].电网技术, 2007, 31(14):36-40.XIONGHao,LIWeiguo,HUANGYanhao,etal.Application of comprehensive data mining method based on fuzzy rough spatial load forecasting[J]. Power System Technology, 2007, 31(14):36-40.
[9]刘自发,庞诚诚,魏建炜,等.基于IAHP和TOPSIS方法的负荷密度指标计算[J].电力系统自动化,2012,36(13):56-59.LIU Zifa, PANG Chengcheng, WEI Jianwei, et al. Index calculation of load density based on IAHP and TOPSIS methods[J]. Automation of Electric Power Systems, 2012,36(13):56-59.
[10]刘宝英,杨仁刚.基于主成分分析的最小二乘支持向量机短期负荷预测模型[J].电力自动化设备,2008,28(11):13-16.LIU Baoying, YANG Rengang. Short term load forecasting modelbasedonLSSVMwithPCA[J].ElectricPower Automation Equipment, 2008, 28(11):13-16.
[11]罗毅,李星龙.基于熵权法和灰色关联分析法的输电网规划方案综合决策[J].电网技术, 2013, 37(1):77-81.LUO Yi, LI Yulong. Comprehensive decision-making of transmission network planning based on entropy weight and grey relational analysis[J]. Power System Technology,2013, 37(1):77-81.
[12]李金超,牛东晓,李金颖,等.基于负荷细分与SVM技术的电力负荷空间分布预测[J].电工电能新技术,2008, 27(1):40-43.LI Jinchao, NIU Dongxiao, LI Jinying, et al. Forecasting based on load decomposition and support vector machine[J].Advanced Technology of Electrical Engineering and Energy,2008, 27(1):40-43.
[13]张宪,苑津莎,杨薛明.基于混沌粒子群算法的配电网规划[J].华北电力大学学报, 2006, 33(3):14-18.ZHANGXian,YUANJinsha,YANGXueming.Distributionnetworkplanningbasedonparticleswarm optimization[J].JournalofNorthChinaElectricPower University, 2006, 33(3):14-18.
[14]苗增强,姚建刚,李婷,等.改进的多目标遗传算法在配电网规划中的应用[J].电力系统及其自动化学报,2009, 21(5):63-67.MIAOZengqiang,YAOJiangang,LITing,etal.Applicationofimprovedmulti-objectivegeneticalgorithm indistributionnetworkplanning[J].Proceedingsofthe CSU-EPSA, 2009, 21(5):63-67.
[15]钟庆,吴捷,伍力,等.基于系统动力学的分区负荷预测[J].电网技术, 2001, 25(3):51-55.ZHONGQing,WUJie,WULi,etal.Subareaload forecasting based on system dynamics[J]. Power System Technology, 2001, 25(3):51-55.
[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):66-71.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):66-71.
[17]肖白,李科,田春筝,等.空间负荷预测中确定元胞负荷合理最大值的主成分分析法[J].电测与仪表,2017,54(14):112-116.XIAOBai,LIKe,TIANChunzheng,etal.APCA method for ascertaining maximal value of cellular load in spatialloadforecasting[J].ElectricalMeasurement&Instrumentation, 2017, 54(14):112-116.