基于灰色关联分析和改进神经网络的10 kV配电网线损预测
|
摘要
为更全面、准确地评估10 kV配电网线损水平,提出了一种基于灰色关联分析和改进神经网络的10kV配电网线线损预测方法。通过灰色关联分析方法定量分析了15个电气指标与10 kV配电网线损的关联性,再经过实际10 kV配电网数据的预测校验,最终确定了最佳的电气特征指标体系;其次使用十折交叉验证法结合试凑法计算分析不同神经网络结构下的模型预测性能,确定了最佳的网络结构,解决了BP神经网络(BPNN)隐含层节点数目多凭经验确定的缺点。考虑到传统的BP神经网络收敛速度慢、易陷入局部极小等缺点,采用自适应遗传算法改进BP神经网络(AGABPNN)的方法,进行学习和预测,并对比分析了该方法和径向基神经网络(RBFNN)、传统的BP神经网络的收敛性和预测准确性。通过某地区329条10kV线路实例计算,3种方法最小预测误差分别为6.71%、12.95%、17.05%,验证了AGA-BPNN具有更好的收敛性和泛化能力。
To estimate the level of 10 kV distribution network line loss more integrally and accurately, a 10 k V distribution network line loss prediction method based on grey correlation analysis and improved artificial neural network is proposed. Relevancies between 15 electrical indexes and 10 kV distribution network line loss are analyzed with grey correlation, and the best electrical characteristic indexes are selected after checked with practical data of 10 kV distribution network. To overcome difficulty in determining the number of nodes in hidden layer, predictive performances of the line loss prediction model under different neural network structures are analyzed with cross validation and test-and-error methods.Considering slow convergence and existence of local minimum in conventional BP neural network(BPNN), adaptive genetic algorithm(AGA) is adopted to improve BP neural network(AGA-BPNN), and compared with RBF neural network(RBFNN) and conventional BP neural network. After calculating actual data of 10 kV lines, minimum prediction error for 3 methods above are 6.71%, 12.95% and 17.05%respectively, proving better convergence and accuracy of AGA-BPNN.
To estimate the level of 10 kV distribution network line loss more integrally and accurately, a 10 k V distribution network line loss prediction method based on grey correlation analysis and improved artificial neural network is proposed. Relevancies between 15 electrical indexes and 10 kV distribution network line loss are analyzed with grey correlation, and the best electrical characteristic indexes are selected after checked with practical data of 10 kV distribution network. To overcome difficulty in determining the number of nodes in hidden layer, predictive performances of the line loss prediction model under different neural network structures are analyzed with cross validation and test-and-error methods.Considering slow convergence and existence of local minimum in conventional BP neural network(BPNN), adaptive genetic algorithm(AGA) is adopted to improve BP neural network(AGA-BPNN), and compared with RBF neural network(RBFNN) and conventional BP neural network. After calculating actual data of 10 kV lines, minimum prediction error for 3 methods above are 6.71%, 12.95% and 17.05%respectively, proving better convergence and accuracy of AGA-BPNN.
引文
[1]彭宇文,刘克文.基于改进核心向量机的配电网线损理论计算方法[J].中国电机工程学报,2011,31(34):120-126.Peng Yuwen,Liu Kewen.A distribution network theoretical line loss calculation method based on improved core vector machine[J].Proceedings of the CSEE,2011,31(34):120-126(in Chinese).
[2]李亚,刘丽平,李柏青,等.基于改进K-Means聚类和BP神经网络的台区线损率计算方法[J].中国电机工程学报,2016,36(17):4543-4552.Li Ya,Liu Liping,Li Baiqing,et al.Calculation of line loss rate in transformer district based on improved K-Means clustering algorithm and BP neural network[J].Proceedings of the CSEE,2016,36(17):4543-4552(in Chinese).
[3]陈得治,郭志忠.基于负荷获取和匹配潮流方法的配电网理论线损计算[J].电网技术,2005,29(1):80-84.Chen Dezhi,Guo Zhizhong.Distribution system theorrical line loss calculation based on load obtaining and matching power flow[J].Power System Technology,2005,29(1):80-84(in Chinese).
[4]李健,黄俊铭,朱建全,等.基于过程状态特征化的配电网线损计算[J].电力系统保护与控制,2017,45(10):55-61.Li Jian,Huang Junming,Zhu Jianquan,et al.Line loss calculation for distribution network based on state characterization[J].Power System Protection and Control,2017,45(10):55-61(in Chinese).
[5]文福拴,韩祯祥.基于分群算法和人工神经元网络的配电网线损计算[J].中国电机工程学报,1993,13(3):43-53.Wen Fushuan,Han Zhenxiang.The calculation of energy losses in distribution systems based on upon a clustering algorithm and an artificial neural network model[J].Proceedings of the CSEE,1993,13(3):41-50(in Chinese).
[6]张勤,马玮,付锦,等.中压配电网规划态线损计算方法[J].电气技术,2018,19(2):42-45.Zhang Qin,Ma Wei,Fu Jin,et al.Line loss calculation for middle voltage distribution network planning[J].Electrical Engineering,2018,19(2):42-45(in Chinese).
[7]李秀卿,赵丽娜,孟庆然,等.IGA优化的神经网络计算配电网理论线损[J].电力系统及其自动化学报,2009,21(5):87-91.Li Xiuqing,Zhao Lina,Meng Qingran,et al.Calculation of line losses in distribution systems using artificial neural network aided by immune genetic algorithm[J].Proceedings of the CSU-EPSA,2009,21(5):87-91(in Chinese).
[8]余卫国,熊幼京,周新风,等.电力网技术线损分析及降损对策[J].电网技术,2006,30(18):54-57.Yu Weiguo,Xiong Youjing,Zhou Xinfeng,et al.Analysis on technical line losses of power grids and countermeasures to reduce line losses[J].Power System Technology,2006,30(18):54-57(in Chinese).
[9]许汉平,侯进峰,施流忠,等.基于状态估计数据的电网线损理论计算方法[J].电网技术,2003,27(3):59-62.Xu Hanping,Hou Jinfeng,Shi Liuzhong,et al.Calculation method of power system line losses based on data of state estimation[J].Power System Technology,2003,27(3):59-62(in Chinese).
[10]丁心海,罗毅芳,刘巍,等.配电网线损理论计算的实用方法-改进迭代法[J].电网技术,2000,24(1):39-42.Ding Xinhai,Luo Yifang,Liu Wei,et al.A new practical method for calculation line loss of distribution network-improved iteration method[J].Power System Technology,2000,24(1):39-42(in Chinese).
[11]邓芳.配网线损实时统计与分析系统[J].电网技术,2007,31(S1):186-188.Deng Fang.Real time measurement and analysis system of line losses in distribution networks[J].Power System Technology,2007,31(S1):186-188(in Chinese).
[12]鲍海,马千.电网线损的物理分布机理[J].中国电机工程学报,2005,25(21):85-89.Bao Hai,Ma Qian.Physical distribution mechanism of network loss for power system[J].Proceedings of the CSEE,2005,25(21):85-89(in Chinese).
[13]安晓华,欧阳森,冯天瑞,等.中压馈线理论线损率标杆值的优化设计方法及应用[J].电网技术,2016,40(1):199-206.An Xiaohua,Ouyang Sen,Feng Tianrui,et al.An optimal design method of theoretical line loss rate benchmark value for medium voltage feeders and its application[J].Power System Technology,2016,40(1):199-206(in Chinese).
[14]牛东晓,谷志红,邢棉,等.基于数据挖掘的SVM短期负荷预测方法研究[J].中国电机工程学报,2006,26(18):6-12.Niu Dongxiao,Gu Zhihong,Xing Mian,et al.Study on forecasting approach to short-term load of SVM based on data mining[J].Proceedings of the CSEE,2006,26(18):6-12(in Chinese).
[15]卢志刚,李爽.基于直接神经动态规划的电网状态估计及线损理论计算[J].电网技术,2008,32(23):50-55.Lu Zhigang,Li Shuang.Power system state estimation and theoretical line loss calculation based on direct neural dynamic programming[J].Power System Technology,2008,32(23):50-55(in Chinese).
[16]苏学能,刘天琪,曹鸿谦,等.基于Hadoop架构的多重分布式BP神经网络的短期负荷预测方法[J].中国电机工程学报,2017,37(17):4966-4973.Su Xueneng,Liu Tianqi,Cao Hongqian,et al.A multiple distributed BP neural networks approach for short-term load forecasting based on hadoop framework[J].Proceedings of the CSEE,2017,37(17):4966-4973(in Chinese).
[17]Srinivasu G S,Rao R N.Artificial neural network approach for prediction of stress-strain curve of near b titanium alloy[J].Rare Metals,2014,33(3):249-257.
[18]Kim H,Ko Y,Jung K H.Artificial neural-network based feeder reconfiguration for loss reduction in distribution systems[J].IEEETransactions on Power Delivery,1993,8(3):1356-1366.
[19]Liu L P,Li B Q,Li Y,et al.Calculation of line loss in low-voltage transformer district based on BP network model optimized by LMalgorithm[C]//Electrical Power and Energy Conference.IEEE,2016:1-6.
[20]Zafar M,Vinh N V,Behera S K,et al.Ethanol mediated As(III)adsorption onto Zn-loaded pinecone biochar:experimental investigation,modeling,and optimization using hybrid artificial neural network-genetic algorithm approach[J].Journal of Environmental Sciences,2017,54(4):114-125.
[21]Wei S G.Artificial neural networks combined with modified genetic algorithm applied to near-infrared quantitative analysis of trimethoprim power[C]//The Third Asian Spectroscopy Conference Xiamen Municipal Government,Xiamen University:2011:1.
[22]袁慧梅,郭喜庆,于海波.中压配电网线损计算新方法[J].电力系统自动化,2002,26(11):50-53.Yuan Huimei,Guo Xiqing,Yu Haibo.New method for calculation energy losses[J].Automation of Electric Power Systems,2002,26(11):50-53(in Chinese).
[23]王吉权.BP神经网络的理论及其在农业机械化中的应用研究[D].沈阳:沈阳农业大学,2011.
[24]Abe Y,Iiguni Y.Fast computation of RBF coefficients for regularly sampled inputs[J].Electronics Letters,2003,39(6):543-544.
[2]李亚,刘丽平,李柏青,等.基于改进K-Means聚类和BP神经网络的台区线损率计算方法[J].中国电机工程学报,2016,36(17):4543-4552.Li Ya,Liu Liping,Li Baiqing,et al.Calculation of line loss rate in transformer district based on improved K-Means clustering algorithm and BP neural network[J].Proceedings of the CSEE,2016,36(17):4543-4552(in Chinese).
[3]陈得治,郭志忠.基于负荷获取和匹配潮流方法的配电网理论线损计算[J].电网技术,2005,29(1):80-84.Chen Dezhi,Guo Zhizhong.Distribution system theorrical line loss calculation based on load obtaining and matching power flow[J].Power System Technology,2005,29(1):80-84(in Chinese).
[4]李健,黄俊铭,朱建全,等.基于过程状态特征化的配电网线损计算[J].电力系统保护与控制,2017,45(10):55-61.Li Jian,Huang Junming,Zhu Jianquan,et al.Line loss calculation for distribution network based on state characterization[J].Power System Protection and Control,2017,45(10):55-61(in Chinese).
[5]文福拴,韩祯祥.基于分群算法和人工神经元网络的配电网线损计算[J].中国电机工程学报,1993,13(3):43-53.Wen Fushuan,Han Zhenxiang.The calculation of energy losses in distribution systems based on upon a clustering algorithm and an artificial neural network model[J].Proceedings of the CSEE,1993,13(3):41-50(in Chinese).
[6]张勤,马玮,付锦,等.中压配电网规划态线损计算方法[J].电气技术,2018,19(2):42-45.Zhang Qin,Ma Wei,Fu Jin,et al.Line loss calculation for middle voltage distribution network planning[J].Electrical Engineering,2018,19(2):42-45(in Chinese).
[7]李秀卿,赵丽娜,孟庆然,等.IGA优化的神经网络计算配电网理论线损[J].电力系统及其自动化学报,2009,21(5):87-91.Li Xiuqing,Zhao Lina,Meng Qingran,et al.Calculation of line losses in distribution systems using artificial neural network aided by immune genetic algorithm[J].Proceedings of the CSU-EPSA,2009,21(5):87-91(in Chinese).
[8]余卫国,熊幼京,周新风,等.电力网技术线损分析及降损对策[J].电网技术,2006,30(18):54-57.Yu Weiguo,Xiong Youjing,Zhou Xinfeng,et al.Analysis on technical line losses of power grids and countermeasures to reduce line losses[J].Power System Technology,2006,30(18):54-57(in Chinese).
[9]许汉平,侯进峰,施流忠,等.基于状态估计数据的电网线损理论计算方法[J].电网技术,2003,27(3):59-62.Xu Hanping,Hou Jinfeng,Shi Liuzhong,et al.Calculation method of power system line losses based on data of state estimation[J].Power System Technology,2003,27(3):59-62(in Chinese).
[10]丁心海,罗毅芳,刘巍,等.配电网线损理论计算的实用方法-改进迭代法[J].电网技术,2000,24(1):39-42.Ding Xinhai,Luo Yifang,Liu Wei,et al.A new practical method for calculation line loss of distribution network-improved iteration method[J].Power System Technology,2000,24(1):39-42(in Chinese).
[11]邓芳.配网线损实时统计与分析系统[J].电网技术,2007,31(S1):186-188.Deng Fang.Real time measurement and analysis system of line losses in distribution networks[J].Power System Technology,2007,31(S1):186-188(in Chinese).
[12]鲍海,马千.电网线损的物理分布机理[J].中国电机工程学报,2005,25(21):85-89.Bao Hai,Ma Qian.Physical distribution mechanism of network loss for power system[J].Proceedings of the CSEE,2005,25(21):85-89(in Chinese).
[13]安晓华,欧阳森,冯天瑞,等.中压馈线理论线损率标杆值的优化设计方法及应用[J].电网技术,2016,40(1):199-206.An Xiaohua,Ouyang Sen,Feng Tianrui,et al.An optimal design method of theoretical line loss rate benchmark value for medium voltage feeders and its application[J].Power System Technology,2016,40(1):199-206(in Chinese).
[14]牛东晓,谷志红,邢棉,等.基于数据挖掘的SVM短期负荷预测方法研究[J].中国电机工程学报,2006,26(18):6-12.Niu Dongxiao,Gu Zhihong,Xing Mian,et al.Study on forecasting approach to short-term load of SVM based on data mining[J].Proceedings of the CSEE,2006,26(18):6-12(in Chinese).
[15]卢志刚,李爽.基于直接神经动态规划的电网状态估计及线损理论计算[J].电网技术,2008,32(23):50-55.Lu Zhigang,Li Shuang.Power system state estimation and theoretical line loss calculation based on direct neural dynamic programming[J].Power System Technology,2008,32(23):50-55(in Chinese).
[16]苏学能,刘天琪,曹鸿谦,等.基于Hadoop架构的多重分布式BP神经网络的短期负荷预测方法[J].中国电机工程学报,2017,37(17):4966-4973.Su Xueneng,Liu Tianqi,Cao Hongqian,et al.A multiple distributed BP neural networks approach for short-term load forecasting based on hadoop framework[J].Proceedings of the CSEE,2017,37(17):4966-4973(in Chinese).
[17]Srinivasu G S,Rao R N.Artificial neural network approach for prediction of stress-strain curve of near b titanium alloy[J].Rare Metals,2014,33(3):249-257.
[18]Kim H,Ko Y,Jung K H.Artificial neural-network based feeder reconfiguration for loss reduction in distribution systems[J].IEEETransactions on Power Delivery,1993,8(3):1356-1366.
[19]Liu L P,Li B Q,Li Y,et al.Calculation of line loss in low-voltage transformer district based on BP network model optimized by LMalgorithm[C]//Electrical Power and Energy Conference.IEEE,2016:1-6.
[20]Zafar M,Vinh N V,Behera S K,et al.Ethanol mediated As(III)adsorption onto Zn-loaded pinecone biochar:experimental investigation,modeling,and optimization using hybrid artificial neural network-genetic algorithm approach[J].Journal of Environmental Sciences,2017,54(4):114-125.
[21]Wei S G.Artificial neural networks combined with modified genetic algorithm applied to near-infrared quantitative analysis of trimethoprim power[C]//The Third Asian Spectroscopy Conference Xiamen Municipal Government,Xiamen University:2011:1.
[22]袁慧梅,郭喜庆,于海波.中压配电网线损计算新方法[J].电力系统自动化,2002,26(11):50-53.Yuan Huimei,Guo Xiqing,Yu Haibo.New method for calculation energy losses[J].Automation of Electric Power Systems,2002,26(11):50-53(in Chinese).
[23]王吉权.BP神经网络的理论及其在农业机械化中的应用研究[D].沈阳:沈阳农业大学,2011.
[24]Abe Y,Iiguni Y.Fast computation of RBF coefficients for regularly sampled inputs[J].Electronics Letters,2003,39(6):543-544.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |