基于RBF神经网络与模糊理论的电力系统短期负荷预测
|
摘要
短期负荷预测是电力系统安全调度、经济运行的重要依据,负荷预测的精度直接影响到电力系统运行的可靠性、经济性和供电质量。因此,寻求合适的负荷预测方法最大限度的提高预测精度具有重要的应用价值。
根据电力负荷特性的变化规律,考虑了日期类型、温度、天气状况等影响负荷预测的因素,本文提出了一种将径向基函数(Radial Basis Function,RBF)神经网络与模糊理论相结合的短期负荷预测的方法。首先,考虑负荷的季节性变化,对春、夏、秋、冬四季分别建立预测模型,采用模糊聚类分析的方法对负荷预测相关数据进行聚类,选用同类特征数据作为RBF神经网络的输入,对神经网络进行训练,从而实现电力系统短期负荷预测;其次,采用在线自调整因子的模糊控制对预测误差进行在线智能修正使预测模型适应负荷的实时变化;最后,在未来电力市场的环境下,电价因素也是一个必须在负荷预测模型中加以考虑的因素,为了克服神经网络在电力市场下进行负荷预测时存在的不足,本文利用RBF神经网络的非线性逼近能力对不考虑电价因素的预测日负荷进行预测,然后根据近期实时电价的变化,应用模糊控制对RBF神经网络的负荷预测结果进行修正。
实际算例表明,本文的预测方法收敛性好、方便实用、有较高的预测精度和较快的训练速度。
Short-term load forecasting is important basis of safely assigning and economically running. The forecasting precision will directly affect the reliability, economy running and supplying power quality of power system. So finding an appropriate load forecasting method to improve the accuracy of precision has important application value.
According to the rule of change of load characteristic, after calculating the factors such as date type, temperature, weather status etc which influencing the load forecasting a forecasting method based on radial basis function neural networks and fuzzy theory. At first, considering load seasonal variation, forecasting models are established to forecast each season including spring, summer, autumn and winter respectively, using fuzzy clustering analysis method, the clustering analysis of the related data of load forecasting are carried out, the data of the same property are used as the input of neural network, train RBF neural network to predict short-term load. Secondly, in order to eliminate forecast error, on-line self-tuning fuzzy control is used, make prediction model adapt to real-time change. Finally, Electricity price is also factor which must be considered in load forecasting model in future power market environment. in order to overcome the defect of the RBF network in power market environment, the article first draws on the nonlinear approaching capacity of the RBF network to forecast the load on the prediction day which takes no account of the factor of electric price, and then, based on the recent changes of real-time price, uses the fuzzy control system to modify the results of load forecasting obtained by using the RBF network.
Practical examples indicate that the forecasting method is convenient and practical, possesses a good convergence, greater forecasting accuracy and faster training speed.
根据电力负荷特性的变化规律,考虑了日期类型、温度、天气状况等影响负荷预测的因素,本文提出了一种将径向基函数(Radial Basis Function,RBF)神经网络与模糊理论相结合的短期负荷预测的方法。首先,考虑负荷的季节性变化,对春、夏、秋、冬四季分别建立预测模型,采用模糊聚类分析的方法对负荷预测相关数据进行聚类,选用同类特征数据作为RBF神经网络的输入,对神经网络进行训练,从而实现电力系统短期负荷预测;其次,采用在线自调整因子的模糊控制对预测误差进行在线智能修正使预测模型适应负荷的实时变化;最后,在未来电力市场的环境下,电价因素也是一个必须在负荷预测模型中加以考虑的因素,为了克服神经网络在电力市场下进行负荷预测时存在的不足,本文利用RBF神经网络的非线性逼近能力对不考虑电价因素的预测日负荷进行预测,然后根据近期实时电价的变化,应用模糊控制对RBF神经网络的负荷预测结果进行修正。
实际算例表明,本文的预测方法收敛性好、方便实用、有较高的预测精度和较快的训练速度。
Short-term load forecasting is important basis of safely assigning and economically running. The forecasting precision will directly affect the reliability, economy running and supplying power quality of power system. So finding an appropriate load forecasting method to improve the accuracy of precision has important application value.
According to the rule of change of load characteristic, after calculating the factors such as date type, temperature, weather status etc which influencing the load forecasting a forecasting method based on radial basis function neural networks and fuzzy theory. At first, considering load seasonal variation, forecasting models are established to forecast each season including spring, summer, autumn and winter respectively, using fuzzy clustering analysis method, the clustering analysis of the related data of load forecasting are carried out, the data of the same property are used as the input of neural network, train RBF neural network to predict short-term load. Secondly, in order to eliminate forecast error, on-line self-tuning fuzzy control is used, make prediction model adapt to real-time change. Finally, Electricity price is also factor which must be considered in load forecasting model in future power market environment. in order to overcome the defect of the RBF network in power market environment, the article first draws on the nonlinear approaching capacity of the RBF network to forecast the load on the prediction day which takes no account of the factor of electric price, and then, based on the recent changes of real-time price, uses the fuzzy control system to modify the results of load forecasting obtained by using the RBF network.
Practical examples indicate that the forecasting method is convenient and practical, possesses a good convergence, greater forecasting accuracy and faster training speed.
引文
[1]牛东晓,曹树华,等.电力负荷预测技术及其应用[M].北京:中国电力出版社,1998:2.
[2]Topalli A K,Erkmen I.A hybrid learning for neural networks applied to short term load forecasting [J].Neurocomputing,2003,51:495-500.
[3]Alex D.Papalexopoulos,Timothy.c.Hesterberg.A Regression-Based Appr-oach To Short-Term System Load Forecasting[J].lEEE Trans.On Power System,1990,5(4).
[4]Suri Vemuri,Wen Liang Huang,Don J.nelson.On-Line Algorithms for Forecasting Hourly Loads of Electric Utility[J].lEEE Trans.On Power Apparatus And Systems,1981,100(8).
[5]Martin T.Hagan,Suzanne M.Behr.The Times Series Approach To Short Term Load Forecasting[J].lEEE Trans.On Power Systems,1987,2(3).
[6]马静波,杨洪耕.自适应卡尔曼滤波在电力系统短期负荷预测中的应用[J].电网技术,2005,29(1):75-79.
[7]邹健,杨莹春,诸静.基于灰色模型的预测模糊控制策略及其应用研究[J].中国电机工程学报,2002,22(9):12-15.
[8]候广松,刘伟生,谢广建.基于相关因素映射和神经网络的短期负荷预测[J].电网技术,2006,30(增刊):553-556.
[9]赵宇红,唐耀庚,张韵辉.基于神经网络和模糊理论的短期负荷预测[J].高电压技术,2006,32(5):107-110.
[10]郧永康,陈维荣,蒋刚,郝文斌.基于混沌理论的短期负荷局域多步预测法[J].电力系统及其自动化学报,2007:19(4):76-79.
[11]Park.D.C,El-Sharkawi,M.A.Electric load forecasting using an artificial neural network[J].IEEE Transaction on Power Systems,1991,6(2):442-449.
[12]Ranaweera.D.K,Hubele.N.F.Application of radial basis function neural network model for short-term load forecasting[J],IEE Proceedings on Generation,Transmission and Distribution,1995,142(1):45-50.
[13]杨帆,吴耀武,熊信银,娄素华,彭丰.用自适应模糊推理系统预测电力短期负荷[J].高电压技术,2007,33(4):129-133.
[14]严华,吴捷,等.模糊集理论在电力系统短期负荷预测中的应用[J].电力系统自动化,2000,6(1):67-72.
[15]谢宏,牛东晓,张国立,杨文璐.一种模糊模型的混合建模方法及在短期负荷预测中的应用[J].中国电机工程学报,2005,25(8):17-22.
[16]高山,张凌浩,等.节假日短期负荷预测的一种实用算法[J].江苏电机工程,2002,21(2):19-21.
【17】Bakirtzi A.G.s,Theocharis J.B.Short term load forecasting using fuzzy neural networks[J].IEEE Transactions on Power Systems,1995,10(3):1518-1524.
【18】Mohammad Tamimi et al.Short term electric load forecasting via fuzzy neural collaboration[J].Electric Power Systems Research,2000,56:243-248.
【19】D.Srinivasan,et al.Practical implementation of a hybrid fuzzy neural network for one-day-ahead load forcasting[J].IEE Pro-Gener.Transm.Disstrib,1998,145(6).
【20】Kassaei H R,Keyhani A,Woung T,et al.A Hybrid Fuzzy Neural network Bus Load Modeling and Predication[J].IEEE Trans on Power Systems,1999,14(2):718-724.
【21】Kim K H,Park J K,Hwang K J,et al.Implementation of Hybrid Short-Term Load Forecasting System Using Artificial Neural Networks and Fuzzy Expert Systems[J].IEEE Trans on Power Systems,1995,10(3):1534-1539.
【22】杨英.一种基于模糊逻辑和神经网络的短期负荷预测的方法[J].四川电力技术,2006,29(4):7-9,25.
【23】赵宇红,唐耀庚,张韵辉.基于神经网络和模糊理论的短期负荷预测[J].高电压技术,2006,32(5):107-110.
【24】钟珞,饶文碧,邹承明著.人工神经网络及其融和应用技术[M].北京:科学出版社,2007:1,20-25.
【25】张雪莹,管霖,谢锦标.采用谱分析建摸和基于人工神经网络的短期负荷预测方案[J].电网技术,2004,28(11):49-52.
【26】王黎明,王艳松.基于RBF神经网络的短期负荷预测[J].电气技术,2007,4:53-55.
【27】曹安照,田丽.基于RBF神经网络的短期电力负荷预测[J].电子科技大学学报,2006,35(4):507-509.
【28】赵剑剑,张步涵,程时杰,等.一种基于径向基函数的短期负荷预测方法[J].电网技术,2003,27(6):22-25.
【29】雷绍兰,孙才新,周湶,张晓星,程其云.基于径向基神经网络和自适应神经模糊系统的电力短期负荷预测方法[J].中国电机工程学报,2005,25(22):78-82.
【30】吴宏晓,侯志俭,刘涌,蒋传文.基于免疫聚类径向基函数网络模型的短期负荷预测[J].中国电机工程学报,2005,25(16):53-56.
【31】刘峤,李渝曾,张少华.RBF网络在节假日短期负荷预测中的应用[J].上海大学学报,2001,7(5):405-408.
【32】刘刚,黄剑华,刘学仁.基于改进型BP神经网络的短期电力负荷预测[J].电气应用,2005,24(12):46-49.
【33】赵福成.基于人工神经网络的短期负荷预测[D].华北电力大学硕士学位论文,2001:12-14.
【34】路广,张伯明,孙宏斌.数据仓库与数据挖掘技术在电力系统中的应用[J].电网技术,2001,8(25):150-200.
[35]王立,朱学峰.基于模糊聚类的多神经网络在短期电力负荷预测中的应用[J].电气应用,2007,26(7):24-27.
[36]徐克圣,王澜.一种自动获得k值的聚类算法[J].大连交通大学学报,2005,28(4):68-71.
[37]尹成群,康丽峰.孙伟.基于模糊聚类和灰色关联分析结合的负荷预测[J].华北电力大学学报,2006,33(6):24-27.
[38]苏炜宏.电力系统短期负荷预测主成分分析和人工神经网络的组合方法[D].南京理工大学硕士学位论文,2002:33-37.
[39]陈志巧.基于模糊理论的电力负荷预测研究[J].山东科技大学学报,2006,25(2):81-83.
[40]张乃尧,阎平凡.神经网络与模糊控制[M].北京:清华大学出版社,1998:184.
[41]吕志米,张保会.基于ANN和模糊控制相结合的电力负荷短期预测方法[J].电力系统自动化,1999,23(22):37-39.
[42]余永权,曾碧.单片机模糊逻辑控制[M].北京:北京航空航天大学出版社,1997:92.
[43]康重庆,夏清,胡左浩,张伯明.电力市场中预测问题的新内涵[J].电力系统自动化,2004,28(18):1-6.
[2]Topalli A K,Erkmen I.A hybrid learning for neural networks applied to short term load forecasting [J].Neurocomputing,2003,51:495-500.
[3]Alex D.Papalexopoulos,Timothy.c.Hesterberg.A Regression-Based Appr-oach To Short-Term System Load Forecasting[J].lEEE Trans.On Power System,1990,5(4).
[4]Suri Vemuri,Wen Liang Huang,Don J.nelson.On-Line Algorithms for Forecasting Hourly Loads of Electric Utility[J].lEEE Trans.On Power Apparatus And Systems,1981,100(8).
[5]Martin T.Hagan,Suzanne M.Behr.The Times Series Approach To Short Term Load Forecasting[J].lEEE Trans.On Power Systems,1987,2(3).
[6]马静波,杨洪耕.自适应卡尔曼滤波在电力系统短期负荷预测中的应用[J].电网技术,2005,29(1):75-79.
[7]邹健,杨莹春,诸静.基于灰色模型的预测模糊控制策略及其应用研究[J].中国电机工程学报,2002,22(9):12-15.
[8]候广松,刘伟生,谢广建.基于相关因素映射和神经网络的短期负荷预测[J].电网技术,2006,30(增刊):553-556.
[9]赵宇红,唐耀庚,张韵辉.基于神经网络和模糊理论的短期负荷预测[J].高电压技术,2006,32(5):107-110.
[10]郧永康,陈维荣,蒋刚,郝文斌.基于混沌理论的短期负荷局域多步预测法[J].电力系统及其自动化学报,2007:19(4):76-79.
[11]Park.D.C,El-Sharkawi,M.A.Electric load forecasting using an artificial neural network[J].IEEE Transaction on Power Systems,1991,6(2):442-449.
[12]Ranaweera.D.K,Hubele.N.F.Application of radial basis function neural network model for short-term load forecasting[J],IEE Proceedings on Generation,Transmission and Distribution,1995,142(1):45-50.
[13]杨帆,吴耀武,熊信银,娄素华,彭丰.用自适应模糊推理系统预测电力短期负荷[J].高电压技术,2007,33(4):129-133.
[14]严华,吴捷,等.模糊集理论在电力系统短期负荷预测中的应用[J].电力系统自动化,2000,6(1):67-72.
[15]谢宏,牛东晓,张国立,杨文璐.一种模糊模型的混合建模方法及在短期负荷预测中的应用[J].中国电机工程学报,2005,25(8):17-22.
[16]高山,张凌浩,等.节假日短期负荷预测的一种实用算法[J].江苏电机工程,2002,21(2):19-21.
【17】Bakirtzi A.G.s,Theocharis J.B.Short term load forecasting using fuzzy neural networks[J].IEEE Transactions on Power Systems,1995,10(3):1518-1524.
【18】Mohammad Tamimi et al.Short term electric load forecasting via fuzzy neural collaboration[J].Electric Power Systems Research,2000,56:243-248.
【19】D.Srinivasan,et al.Practical implementation of a hybrid fuzzy neural network for one-day-ahead load forcasting[J].IEE Pro-Gener.Transm.Disstrib,1998,145(6).
【20】Kassaei H R,Keyhani A,Woung T,et al.A Hybrid Fuzzy Neural network Bus Load Modeling and Predication[J].IEEE Trans on Power Systems,1999,14(2):718-724.
【21】Kim K H,Park J K,Hwang K J,et al.Implementation of Hybrid Short-Term Load Forecasting System Using Artificial Neural Networks and Fuzzy Expert Systems[J].IEEE Trans on Power Systems,1995,10(3):1534-1539.
【22】杨英.一种基于模糊逻辑和神经网络的短期负荷预测的方法[J].四川电力技术,2006,29(4):7-9,25.
【23】赵宇红,唐耀庚,张韵辉.基于神经网络和模糊理论的短期负荷预测[J].高电压技术,2006,32(5):107-110.
【24】钟珞,饶文碧,邹承明著.人工神经网络及其融和应用技术[M].北京:科学出版社,2007:1,20-25.
【25】张雪莹,管霖,谢锦标.采用谱分析建摸和基于人工神经网络的短期负荷预测方案[J].电网技术,2004,28(11):49-52.
【26】王黎明,王艳松.基于RBF神经网络的短期负荷预测[J].电气技术,2007,4:53-55.
【27】曹安照,田丽.基于RBF神经网络的短期电力负荷预测[J].电子科技大学学报,2006,35(4):507-509.
【28】赵剑剑,张步涵,程时杰,等.一种基于径向基函数的短期负荷预测方法[J].电网技术,2003,27(6):22-25.
【29】雷绍兰,孙才新,周湶,张晓星,程其云.基于径向基神经网络和自适应神经模糊系统的电力短期负荷预测方法[J].中国电机工程学报,2005,25(22):78-82.
【30】吴宏晓,侯志俭,刘涌,蒋传文.基于免疫聚类径向基函数网络模型的短期负荷预测[J].中国电机工程学报,2005,25(16):53-56.
【31】刘峤,李渝曾,张少华.RBF网络在节假日短期负荷预测中的应用[J].上海大学学报,2001,7(5):405-408.
【32】刘刚,黄剑华,刘学仁.基于改进型BP神经网络的短期电力负荷预测[J].电气应用,2005,24(12):46-49.
【33】赵福成.基于人工神经网络的短期负荷预测[D].华北电力大学硕士学位论文,2001:12-14.
【34】路广,张伯明,孙宏斌.数据仓库与数据挖掘技术在电力系统中的应用[J].电网技术,2001,8(25):150-200.
[35]王立,朱学峰.基于模糊聚类的多神经网络在短期电力负荷预测中的应用[J].电气应用,2007,26(7):24-27.
[36]徐克圣,王澜.一种自动获得k值的聚类算法[J].大连交通大学学报,2005,28(4):68-71.
[37]尹成群,康丽峰.孙伟.基于模糊聚类和灰色关联分析结合的负荷预测[J].华北电力大学学报,2006,33(6):24-27.
[38]苏炜宏.电力系统短期负荷预测主成分分析和人工神经网络的组合方法[D].南京理工大学硕士学位论文,2002:33-37.
[39]陈志巧.基于模糊理论的电力负荷预测研究[J].山东科技大学学报,2006,25(2):81-83.
[40]张乃尧,阎平凡.神经网络与模糊控制[M].北京:清华大学出版社,1998:184.
[41]吕志米,张保会.基于ANN和模糊控制相结合的电力负荷短期预测方法[J].电力系统自动化,1999,23(22):37-39.
[42]余永权,曾碧.单片机模糊逻辑控制[M].北京:北京航空航天大学出版社,1997:92.
[43]康重庆,夏清,胡左浩,张伯明.电力市场中预测问题的新内涵[J].电力系统自动化,2004,28(18):1-6.