知识库在短期电力负荷预测中的应用研究
|
摘要
电力负荷预测中非正常日的负荷预测是提高整体预测精度的关键。本文提出了一种基于知识库技术的新型短期负荷预测方法。首先,利用小波坏数据检测原理和软阈值细节消噪法对原始负荷中的坏数据进行预处理。其次,将处理后的负荷数据及其影响因素按照事例推理的表示方法组织成事例型知识库;利用k-最近邻法检索出与待测事例属性相近的相似事例,其中,采用基于粗糙集的权值确定法来确定负荷事例影响因素的属性权值;在事例精简过程中,利用信息熵与主成分分析法联合对相似事例的负荷数据冗余进行约简;利用得到的相似事例的负荷数据对基于动态数值优化算法的BP神经网络进行训练学习;针对非正常日,采用基于决策树的数据挖掘技术构造出修正模型以便进一步修正预测;最后,预测结果按照事例表示方法作为更新资源存储于知识库中;利用本文方法对实际的地区电网进行了测试,结果表明,该方法对于非正常日的负荷预测具有较高的预测精度和较强的适应能力。
The key to improve the whole load prediction accuracy is properly handling the prediction problem in abnormal days. A novel approach for Short-Term Load Forecasting (STLF) based on knowledge base technology is put forward in the dissertation. First of all, through adjusting amplitude of wavelet modulus maxima and processing the wavelet decomposed detail signal by soft threshold based on wavelet analysis and singularity theory, fault data in original loads are eliminated. Then, the knowledge base filled with cases is constituted with processed load data and influential factors which are organized in according to case presentation. The k-nearest-neighbor is applied to find the most similar cases whose cases attributes are nearest with the cases to be predicted, and the attributes weights of influential factors are calculated by weights computing based on rough set. In the process of extraction, information entropy and principal component analysis are integrated to reduce similar cases set. The processed load sequence from similar cases is used to train the BP neural network based on Levenberg-Marquardt dynamic numerical optimization algorithm. Aiming at abnormal days, data mining technology based on decision-tree is used to construct revision model so that to make a further revision on forecasting. Finally, the forecasting results are preserved in cases set in according to case presentation as refreshment resources. The testing results of STLF in actual power network show that the proposed method aiming at abnormal day possesses higher forecasting accuracy and better adaptability.
The key to improve the whole load prediction accuracy is properly handling the prediction problem in abnormal days. A novel approach for Short-Term Load Forecasting (STLF) based on knowledge base technology is put forward in the dissertation. First of all, through adjusting amplitude of wavelet modulus maxima and processing the wavelet decomposed detail signal by soft threshold based on wavelet analysis and singularity theory, fault data in original loads are eliminated. Then, the knowledge base filled with cases is constituted with processed load data and influential factors which are organized in according to case presentation. The k-nearest-neighbor is applied to find the most similar cases whose cases attributes are nearest with the cases to be predicted, and the attributes weights of influential factors are calculated by weights computing based on rough set. In the process of extraction, information entropy and principal component analysis are integrated to reduce similar cases set. The processed load sequence from similar cases is used to train the BP neural network based on Levenberg-Marquardt dynamic numerical optimization algorithm. Aiming at abnormal days, data mining technology based on decision-tree is used to construct revision model so that to make a further revision on forecasting. Finally, the forecasting results are preserved in cases set in according to case presentation as refreshment resources. The testing results of STLF in actual power network show that the proposed method aiming at abnormal day possesses higher forecasting accuracy and better adaptability.
引文
[1]肖国泉,王春,张福伟.电力负荷预测.北京:中国电力出版社,2001
[2]Kandil M S,El-Debeiky S M,Hasanien N E. Long-term Load Forecasting for Fast Developing Utility Using a Knowledge-based Expert System. IEEE Trans on Power Systems,2002,17(2):49l～496
[3]牛东晓,曹树华,赵磊,等.电力负荷预测技术及应用.北京:中国电力出版社,1998
[4]Komprej I,Zunko P. Short term load forecasting.Proceeding of The 6th Mediterranean Electrotechnical Conference, IEEE, Ljubljana, 22～24 May, 1991
[5]Amjady N. Short-term hourly load forecasting using time-series modeling with peak load estimation capability. IEEE Transactions on Power Systems, Volume:16,Issue:3,Aug.2001,Pages:498～505
[6]Moghram I,Rahman S. Analysis and evaluation of five short-term load forecasting techniques.IEEE Transactions on Power Systems, Volume:4, Issue:4,Nov.1989,Pages:1484～1491
[7]Papalexopoulos A D,Hesterberg T C.A regression-based approach to short-term system load forecasting.IEEE Transactions on Power Systems. Volume:5,Issue:4,Nov.1990,Pages:1535～1547
[8]Cho M.Y., Hwang J.C., Chen C.S..Customer short term load forecasting by using ARIMA transfer function model. Proceedings of the International Conference on Energy Management and Power Delivery. EMPD,vol.1,1995, pp.317～322
[9]Trudnowski D J,McReynolds W L,Johnson J M.Real-time very short-term loadprediction for power-system automatic generation control.IEEE Transactions on Control Systems Technology. Volume:9,Issue:2,March 2001,Pages:254～260
[10]Chan S H,Ngan H W,Chow W L. A flexible load forecasting model for integrated resources planning.Proceedings of. DRPT 2000.International Conference on Electric Utility Deregulation and Restructuring and Power Technologies,4～7 April 2000,Pages:562～565
[11]张国江,邱家驹,李继红.基于模糊推理系统的多因素电力负荷预测.电力系统自动化,2002,26(5):49～53
[12]谷志红,牛东晓,王会青.广义回归神经网络模型在短期电力负荷预测中的应用研究.中国电力, 2006,36(4):1～14
[13]孟凡威.基于粒子群算法热力站供热负荷预测与控制研究:[硕士学位论文].大连:大连理工大学,2002
[14]宋超,黄民翔,叶剑斌.小波分析方法在电力系统短期负荷预测中的应用.电力系统及其自动化学报,2002,14(3):8～12
[15]张文哲,陈刚,吴迎霞.基于小波理论对负荷预测中不良数据的处理.重庆大学学报,2004,27(6):77～81
[16]林开英,俞集辉.神经网络短期负荷预测中的数据分析.重庆大学学报,2002,25(9):5～7
[17]蔡自兴.<美>约翰.德尔金,龚涛.高级专家系统:原理、设计及应用.北京:科学出版社,2005
[18]赵希正.中国电力负荷特性分析与预测.北京:中国电力出版社,2002
[19]张国江.软计算方法和数据挖掘理论在电力系统负荷预测中的应用:[博士学位论文].杭州:浙江大学,2002
[20]MALLAT. Singularity detection and processing with wavelets. IEEE Trans on IT,1992,38(2):617～643
[21]邰能灵,侯志俭.小波模糊神经网络在电力系统短期负荷预测中的应用.中国电机工程学报,2004,24(1):24～29
[22]张文哲,陈刚,吴迎霞.基于小波理论对负荷预测中不良数据的处理.重庆大学学报,2004,27(6):77～81
[23]SehankR,Abelson R R. Goals and Understanding[M],Erlbanum:Eksevier Science,1997,165～176
[24]Schank R. Dynmaic Memory:A Theory of Reminding and Learning in Computers and People[M],London:Cambridge University Press,1982
[25]Kolodner J. Maintaining organization in a dynamic long-term memory [J],Cognitive Science,1983,7(4):243～280
[26]Hennessy D,Hinkle D. Applying Case-based reasoning to autoclave loading[J],IEEE Expert,1992,7(5):21～26
[27]毛权,周济,余俊.基于实例原型的设计模型研究[J],高技术通讯,1995,71～76
[28]郭艳红,邓贵仕.基于事例的推理(CBR)研究综述.计算机工程与应用,2004,40(21):14
[29]陆汝铃.世纪之交的知识工程与知识科学.北京:清华大学出版社,2001
[30]赵登福,吴娟,刘昱,等.基于事例推理的短期负荷预测[J].西安交通大学学报,2003,37(6):608～611
[31]史忠植.知识发现.北京:清华大学出版社 2002:89～92
[32]Watoson l. Case-based reasoning is methodology not a technology [J]. Knowledge-based System,1999:12(5,6):303～308
[33]Riesbecd C K,Schank R C. Inside Case-Based Reasoning [M]. Hillsdale,New Jersey: Lawrence Erlbaum Associates Inc,1989
[34]Kalyan M G, Ai R M Empirical evaluation of retrieval in case-based reasoning systems using modified cosine matching function [J].IEEE Transactions on:Systems,Man,and Cybernetics:Systems and Humans,1997,9(5):601～612
[35]Henrique S H,Carlos E P,Reinaldo C S.Neural networks for short-term load forecasting:a review and evaluation[J].IEEE Transactions on Power Systems,2001,16(1):44～55
[36]PAL S,SIMON C.Foundations of Soft Case-based Reasoning.New York(NY, USA):A Wiley-Interscience Publication,2003.
[37]Bakirtzls A G,Petridls V,Klartzis S J,eta1.A neural network short term load forecasting model for the Greek power system [J]. IEEE Transactions on Power Systems,1996,11(2):858～863.
[38]谢宏,程浩忠,张国立,等.基于粗糙集理论建立短期电力负荷神经网络预测模型[J].中国电机工程学报,2003,23(11):1～4
[39]张文修,吴伟志,梁古业,等.粗糙集理论与方法[M].北京:科学出版社,2001.
[40]曾黄麟.粗集理论及其应用[M].重庆:重庆大学出版社,1998
[41]Pawlak Z . Rough Set theory and its Applications to Data Analysis[J].Cybernetics and systems,1998:(29):661～688
[42]王国胤.Rough 集理论与知识获取[M].西安:西安交通大学出版社,2001:208～210
[43]Radzikowska A M, Kerre E E. A comparative study of fuzzy rough sets[J].Fuzzy Sets and Systems,2002,126(1):137～l56
[44]Dubois D, Prade H. Rough fuzzy sets and fuzzy rough sets [J].International Journal of General Systems,1990,17 (2):191～209
[45]Jensen R,Shen Q.Fuzzy-rough sets for descriptive dimensionality reduction[C].Proceedings of the 11th International Conference on Fuzzy Systems,USA,2002
[46]魏传锋,李运泽,王浚.改进的最近邻法在基于事例推理中的应用,系统仿真学报,2005,12(5):1045～1047
[47]Sun Wei,Jian Changlu,He Yujun.Application of Neural Network Model Combining Information entropy and Colony Clustering Theory for Short-Term Load Forecasting . Conference on Machine Learning and Cybernetics,2005, Vol. 8,No.13,pp.4645～4650
[48]王志征,余岳峰,姚国平.主成份分析法在电力负荷预测中的应用.电力需求侧管理.2003,5(3):21～24
[49]柳进,唐降龙.基于主成分分析 L-M 神经网络高峰负荷预测研究.继电器.2004,32(13):24～27
[50]Jiawei H,Micheline K. Data Mining:Concepts and Techniques. Simon Fraser University:Morgan Kaufmann Publishers,2000
[51]Kandil M S,El-Debeiky S M ,Hasanien N E.Long-term Load Forecasting for Fast Developing Utility Using a Knowledge-based Expert System.IEEE Trans on Power Systems,2002,17(2):49l～496
[52]Hirota K,Pedrycz W.Fuzzy Computing for Data Mining.Proceedings of the IEEE,l999,87(9):l575～l600
[53]Breiman L,Friedman J H,Olshen R A,eta1.Classification and Regression Trees.New York:Chapman & Hall,l984
[2]Kandil M S,El-Debeiky S M,Hasanien N E. Long-term Load Forecasting for Fast Developing Utility Using a Knowledge-based Expert System. IEEE Trans on Power Systems,2002,17(2):49l～496
[3]牛东晓,曹树华,赵磊,等.电力负荷预测技术及应用.北京:中国电力出版社,1998
[4]Komprej I,Zunko P. Short term load forecasting.Proceeding of The 6th Mediterranean Electrotechnical Conference, IEEE, Ljubljana, 22～24 May, 1991
[5]Amjady N. Short-term hourly load forecasting using time-series modeling with peak load estimation capability. IEEE Transactions on Power Systems, Volume:16,Issue:3,Aug.2001,Pages:498～505
[6]Moghram I,Rahman S. Analysis and evaluation of five short-term load forecasting techniques.IEEE Transactions on Power Systems, Volume:4, Issue:4,Nov.1989,Pages:1484～1491
[7]Papalexopoulos A D,Hesterberg T C.A regression-based approach to short-term system load forecasting.IEEE Transactions on Power Systems. Volume:5,Issue:4,Nov.1990,Pages:1535～1547
[8]Cho M.Y., Hwang J.C., Chen C.S..Customer short term load forecasting by using ARIMA transfer function model. Proceedings of the International Conference on Energy Management and Power Delivery. EMPD,vol.1,1995, pp.317～322
[9]Trudnowski D J,McReynolds W L,Johnson J M.Real-time very short-term loadprediction for power-system automatic generation control.IEEE Transactions on Control Systems Technology. Volume:9,Issue:2,March 2001,Pages:254～260
[10]Chan S H,Ngan H W,Chow W L. A flexible load forecasting model for integrated resources planning.Proceedings of. DRPT 2000.International Conference on Electric Utility Deregulation and Restructuring and Power Technologies,4～7 April 2000,Pages:562～565
[11]张国江,邱家驹,李继红.基于模糊推理系统的多因素电力负荷预测.电力系统自动化,2002,26(5):49～53
[12]谷志红,牛东晓,王会青.广义回归神经网络模型在短期电力负荷预测中的应用研究.中国电力, 2006,36(4):1～14
[13]孟凡威.基于粒子群算法热力站供热负荷预测与控制研究:[硕士学位论文].大连:大连理工大学,2002
[14]宋超,黄民翔,叶剑斌.小波分析方法在电力系统短期负荷预测中的应用.电力系统及其自动化学报,2002,14(3):8～12
[15]张文哲,陈刚,吴迎霞.基于小波理论对负荷预测中不良数据的处理.重庆大学学报,2004,27(6):77～81
[16]林开英,俞集辉.神经网络短期负荷预测中的数据分析.重庆大学学报,2002,25(9):5～7
[17]蔡自兴.<美>约翰.德尔金,龚涛.高级专家系统:原理、设计及应用.北京:科学出版社,2005
[18]赵希正.中国电力负荷特性分析与预测.北京:中国电力出版社,2002
[19]张国江.软计算方法和数据挖掘理论在电力系统负荷预测中的应用:[博士学位论文].杭州:浙江大学,2002
[20]MALLAT. Singularity detection and processing with wavelets. IEEE Trans on IT,1992,38(2):617～643
[21]邰能灵,侯志俭.小波模糊神经网络在电力系统短期负荷预测中的应用.中国电机工程学报,2004,24(1):24～29
[22]张文哲,陈刚,吴迎霞.基于小波理论对负荷预测中不良数据的处理.重庆大学学报,2004,27(6):77～81
[23]SehankR,Abelson R R. Goals and Understanding[M],Erlbanum:Eksevier Science,1997,165～176
[24]Schank R. Dynmaic Memory:A Theory of Reminding and Learning in Computers and People[M],London:Cambridge University Press,1982
[25]Kolodner J. Maintaining organization in a dynamic long-term memory [J],Cognitive Science,1983,7(4):243～280
[26]Hennessy D,Hinkle D. Applying Case-based reasoning to autoclave loading[J],IEEE Expert,1992,7(5):21～26
[27]毛权,周济,余俊.基于实例原型的设计模型研究[J],高技术通讯,1995,71～76
[28]郭艳红,邓贵仕.基于事例的推理(CBR)研究综述.计算机工程与应用,2004,40(21):14
[29]陆汝铃.世纪之交的知识工程与知识科学.北京:清华大学出版社,2001
[30]赵登福,吴娟,刘昱,等.基于事例推理的短期负荷预测[J].西安交通大学学报,2003,37(6):608～611
[31]史忠植.知识发现.北京:清华大学出版社 2002:89～92
[32]Watoson l. Case-based reasoning is methodology not a technology [J]. Knowledge-based System,1999:12(5,6):303～308
[33]Riesbecd C K,Schank R C. Inside Case-Based Reasoning [M]. Hillsdale,New Jersey: Lawrence Erlbaum Associates Inc,1989
[34]Kalyan M G, Ai R M Empirical evaluation of retrieval in case-based reasoning systems using modified cosine matching function [J].IEEE Transactions on:Systems,Man,and Cybernetics:Systems and Humans,1997,9(5):601～612
[35]Henrique S H,Carlos E P,Reinaldo C S.Neural networks for short-term load forecasting:a review and evaluation[J].IEEE Transactions on Power Systems,2001,16(1):44～55
[36]PAL S,SIMON C.Foundations of Soft Case-based Reasoning.New York(NY, USA):A Wiley-Interscience Publication,2003.
[37]Bakirtzls A G,Petridls V,Klartzis S J,eta1.A neural network short term load forecasting model for the Greek power system [J]. IEEE Transactions on Power Systems,1996,11(2):858～863.
[38]谢宏,程浩忠,张国立,等.基于粗糙集理论建立短期电力负荷神经网络预测模型[J].中国电机工程学报,2003,23(11):1～4
[39]张文修,吴伟志,梁古业,等.粗糙集理论与方法[M].北京:科学出版社,2001.
[40]曾黄麟.粗集理论及其应用[M].重庆:重庆大学出版社,1998
[41]Pawlak Z . Rough Set theory and its Applications to Data Analysis[J].Cybernetics and systems,1998:(29):661～688
[42]王国胤.Rough 集理论与知识获取[M].西安:西安交通大学出版社,2001:208～210
[43]Radzikowska A M, Kerre E E. A comparative study of fuzzy rough sets[J].Fuzzy Sets and Systems,2002,126(1):137～l56
[44]Dubois D, Prade H. Rough fuzzy sets and fuzzy rough sets [J].International Journal of General Systems,1990,17 (2):191～209
[45]Jensen R,Shen Q.Fuzzy-rough sets for descriptive dimensionality reduction[C].Proceedings of the 11th International Conference on Fuzzy Systems,USA,2002
[46]魏传锋,李运泽,王浚.改进的最近邻法在基于事例推理中的应用,系统仿真学报,2005,12(5):1045～1047
[47]Sun Wei,Jian Changlu,He Yujun.Application of Neural Network Model Combining Information entropy and Colony Clustering Theory for Short-Term Load Forecasting . Conference on Machine Learning and Cybernetics,2005, Vol. 8,No.13,pp.4645～4650
[48]王志征,余岳峰,姚国平.主成份分析法在电力负荷预测中的应用.电力需求侧管理.2003,5(3):21～24
[49]柳进,唐降龙.基于主成分分析 L-M 神经网络高峰负荷预测研究.继电器.2004,32(13):24～27
[50]Jiawei H,Micheline K. Data Mining:Concepts and Techniques. Simon Fraser University:Morgan Kaufmann Publishers,2000
[51]Kandil M S,El-Debeiky S M ,Hasanien N E.Long-term Load Forecasting for Fast Developing Utility Using a Knowledge-based Expert System.IEEE Trans on Power Systems,2002,17(2):49l～496
[52]Hirota K,Pedrycz W.Fuzzy Computing for Data Mining.Proceedings of the IEEE,l999,87(9):l575～l600
[53]Breiman L,Friedman J H,Olshen R A,eta1.Classification and Regression Trees.New York:Chapman & Hall,l984