基于EMD和高斯过程回归组合模型的短期电力负荷预测方法研究
|
摘要
电力短期负荷预测是电力系统运行和管理中的一个重要组成部分。提高其预测质量,对提高电力系统运行的安全性、经济性、可靠性以及供电质量均有积极作用。随着人工智能技术的不断发展,短期负荷预测的智能方法大量涌现,预测准确度得到一定程度的改善。但总体上看,短期负荷的准确预测仍是一个难题。如何在现有的方法上推陈出新,提高其预测精度,是研究人员面临的重点问题。
短期电力负荷是一个非线性、非平稳的随机过程,负荷的变化受到多种外界因素影响。本文首先对短期负荷的特点、构成及其相关影响因素进行了研究,并对现有的各种短期负荷预测分析方法进行了总结。在此基础上,尝试将基于机器学习的高斯过程回归理论引入短期负荷预测。针对短期负荷预测中负荷与影响因素之间的复杂非线性关系,充分考虑了历史负荷和气象因素的影响,将预测日前连续多日的历史最大负荷和预测日平均气温作为模型输入,建立了基于高斯过程回归的短期负荷预测模型,该模型具有参数少、参数寻优容易,易收敛等优点。
考虑到短期负荷是由不同频率的特征分量组成这一特点,将经验模态分解理论加入到短期负荷预测中的数据预处理环节,将短期负荷序列分解成若干周期分量和一个趋势分量,运用高斯过程回归理论对这些分量分别建模,最后通过重构得到预测结果。仿真结果表明,将经验模态分解和高斯过程回归理论应用于短期电力负荷组合预测是可行的,有着较高的预测准确度,能较好地反映负荷的变化趋势,并具有良好的自适应性。
Power short-term load forecasting is an important part of dispatch and operation for power system, which accuracy will directly affect the security, economical efficiency and quality of power systems. With the development of the artificial intelligence, many new methods and technologies of short-term load forecasting are emerged in large numbers, which raise a high requirement for short-term load forecasting. Therefore, how to improve the forecasting precision is the emphasis on the study of short-term load forecasting.
At first, the constituents, characteristics and influenced factors of the short-term load was analyzed in this paper. It indicated that the short-term load is a non-liner and a non-smooth process, the changes of load data are influenced by many factors. The relevance is most evident between average temperature and load data, so the paper takes the average temperature into account. Then summarized the methods recently, and firstly used Gaussian regression processes in the short-term load forecasting. As to the nonlinear relationship between load and the influencing factors, historical load data and meteorological factor were taking into account, and the maxima load data of last five day before predicting day and the predicting daily average temperature were used as the input data, then the short-term load forecasting model was built based on Gaussian regression processes. The proposed model has such advantages as few parameters, easy to optimize parameter, and fast convergence.
Short-term load of power systems can be considered as linear combination of sub-series characterized by different frequencies, so the Empirical Mode Decomposition (EMD) was used for pre-procession of short-term load forecasting data. From the composition of load data, based on EMD the load series is decomposed into different lots of stable series and a surplus component, then take Gaussian regression processes theory establish model, finally reconstructed the forecasted signals of the components and abstain the ultimate forecasting result. The simulation shows the accuracy of the proposed combined model is considerable, and it is feasible to introduce Gaussian regression processes to the electric power load forecasting field. The proposed method has high accuracy while the change trend of load can be well reflected.
短期电力负荷是一个非线性、非平稳的随机过程,负荷的变化受到多种外界因素影响。本文首先对短期负荷的特点、构成及其相关影响因素进行了研究,并对现有的各种短期负荷预测分析方法进行了总结。在此基础上,尝试将基于机器学习的高斯过程回归理论引入短期负荷预测。针对短期负荷预测中负荷与影响因素之间的复杂非线性关系,充分考虑了历史负荷和气象因素的影响,将预测日前连续多日的历史最大负荷和预测日平均气温作为模型输入,建立了基于高斯过程回归的短期负荷预测模型,该模型具有参数少、参数寻优容易,易收敛等优点。
考虑到短期负荷是由不同频率的特征分量组成这一特点,将经验模态分解理论加入到短期负荷预测中的数据预处理环节,将短期负荷序列分解成若干周期分量和一个趋势分量,运用高斯过程回归理论对这些分量分别建模,最后通过重构得到预测结果。仿真结果表明,将经验模态分解和高斯过程回归理论应用于短期电力负荷组合预测是可行的,有着较高的预测准确度,能较好地反映负荷的变化趋势,并具有良好的自适应性。
Power short-term load forecasting is an important part of dispatch and operation for power system, which accuracy will directly affect the security, economical efficiency and quality of power systems. With the development of the artificial intelligence, many new methods and technologies of short-term load forecasting are emerged in large numbers, which raise a high requirement for short-term load forecasting. Therefore, how to improve the forecasting precision is the emphasis on the study of short-term load forecasting.
At first, the constituents, characteristics and influenced factors of the short-term load was analyzed in this paper. It indicated that the short-term load is a non-liner and a non-smooth process, the changes of load data are influenced by many factors. The relevance is most evident between average temperature and load data, so the paper takes the average temperature into account. Then summarized the methods recently, and firstly used Gaussian regression processes in the short-term load forecasting. As to the nonlinear relationship between load and the influencing factors, historical load data and meteorological factor were taking into account, and the maxima load data of last five day before predicting day and the predicting daily average temperature were used as the input data, then the short-term load forecasting model was built based on Gaussian regression processes. The proposed model has such advantages as few parameters, easy to optimize parameter, and fast convergence.
Short-term load of power systems can be considered as linear combination of sub-series characterized by different frequencies, so the Empirical Mode Decomposition (EMD) was used for pre-procession of short-term load forecasting data. From the composition of load data, based on EMD the load series is decomposed into different lots of stable series and a surplus component, then take Gaussian regression processes theory establish model, finally reconstructed the forecasted signals of the components and abstain the ultimate forecasting result. The simulation shows the accuracy of the proposed combined model is considerable, and it is feasible to introduce Gaussian regression processes to the electric power load forecasting field. The proposed method has high accuracy while the change trend of load can be well reflected.
引文
[1]康重庆,夏清,刘梅.电力系统负荷预测.北京：中国电力出版社,2007
[2]雷绍兰,孙才新,周湶,等.一种多变量时间序列的短期负荷预测方法.电工技术学报,2005,20(4)：62-67
[3]李晓波,罗枚,冯凯.短期负荷预测神经网络方法比较.继电器,2007,35(6)：49-53
[4]谢宏,牛东晓,张国立,等.一种模糊模型的混合建模方法及其在短期负荷预测中的应用.中国电机工程学报,2005,25(8)：17-22
[5]李元诚,方廷健,于尔铿.短期负荷预测的支持向量机方法研究.中国电机工程学报,2003,23(6)：55-59
[6]卢建昌,王柳.基于时序分析的神经网络短期负荷预测研究.中国电力,2005,38(7)：11-14
[7]沈秀汶,吴耀武,熊信银.基于有偏最小最大回归的短期负荷预测.电力系统及其自动化学报,2007,19(4)：46-49
[8]曹安照,田丽.基于RBF神经网络的短期电力负荷预测.电子科技大学学报,2006,35(4)：507-509
[9]于希宁,牛成林,李建强.基于决策树和专家系统的短期电力负荷预测系统.华北电力大学学报,2005,32(5)：57-61
[10]陈志巧.基于模糊理论的电力负荷预测研究.山东科技大学学报(自然科学版),2006,25(2)：82-83
[11]牛东晓,贾建荣.改进GM(1,1)模型在电力负荷预测中的应用.电力科学与工程,2008,24(4)：28-30
[12]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
[13]郑永康,陈维荣,蒋刚,等.基于混沌理论的短期负荷局域多步预测法.电力系统及其自动化学报,2007,19(4)：76-79
[14]范新桥,霍利民,黄丽华,等.基于遗传程序设计方法的短期电力负荷预测.华北电力大学学报,2007,34(5)：49-52
[15]Taylor J W, Buizza R. Neural network load forecasting with weather ensemble predictions[J]. IEEE Transactions On Power Systems,2002,17(3):626—632.
[16]李明干,孙健利,刘沛.基于卡尔曼滤波的电力系统短期负荷预测.继电器,2004,32(4)：9-12
[17]MacKay D J C. Introduction to Gaussian Processes[R]. Cambridge, UK: Cambridge University,1998
[18]Rasmussen C E, Williams K I. Gaussian processes for machine learning[M]. Massachusetts:MIT Press,2006
[19]牛东晓,曹树华,卢建昌,赵磊.电力负荷预测技术及其应用.北京：中国电力出版社,2009
[20]查特菲尔德(Chatterfield).时间序列分析导论.北京：宇航出版社,1986：108～113
[21]Chao-Ming Huang, Chi-Jen Huang, Ming-Li Wang. A particle swarm optimization to Identifying the ARMAX model for short-term load forecasting Power Systems, IEEE Transaction on Vol.20,No.2,2005,pp.1126-1133
[22]Park Dong C, El-Sharkawi M.A, Marks Robert, etc. Electric load forecasting using an artificial neural network. IEEE Transactions on Power Systems, Vol.6, No.2.May 1991,442-449
[23]W.Charytoniuk, M.S.Chen. Neural Network Design for Short-Term Load Fore-casting. Conference on Electric Utility Deregulation and Restructuring and Power Technologies 2000,4-7 April 2000,554-561
[24]Kim Kwang-Ho, Park jong-Keun, Hwang Kab-Ju, etc. Implementation of hybrid short-term load forecasting system using artificial neural networks and fuzzy expert systems.IEEE Transactionson Power Systems, vol.10, no.3, Aug.1995,1534-1539
[25]K.-L.Ho,Y.-Y.Hsu,C.-F.Chen. Short Term load forecasting of a Taiwanese power system using a knowledge based expert system. IEEE Transactions on Power Systems, Vol.5,No.4,1990,1214-1221
[26]曾令生,张文生,伏样运,等.基于模糊识别与模糊聚类理论的短期负荷预测.电工技术学报,2002,17(5)：83—86
[27]邰能灵,侯志俭,李涛,等.基于小波分析的电力系统短期负荷预测方法.中国电机工程学报,2003,VoL.23(1)：45～50
[28]Bo-Juen Chen, Ming-Wei Chang, and Chih-Jen Lin. Load Forecasting Using Support Vector Machines:A Study on EUNITE Competition 2001. IEEE Transactions on Power Systems, Vol.19, No.4 Mar. 2004,pp.1821-1830
[29]Suykens. J.A.K.& Vandewalle.J. Least squares support vector machine classifiers. Neural Processing Letters,9,1999.pp.293-300
[30]Cristianini N, Shawe-Taylor J. An introduction to Support Vector Machines and other kernel based learning methods. Cambridge University Press,2000
[31]赵登福,王蒙,张讲社.基于支持向量机方法的短期负荷预测.中国工程电机学报,2002,22(4)：26—30
[32]穆钢,侯凯元,杨右虹,等.负荷预报中负荷规律性方法的研究.中国电机工程学报,2001,21(10)：96～101
[33]朱陶业,李应求,张颖,等.提高时间序列气象适应性的短期电力负荷预测算法.中国电机工程学报,2006,26(23)：14～19
[34]Hua-Xiang Zhang, Liang Zhang, Shang-Teng Huang. A Machine Learning Approach to Automated Negotiation, High Technology LettersIEEE Transaction on Vol.10, No.3,2004,61-65
[35]熊志化.高斯过程模型及其在工业过程观测量中的应用研究：[博士学位论文].上海：上海交通大学,2006
[36]熊志化,张继承,邵惠鹤.基于高斯过程的软测量建模.系统仿真学报,2005,17(4)：793—794,800
[37]苏国韶,宋咏春,燕柳斌.岩体爆破效应预测的一种新方法.岩石力学与工程学报,2007,7(26)：3510-3511
[38]Matthias Seeger. Gaussian process for machine learning. International Journal of Neural Systerms,2004,14(2):69—106
[39]王华忠.高斯过程及其在软测量建模中的应用.化工学报,2007,58(1)：2840—2845
[40]Huang N E, et al. The Empirical Node Decomposition and Hilbert Spectrum for Nonlinear and Non—Stationary Time Series Analysis. Proc R Soc Lond,1998.454(12):903-995
[41]胡桥,何正嘉,訾艳阳等.一种新的混合智能预测模型及其在故障诊断中的应用.西安交通大学学报,2005,39(9)：928-932
[42]Wu Z, Huang N E. A study of the characteristics of white noise using the empirical mode decomposition method. Process of the Royal Society of London,2003, A460:1597-1611
[43]孙艳争,黄炜,余波.基于EMD的非线性信号自适应分析.电子科技大学学报,2007,36(1)：24-26
[44]王秋生,段丹辉.经验模态分解的边界效应处理技术.计算机测量与控制,2006,14(12)：1673-1675
[45]祝志慧,孙云莲,季宇.基于EMD和SVM的短期负荷预测.高电压技术,2007,33(5)：118-121
[46]玄兆燕,杨公训.经验模态分解在大气时间序列预测中的应用.自动化学报,2008,34(1)：97-101
[47]卢晓亭,孙勇,笪良龙等.基于EMD和BP神经网络海水温度时间序列预测研究.海洋技术,2009,28(3)：79-82
[48]Zhang Xun, Lai K. A new approach for crude oil price analysis based on Empirical Mode Decomposition. Energy Economics,2008,30(3):905-918
[49]Ibrahim Moghram, Salfur Rahman. Analysis and Evaluation of Five Short-Term Load Forecasting Techniques. IEEE Transactions on Power System.1989, Vol.4(4):1484～1491
[50]张文哲,陈刚.电力市场下负荷预测综述.渝西学院学报(自然科学版),2003,2(3)：70-74
[2]雷绍兰,孙才新,周湶,等.一种多变量时间序列的短期负荷预测方法.电工技术学报,2005,20(4)：62-67
[3]李晓波,罗枚,冯凯.短期负荷预测神经网络方法比较.继电器,2007,35(6)：49-53
[4]谢宏,牛东晓,张国立,等.一种模糊模型的混合建模方法及其在短期负荷预测中的应用.中国电机工程学报,2005,25(8)：17-22
[5]李元诚,方廷健,于尔铿.短期负荷预测的支持向量机方法研究.中国电机工程学报,2003,23(6)：55-59
[6]卢建昌,王柳.基于时序分析的神经网络短期负荷预测研究.中国电力,2005,38(7)：11-14
[7]沈秀汶,吴耀武,熊信银.基于有偏最小最大回归的短期负荷预测.电力系统及其自动化学报,2007,19(4)：46-49
[8]曹安照,田丽.基于RBF神经网络的短期电力负荷预测.电子科技大学学报,2006,35(4)：507-509
[9]于希宁,牛成林,李建强.基于决策树和专家系统的短期电力负荷预测系统.华北电力大学学报,2005,32(5)：57-61
[10]陈志巧.基于模糊理论的电力负荷预测研究.山东科技大学学报(自然科学版),2006,25(2)：82-83
[11]牛东晓,贾建荣.改进GM(1,1)模型在电力负荷预测中的应用.电力科学与工程,2008,24(4)：28-30
[12]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
[13]郑永康,陈维荣,蒋刚,等.基于混沌理论的短期负荷局域多步预测法.电力系统及其自动化学报,2007,19(4)：76-79
[14]范新桥,霍利民,黄丽华,等.基于遗传程序设计方法的短期电力负荷预测.华北电力大学学报,2007,34(5)：49-52
[15]Taylor J W, Buizza R. Neural network load forecasting with weather ensemble predictions[J]. IEEE Transactions On Power Systems,2002,17(3):626—632.
[16]李明干,孙健利,刘沛.基于卡尔曼滤波的电力系统短期负荷预测.继电器,2004,32(4)：9-12
[17]MacKay D J C. Introduction to Gaussian Processes[R]. Cambridge, UK: Cambridge University,1998
[18]Rasmussen C E, Williams K I. Gaussian processes for machine learning[M]. Massachusetts:MIT Press,2006
[19]牛东晓,曹树华,卢建昌,赵磊.电力负荷预测技术及其应用.北京：中国电力出版社,2009
[20]查特菲尔德(Chatterfield).时间序列分析导论.北京：宇航出版社,1986：108～113
[21]Chao-Ming Huang, Chi-Jen Huang, Ming-Li Wang. A particle swarm optimization to Identifying the ARMAX model for short-term load forecasting Power Systems, IEEE Transaction on Vol.20,No.2,2005,pp.1126-1133
[22]Park Dong C, El-Sharkawi M.A, Marks Robert, etc. Electric load forecasting using an artificial neural network. IEEE Transactions on Power Systems, Vol.6, No.2.May 1991,442-449
[23]W.Charytoniuk, M.S.Chen. Neural Network Design for Short-Term Load Fore-casting. Conference on Electric Utility Deregulation and Restructuring and Power Technologies 2000,4-7 April 2000,554-561
[24]Kim Kwang-Ho, Park jong-Keun, Hwang Kab-Ju, etc. Implementation of hybrid short-term load forecasting system using artificial neural networks and fuzzy expert systems.IEEE Transactionson Power Systems, vol.10, no.3, Aug.1995,1534-1539
[25]K.-L.Ho,Y.-Y.Hsu,C.-F.Chen. Short Term load forecasting of a Taiwanese power system using a knowledge based expert system. IEEE Transactions on Power Systems, Vol.5,No.4,1990,1214-1221
[26]曾令生,张文生,伏样运,等.基于模糊识别与模糊聚类理论的短期负荷预测.电工技术学报,2002,17(5)：83—86
[27]邰能灵,侯志俭,李涛,等.基于小波分析的电力系统短期负荷预测方法.中国电机工程学报,2003,VoL.23(1)：45～50
[28]Bo-Juen Chen, Ming-Wei Chang, and Chih-Jen Lin. Load Forecasting Using Support Vector Machines:A Study on EUNITE Competition 2001. IEEE Transactions on Power Systems, Vol.19, No.4 Mar. 2004,pp.1821-1830
[29]Suykens. J.A.K.& Vandewalle.J. Least squares support vector machine classifiers. Neural Processing Letters,9,1999.pp.293-300
[30]Cristianini N, Shawe-Taylor J. An introduction to Support Vector Machines and other kernel based learning methods. Cambridge University Press,2000
[31]赵登福,王蒙,张讲社.基于支持向量机方法的短期负荷预测.中国工程电机学报,2002,22(4)：26—30
[32]穆钢,侯凯元,杨右虹,等.负荷预报中负荷规律性方法的研究.中国电机工程学报,2001,21(10)：96～101
[33]朱陶业,李应求,张颖,等.提高时间序列气象适应性的短期电力负荷预测算法.中国电机工程学报,2006,26(23)：14～19
[34]Hua-Xiang Zhang, Liang Zhang, Shang-Teng Huang. A Machine Learning Approach to Automated Negotiation, High Technology LettersIEEE Transaction on Vol.10, No.3,2004,61-65
[35]熊志化.高斯过程模型及其在工业过程观测量中的应用研究：[博士学位论文].上海：上海交通大学,2006
[36]熊志化,张继承,邵惠鹤.基于高斯过程的软测量建模.系统仿真学报,2005,17(4)：793—794,800
[37]苏国韶,宋咏春,燕柳斌.岩体爆破效应预测的一种新方法.岩石力学与工程学报,2007,7(26)：3510-3511
[38]Matthias Seeger. Gaussian process for machine learning. International Journal of Neural Systerms,2004,14(2):69—106
[39]王华忠.高斯过程及其在软测量建模中的应用.化工学报,2007,58(1)：2840—2845
[40]Huang N E, et al. The Empirical Node Decomposition and Hilbert Spectrum for Nonlinear and Non—Stationary Time Series Analysis. Proc R Soc Lond,1998.454(12):903-995
[41]胡桥,何正嘉,訾艳阳等.一种新的混合智能预测模型及其在故障诊断中的应用.西安交通大学学报,2005,39(9)：928-932
[42]Wu Z, Huang N E. A study of the characteristics of white noise using the empirical mode decomposition method. Process of the Royal Society of London,2003, A460:1597-1611
[43]孙艳争,黄炜,余波.基于EMD的非线性信号自适应分析.电子科技大学学报,2007,36(1)：24-26
[44]王秋生,段丹辉.经验模态分解的边界效应处理技术.计算机测量与控制,2006,14(12)：1673-1675
[45]祝志慧,孙云莲,季宇.基于EMD和SVM的短期负荷预测.高电压技术,2007,33(5)：118-121
[46]玄兆燕,杨公训.经验模态分解在大气时间序列预测中的应用.自动化学报,2008,34(1)：97-101
[47]卢晓亭,孙勇,笪良龙等.基于EMD和BP神经网络海水温度时间序列预测研究.海洋技术,2009,28(3)：79-82
[48]Zhang Xun, Lai K. A new approach for crude oil price analysis based on Empirical Mode Decomposition. Energy Economics,2008,30(3):905-918
[49]Ibrahim Moghram, Salfur Rahman. Analysis and Evaluation of Five Short-Term Load Forecasting Techniques. IEEE Transactions on Power System.1989, Vol.4(4):1484～1491
[50]张文哲,陈刚.电力市场下负荷预测综述.渝西学院学报(自然科学版),2003,2(3)：70-74