短期电力负荷预测方法研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
电力系统的正常运行是关系到国计民生的头等问题,如何保证电力系统正常运行时现在及将来科研工作的主要课题。而负荷预测为电力系统正常运行提供了可靠的依据,尤其短期电力负荷预测具有重要的意义。负荷预测精度的好坏影响整个国家经济、社会、生活的正常进行。
     本文叙述了电力系统负荷预测的背景和研究意义,以及负荷预测的概念、特点等,并叙述了几种常见的预测评价指标。阐述了电力负荷的种类和规律。在此基础上,分析了指数平滑法、灰色预测模型和人工神经网络模型三种单一短期电力负荷预测方法。文中接着论述了组合预测方法的概念、特点及数学模型。叙述了多种固定权组合预测方法:等权平均组合预测、基于误差平法和最小的思想来确定权重系数以及它们的计算公式及步骤。重点分析了变权系数组合预测模型中的模糊变权系数组合模型方法及神经网络组合预测方法。为了克服了BP神经网络缺点,本文依次采用了基于小波神经网络和粒子群优化的小波神经网络两种组合预测方法,并引入模糊聚类分析的方法筛选小波神经网络的训练样本,使小波神经网络的训练更具有针对性。通过仿真验证了这两种方法预测精度比BP神经网络都有了改善,并且粒子群优化算法改善了小波神经网络预测精度。
     叙述了一种新的递归神经网络即回声状态网络的结构特点、学习过程及预测方法。并在已有对电力负荷混沌性分析的基础上,通过电力负荷时间序列相空间重构,提出了一种基于回声状态网络的短期电力负荷预测方法,通过实验仿真验证了这种方法在电力负荷预测中的有效性。并建立了一种短期负荷的回声状态网络组合预测模型,仿真验证了该方法的有效性。
The normal operation of the power system is related to the national economy, the main topic of how to ensure the normal operation of the power system current and future research work.And power system load forecasting in order to ensure the normal operation of the power system, provides a reliable basis, especially short-term power load forecasting.The prediction accuracy of electric power system of good or bad influences electric power system and its economic value and operation safety of power supply quality. At present, there are many load forecasting model, both single model and combination prediction model.
     This paper describes the research meaning and background of short-term power system load forecasting and the concepts and characteristics of the load forecasting, analyzing the composition, characteristics and regularity of the power load, and citing several forecast evaluation index. On this basis, the method of time series and artificial neural network model of short-term load forecasting method is analyzed. Time series is divided into stationary time series and non-stationary time series, accordingly, the different specific time series forecasting method are proposed, and the steps of time series models is pointed out. The paper discusses the concept, features and mathematical model of the combination forecasting method. Several common fixed combination of prediction methods are pointed out, such as equally weighted average combination of forecasts, determining the weight coefficients based on the error level and the formula and steps are described. The combined model of fuzzy variable weight coefficient method and neural network combination forecasting method of variable weight coefficient prediction model are analyzed. In order to overcome the shortcomings of the BP neural network, two prediction methods are proposed on the base of and PSO(particle swarm optimization)-WNN(wavelet neural network).And fuzzy clustering analysis method is introduced to filer the training samples of wavelet neural network. The prediction accuracy of those two methods has been improved, and particle swarm optimization is very important.
     The structural characteristics network learning process, and prediction methods of the echo state networks in a new recurrent neural are described. In the light of chaos analysis of the power load,and on the basis of the power load phase space reconstruction, a short-term load forecasting method based on echo state networks is proposed. The effectiveness of this method in power load forecasting is showed through experimental simulation. And a short-term load combinations prediction model based on echo state network is proposed. Simulation results shows that this model is very good.
引文
[1]牛东晓,曹树华,赵磊.电力负荷预测技术及其应用[M].中国电力出版社,1998.
    [2]刘晨辉.电力系统负荷预报理论与方法[M].哈尔滨工业大学出版社,1987.
    [3]康重庆,夏清,张伯明.电力系统负荷预测研究综述与发展方向的探讨[J].电力系统自化,2004,25(17):1-11.
    [4]张绍和,黄东惠,杜文广,等.平滑系数优化的季节性指数平滑法[J].太原工业大学报,1989,20(2):71-75.
    [5]何大四,张旭.改进的季节性指数平滑法预测空调负荷分析[J].同济大学学报,2005,33(12):1672-1676.
    [6]ShyhJier Huang.Short-Term Load Forecasting Via ARMA Model Identification Includin-g NonGaussian Process Consideratinos[J].IEEE Tmasactions on Power Sysetms,2003,18 (2):673-679.
    [7]荣雅君,殷桂梁,陈保国.电力系统中长期负荷预测的灰色动态模型研究[J].东北重型机械学院学报.1997,21(4):314-317.
    [8]张洪明,廖培鸿,何建中.电网规划的灰色系统方法[J].电网技术,1995,19(12):19-23.
    [9]孙辉,姜梅,陈继侠.灰色理论在中长期电力负荷预测中的应用研究[J].东北电力学院学报.1997,17(2):18-23
    [10]陈志业,牛晓东,张英怀,等.电网短期电力负荷预测系统的研究[J].中国电机工程学报,1995,15(1):30-35.
    [11]袁明友,肖先勇,杨洪耕,等.基于灰色理论的供电系统负荷中长期预测模型及其应用[J].四川大学学报(工程科学版),2002,34(4):121-123.
    [12]张俊芳,吴伊昂,吴军基.基于灰色理论负荷预测的应用研究[J].电力自动化设备,2004,24(5):24-26.
    [13]张伏生,汪鸿.基于最小二乘回归分析的短期负荷预测[J].电网技术,2003,27(3):27-40.
    [14]K.-L.Ho,Y-Y.Hsu,C-F.Chen.Short term load forecasting of a Taiwneese Power System using a knowledge based expert sysetm[J],IEEE Transactions on Power Sysetms,1990,. 5(4):1214-1221.
    [15]严华,吴捷,杨苹.智能化的短期负荷预测系统[J].电力自动化设备,2000,20(2):7-10.
    [16]Park DC,EI-Sharkawi MA,Marks RJ,et al. Electric Load Forecasting Using an Artificial Network[J]. IEEE Trans on Power Systems,1991,6(2):422-449.
    [17]Vermaak J,Botha EC.Recurrent Neural Networks for Short-term Load Forecasting[J].IEEE Trans on Power Systems,1998,13(1):126-132.
    [18]林开英,俞集辉.神经网络短期负荷预测中的数据分析[J].重庆大学学报,2002,25(9):5-7.
    [19]Lamedica R,Prudenzi A, Sforna M. A Network Based Technique for Short-Term Forecasting of Anomalous Load Periods[J]. IEEE Trans on Power Systems,1996,11(4):1749-1756.
    [20]刘玲,严登俊,龚灯才,等.基于粒子群模糊神经网络的短期电力负荷预测[J].电力系统及 其自动化学报,2006,18(3):47-50.
    [21]傅忠云.粒子群优化BP算法在电力系统短期负荷预测中的应用[J].重庆工学院学报(自然科学版),2007,21(10):93-96.
    [22]张昊,吴捷,郁滨.电力负荷的模糊预测方法[J].电力系统自动化,1997,21(12):11-20.
    [23]顾洁.电力系统中长期负荷预测的模糊算法[J].上海交通大学学报,2002,36(2):255-258.
    [24]郁滨,张昊,吴捷,等.自适应模糊系统理论在负荷预测中的应用研究[J].控制与决策,1995,14(3):223-228.
    [25]冯丽,邱家驹.基于模糊多目标遗传优化算法的节假日电力负荷预测[J].中国电机工程学报,2005,25(10):29-34.
    [26]冉启文,单永正,王骐,等.电力系统短期负荷预报的小波—神经网络-PARIMA方法[J].中国电机工程学报,2003,23(3):38-42.
    [27]杨延西,刘丁.基于小波变换和最小二乘支持向量机的短期电力负荷预测[J].电网技术,2005,29(13):60-64.
    [28]姚李孝,刘学琴.基于小波分析的月度负荷组合预测[J].电网技术,2007,31(19):65-68.
    [29]张大海,江世芳,毕研秋,等.基于小波神经网络的电力负荷预测方法[J].电力自动化设备(8):29-32.
    [30]张步涵,陆俭.一种基于小波神经元网络的短期负荷预测方法[J].电网技术,2004,28(7):15-18.
    [31]张涛,赵登福,周琳,等.基于RBF神经网络和专家系统的短期负荷预测方法[J].西安交通大学学报,2001,35(4):331-334.
    [32]吕志来,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.
    [33]赖晓平,周鸿兴,云昌钦.混合模型神经网络在短期负荷预测中的应用[J].控制理论与应用,2000,17(1):69-72.
    [34]谢开贵,李春燕,周家启.基于神经网络的负荷组合预测模型研究[J].中国电机工程学报,2002,22(7):85-89.
    [35]吉培荣,黄巍松,胡翔勇.灰色预测模型特性的研究[J].系统工程理论与实践,2001,9:105-108.
    [36]Park DC,et al.Electric load forecasting using artificial neural networks [J].IEEE Transaction on PWRS.1991,6(2):648-655,
    [37]Peng TM,et al.Advancement in the application of neural networks for short-term load forecasting[J].IEEE PES 1991 Summer Meeting,PWRS.
    [38]杜莉,张建军.神经网络在电力负荷预测中的应用研究[J].计算机仿真,2011,28(10):297-300.
    [39]李智勇,童调生,张帆,等.神经网络并行进化设计及其在短期电力负荷预测中的应用[J].仪器仪表学报,2005,26(1):88-92.
    [40]彭显刚,胡松峰,吕大勇.基于RBF神经网络的短期负荷预测方法综述[J].电力系统保护与控制,2011,39(17):144-148.
    [41]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.
    [42]陆宁,周建中,何耀耀.粒子群优化的神经网络模型在短期负荷预测中的应用[J].电力系统保护与控制,2010,38(12):65-68.
    [43]郭伟伟,刘家学,马云龙,等.基于改进RBF网络算法的电力系统短期负荷预测[J].电力系统保护与控制,2008,36(23):45-48.
    [44]李蔚,盛德仁,陈坚红,等.双重BP神经网络组合模型在实时数据预测中的应用[J].中国电机工程学报,2007,27(17):94-97.
    [45]牛东晓,邢棉,谢宏.短期电力负荷预测的小波神经元网络模型的研究[J].电网技术,1999,23(4):21-24.
    [46]向峥嵘,王学平.基于小波-神经网络的电力系统短期负荷预测[J].系统仿真学报,2008,,20(18):5018-5020.
    [47]张大海,江世芳,毕研秋,等.基于小波神经网络的电力负荷预测方法[J].电力自动化设备,2003,23(8):29-32.
    [48]陈有根,危韧勇,钟雪平小波神经网络在短期电力负荷预测中的应用[J].中南工业大学学报(自然科学版),2003,34(4):402-405.
    [49]张智晟,段晓燕,李伟婕,等.优化动态递归小波神经网络短期负荷预测模型[J].电力系统及其自动化学报,2009,21(5):30-35.
    [50]孙广强.中长期电力负荷组合预测模型与方法的研究[D].硕士学位论文,长沙,湖南大学,2010.
    [51]文新辉,牛明洁.一种新的基于神经网络的非线性组合预测方法[J].系统工程理论与实践,1994,12:66-72.
    [52]林锦顺,姚俭.基于BP神经网络的组合预测及在电力负荷的应用[J].上海理工大学学报,2005,27(5):451-455.
    [53]高新波.模糊聚类分析及其应用[M].西安:西安电子科技大学出版社,2005.
    [54]伊瑞.电力负荷预测中的数学方法及应用研究[J].硕士学位论文,长沙,湖南大学,2003.
    [55]刘双,杨丽徙,王志刚,等.基于Matlab神经网络工具箱的电力负荷组合预测模型[J].电力自动化设备,2003,23(3):59-61.
    [56]权先璋,蒋传文,张勇传.电力负荷的混沌预测方法[J].华中理工大学学报,2000,28(7):92-94.
    [57]李天云,刘自发.电力负荷的混沌特性及预测[J].中国电机工程学报,2000,20(11):36-40.
    [58]Packard N H,Crutchfield J P,Farmer J D, et al.Geometry from a time series[J].Physical Review Letters.1980,45(9):712-716.
    [59]Takens F.Detecting strange attractors in turbulence.In:Dynamical Systems and Turbulen ce[J].Berlin:Springer-Verlag,1981:366-381.
    [60]Kugiumtzis D.State space reconstruction parameters in the analysis of chaotic time series the role of the time window length[J].Physica D:Nonlinear Phenomena.1996,95(1):13-28.
    [61]AlbanoA M.SVD and Grassberger-Procaccia algorithm[J].Phy Rev:A,1988,38(20):3017-3026.
    [62]韩敏,王亚楠.基于储备池主要成分分析的多元时间序列预测研究[J].控制与决 策,2009,24(10):1526-1530.
    [63]彭宇,王建民,彭喜元.基于回声状态网络的时间序列预测方法研究[J].电子学报,2010,38(2A):148-154.
    [64]H Jaeger.The echo state approach to analyzing and training recurrent neural networks [R].GMD Report 148,GMD-German National Research Institute for Computer Science, 2001.
    [65]韩敏,史志伟,郭伟.储备池状态空间重构与混沌时间序列预测[J].物理学报,2007,56(1):43-49.
    [66]张志明,程惠涛,徐鸿,等.神经网络组合预报模型及其在汽轮发电机组状态检修中的应用[J].中国电机工程学报,2003,23(9):204-206.
NGLC 2004-2010.National Geological Library of China All Rights Reserved.
Add:29 Xueyuan Rd,Haidian District,Beijing,PRC. Mail Add: 8324 mailbox 100083
For exchange or info please contact us via email.