一种短期电力负荷预测方法
|
摘要
针对短期电力负荷预测中影响因素多、变化随机、非线性等特点,提出一种相似日的优化BP神经网络短期电力负荷预测方法。考虑到短期负荷波动的影响因素较多,相似日的选取综合了气象因素、日期因素和时间距离因素。同时,在负荷预测中常用的BP神经网络预测方法的基础上,引入遗传算法对BP神经网络算法的初始权值和阈值寻优进行改进。仿真表明优化BP神经网络算法与相似日结合的方法预测时在稳定性和精确度方面得到较大的提高。
According to plenty of influence, random changing and nonlinear characteristics of short-term power load forecasting, this paper proposed an optimized back propagation neural networks algorithms based on similar day. Due to there are many influence factors affect the power load variation, the similar day method synthesize meteorological factors, the data factors and time interval factors. The paper introducing genetic algorithms to improve the BP neural networks by optimizing the initial weights and threshold values. The simulation result shows that the combination of optimized back propagation neural networks algorithms and similar day method used to power load prediction get a large enhancement in terms of precision and stability.
According to plenty of influence, random changing and nonlinear characteristics of short-term power load forecasting, this paper proposed an optimized back propagation neural networks algorithms based on similar day. Due to there are many influence factors affect the power load variation, the similar day method synthesize meteorological factors, the data factors and time interval factors. The paper introducing genetic algorithms to improve the BP neural networks by optimizing the initial weights and threshold values. The simulation result shows that the combination of optimized back propagation neural networks algorithms and similar day method used to power load prediction get a large enhancement in terms of precision and stability.
引文
[1]中国电力大数据发展白皮书[M].北京:中国电力出版社,2013.The white paper for the development of Chinese electricpower big data[M].Beijing:China Electric Power Press,2013.
[2]廖旎焕,胡智宏,马莹莹,等.电力系统短期负荷预测方法综述[J].电力系统保护与控制,2011,39(1):147-152.LIAO Nihuan,HU Zhihong,MA Yingying,et al.Review of the short-term load forecasting methods of electric power system[J].Power System Protection and Control,2011,39(1):147-152.
[3]马明,孙璞玉,张焰,等.电力负荷优化组合及其在城网改造中的应用[J].电网与清洁能源,2014,30(8):37-42.MA Ming,SUN Puyu,ZHANG Yan,et al.Optimal combination of power loads and its application in urban power network renovation[J].Power System and Clean Energy,2014,30(8):37-42.
[4]赵宏伟,任震,黄雯莹.考虑周周期性的短期负荷预测[J].中国电机工程学报,1997,17(3):211-213.Zhao Hongwei,Ren Zhen,Huang Wenying.Short-term load forecasting considering weekly period based on PAR[J].Proceedings of the CSEE,1997,17(3):211-213.
[5]雷绍兰,孙才新,周湶,等.电力短期负荷的多变量时间序列线性回归预测方法研究[J].中国电机工程学报2006,26(2):25-29.Lei Shaolan,Sun Caixin,Zhou Quan,et al.The researchof local linear model of short-term electrical load onmultivariate time series[J].Proceedings of the CSEE,2006,26(2):25-29.
[6]牛成林,于希宁,李建强.专家系统在电力预测负荷中的应用[J].仪器仪表用户,2005,04:67-68.NIU C L,YU X N,LI J Q.The application of expert system in electric load forecasting[J].Chinese Journal of Scientific Instrument.2005,04:67-68.
[7]于海燕,张凤玲.基于模糊神经网络的电力负荷短期预测[J].电网技术,2007,03:68-72.YU H Y,ZHANG F L.Short-Term Load Forecasting Based on Fuzzy Neural Network[J].Power System Technology,2007,03:68-72.
[8]Y.Xu,P.Du.Researching about Short-Term Power Load Forecasting Based on Improved BP ANN Algorithm[J].First International Conference on Information Science and Engineering,2009,pp.4094-4097.
[9]Y.Mao,F.Yang and C.Wang,"Application of BP network to short-term power load forecasting considering weather factor,"2011 International Conference on Electric Information and Control Engineering,Wuhan,2011,pp.172-175.
[10]李海龙.考虑实时气象因素的电力系统短期负荷预测[D].华北电力大学,2015.LI H L.Short-term Load Forecasting of Power System Considering Real-Time Weather Factors[D].Beijing:North China Electric Power University,2015.
[11]Q.Mu,Y.Wu,X.Pan,L.Huang,X.Li.Short-term Load Forecasting Using Improved Similar Days Method[J].AsiaPacific Power and Energy Engineering Conference.2010,pp.1-4.
[12]A.h.Jiang,N.x.Liang.Short-term load forecasting using support vector machine optimized by the improved fruit fly algorithm and the similar day method[J].China International Conference on Electricity Distribution(CICED).2014,pp.1466-1471.
[13]王欣,刘俊杰.基于贝叶斯定理的支持向量机短期负荷预测[J].新型工业化,2014,4(12):20-24.WANG Xin,LIU Junjie.Short-term load forecasting based on Bayes'theorem Support vector machine[J].The Journal of New Industrialization,2014,4(12):20-24.
[14]任金霞,游鑫,余志武.电力系统短期电力负荷预测仿真研究[J].计算机仿真,2015,05:132-135+149.REN J X,YOU X,YU ZHI W.Short-Term Load Forecasting Based on DFNN[J].Computer Simulation,2015,05:132-135+149.
[15]陈皓,崔杜武.基于族群进化计算的多项式回归电力负荷预测[J].软件,2011,05:34-37.CEHN H,CUI D W.Ethnic Group Evolutionary Computation Based Polynomial Regression Forecast for Electricity Load[J].Software,2011,05:34-37.
[16]沈沉,秦建,盛万兴,方恒福.基于小波聚类的配变短期负荷预测方法研究[J].电网技术,2016,02:521-526.
[17]Y.He,Q.Xu.Short-Term Power Load Forecasting Based on Self-Adapting PSO-BP Neural Network Model[J].Fourth International Conference on Computational and Information Sciences,2012,pp.1096-1099.
[18]王沥,邝育军.一种基于蚁群算法的BP神经网络优化方法研究[J].新型工业化,2012,2(4):8-15.WANG Li,KUANG Yujun.Research of BP neural network optimizing method based on Ant Colony Algorithm[J].The Journal of New Industrialization,2012,2(4):8-15.
[19]王宏涛,孙剑伟.基于BP神经网络和SVM的分类方法研究[J].软件,2015,36(11):96-99.WANG Hong-tao,SUN Jian-Wei.Research in the Classification Method Based on BP Network and SVM[J].Computer Engineering&Software,2015,36(11):96-99.
[20]安大海,蒋砚军.基于BP神经网络的人脸识别系统[J].软件,2015,36(12):76-79.AN Da-hai,JIANG Yan-jun.A Face Rceognition System Based on BP Neura;Network[J].Computer Engineering&Software.2015,36(12):76-79
[21]王沥,邝育军.一种基于蚁群算法的BP神经网络优化方法研究[J].新型工业化,2012,2(4):8-15.WANG Li,KUANG Yujun.Research of BP neural network optimizing method based on Ant Colony Algorithm[J].The Journal of New Industrialization,2012,2(4):8-15.
[22]Kenneth D.Kuhn.A methodology for identifying similar days in air traffic flow management initiative planning[J].Transportation Research Part C,2016,69:1-15.
[2]廖旎焕,胡智宏,马莹莹,等.电力系统短期负荷预测方法综述[J].电力系统保护与控制,2011,39(1):147-152.LIAO Nihuan,HU Zhihong,MA Yingying,et al.Review of the short-term load forecasting methods of electric power system[J].Power System Protection and Control,2011,39(1):147-152.
[3]马明,孙璞玉,张焰,等.电力负荷优化组合及其在城网改造中的应用[J].电网与清洁能源,2014,30(8):37-42.MA Ming,SUN Puyu,ZHANG Yan,et al.Optimal combination of power loads and its application in urban power network renovation[J].Power System and Clean Energy,2014,30(8):37-42.
[4]赵宏伟,任震,黄雯莹.考虑周周期性的短期负荷预测[J].中国电机工程学报,1997,17(3):211-213.Zhao Hongwei,Ren Zhen,Huang Wenying.Short-term load forecasting considering weekly period based on PAR[J].Proceedings of the CSEE,1997,17(3):211-213.
[5]雷绍兰,孙才新,周湶,等.电力短期负荷的多变量时间序列线性回归预测方法研究[J].中国电机工程学报2006,26(2):25-29.Lei Shaolan,Sun Caixin,Zhou Quan,et al.The researchof local linear model of short-term electrical load onmultivariate time series[J].Proceedings of the CSEE,2006,26(2):25-29.
[6]牛成林,于希宁,李建强.专家系统在电力预测负荷中的应用[J].仪器仪表用户,2005,04:67-68.NIU C L,YU X N,LI J Q.The application of expert system in electric load forecasting[J].Chinese Journal of Scientific Instrument.2005,04:67-68.
[7]于海燕,张凤玲.基于模糊神经网络的电力负荷短期预测[J].电网技术,2007,03:68-72.YU H Y,ZHANG F L.Short-Term Load Forecasting Based on Fuzzy Neural Network[J].Power System Technology,2007,03:68-72.
[8]Y.Xu,P.Du.Researching about Short-Term Power Load Forecasting Based on Improved BP ANN Algorithm[J].First International Conference on Information Science and Engineering,2009,pp.4094-4097.
[9]Y.Mao,F.Yang and C.Wang,"Application of BP network to short-term power load forecasting considering weather factor,"2011 International Conference on Electric Information and Control Engineering,Wuhan,2011,pp.172-175.
[10]李海龙.考虑实时气象因素的电力系统短期负荷预测[D].华北电力大学,2015.LI H L.Short-term Load Forecasting of Power System Considering Real-Time Weather Factors[D].Beijing:North China Electric Power University,2015.
[11]Q.Mu,Y.Wu,X.Pan,L.Huang,X.Li.Short-term Load Forecasting Using Improved Similar Days Method[J].AsiaPacific Power and Energy Engineering Conference.2010,pp.1-4.
[12]A.h.Jiang,N.x.Liang.Short-term load forecasting using support vector machine optimized by the improved fruit fly algorithm and the similar day method[J].China International Conference on Electricity Distribution(CICED).2014,pp.1466-1471.
[13]王欣,刘俊杰.基于贝叶斯定理的支持向量机短期负荷预测[J].新型工业化,2014,4(12):20-24.WANG Xin,LIU Junjie.Short-term load forecasting based on Bayes'theorem Support vector machine[J].The Journal of New Industrialization,2014,4(12):20-24.
[14]任金霞,游鑫,余志武.电力系统短期电力负荷预测仿真研究[J].计算机仿真,2015,05:132-135+149.REN J X,YOU X,YU ZHI W.Short-Term Load Forecasting Based on DFNN[J].Computer Simulation,2015,05:132-135+149.
[15]陈皓,崔杜武.基于族群进化计算的多项式回归电力负荷预测[J].软件,2011,05:34-37.CEHN H,CUI D W.Ethnic Group Evolutionary Computation Based Polynomial Regression Forecast for Electricity Load[J].Software,2011,05:34-37.
[16]沈沉,秦建,盛万兴,方恒福.基于小波聚类的配变短期负荷预测方法研究[J].电网技术,2016,02:521-526.
[17]Y.He,Q.Xu.Short-Term Power Load Forecasting Based on Self-Adapting PSO-BP Neural Network Model[J].Fourth International Conference on Computational and Information Sciences,2012,pp.1096-1099.
[18]王沥,邝育军.一种基于蚁群算法的BP神经网络优化方法研究[J].新型工业化,2012,2(4):8-15.WANG Li,KUANG Yujun.Research of BP neural network optimizing method based on Ant Colony Algorithm[J].The Journal of New Industrialization,2012,2(4):8-15.
[19]王宏涛,孙剑伟.基于BP神经网络和SVM的分类方法研究[J].软件,2015,36(11):96-99.WANG Hong-tao,SUN Jian-Wei.Research in the Classification Method Based on BP Network and SVM[J].Computer Engineering&Software,2015,36(11):96-99.
[20]安大海,蒋砚军.基于BP神经网络的人脸识别系统[J].软件,2015,36(12):76-79.AN Da-hai,JIANG Yan-jun.A Face Rceognition System Based on BP Neura;Network[J].Computer Engineering&Software.2015,36(12):76-79
[21]王沥,邝育军.一种基于蚁群算法的BP神经网络优化方法研究[J].新型工业化,2012,2(4):8-15.WANG Li,KUANG Yujun.Research of BP neural network optimizing method based on Ant Colony Algorithm[J].The Journal of New Industrialization,2012,2(4):8-15.
[22]Kenneth D.Kuhn.A methodology for identifying similar days in air traffic flow management initiative planning[J].Transportation Research Part C,2016,69:1-15.