肖勇;杨劲锋;马千里;阙华坤;王家兵;秦州;

• 1:广东电网公司电力科学研究院
• 2:华南理工大学计算机科学与工程学院

摘要(Abstract)：

电力负荷预测特别是实时电力负荷预测是电力系统规划的重要组成部分,也是电力系统可靠、经济运行的基础。针对回声状态神经网络在实时负荷预测中存在易受噪声影响、鲁棒性不强、不稳定的问题,提出了将基于模块化回声状态网络的方法应用于实时电力负荷预测中。根据输入时序数据所引起的储蓄池内部状态的相似性对储蓄池空间进行模块划分,将此高维空间划分为多个子模块,针对每一个模块训练一个读出器,最后把各个模块的输出结果集成输出。利用模块化回声状态网络模型,对大客户的实时负荷数据进行预测,并与几种短期负荷预测模型进行精度和稳定性的对比实验,结果表明,模块化回声状态网络在实时负荷预测中既提高了预测精度,又增强了预测的稳定性和泛化性能。

关键词(KeyWords)： 实时负荷预测;模块化回声状态网络;时间序列

Abstract:

Keywords:

基金项目(Foundation): 高等学校博士学科点专项科研基金(20110172120027);; 广东省自然科学基金资助项目(S2012010009961)~~

作者(Author): 肖勇;杨劲锋;马千里;阙华坤;王家兵;秦州;

Email:

DOI: 10.13335/j.1000-3673.pst.2015.03.033

参考文献(References)：

• [1]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(in Chinese).
• [2]刘国徽,刘小满,余雪芳,等.基于ARIMA和LS-SVM组合模型的短期负荷预测[J].广东电力,2010,23(11):14-17.Liu Guohui,Liu Xiaoman,Yu Xuefang,et al.Short-term load forecasting based of ARIMA-LSVM Model[J].Guangdong Electric Power,2010,23(11):14-17(in Chinese).
• [3]梁志珊,王丽敏,付大鹏,等.基于Lyapunov指数的电力系统短期负荷预测[J].中国电机工程学报,1998,18(5):368-371,376.Liang Zhishan,Wang Liming,Fu Da Peng,et al.Short-time load forecasting based on the maximum lyapunov exponent[J].Proceedings of the CSEE,1998,18(5):368-371,376(in Chinese).
• [4]何洋,邹波,李文启,等.基于混沌理论的电力系统短期负荷预测的局域模型[J].华北电力大学学报(自然科学版),2013,40(4):43-50.He Yang,Zou Bo,Li Wenqi,et al.A chaos theory based local model for short-term load forecasting[J].Journal of North China Electric Power University(Natural Science Edition),2013,40(4):43-50(in Chinese).
• [5]祖哲,毕贵红,刘力.基于混沌理论的电力系统短期负荷预测模型研究[C]//2012 International Conference on Electronic Information and Electrical Engineering.Changsha,Hunan,China:Atlantis Press,2012:904-911.
• [6]陈刚,周杰,张雪君,等.基于BP与RBF级联神经网络的日负荷预测[J].电网技术,2009,33(12):101-105.Chen Gang,Zhou Jie,Zhang Xuejun,et al.A daily load forecasting methods based on cascaded back propagation and radial basis function neural networks[J].Power System Technology,2009,33(12):101-105(in Chinese).
• [7]张平,潘学萍,薛文超.基于小波分解模糊灰色聚类和BP神经网络的短期负荷预测[J].电力自动化设备,2012,32(11):121-125,141.Zhang Ping,Pan Xueming,Xue Wenchao.Short-term load forecasting based on wavelet decomposition,fuzzy gray correlation clustering and BP neural network[J].Electric Power Automation Equipment,2012,32(11):121-1125,141(in Chinese).
• [8]杨奎河,王宝树,赵玲玲.基于神经网络矫正的非线性短时负荷预测模型[J].系统工程与电子技术,2004,26(11):1710-1713.Yang Kuihe,Wang Baoshu,Zhao Lingling.Nonlinear short-term load forecasting model based on neural networks correction[J].Systems Engineering and Electronics,2004,26(11):1710-1713(in Chinese).
• [9]周建中,张亚超,李清清,等.基于动态自适应径向基函数网络的概率性短期负荷预测[J].电网技术,2010,34(3):37-41.Zhou Jianzhong,Zhang Yachao,Li Qingqing,et al.Probabilistic short-term load forecasting based on dynamic self-adaptive radial basis function network[J].Power System Technology,2010,34(3):37-41(in Chinese).
• [10]王孔森,盛戈皞,孙旭日,等.基于径向基神经网络的输电线路动态容量在线预测[J].电网技术,2013,37(6):1719-1725.Wang Kongsen,Sheng Gehao,Sun Xuri,et al.Online prediction of transmission dynamic line rating based on radial basis function neural network[J].Power System Technology,2013,37(6):1719-1725(in Chinese).
• [11]刘瑞叶,黄磊.基于动态神经网络的风电场输出功率预测[J].电力系统自动化,2012,36(11):19-22,37.Liu Ruiye,Wang Lei.Wind power forecasting based on dynamic neural network[J].Automation of Electric Systems,2012,36(11):19-22,37(in Chinese).
• [12]Du Juan.An improved TSK-Type dynamic fuzzy neural network approach for short-term load forecasting[J].Power System Technology,2010,34(4):69-75.
• [13]Jaeger H,Haas H.Harnessing nonlinearity:predicting chaotic systems and saving energy in wireless communication[J].Science,2004,304(5667):78-80.
• [14]Song Q S,Zhao X M,Feng Z,et al.Hourly electric load forecasting algorithm based on echo state neural network[C]//2011 23rd Chinese Control and Decision Conference.Mianyang,China:IEEE,2011:3893-3897.
• [15]嵇灵,牛东晓,吴焕苗.基于贝叶斯框架和回声状态网络的日最大负荷预测研究[J].电网技术,2012,36(11):82-86.Ji Ling,Niu Dongxiao,Wu Huanmiao.Daily peak load forecasting based on Bayesian framework and echo state network[J].Power System Technology,2012,36(11):82-86(in Chinese).
• [16]Deihimi A,Showkati H.Application of echo state networks in short-term electric load forecasting[J].Energy,2012,39(1):327-340.
• [17]Deihimi A,Orang O,Showkati H.Short-term electric load and temperature forecasting using wavelet echo state networks with neural reconstruction[J].Energy,2013,57(1):382-401.
• [18]Shi Z,Han M.Support vector echo-state machine for chaotic time-series prediction[J].IEEE Trans on Neural Networks,2007,18(2):359-372.
• [19]Ma Q L,Chen W B.Modular state space of echo state network[J].Neurocomputing,2013,122(25):406-417.
• [20]Takens F.Detecting strange attractors in turbulence[J].Lecture Notes in Math,1981,898(1):366-381.
• [21]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):43-50.Han Min,Shi Zhiwei,Guo Wei.Reservoir neural state reconstruction and chaotic time series prediction[J].Acta Physica Sinica,2007,56(1):43-50(in Chinese)
• [22]Sollich P,Krogh A.Learning with ensembles:how over-fitting can be useful[C]//1996 Advances in Neural Information Processing Systems.Cambridge,MA:MIT Press,1996:190-196.