梁智;孙国强;李虎成;卫志农;臧海祥;周亦洲;陈霜;

• 1:河海大学能源与电气学院
• 2:国网江苏省电力公司电力科学研究院

摘要(Abstract)：

为提高短期负荷预测精度,采用变分模态分解(variational mode decomposition,VMD)技术将原始历史负荷序列分解为一系列特征互异的模态函数,对每个模态函数进行特征分析并分别建立负荷预测模型。电力系统负荷预测建模过程中,选取有效的输入变量是提高预测精度技术措施之一,该文采用互信息度量影响因素与输出变量间的相关性,可选取出对负荷影响较大的输入变量集合。传统的神经网络负荷预测模型难以训练多层网络,从而影响其预测精度。而深度信念网络(deep belief network,DBN)采用非监督贪心逐层训练算法构成多隐含层感知器结构,在回归预测分析中展现出优良的性能,已成为深度学习领域研究热点。因此,该文借助DBN算法对每个模态函数建立预测模型,提高了预测精度。由于DBN网络权值的随机初始化,使得目标函数在学习训练过程中容易陷入局部最优,采用改进粒子群算法优化网络权值,增强了DBN预测性能。最后,算例测试表明该文模型的有效性。

关键词(KeyWords)： 短期负荷预测;变分模态分解;输入变量选择;互信息;粒子群算法;优化深度信念网络

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金项目(51507052);; 江苏省电力公司科技项目《大规模用户与主动配电网的双向友好互动技术研究》资助项目(J2016015);; 江苏省智能电网技术与装备重点实验室课题资助~~

作者(Author): 梁智;孙国强;李虎成;卫志农;臧海祥;周亦洲;陈霜;

Email:

DOI: 10.13335/j.1000-3673.pst.2017.0937

参考文献(References)：

• [1]Hossein V A,Yousefi M M R,Araabi B N,et al.Combination of singular spectrum analysis and autoregressive model for short term load forecasting[C]//2007 IEEE Lausanne POWERTECH.Lausanne,Switzerland:Power and Electronics Society,2007:1090-1093.
• [2]万昆,柳瑞禹.区间时间序列向量自回归模型在短期电力负荷预测中的应用[J].电网技术,2012,36(11):77-81.Wan Kun,Liu Ruiyu.Application of interval time-series vector autoregressive model in short-term load forecasting[J].Power System Technology,2012,36(11):77-81(in Chinese).
• [3]李妮,江岳春,黄珊,等.基于累积式自回归动平均传递函数模型的短期负荷预测[J].电网技术,2009,33(8):93-97.Li Ni,Jiang Yuechun,Huang Shan,et al.Short-term load forecasting based on ARIMA transfer function model[J].Power System Technology,2009,33(8):93-97(in Chinese).
• [4]Guan C,Luh P B,Michel L D,et al.Hybrid Kalman filters for very short-term load forecasting and prediction interval estimation[J].IEEE Transactions on Power Systems,2013,28(4):3806-3817.
• [5]Azadeh A,Ghaderi S F,Sheikhalishahi M,et al.Optimization of short load forecasting in electricity market of Iran using artificial neural networks[J].Optimization and Engineering,2014,15(2):485-508.
• [6]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).
• [7]Li P,Li Y,Xiong Q,et al.Application of a hybrid quantized Elman neural network in short-term load forecasting[J].International Journal of Electrical Power&Energy Systems,2014,55(2):749-759.
• [8]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).
• [9]谢宏,魏江平,刘鹤立.短期负荷预测中支持向量机模型的参数选取和优化方法[J].中国电机工程学报,2006,26(22):17-22.Xie Hong,Wei Jiangping,Liu Heli.Parameter selection and optimization method of SVM model for short-term load forecasting[J].Proceedings of the CSEE,2006,26(22):17-22(in Chinese).
• [10]李元诚,方廷健,于尔铿,等.短期负荷预测的支持向量机方法研究[J].中国电机工程学报,2003,23(6):55-59.Li Yuancheng,Fang Tingjian,Yu Erkeng,et al.Study of support vector machines for short-term load forecasting[J].Proceedings of the CSEE,2003,23(6):55-59(in Chinese).
• [11]葛少云,贾鸥莎,刘洪.基于遗传灰色神经网络模型的实时电价条件下短期电力负荷预测[J].电网技术,2012,36(1):224-229.Ge Shaoyun,Jia Ousha,Liu Hong.A gray neural network model improved by genetic algorithm for short-term load forecasting in price-sensitive environment[J].Power System Technology,2012,36(1):224-229(in Chinese).
• [12]王保义,王冬阳,张少敏.基于Spark和IPPSO_LSSVM的短期分布式电力负荷预测算法[J].电力自动化设备,2016,36(1):117-122.Wang Baoyi,Wang Dongyang,Zhang Shaomin.Distributed short-term load forecasting algorithm based on Spark and IPPSO_LSSVM[J].Electric Power Automation Equipment,2016,36(1):117-122(in Chinese).
• [13]曾鸣,吕春泉,田廓,等.基于细菌群落趋药性优化的最小二乘支持向量机短期负荷预测方法[J].中国电机工程学报,2011,31(34):93-99.Zeng Ming,Lv Chunquan,Tian Kuo,et al.Least squares-support vector machine load forecasting approach optimized by bacterial colony chemotaxis method[J].Proceedings of the CSEE,2011,31(34):93-99(in Chinese).
• [14]孙谦,姚建刚,赵俊,等.基于最优交集相似日选取的短期母线负荷综合预测[J].中国电机工程学报,2013,33(4):126-134.Sun Qian,Yao Jiangang,Zhao Jun,et al.Short-term bus load integrated forecasting based on selecting optimal intersection similar days[J].Proceedings of the CSEE,2013,33(4):126-134(in Chinese).
• [15]李小燕,文福拴,卢恩,等.基于相似日负荷修正的台风期间短期负荷预测[J].电力系统及其自动化学报,2013,25(3):82-89.Li Xiaoyan,Wen Fushuan,Lu En,et al.Short-term load forecasting in typhoon periods based on load modification of similar days[J].Proceedings of the CSU-EPSA,2013,25(3):82-89(in Chinese).
• [16]Ceperic E,Ceperic V,Baric A.A strategy for short-term load forecasting by support vector regression machines[J].IEEE Transactions on Power Systems,2013,28(4):4356-4364.
• [17]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].电力系统自动化,2004,28(17):1-11.Kang Chongqing,Xia Qing,Zhang Boming.Review of power system load forecasting and its development[J].Automation of Electric Power System,2004,28(17):1-11(in Chinese).
• [18]李野,康重庆,陈新宇.综合预测模型及其单一预测方法的联合参数自适应优化[J].电力系统自动化,2010,34(22):36-40.Li Ye,Kang Chongqing,Chen Xinyu.Joint adaptive training of parameters in integrated models and related single forecasting methods[J].Automation of Electric Power System,2010,34(22):36-40(in Chinese).
• [19]牛东晓,魏亚楠.基于FHNN相似日聚类自适应权重的短期电力负荷组合预测[J].电力系统自动化,2013,37(3):54-57.Niu Dongxiao,Wei Yanan.Short-term power load combinatorial forecast adaptively weighted by FHNN similar-day clustering[J].Automation of Electric Power System,2013,37(3):54-57(in Chinese).
• [20]唐衍,顾洁,张宇俊,等.基于EMD理论的短期负荷预测[J].电力需求侧管理,2011,13(1):15-19.Tang Yan,Gu Jie,Zhang Yujun,et al.Short-term load forecasting based on EMD theory[J].Power Demand Side Management,2011,13(1):15-19(in Chinese).
• [21]张金良,谭忠富.基于经验模态分解和计量经济学模型及混沌模型的短期负荷预测[J].电网技术,2011,35(9):181-187.Zhang Jinliang,Tan Zhongfu.Short-term load forecasting based on empirical mode decomposition,econometric model and chaotic model[J].Power System Technology,2011,35(9):181-187(in Chinese).
• [22]陈艳平,毛弋,陈萍,等.基于EEMD-样本熵和Elman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,2016,28(3):59-64.Chen Yanping,Mao Yi,Chen Ping,et al.Short-term power load forecasting based on ensemble empirical mode decomposition-sample entropy and Elman neural network[J].Proceedings of the CSU-EPSA,2016,28(3):59-64(in Chinese).
• [23]Dedinec A,Filiposka S,Dedinec A,et al.Deep belief network based electricity load forecasting:An analysis of Macedonian case[J].Energy,2016,115:1688-1700.
• [24]Qiu X,Zhang L,Ren Y,et al.Ensemble deep learning for regression and time series forecasting[C]//2014 IEEE Symposium on Computational Intelligence in Ensemble Learning.Orlando,Florida,United states:IEEE Computational Intelligence Society,2014:1-6.
• [25]Dragomiretskiy K,Zosso D.Variational mode decomposition[J].IEEE Transactions on Signal Processing,2013,62(3):531-544.
• [26]Nair V,Hinton G E.Rectified linear units improve restricted Boltzmann machines[C]//27th International Conference on Machine Learning.Haifa,Israel:International Machine Learning Society,2010:807-814.
• [27]Hinton G E,Salakhutdinov R R.Reducing the dimensionality of data with neural networks[J].Science,2006,313(5786):504-507.
• [28]Hinton G,Osindero S,Teh Y.A fast learning algorithm for deep belief nets[J].Neural Computation,1989,18(7):1527-1554.
• [29]Cheng R,Jin Y.A social learning particle swarm optimization algorithm for scalable optimization[J].Information Sciences,2015,291(6):43-60.
• [30]Vahabie A H,Yousefi M M R,Araabi B N,et al.Mutual information based input selection in neuro-fuzzy modeling for short term load forecasting of Iran National Power System[C]//2007 IEEE International Conference on Control and Automation.Guangzhou,China:IEEE,2007:2710-2715.