基于深层神经网络的电力负荷预测Power Load Forecast Based on Deep Neural Networks
何琬;刘进;朱肖晶;
摘要(Abstract)：
精确的电力负荷预测具有很大的经济和社会效益。本文基于深层神经网络研究负荷预测。文章首先分析了负荷预测中用到的关键特征,接着描述了深层神经网络和有监督的判别式预训练方法,以及文中使用的三种激活函数。最后,在一个较大的电力负荷数据集上比较了不同神经网络模型的预测效果。实验结果表明,使用有监督的预训练的深层神经网络具有最好的预测精度。
关键词(KeyWords)： 负荷预测;深层神经网络;预训练;激活函数
基金项目(Foundation):
作者(Authors): 何琬;刘进;朱肖晶;
DOI: 10.19758/j.cnki.issn1673-288x.2016.01.026
参考文献(References)：
- [1]E.A.Feinberg and D.Genethliou.Applied Mathematics for Restructured Electric Power Systems:Optimization,Control,and Computational Intelligence[M].Springer,2005,pp.269-285.
- [2]G.A.N Mbamalu and M.E.El-Hawary.Load forecasting via suboptimal seasonal autoregressive models and iteratively reweighted least squares estimation[J].IEEE Transactions on Power Systems,1993,vol.8,no.1,pp.343-348.
- [3]S.J.Kiartzis and A.G.Bakirtzis.A fuzzy expert system for peak load forecasting:application to the Greek power system[C].Proceedings of the 10th Mediterranean Electrotechnical Conference,2000,3:1097-1100.
- [4]J.W.Taylor,Short-term load forecasting with exponentially weighted methods[J].IEEE Transactions on Power Systems,2012,vol.27,no.1,pp.458-464.
- [5]S.J.Huang and K.R.Shih.Short-term load forecasting via ARMA model identification including non-Gaussian process considerations[J].IEEE Transactions on Power Systems,2003,vol.18,no.2,pp.673-679.
- [6]M.W.Chang,B.J.Chen and C.J.Lin.EUNITE network competition:electricity load forecasting[R].EUNITE network competition,2001.
- [7]J.R.Lloyd.Hierarchical load forecasting using gradient boosting machines and Gaussian processes[R].GEFCom,2012.
- [8]T.M.Peng,N.F.Hubele and G.G.Karady.Advancement in the application of neural networks for short-term load forecasting[J].IEEE Transactions on Power Systems,1992,vol.7,no.1,pp.250-257.
- [9]祝燕萍,方鸽飞.基于动态自适应神经网络和人体舒适度的短期负荷预测[J].电力系统保护与控制,2012,Vol 40,No.1,pp.56-61.
- [10]史会峰,牛东晓,卢艳霞.基于贝叶斯神经网络短期负荷预测模型[J].中国管理科学,2012,20(4):118-124.
- [11]G.E.Hinton,S.Osindero and Y.The.A fast learning algorithm for deep belief nets[J].Neural Computation,2006,18,pp.1527-1554.
- [12]Y.Bengio.Learning Deep Architectures For AI:Foundations and Trends in Machine Learning[M].NOW Publishers,2009,pp.1-127.
- [13]J.Nocedal and S.J.Wright.Numerical Optimization[M],Springer,Second Edition,2006.
- [14]A.Mohamed,G.E.Dahl and G.E.Hinton.Acoustic modeling using deep belief networks[J].IEEE Transactions.on Audio,Speech,and Language Processing,2012,20,pp.14-22.
- [15]I.J.Goodfellow,D.Warde-Farley,M.Mirza,A.Couville,Y.Bengio.Maxout networks[J].Journal of Machine Learning Research,2013,WCP vol 28(3),pp.1319-1327.
- [16]X.Glorot,A.Bordes and Y.Bengio.Deep sparse rectifier networks[J].Journal of Machine Learning Research,2011,WCP vol.15,pp.315-323.