Structural combination of seasonal exponential smoothing forecasts applied to load forecasting

This article draws from research on ensembles in computational intelligence to propose structural combinations of forecasts, which are point forecast combinations that are based on information from the parameters of the individual models that generated the forecasts. Two types of structural combination are proposed which use seasonal exponential smoothing as base models, and are applied to forecast short-term electricity demand. Although forecasting performance may depend on how ensembles are generated, results show that the proposed combinations can outperform competitive benchmarks. The methods can be used to forecast other seasonal data and be extended to different types of forecasting models.

[1]  Carlos E. Pedreira,et al.  Neural networks for short-term load forecasting: a review and evaluation , 2001 .

[2]  Asaad Y. Shamseldin,et al.  A non-linear combination of the forecasts of rainfall-runoff models by the first-order Takagi–Sugeno fuzzy system , 2001 .

[3]  A. Fiordaliso.  A nonlinear forecasts combination method based on Takagi–Sugeno fuzzy systems , 1998 .

[4]  S. Saeedeh Sadegh,et al.  Forecasting energy consumption using ensemble ARIMA-ANFIS hybrid algorithm , 2016 .

[5]  J. Scott Armstrong,et al.  Principles of forecasting : a handbook for researchers and practitioners , 2001 .

[6]  James W. Taylor,et al.  Using combined forecasts with changing weights for electricity demand profiling , 2000, J. Oper. Res. Soc..

[7]  Ping-Feng Pai,et al.  Forecasting regional electricity load based on recurrent support vector machines with genetic algorithms , 2005 .

[8]  R. Buizza,et al.  Using weather ensemble predictions in electricity demand forecasting , 2003 .

[9]  James W. Taylor,et al.  Triple seasonal methods for short-term electricity demand forecasting , 2010, Eur. J. Oper. Res..

[10]  Heung Wong,et al.  Determining when to update the weights in combined forecasts for product demand--an application of the CUSUM technique , 2004, Eur. J. Oper. Res..

[11]  A. T. C. Goh,et al.  Back-propagation neural networks for modeling complex systems , 1995, Artif. Intell. Eng..

[12]  J. Stock,et al.  Combination forecasts of output growth in a seven-country data set , 2004 .

[13]  C. Granger,et al.  Modelling Nonlinear Economic Relationships , 1995 .

[14]  Tom Heskes,et al.  Clustering ensembles of neural network models , 2003, Neural Networks.

[15]  Guoqiang Peter Zhang,et al.  A neural network ensemble method with jittered training data for time series forecasting , 2007, Inf. Sci..

[16]  Wei Tang,et al.  Ensembling neural networks: Many could be better than all , 2002, Artif. Intell..

[17]  J. M. Bates,et al.  The Combination of Forecasts , 1969 .

[18]  Timo Teräsvirta,et al.  The combination of forecasts using changing weights , 1994 .

[19]  Derek W. Bunn,et al.  The persistence of specification problems in the distribution of combined forecast errors , 1998 .

[20]  Fotios Petropoulos,et al.  Exploring the sources of uncertainty: Why does bagging for time series forecasting work? , 2018, Eur. J. Oper. Res..

[21]  Rob J Hyndman,et al.  Forecasting with Exponential Smoothing: The State Space Approach , 2008 .

[22]  Sven F. Crone,et al.  Advances in forecasting with neural networks? Empirical evidence from the NN3 competition on time series prediction , 2011 .

[23]  Todd E. Clark,et al.  Forecast Combination Across Estimation Windows , 2011 .

[24]  Peter Reinhard Hansen,et al.  The Model Confidence Set , 2010 .

[25]  F. Petropoulos,et al.  Improving forecasting by estimating time series structural components across multiple frequencies , 2014 .

[26]  Tao Hong,et al.  Improving short term load forecast accuracy via combining sister forecasts , 2016 .

[27]  J. W. Taylor,et al.  Short-term electricity demand forecasting using double seasonal exponential smoothing , 2003, J. Oper. Res. Soc..

[28]  Bing-Yi Jing.  On the relative performance of the block bootstrap for dependent data , 1997 .

[29]  Silja Meyer-Nieberg,et al.  Electric load forecasting methods: Tools for decision making , 2009, Eur. J. Oper. Res..

[30]  S. Kolassa.  Combining exponential smoothing forecasts using Akaike weights , 2011 .

[31]  G. David Garson,et al.  Interpreting neural-network connection weights , 1991 .

[32]  Alagan Anpalagan,et al.  Boosted neural networks for improved short-term electric load forecasting , 2017 .

[33]  E. Mizutani,et al.  Neuro-Fuzzy and Soft Computing-A Computational Approach to Learning and Machine Intelligence [Book Review] , 1997, IEEE Transactions on Automatic Control.

[34]  R. Clemen.  Combining forecasts: A review and annotated bibliography , 1989 .

[35]  Nikola Kasabov,et al.  Foundations Of Neural Networks, Fuzzy Systems, And Knowledge Engineering [Books in Brief] , 1996, IEEE Transactions on Neural Networks.

[36]  Song Li,et al.  An ensemble approach for short-term load forecasting by extreme learning machine , 2016 .

[37]  George Athanasopoulos,et al.  Forecasting: principles and practice , 2013 .

[38]  Michael P. Clements,et al.  Forecast Encompassing Tests and Probability Forecasts , 2010 .

[39]  Tom Gedeon,et al.  Use of Noise to Augment Training Data: A Neural Network Method of Mineral–Potential Mapping in Regions of Limited Known Deposit Examples , 2003 .

[40]  Johan A. K. Suykens,et al.  Load forecasting using a multivariate meta-learning system , 2013, Expert Syst. Appl..

[41]  J. Friedman.  Multivariate adaptive regression splines , 1990 .

[42]  P. McSharry,et al.  A comparison of univariate methods for forecasting electricity demand up to a day ahead , 2006 .

[43]  Derek W. Bunn,et al.  Review of guidelines for the use of combined forecasts , 2000, Eur. J. Oper. Res..

[44]  Robert Fildes,et al.  Principles of Business Forecasting , 2012 .

[45]  Rob J Hyndman,et al.  Bagging exponential smoothing methods using STL decomposition and Box–Cox transformation , 2016 .

[46]  Mark J. Kamstra,et al.  Forecast combining with neural networks , 1996 .

[47]  JinXing Che,et al.  Optimal sub-models selection algorithm for combination forecasting model , 2015, Neurocomputing.

[48]  Rob J Hyndman,et al.  Forecasting Time Series With Complex Seasonal Patterns Using Exponential Smoothing , 2011 .