Machine Learning Techniques for Short-Term Electric Power Demand Prediction

Since several years ago, power consumption forecast has at- tracted considerable attention from the scientific community. Although there exist several works that deal with this issue, it remains open. The good management of energy consumption in HVAC (Heating, Ventilation and Air Conditioning) systems for large households and public buildings may benefit from a sustainable development in terms of economy and environmental preservation. In this paper, several Machine Learning tech- niques are evaluated and compared with a linear technique (Robust Multi- ple Linear Regression) and a na¨ove method. All methods have been applied to five buildings of the University of Leon (Spain), the results indicate non- linear techniques outperform the linear one in most scenarios.

[1]  P. Holland,et al.  Robust regression using iteratively reweighted least-squares , 1977 .

[2]  Yongkang Zheng,et al.  Short-Term Load Forecasting Based on Gaussian Wavelet SVM , 2011 .

[3]  Simon Haykin,et al.  Neural Networks and Learning Machines , 2010 .

[4]  R. Shah,et al.  Least Squares Support Vector Machines , 2022 .

[5]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[6]  A. Goia,et al.  Functional clustering and linear regression for peak load forecasting , 2010 .

[7]  Johan A. K. Suykens,et al.  Coupled Simulated Annealing , 2010, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[8]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[9]  Mita Nasipuri,et al.  Human face recognition using fuzzy multilayer perceptron , 2010, Soft Comput..

[10]  Fábio Gonçalves Jota,et al.  Building load management using cluster and statistical analyses , 2011 .

[11]  T. Hassard,et al.  Applied Linear Regression , 2005 .

[12]  Didier Vincent,et al.  Application of multilayer perceptron neural networks for predicting the permeability tensor components of thin ferrite films , 2011 .

[13]  Nor Azam Ramli,et al.  Robust Regression Models for Predicting PM10 Concentration in an Industrial Area , 2012 .

[14]  Guang-Bin Huang,et al.  Extreme learning machine: a new learning scheme of feedforward neural networks , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[15]  Larry D. Paarmann,et al.  Adaptive online load forecasting via time series modeling , 1995 .

[16]  C.S. Ozveren,et al.  Short term load forecasting using Multiple Linear Regression , 2007, 2007 42nd International Universities Power Engineering Conference.

[17]  Malik Beshir Malik,et al.  Applied Linear Regression , 2005, Technometrics.

[18]  Yongli Wang,et al.  Short-term power load forecasting based on IVL-BP neural network technology , 2012 .

[19]  Dianhui Wang,et al.  Extreme learning machines: a survey , 2011, Int. J. Mach. Learn. Cybern..