A review and analysis of regression and machine learning models on commercial building electricity load forecasting

Electricity load forecasting is an important tool which can be utilized to enable effective control of commercial building electricity loads. Accurate forecasts of commercial building electricity loads can bring significant environmental and economic benefits by reducing electricity use and peak demand and the corresponding GHG emissions. This paper presents a review of different electricity load forecasting models with a particular focus on regression models, discussing different applications, most commonly used regression variables and methods to improve the performance and accuracy of the models. A comparison between the models is then presented for forecasting day ahead hourly electricity loads using real building and Campus data obtained from the Kensington Campus and Tyree Energy Technologies Building (TETB) at the University of New South Wales (UNSW). The results reveal that Artificial Neural Networks with Bayesian Regulation Backpropagation have the best overall root mean squared and mean absolute percentage error performance and almost all the models performed better predicting the overall Campus load than the single building load. The models were also tested on forecasting daily peak electricity demand. For each model, the obtained error for daily peak demand forecasts was higher than the average day ahead hourly forecasts. The regression models which were the main focus of the study performed fairly well in comparison to other more advanced machine learning models.

[1]  Anna Bruce,et al.  Peak load characteristics of Sydney office buildings and policy recommendations for peak load reduct , 2011 .

[2]  Ming-Wei Chang,et al.  Load Forecasting Using Support Vector Machines: A Study on EUNITE Competition 2001 , 2004, IEEE Transactions on Power Systems.

[3]  L. Suganthi,et al.  Energy models for demand forecasting—A review , 2012 .

[4]  B. De Moor,et al.  Short-term load forecasting, profile identification, and customer segmentation: a methodology based on periodic time series , 2005, IEEE Transactions on Power Systems.

[5]  Stéphane Ploix,et al.  A prediction system for home appliance usage , 2013 .

[6]  M.T. Hagan,et al.  Backpropagation through time for a general class of recurrent network , 2001, IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222).

[7]  J. McBride,et al.  The effects of varying indoor air temperature and heat gain on the measurement of retrofit savings , 1998 .

[8]  Isaac Turiel,et al.  Simplified energy analysis methodology for commercial buildings , 1984 .

[9]  Alistair B. Sproul,et al.  Optimisation of energy management in commercial buildings with weather forecasting inputs: A review , 2014 .

[10]  Margaret F. Fels.  PRISM: An Introduction , 1986 .

[11]  Yoseba K. Penya,et al.  Optimal combined short-term building load forecasting , 2011, 2011 IEEE PES Innovative Smart Grid Technologies.

[12]  Kelvin K. W. Yau,et al.  Predicting electricity energy consumption: A comparison of regression analysis, decision tree and neural networks , 2007 .

[13]  Mohammad Yusri Hassan,et al.  A review on applications of ANN and SVM for building electrical energy consumption forecasting , 2014 .

[14]  David E. Claridge,et al.  Ambient-temperature regression analysis for estimating retrofit savings in commercial buildings , 1998 .

[15]  Lei Chen,et al.  A neural network-based multi-zone modelling approach for predictive control system design in commercial buildings , 2015 .

[16]  S. Beck,et al.  Using regression analysis to predict the future energy consumption of a supermarket in the UK , 2014 .

[17]  T. Simpson,et al.  Analysis of support vector regression for approximation of complex engineering analyses , 2005, DAC 2003.

[18]  David E. Claridge,et al.  Multivariate Regression Modeling , 1998 .

[19]  Julio R. Gómez Sarduy,et al.  Linear and non-linear methods for prediction of peak load at University of São Paulo , 2016 .

[20]  Joseph C. Lam,et al.  Multiple regression models for energy use in air-conditioned office buildings in different climates , 2010 .

[21]  Sylvain Robert,et al.  State of the art in building modelling and energy performances prediction: A review , 2013 .

[22]  Hesham K. Alfares,et al.  Electric load forecasting: Literature survey and classification of methods , 2002, Int. J. Syst. Sci..

[23]  Karlson Hargroves,et al.  Energy transformed: Sustainable energy solutions for climate change mitigation , 2007 .

[24]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[25]  Ram Rajagopal,et al.  Short Term Electricity Load Forecasting on Varying Levels of Aggregation , 2014, ArXiv.

[26]  Marti A. Hearst.  Trends & Controversies: Support Vector Machines , 1998, IEEE Intell. Syst..

[27]  David E. Claridge,et al.  Using synthetic data to evaluate multiple regression and principal component analyses for statistical modeling of daily building energy consumption , 1994 .

[28]  Dan Brown,et al.  Estimating Industrial Building Energy Savings using Inverse Simulation , 2011 .

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

[30]  Frédéric Magoulès,et al.  A review on the prediction of building energy consumption , 2012 .

[31]  Arun Kumar,et al.  A review on modeling and simulation of building energy systems , 2016 .

[32]  T. Chai,et al.  Root mean square error (RMSE) or mean absolute error (MAE)? – Arguments against avoiding RMSE in the literature , 2014 .

[33]  Jean-Louis Scartezzini,et al.  A simplified correlation method accounting for heating and cooling loads in energy-efficient buildings , 1998 .

[34]  Robert H. Shumway,et al.  Time series analysis and its applications : with R examples , 2017 .

[35]  Jiaping Liu,et al.  Building energy simulation using multi-years and typical meteorological years in different climates , 2008 .

[36]  K. P. Singh,et al.  Support vector machines in water quality management. , 2011, Analytica chimica acta.

[37]  Nima Amjady,et al.  Short-term hourly load forecasting using time-series modeling with peak load estimation capability , 2001 .

[38]  Nabil Nassif.  Single and Multivariate Regression Models for Estimating Monthly Energy Consumption in Schools in Hot and Humid Climates , 2013 .

[39]  R. Ramanathan,et al.  Short-run forecasts of electricity loads and peaks , 1997 .

[40]  S. Ranji Ranjithan,et al.  Multivariate regression as an energy assessment tool in early building design , 2012 .

[41]  Minghong Lin,et al.  Stochastic analysis of file-swarming systems , 2007, Perform. Evaluation.

[42]  Shengwei Wang,et al.  Development of prediction models for next-day building energy consumption and peak power demand using data mining techniques , 2014 .

[43]  Bridget Fowler,et al.  A Sociological Analysis of the Satanic Verses Affair , 2000 .

[44]  Mark Beale,et al.  Neural Network Toolbox™ User's Guide , 2015 .

[45]  Trevor Hastie,et al.  An Introduction to Statistical Learning , 2013, Springer Texts in Statistics.

[46]  T. Hesterberg,et al.  A regression-based approach to short-term system load forecasting , 1989, Conference Papers Power Industry Computer Application Conference.

[47]  Michael D. Sohn,et al.  A regression-based approach to estimating retrofit savings using the Building Performance Database , 2016 .

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

[49]  Max Henrion,et al.  Uncertainty: A Guide to Dealing with Uncertainty in Quantitative Risk and Policy Analysis , 1990 .

[50]  Alberto Hernandez Neto,et al.  Comparison between detailed model simulation and artificial neural network for forecasting building energy consumption , 2008 .

[51]  David E. Claridge,et al.  The functional basis of steady-state thermal energy use in air-side HVAC equipment , 1995 .

[52]  Y. Tanaka.  Sensitivity analysis in principal component analysis:influence on the subspace spanned by principal components. , 1988 .

[53]  Danny H.W. Li,et al.  Simple Regression Models for Fully Air-conditioned Public Sector Office Buildings in Subtropical Climates , 2002 .

[54]  V. Lo Brano,et al.  Short-term prediction of household electricity consumption: Assessing weather sensitivity in a Mediterranean area , 2008 .

[55]  C. Willmott,et al.  Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance , 2005 .

[56]  Zeyu Wang,et al.  A review of artificial intelligence based building energy use prediction: Contrasting the capabilities of single and ensemble prediction models , 2017 .