Comparison of linear regression and artificial neural networks models to predict heating and cooling energy demand, energy consumption and CO2 emissions

An attempt has been made to develop linear regression models and Artificial Neural Networks (ANN) to predict the heating and cooling energy demands, energy consumptions and CO2 emissions of office buildings in Chile. The calculation of dependent variables to calibrate and evaluate the models has been determined starting from the ISO 13790:2008 standard, assigning constructive characteristics to each of the geometries studied based on the Chilean standards, studying 77,000 cases. A total of 8 fundamental variables have been considered to cover the design parameters. In energy consumption and CO2 emissions cases, the linear regression models that offer a better performance are those where the predictive variables have been transformed. Whereas, the multilayer perceptron adjusted over the variables without being transformed, provides greater accuracy in the determination of the demand, consumption and CO2 emissions both for heating and cooling, offering ECM values closer to 0, with an R2 coefficient above 99%. It is foreseen that the models developed can be used to estimate the energy saving between different design outlines during the project phases when the construction standards, systems and internal loads are defined.

[1]  Mohamed El Mankibi,et al.  Genetic algorithms based optimization of artificial neural network architecture for buildings’ indoor discomfort and energy consumption prediction , 2012 .

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

[3]  Aie,et al.  World Energy Outlook 2013 , 2013 .

[4]  Giuliano Dall'O',et al.  On the use of an energy certification database to create indicators for energy planning purposes: Application in northern Italy , 2015 .

[5]  Carlos Rubio-Bellido,et al.  Aplicabilidad de estrategias genéricas de diseño pasivo en edificaciones bajo la influencia del cambio climático en Concepción y Santiago, Chile , 2015 .

[6]  G Banos,et al.  Impact of single nucleotide polymorphisms in leptin, leptin receptor, growth hormone receptor, and diacylglycerol acyltransferase (DGAT1) gene loci on milk production, feed, and body energy traits of UK dairy cows. , 2008, Journal of dairy science.

[7]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[8]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[9]  Toke Rammer Nielsen,et al.  Building energy optimization in the early design stages: A simplified method , 2015 .

[10]  Er-Wei Bai,et al.  Developing a whole building cooling energy forecasting model for on-line operation optimization using proactive system identification , 2016 .

[11]  Giuliano Dall'O',et al.  Application of neural networks for evaluating energy performance certificates of residential buildings , 2016 .

[12]  Srdjan Vukmirović,et al.  Use of Neural Networks for modeling and predicting boiler's operating performance , 2012 .

[13]  Jin Yang,et al.  On-line building energy prediction using adaptive artificial neural networks , 2005 .

[14]  Luis Pérez-Lombard,et al.  A review on buildings energy consumption information , 2008 .

[15]  Rajesh Kumar,et al.  Energy analysis of a building using artificial neural network: A review , 2013 .

[16]  Carlos Rubio-Bellido,et al.  Optimization of annual energy demand in office buildings under the influence of climate change in Chile , 2016 .

[17]  V. I. Hanby,et al.  Regression models for predicting UK office building energy consumption from heating and cooling demands , 2013 .

[18]  James A. Rodger,et al.  A fuzzy nearest neighbor neural network statistical model for predicting demand for natural gas and energy cost savings in public buildings , 2014, Expert Syst. Appl..

[19]  Tony N.T. Lam,et al.  Artificial neural networks for energy analysis of office buildings with daylighting , 2010 .

[20]  William N. Venables,et al.  Modern Applied Statistics with S , 2010 .

[21]  António E. Ruano,et al.  Prediction of building's temperature using neural networks models , 2006 .

[22]  Steve Sorrell,et al.  Reducing energy demand: A review of issues, challenges and approaches , 2015 .

[23]  Chirag Deb,et al.  Forecasting diurnal cooling energy load for institutional buildings using Artificial Neural Networks , 2016 .

[24]  Àngela Nebot,et al.  Hybrid methodologies for electricity load forecasting: Entropy-based feature selection with machine learning and soft computing techniques , 2015 .

[25]  Teresa Wu,et al.  Short-term building energy model recommendation system: A meta-learning approach , 2016 .

[26]  Carlos Rubio-Bellido,et al.  Multivariable regression analysis to assess energy consumption and CO2 emissions in the early stages of offices design in Chile , 2016 .

[27]  V. Geros,et al.  Modeling and predicting building's energy use with artificial neural networks: Methods and results , 2006 .

[28]  Kristoffer Negendahl,et al.  Building performance simulation in the early design stage: An introduction to integrated dynamic models , 2015 .

[29]  Leopold,et al.  Application of artificial neural network for predicting hourly indoor air temperature and relative humidity in modern building in humid region , 2016 .

[30]  T. McMahon,et al.  Updated world map of the Köppen-Geiger climate classification , 2007 .

[31]  Manuel R. Arahal,et al.  A prediction model based on neural networks for the energy consumption of a bioclimatic building , 2014 .

[32]  A. Kialashaki,et al.  Modeling of the energy demand of the residential sector in the United States using regression models and artificial neural networks , 2013 .

[33]  Gabriele Comodi,et al.  The role of data sample size and dimensionality in neural network based forecasting of building heating related variables , 2016 .

[34]  B. Rudolf,et al.  World Map of the Köppen-Geiger climate classification updated , 2006 .

[35]  J. Kurnitski,et al.  Performance of EN ISO 13790 utilisation factor heat demand calculation method in a cold climate , 2007 .

[36]  Fu Xiao,et al.  Quantitative energy performance assessment methods for existing buildings , 2012 .

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

[38]  Jesús M. Zamarreño,et al.  Prediction of hourly energy consumption in buildings based on a feedback artificial neural network , 2005 .

[39]  V. I. Hanby,et al.  UK office buildings archetypal model as methodological approach in development of regression models for predicting building energy consumption from heating and cooling demands , 2013 .