Exploratory Analysis of Machine Learning Techniques to predict Energy Efficiency in Buildings

The utilization of energy in the most efficient manner is an urgent demand of the modern era, as energy is being used in each and every field. Globally buildings consume the largest percentage of energy, and HVAC system consumes most of the energy in a building. HVAC maintains desired temperature within a building by meeting Heating load and Cooling load requirements. These requirements should be less to lessen energy consumption and achieve energy efficiency. Some of the characteristics of buildings greatly affect the Heating load and Cooling load requirements. This research analyses eight important characteristics of a building-Relative Compactness, Surface Area, Wall Area, Roof Area, Overall Height, orientation, Glazing Area, Glazing Area Distribution and uses them for predicting Heating load and Cooling load. Experiments have been performed using three Machine Learning algorithms-Multiple Linear Regression, K Nearest Neighbours, Support Vector Regresion and three Ensemble algorithms-Random Forests, Gradient Boosting Machines, Extreme Gradient Boosting. Models have been evaluated using performance metrics: RMSE, MSE, MAE, R Squared and Accuracy. Results show that Ensemble techniques outperform Machine Learning techniques with an appreciable margin.

[1]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

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

[3]  Dominic T. J. O'Sullivan,et al.  The suitability of machine learning to minimise uncertainty in the measurement and verification of energy savings , 2018 .

[4]  Sachin Kumar,et al.  A novel method based on extreme learning machine to predict heating and cooling load through design and structural attributes , 2018, Energy and Buildings.

[5]  Sanjiban Sekhar Roy,et al.  Estimating heating load in buildings using multivariate adaptive regression splines, extreme learning machine, a hybrid model of MARS and ELM , 2018 .

[6]  Ngoc-Tri Ngo.  Early predicting cooling loads for energy-efficient design in office buildings by machine learning , 2019, Energy and Buildings.

[7]  Hyo Seon Park,et al.  Development of a new energy benchmark for improving the operational rating system of office buildings using various data-mining techniques , 2016 .

[8]  Liu Yang,et al.  Building energy efficiency in different climates , 2008 .

[9]  Jasleen Kaur Sethi,et al.  Ambient Air Quality Estimation using Supervised Learning Techniques , 2018, EAI Endorsed Trans. Scalable Inf. Syst..

[10]  Sarat Chandra Nayak,et al.  Escalation of Forecasting Accuracy through Linear Combiners of Predictive Models , 2018, EAI Endorsed Trans. Scalable Inf. Syst..

[11]  Sarah Jane Delany.  k-Nearest Neighbour Classifiers , 2007 .

[12]  Athanasios Tsanas,et al.  Accurate quantitative estimation of energy performance of residential buildings using statistical machine learning tools , 2012 .

[13]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[14]  Paulo Carreira,et al.  Can HVAC really learn from users? A simulation-based study on the effectiveness of voting for comfort and energy use optimization , 2018, Sustainable Cities and Society.

[15]  Zoltán Nagy,et al.  Using machine learning techniques for occupancy-prediction-based cooling control in office buildings , 2018 .

[16]  Kevin M. Smith,et al.  Forecasting energy consumption of multi-family residential buildings using support vector regression: Investigating the impact of temporal and spatial monitoring granularity on performance accuracy , 2014 .

[17]  Wai Oswald Chong,et al.  Building energy modeling (BEM) using clustering algorithms and semi-supervised machine learning approaches , 2016 .

[18]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[19]  J. Friedman.  Stochastic gradient boosting , 2002 .

[20]  Yacine Rezgui,et al.  Trees vs Neurons: Comparison between random forest and ANN for high-resolution prediction of building energy consumption , 2017 .

[21]  Damien Picard,et al.  Approximate model predictive building control via machine learning , 2018 .

[22]  Sergio Gil-Lopez,et al.  An energy-efficient predictive control for HVAC systems applied to tertiary buildings based on regression techniques , 2017 .

[23]  Jui-Sheng Chou,et al.  Modeling heating and cooling loads by artificial intelligence for energy-efficient building design , 2014 .

[24]  Andrew Kusiak,et al.  Multi-objective optimization of the HVAC (heating, ventilation, and air conditioning) system performance , 2015 .

[25]  Chirag Deb,et al.  Using artificial neural networks to assess HVAC related energy saving in retrofitted office buildings , 2018 .

[26]  Luis M. Candanedo,et al.  Data driven prediction models of energy use of appliances in a low-energy house , 2017 .