Extreme Gradient Boosting Algorithm for Energy Optimization in buildings pertaining to HVAC plants

With the recent advancements in technology, energy is being consumed at a great pace in almost every region. Buildings are the biggest consumer of energy, almost 40% of total energy is being consumed by the buildings. The purpose of this research is to investigate Ensemble Learning based optimal solution for predicting energy consumption in Heating, Ventilation and Air Conditioning (HVAC) plants as the HVAC unit consumes a large percentage of energy in buildings. The study focuses on Cooling Tower data of HVAC plants as Cooling Tower carries a major responsibility for maintaining ambient within a building. In this paper,four Regression techniques namely Multiple Linear Regression, Random Forests, Gradient Boosting Machines and ExtremeGradient Boosting have been experimented. The findings reveal that Extreme Gradient Boosting Ensemble outperforms with higher accuracy and lower in overfitting.

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

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

[3]  Gunnar Rätsch,et al.  An Introduction to Boosting and Leveraging , 2002, Machine Learning Summer School.

[4]  Jinkyun Cho,et al.  Energy-cost analysis of HVAC system for office buildings: Development of a multiple prediction methodology for HVAC system cost estimation , 2018, Energy and Buildings.

[5]  Yonghong Peng,et al.  A novel ensemble machine learning for robust microarray data classification , 2006, Comput. Biol. Medicine.

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

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

[8]  A. Prasad,et al.  Newer Classification and Regression Tree Techniques: Bagging and Random Forests for Ecological Prediction , 2006, Ecosystems.

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

[10]  Kim F. Nimon,et al.  Understanding the Results of Multiple Linear Regression , 2013 .

[11]  Miriam A. M. Capretz,et al.  An ensemble learning framework for anomaly detection in building energy consumption , 2017 .

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

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

[14]  J. Suykens,et al.  Component-Based Machine Learning Modelling Approach for Design Stage Building Energy Prediction: Weather Conditions and Size , 2017, Building Simulation Conference Proceedings.

[15]  Alípio Mário Jorge,et al.  Ensemble approaches for regression: A survey , 2012, CSUR.

[16]  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.

[17]  Saifur Rahman,et al.  Power disaggregation of combined HVAC loads using supervised machine learning algorithms , 2018, Energy and Buildings.

[18]  S. Sosvilla‐Rivero,et al.  Linkages in international stock markets: evidence from a classification procedure , 2010 .

[19]  Energy Optimization in Buildings Using Machine Learning Techniques: A Survey , 2018 .

[20]  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 .

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

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

[23]  Grace Ding,et al.  Developing a Hybrid Model of Prediction and Classification Algorithms for Building Energy Consumption , 2017 .

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

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