A machine learning and deep learning based approach to predict the thermal performance of phase change material integrated building envelope

Abstract This study aims to develop a machine learning and deep learning-based model for thermal performance prediction of PCM integrated roof building. Performance prediction is carried out using the newly proposed MKR index. Five machine learning and one deep learning technique are explored in order to predict the thermal performance of PCM integrated roof considering variations in thermophysical properties of PCM. Total 500 data points are generated using numerical simulations considering variations in thermophysical properties of PCM. The five machine learning models used in this study are Random forest regression, Extra trees regression, Gradient boosting regression, Extreme Gradient boosting regression, and Catboost regression. The results indicate that Gradient boosting regression is the best-performing model compared to other machine learning models. An artificial neural network is used as a deep learning approach for predicting the MKR index. The ANN-based model performed best among all five machine learning models and proved its efficacy in training, testing, and sensitivity analysis with the independent dataset.

[1]  Esam M. Alawadhi,et al.  Concrete roof with cylindrical holes containing PCM to reduce the heat gain , 2013 .

[2]  Yacine Rezgui,et al.  Predictive modelling for solar thermal energy systems: A comparison of support vector regression, random forest, extra trees and regression trees , 2018, Journal of Cleaner Production.

[3]  Kamal Abdel Radi Ismail,et al.  Comparison between PCM filled glass windows and absorbing gas filled windows , 2008 .

[4]  Esam M. Alawadhi,et al.  Building roof with conical holes containing PCM to reduce the cooling load: Numerical study , 2011 .

[5]  Dibakar Rakshit,et al.  Thermal energy performance of an academic building with sustainable probing and optimization with evolutionary algorithm , 2020, Thermal Science and Engineering Progress.

[6]  Yacine Rezgui,et al.  Tree-based ensemble methods for predicting PV power generation and their comparison with support vector regression , 2018, Energy.

[7]  Beat Lehmann,et al.  Development of a thermally activated ceiling panel with PCM for application in lightweight and retrofitted buildings , 2004 .

[8]  Philip C. Eames,et al.  Phase Change Material Wallboard (PCMW) melting temperature optimisation for passive indoor temperature control , 2019, Renewable Energy.

[9]  Moncef L. Nehdi,et al.  Machine learning prediction of compressive strength for phase change materials integrated cementitious composites , 2020 .

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

[11]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[12]  M. K. Rathod,et al.  Passive cooling techniques for building and their applicability in different climatic zones—The state of art , 2019, Energy and Buildings.

[13]  Pierre Geurts,et al.  Extremely randomized trees , 2006, Machine Learning.

[14]  Ibrahim Dincer,et al.  Heat transfer analysis of phase change process in a finned-tube thermal energy storage system using artificial neural network , 2007 .

[15]  Tanveer Ahmad,et al.  A comprehensive overview on the data driven and large scale based approaches for forecasting of building energy demand: A review , 2018 .

[16]  Per Heiselberg,et al.  A new ventilated window with PCM heat exchanger—Performance analysis and design optimization , 2018, Energy and Buildings.

[17]  Nor Azuana Ramli,et al.  Energy consumption prediction by using machine learning for smart building: Case study in Malaysia , 2020, Developments in the Built Environment.

[18]  Junliang Fan,et al.  Comparison of Support Vector Machine and Extreme Gradient Boosting for predicting daily global solar radiation using temperature and precipitation in humid subtropical climates: A case study in China , 2018 .

[19]  Engin Avci,et al.  Speech recognition using a wavelet packet adaptive network based fuzzy inference system , 2006, Expert Syst. Appl..

[20]  Dibakar Rakshit,et al.  Dynamic optimization of multi-retrofit building envelope for enhanced energy performance with a case study in hot Indian climate , 2020 .

[21]  Jianlei Niu,et al.  Performance of cooled-ceiling operating with MPCM slurry , 2009 .

[22]  Haifeng Guo,et al.  A new kind of phase change material (PCM) for energy-storing wallboard , 2008 .

[23]  Dong Li,et al.  Numerical analysis on thermal performance of roof contained PCM of a single residential building , 2015 .

[24]  Venkat Pranesh,et al.  Thermal energy storage system operating with phase change materials for solar water heating applications: DOE modelling , 2017 .

[25]  S. K. Tyagi,et al.  Phase change material (PCM) based thermal management system for cool energy storage application in building: An experimental study , 2012 .

[26]  Engin Avci,et al.  Forecasting of thermal energy storage performance of Phase Change Material in a solar collector using soft computing techniques , 2010, Expert Syst. Appl..

[27]  M. K. Rathod,et al.  Numerical model for evaluating thermal performance of residential building roof integrated with inclined phase change material (PCM) layer , 2020 .

[28]  A. Campos-Celador,et al.  Dynamic neural networks to analyze the behavior of phase change materials embedded in building envelopes , 2019, Applied Thermal Engineering.

[29]  Yingjiu Pan,et al.  Estimation of real-driving emissions for buses fueled with liquefied natural gas based on gradient boosted regression trees. , 2019, The Science of the total environment.

[30]  Henrik Madsen,et al.  Multi-site solar power forecasting using gradient boosted regression trees , 2017 .

[31]  Max Kuhn,et al.  Applied Predictive Modeling , 2013 .

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

[33]  Runming Yao,et al.  A machine-learning-based approach to predict residential annual space heating and cooling loads considering occupant behaviour , 2020, Energy.

[34]  M. K. Rathod,et al.  Selection of phase change material and establishment of thermophysical properties of phase change material integrated with roof of a building using Measure of Key Response index: Proposal of a new parameter , 2020 .

[35]  M. K. Rathod,et al.  Thermal stability of phase change materials used in latent heat energy storage systems: A review , 2013 .

[36]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[37]  Juan M. Corchado,et al.  Machine Learning Models for Electricity Consumption Forecasting: A Review , 2019, 2019 2nd International Conference on Computer Applications & Information Security (ICCAIS).

[38]  Dibakar Rakshit,et al.  Thermal Performance Evaluation of Building Roofs Embedded PCM for Multi-climatic Zones , 2018 .

[39]  Fariborz Haghighat,et al.  Assessing long-term performance of centralized thermal energy storage system , 2014 .

[40]  Amina Mourid,et al.  Thermal Behavior of a Building Provided With Phase-Change Materials on the Roof and Exposed to Solar Radiation , 2017 .

[41]  Amin Shahsavar,et al.  Heat transfer reduction in buildings by embedding phase change material in multi-layer walls: Effects of repositioning, thermophysical properties and thickness of PCM , 2019, Energy Conversion and Management.

[42]  Soteris A. Kalogirou,et al.  Artificial neural networks in renewable energy systems applications: a review , 2001 .

[43]  Yuekuan Zhou,et al.  Machine-learning based hybrid demand-side controller for high-rise office buildings with high energy flexibilities , 2020 .

[44]  Joeri Van Mierlo,et al.  Random forest regression for online capacity estimation of lithium-ion batteries , 2018, Applied Energy.

[45]  Yacine Rezgui,et al.  A zone-level, building energy optimisation combining an artificial neural network, a genetic algorithm, and model predictive control , 2018 .

[46]  Hazem Elzarka,et al.  Advanced machine learning techniques for building performance simulation: a comparative analysis , 2018, Journal of Building Performance Simulation.

[47]  R. Velraj,et al.  Effect of double layer phase change material in building roof for year round thermal management , 2008 .