Predictive modelling for solar thermal energy systems: A comparison of support vector regression, random forest, extra trees and regression trees

Predictive analytics play an important role in the management of decentralised energy systems. Prediction models of uncontrolled variables (e.g., renewable energy sources generation, building energy consumption) are required to optimally manage electrical and thermal grids, making informed decisions and for fault detection and diagnosis. The paper presents a comprehensive study to compare tree-based ensemble machine learning models (random forest – RF and extra trees – ET), decision trees (DT) and support vector regression (SVR) to predict the useful hourly energy from a solar thermal collector system. The developed models were compared based on their generalisation ability (stability), accuracy and computational cost. It was found that RF and ET have comparable predictive power and are equally applicable for predicting useful solar thermal energy (USTE), with root mean square error (RMSE) values of 6.86 and 7.12 on the testing dataset, respectively. Amongst the studied algorithms, DT is the most computationally efficient method as it requires significantly less training time. However, it is less accurate (RMSE = 8.76) than RF and ET. The training time of SVR was 1287.80 ms, which was approximately three times higher than the ET training time.

[1]  Chuntian Cheng,et al.  Using support vector machines for long-term discharge prediction , 2006 .

[2]  Jiejin Cai,et al.  Applying support vector machine to predict hourly cooling load in the building , 2009 .

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

[4]  A. Roli.  Artificial Neural Networks , 2012, Lecture Notes in Computer Science.

[5]  V. Rodriguez-Galiano,et al.  Machine learning predictive models for mineral prospectivity: an evaluation of neural networks, random forest, regression trees and support vector machines , 2015 .

[6]  Matthew J. Eckelman,et al.  Predictive modeling for US commercial building energy use: A comparison of existing statistical and machine learning algorithms using CBECS microdata , 2018 .

[7]  Zeyu Wang,et al.  Random Forest based hourly building energy prediction , 2018, Energy and Buildings.

[8]  Yacine Rezgui,et al.  Computational intelligence techniques for HVAC systems: A review , 2016, Building Simulation.

[9]  Evgueniy Entchev,et al.  Adaptive Neuro-Fuzzy Inference System modelling for performance prediction of solar thermal energy system , 2016 .

[10]  Vittorio Cesarotti,et al.  Energy consumption control automation using Artificial Neural Networks and adaptive algorithms: Proposal of a new methodology and case study , 2016 .

[11]  W. Beckman,et al.  Solar Engineering of Thermal Processes , 1985 .

[12]  Brian Vad Mathiesen,et al.  Smart Energy Systems for coherent 100% renewable energy and transport solutions , 2015 .

[13]  Gilles Notton,et al.  A building integrated solar collector: Performances characterization and first stage of numerical calculation , 2013 .

[14]  Chul-Hwan Kim,et al.  Application of Neural Network to One-Day-Ahead 24 hours Generating Power Forecasting for Photovoltaic System , 2007, 2007 International Conference on Intelligent Systems Applications to Power Systems.

[15]  S. L. Shimi,et al.  Modeling of solar PV module and maximum power point tracking using ANFIS , 2014 .

[16]  A. Kusiak,et al.  Short-Term Prediction of Wind Farm Power: A Data Mining Approach , 2009, IEEE Transactions on Energy Conversion.

[17]  Adnan Sözen,et al.  Determination of efficiency of flat-plate solar collectors using neural network approach , 2008, Expert Syst. Appl..

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

[19]  Yacine Rezgui,et al.  Building energy metering and environmental monitoring – A state-of-the-art review and directions for future research , 2016 .

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

[21]  Kewei Cheng,et al.  Novel Method for Measuring the Heat Collection Rate and Heat Loss Coefficient of Water-in-Glass Evacuated Tube Solar Water Heaters Based on Artificial Neural Networks and Support Vector Machine , 2015 .

[22]  Soteris A. Kalogirou,et al.  Artificial neural networks for the performance prediction of large solar systems , 2014 .

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

[24]  Joao P. S. Catalao,et al.  Short-term wind power forecasting in Portugal by neural networks and wavelet transform , 2011 .

[25]  L. Breiman.  Heuristics of instability and stabilization in model selection , 1996 .

[26]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[27]  Soteris A. Kalogirou,et al.  Solar thermal collectors and applications , 2004 .

[28]  Gilles Notton,et al.  New Patented Solar Thermal Concept for High Building Integration: Test and Modeling , 2013 .

[29]  Thomas G. Dietterich.  Multiple Classifier Systems , 2000, Lecture Notes in Computer Science.

[30]  W. Rivera,et al.  Short term wind speed forecasting in La Venta, Oaxaca, México, using artificial neural networks , 2009 .

[31]  S. Karslı,et al.  Performance analysis of new-design solar air collectors for drying applications , 2007 .

[32]  Engin Gedik,et al.  Investigation on thermal performance calculation of two type solar air collectors using artificial neural network , 2011, Expert Syst. Appl..

[33]  István Farkas,et al.  Neural network modelling of thermal stratification in a solar DHW storage , 2010 .

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

[35]  Wai Kean Yap,et al.  An off-grid hybrid PV/diesel model as a planning and design tool, incorporating dynamic and ANN modelling techniques , 2015 .

[36]  Pramod K. Varshney,et al.  Decision tree regression for soft classification of remote sensing data , 2005 .

[37]  G. Giebel,et al.  Short-term prediction of wind farm output , 1999 .

[38]  Brian Vad Mathiesen,et al.  4th Generation District Heating (4GDH) Integrating smart thermal grids into future sustainable energy systems , 2014 .

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

[40]  Richard A. Wasniowski.  Using support vector machines in data mining , 2004 .

[41]  B. Dong,et al.  Applying support vector machines to predict building energy consumption in tropical region , 2005 .

[42]  Cesare Pautasso,et al.  Multiple Classifier System , 2009, Encyclopedia of Database Systems.

[43]  Yacine Rezgui,et al.  Holistic modelling techniques for the operational optimisation of multi-vector energy systems , 2018, Energy and Buildings.

[44]  G. Florides,et al.  Development of a neural network-based fault diagnostic system for solar thermal applications , 2008 .

[45]  Zakaria Mohd. Amin,et al.  Mathematical modelling of counter flow v-grove solar air collector , 2013 .

[46]  David Harrison,et al.  Predicted and in situ performance of a solar air collector incorporating a translucent granular aerogel cover , 2012 .

[47]  Zheng Liu,et al.  Real-Time Lane Estimation Using Deep Features and Extra Trees Regression , 2015, PSIVT.

[48]  Lars Kai Hansen,et al.  Neural Network Ensembles , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[49]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[50]  Abdulkadir Sengür,et al.  Artificial neural network and wavelet neural network approaches for modelling of a solar air heater , 2009, Expert Syst. Appl..

[51]  Daniel Ambach,et al.  Short-term wind speed forecasting in Germany , 2015, 1509.03116.

[52]  Youngdeok Hwang,et al.  Artificial neural network model for forecasting sub-hourly electricity usage in commercial buildings , 2016 .