PREDICTION MODEL OF PUBLIC HOUSES’ HEATING SYSTEMS: A COMPARISON OF SUPPORT VECTOR MACHINE METHOD AND RANDOM FOREST METHOD

Andrii Perekrest

pksg13@gmail.com
Kremenchuk Mykhailo Ostrohradskyi National University (Ukraine)
http://orcid.org/0000-0002-7728-9020

Vladimir Chenchevoi


Kremenchuk Mykhailo Ostrohradskyi National University (Ukraine)
http://orcid.org/0000-0002-6478-3767

Olga Chencheva


Kremenchuk Mykhailo Ostrohradskyi National University (Ukraine)
http://orcid.org/0000-0002-5691-7884

Alexandr Kovalenko


Cherkasy State Technological University (Ukraine)
http://orcid.org/0000-0002-5073-3507

Mykhailo Kushch-Zhyrko


Kremenchuk Mykhailo Ostrohradskyi National University (Ukraine)
http://orcid.org/0000-0001-9622-9114

Aliya Kalizhanova


University of Power Engineering and Telecommunications; Institute of Information and Computational Technologies MES CS RK (Kazakhstan)
http://orcid.org/0000-0002-5979-9756

Yedilkhan Amirgaliyev


Institute of Information and Computational Technologies MES CS RK (Kazakhstan)
http://orcid.org/0000-0002-6528-0619

Abstract

Data analysis and predicting play an important role in managing heat-supplying systems. Applying the models of predicting the systems’ parameters is possible for qualitative management, accepting appropriate decisions relating control that will be aimed at increasing energy efficiency and decreasing the amount of the consumed power source, diagnosing and defining non-typical processes in the functioning of the systems. The article deals with comparing two methods of ma-chine learning: random forest (RF) and support vector machine (SVM) for predicting the temperature of the heat-carrying agent in the heating system based on the data of electronic weather-dependent controller. The authors use the following parameters to compare the models: accuracy, source cost and the opportunity to interpret the results and non-obvious interrelations. The time spent for defining the optimal hyperparameters and conducting the SVM model training is deter-mined to exceed significantly the data of the RF parameter despite the close meanings of the root mean square error (RMSE). The change from 15-min data to once-a-minute ones is done to improve the RF model accuracy. RMSE of the RF model on the test data equals 0.41°С. The article studies the importance of the contribution of variables to the prediction accuracy.


Keywords:

building heat supply, random forest, support vector machine

Ahmad M. V. et al.: Tree-based ensemble methods for predicting PV power generation and their comparison with support vector regression. Energy 164, 2018, 465–474.
DOI: https://doi.org/10.1016/j.energy.2018.08.207   Google Scholar

Ahmad, M. V. et al.: Predictive modelling for solar thermal energy systems: A comparison of support vector regression, random forest, extra trees and regression trees. Journal of Cleaner Production 203, 2018, 810–821.
DOI: https://doi.org/10.1016/j.jclepro.2018.08.207   Google Scholar

Ahmad M. W. et al.: Trees vs Neurons: Comparison between random forest and ANN for high-resolution prediction of building energy consumption. Energy and Buildings 147, 2017, 77–89.
DOI: https://doi.org/10.1016/j.enbuild.2017.04.038   Google Scholar

Azarov A. D. et al.: Class of numerical systems for pipe-line bit sequential development of multiple optoelectronic data streams. Proc. SPIE 4425, 2001, 406-409.
DOI: https://doi.org/10.1117/12.429761   Google Scholar

Azarov A.D. et al.: Static and dynamic characteristics of the self-calibrating multibit ADC analog components. Proc. SPIE 8698, 2012, 86980N.
DOI: https://doi.org/10.1117/12.2019737   Google Scholar

Breiman L.: Out-of-bag estimation. Tech. rep. University of California, 1996 [https://www.stat.berkeley.edu/~breiman/OOBestimation.pdf].
  Google Scholar

Breiman L.: Random Forests. Machine Learning 45(1), 2001, 5–32.
DOI: https://doi.org/10.1023/A:1010933404324   Google Scholar

Dong B. et al.: Applying support vector machines to predict building energy consumption in tropical region. Energy and Buildings 37(5), 2005, 545–553.
DOI: https://doi.org/10.1016/j.enbuild.2004.09.009   Google Scholar

Esen H. et al.: Modelling of a new solar air heater through least-squares support vector machines. Expert Systems with Applications 36(7), 2009, 10673–1068.
DOI: https://doi.org/10.1016/j.eswa.2009.02.045   Google Scholar

Geng Y. et al.: Building energy performance diagnosis using energy bills and weather data. Energy and Buildings 172, 2018, 181–191.
DOI: https://doi.org/10.1016/j.enbuild.2018.04.047   Google Scholar

Kaczmarek C. et al.: Measurement of pressure sensitivity of modal birefringence of birefringent optical fibers using a Sagnac interferometer. Optica Applicata 45(1), 2015, 5–14.
DOI: https://doi.org/10.1109/ICSENS.2015.7370173   Google Scholar

Kukharchuk V. V. et al.: Method of magneto-elastic control of mechanic rigidity in assemblies of hydropower units. Proc. SPIE 10445, 2017, 104456A.
DOI: https://doi.org/10.1117/12.2280974   Google Scholar

Kukharchuk V. V. et al.: Noncontact method of temperature measurement based on the phenomenon of the luminophor temperature decreasing. Proc. SPIE 10031, 2016, 100312F.
DOI: https://doi.org/10.1117/12.2249358   Google Scholar

Kukharchuk V. V. et al.: Discrete wavelet transformation in spectral analysis of vibration processes at hydropower units. Przegląd Elektrotechniczny 93(5), 2017, 65–68.
  Google Scholar

Kvyetnyy R. et al.: Blur recognition using second fundamental form of image surface. Proc. SPIE 9816, 2015, 98161A.
DOI: https://doi.org/10.1117/12.2229103   Google Scholar

Kvyetnyy R. et al.: Method of image texture seg-mentation using Laws' energy measures. Proc. SPIE 10445, 2017, 1044561.
DOI: https://doi.org/10.1117/12.2280891   Google Scholar

Kvyetnyy R. et al.: Modification of fractal coding algorithm by a combination of modern technologies and parallel computations. Proc. SPIE 9816, 2015, 98161R.
DOI: https://doi.org/10.1117/12.2229009   Google Scholar

Osadchuk A. et al.: Pressure transducer of the on the basis of reactive properties of transistor structure with negative resistance. Proc. SPIE 9816, 2015, 98161C.
DOI: https://doi.org/10.1117/12.2229211   Google Scholar

Osadchuk O. et al.: The Generator of Superhigh Frequencies on the Basis Silicon Germanium Heterojunction Bipolar Transistors. 13th International Conference on Modern Problems of Radio Engineering, Telecommunications and Computer Science (TCSET), 2016, 336 – 338.
DOI: https://doi.org/10.1109/TCSET.2016.7452051   Google Scholar

Paluszyska A.: Structure mining and knowledge extraction from random forest with applications to The Cancer Genome Atlas project. 2017. [https://rawgit.com/geneticsMiNIng/BlackBoxOpener/master/randomForestExplainer_Master_thesis.pdf].
  Google Scholar

Parfenenko Yu. V. et al.: Prediction the heat consumption of social and public sector buildings using neural networks. Radio Electronics, Computer Science, Control 2, 2015, 41–46.
DOI: https://doi.org/10.15588/1607-3274-2015-2-5   Google Scholar

Perekrest A. et al.: Key Performance Indicators Assessment Methodology Principles Adaptation for Heating Systems of Administrative and Residential Buildings. IEEE Problems of Automated Electrodrive. Theory and Practice (PAEP), 2020, 1–4.
DOI: https://doi.org/10.1109/PAEP49887.2020.9240784   Google Scholar

Perekrest A. et al.: Complex information and technical solutions for energy management of municipal energetics. Proc. SPIE 10445, 2017, 1044567.
DOI: https://doi.org/10.1117/12.2280962   Google Scholar

Ruiz L. G. B. et al.: Energy consumption forecasting based on Elman neural networks with evolutive optimization. Expert Systems with Applications 92, 2018, 380–389.
DOI: https://doi.org/10.1016/j.eswa.2017.09.059   Google Scholar

Smolarz A. et al.: Fuzzy controller for a lean premixed burner. Przegląd Elektrotechniczny 86(7), 2010, 287–289.
  Google Scholar

Vapnik V., Chapelle O.: Bounds on error expectation for suport vector machines. Neural Computation 12 (9), 2000, 2013–2036.
DOI: https://doi.org/10.1162/089976600300015042   Google Scholar

Vedmitskyi Y. G. et al.: New non-system physical quantities for vibration monitoring of transient processes at hydropower facilities, integral vibratory accelerations. Przegląd Elektrotechniczny 93(3), 2017, 69–72.
DOI: https://doi.org/10.15199/48.2017.03.17   Google Scholar

Wei Y. et al.: A review of data-driven approaches for prediction and classification of building energy consumption. Renewable and Sustainable Energy Reviews 82, 2018, 1027–1047.
DOI: https://doi.org/10.1016/j.rser.2017.09.108   Google Scholar

Wójcik W. et al.: Concept of application of signals from fiber-optic system for flame monitoring to control separate pulverized coal burner. Proc. SPIE 5484, 2004, 427–431.
DOI: https://doi.org/10.1117/12.569041   Google Scholar

Wójcik W. et al.: Vision based monitoring of coal flames source. Przegląd Elektrotechniczny 84(3), 2008, 241–243.
  Google Scholar

Download


Published
2022-09-30

Cited by

Perekrest, A., Chenchevoi, V., Chencheva, O., Kovalenko, A., Kushch-Zhyrko, M., Kalizhanova, A., & Amirgaliyev, Y. (2022). PREDICTION MODEL OF PUBLIC HOUSES’ HEATING SYSTEMS: A COMPARISON OF SUPPORT VECTOR MACHINE METHOD AND RANDOM FOREST METHOD. Informatyka, Automatyka, Pomiary W Gospodarce I Ochronie Środowiska, 12(3), 34–39. https://doi.org/10.35784/iapgos.3032

Authors

Andrii Perekrest 
pksg13@gmail.com
Kremenchuk Mykhailo Ostrohradskyi National University Ukraine
http://orcid.org/0000-0002-7728-9020

Authors

Vladimir Chenchevoi 

Kremenchuk Mykhailo Ostrohradskyi National University Ukraine
http://orcid.org/0000-0002-6478-3767

Authors

Olga Chencheva 

Kremenchuk Mykhailo Ostrohradskyi National University Ukraine
http://orcid.org/0000-0002-5691-7884

Authors

Alexandr Kovalenko 

Cherkasy State Technological University Ukraine
http://orcid.org/0000-0002-5073-3507

Authors

Mykhailo Kushch-Zhyrko 

Kremenchuk Mykhailo Ostrohradskyi National University Ukraine
http://orcid.org/0000-0001-9622-9114

Authors

Aliya Kalizhanova 

University of Power Engineering and Telecommunications; Institute of Information and Computational Technologies MES CS RK Kazakhstan
http://orcid.org/0000-0002-5979-9756

Authors

Yedilkhan Amirgaliyev 

Institute of Information and Computational Technologies MES CS RK Kazakhstan
http://orcid.org/0000-0002-6528-0619

Statistics

Abstract views: 217
PDF downloads: 138


Most read articles by the same author(s)