PREDICTION THE HEAT CONSUMPTION OF SOCIAL AND PUBLIC SECTOR BUILDINGS USING NEURAL NETWORKS

Authors

  • Yu. V. Parfenenko Sumy State University, Sumy, Ukraine, Ukraine
  • V. V. Shendryk Sumy State University, Sumy, Ukraine, Ukraine
  • O. S. Galichenko Sumy State University, Sumy, Ukraine, Ukraine

DOI:

https://doi.org/10.15588/1607-3274-2015-2-5

Keywords:

heat consumption, management, modeling, information systems, prediction, neural networks, energy saving.

Abstract

The method of improvement the process of decision support to improve management of heat supplies’ modes through the development
of prediction heat consumption model of the social and public sector building is proposed. The object of the study is the process of choosing
the most optimal architecture of the neural network to solve goals of forecasting of heat consumption of the building of social and public
sector. The subject of the study is models prediction heat consumption of buildings of social and public sector using artificial neural networks.
The purpose of this study is to improve the forecasting reliability of heat energy demand of social and public sector buildings. Models of shortterm prediction of heat energy demand of social and public sector buildings using artificial neural networks that take into account the influence of weather conditions, fluctuations in demand for thermal energy depending on the type of day of the week and the previous values of heat energy demand are proposed. Models are based on such architectures of neural network’s as a nonlinear network input-output, a nonlinear autoregressive network, a nonlinear autoregressive neural network with external inputs. The proposed models were implemented in the programming environment Matlab, to train their the Levenberg-Marquard algorithm was used. Experiments on the study of the accuracy of the developed models, which showed that the greatest accuracy of prediction can be achieved by using a model type NARX, were carried. Using the proposed model within the information system «HeatCAM» for the prediction of building’s heat consumption during the heating season
can increase the effectiveness of decision support in the management of heating modes, which reduces heat consumption.

References

Системные исследования в энергетике: Ретроспектива научных направлений СЭИ-ИСЭМ / отв. ред. Н. И. Воропай. – Новосибирск : Наука, 2010. – 686 с. 2. Вороновский Г. К. Проблемы и перспективы использования искусственных нейронных сетей в энергетике. Ч. 2. Управление / Г. К. Вороновский, К. В. Махотило, С. А. Сергеев // Пробл. заг. енергетики. – 2007. – № 16. – С. 54–67. 3. Chramcov B. Heat Demand Forecasting for Concrete District Heating System / B. Chramcov, Ja. Baláte, M. Princ // International Journal of Mathematical Models and Methods in Applied Sciences. – 2010. – Vol. 4, No. 4. – P. 231–239. 4. Bacher P. Short-term heat load forecasting for single family houses / P. Bacher, H. Madsen // Energy and Buildings. – 2013. – Vol. 65. – P.101–112. 5. Kontu K. Forecasting district heating consumption based on customer measurements [Electronic resource] / K. Kontu // International association EUROHEAT & POWER. – Access mode: http://www.euroheat.org/Files/Filer/Presentations/20130527_EHP_Congress/130527_1600_1730_Pl_6_Kaisa Kontu.pdf. 6. Grosswindhager S. Online Short-Term Forecast of System heat Load in District Heating Networks / S. Grosswindhager, A. Voigt, M. Kozek // ISF 2011 : the 31st International Symposium on Forecasting, Prague, Czech Republic, 26–29 June 2011 :conference proceedings. – Lancaster : International Institute of Forecasters, 2011. – P. 1–8. 7. Dostál P. Prediction of the heat supply daily diagram via artificial neural network / P. Dostál, B. Chramcov, Ja.Baláte // East West Fuzzy Colloquium : proceedings. Zittau, Germany, 2002. – P. 178–183. 8. Buhari M. Short-Term Load Forecasting Using Artificial Neural Network / M. Buhari, S. S. Adamu // IMECS 2012 : International MultiConference of Engineers and Computer Scientist, Hong Kong, 14–16 Mar 2012 : proceedings. – Hong Kong, 2012. 9. Grzenda M. Consumer-oriented heat consumption prediction / M. Grzenda // Control and Cybernetics. – 2012. – Vol. 41, No. 1. – P. 213–240.

Downloads

Published

2014-11-21

How to Cite

Parfenenko, Y. V., Shendryk, V. V., & Galichenko, O. S. (2014). PREDICTION THE HEAT CONSUMPTION OF SOCIAL AND PUBLIC SECTOR BUILDINGS USING NEURAL NETWORKS. Radio Electronics, Computer Science, Control, (2). https://doi.org/10.15588/1607-3274-2015-2-5

Issue

No. 2 (2015): Radio Electronics, Computer Science, Control

Section

Neuroinformatics and intelligent systems

License

Copyright (c) 2015 Yu. V. Parfenenko, V. V. Shendryk, O. S. Galichenko

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Creative Commons Licensing Notifications in the Copyright Notices

The journal allows the authors to hold the copyright without restrictions and to retain publishing rights without restrictions.

The journal allows readers to read, download, copy, distribute, print, search, or link to the full texts of its articles.

The journal allows to reuse and remixing of its content, in accordance with a Creative Commons license СС BY -SA.

Authors who publish with this journal agree to the following terms:

  • Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License CC BY-SA that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.

  • Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.

  • Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.