Forecasting the Energy Consumption of an Industrial Enterprise Based on the Neural Network Model

• Autorzy: Kalinchyk Vasyl , Meita Olexandr , Pobigaylo Vitalii , Kalinchyk Vitalii , Filyanin Danylo

Identyfikatory

DOI

10.54740/ros.2021.033

• Języki publikacji: EN

Abstrakty

EN

This research paper investigates the application of neural network models for forecasting in energy. The results of forecasting the weekly energy consumption of the enterprise according to the model of a multilayer perceptron at different values of neurons and training algorithms are given. The estimation and comparative analysis of models depending on model parameters is made.

Słowa kluczowe

EN

electrical load; daily schedule; modelling; neural network; multilayer perceptron; MLP

• Wydawca: Politechnika Koszalińska
• Czasopismo: Rocznik Ochrona Środowiska
• Rocznik: 2021
• Tom: Tom 23
• Strony: 484--492
• Opis fizyczny: Bibliogr. 20 poz., rys., tab.

Twórcy

autor

Kalinchyk Vasyl

• Department of Power Supply, National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute"

• https://orcid.org/0000-0003-4028-0185

autor

Meita Olexandr

• Department of Electromechanical Equipment of Energy Production, National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute"

• https://orcid.org/0000-0002-4132-5202

autor

Pobigaylo Vitalii

• Department of Power Supply, National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute"

• https://orcid.org/0000-0003-2673-7329

autor

Kalinchyk Vitalii

• Department of Labor, Industrial and Civil Safety, National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute"

• https://orcid.org/0000-0003-3931-646X

autor

Filyanin Danylo

• Department of Power Supply, National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute"

• https://orcid.org/0000-0003-3576-3633

Bibliografia

• Chernenko, P.O. (2016). Peculiarities of short-term forecasting of electric load of power system with essential component of industrial power consumption / P.O. Chernenko, O.V. Martyniuk, V.O. Miroshnyk // Proceedings of the Institute of Electrodynamics of the National Academy of Sciences of Ukraine. 43. 24-31.
• Chuchueva, I.A. (2012). Model for forecasting time series based on a sample of maximum similarity: dissertation of the PhD: 05.13.18 / Chuchueva I.A. Moscow, 153.
• Dreyfus, G. (2005). Neural Networks. Springer, 386.
• Haykin, S. (1999). Neural Networks: A Comprehensive Foundation, 2nd Edition, Prentice-Hall.
• Kalinchik, V.P. (2013). Forecasting of indicators of energy consumption, generation and cost of the received energy / Kalinchik V.P., Kokorina M.T.: NTUU "KPI" N.-i. Institute of Automation and Power Engineering "Energy". Kiev, 14: bibliographic illustrations: 7 – deposit in SSTLU Ukraine 22.07.13, 35 Uk.
• Kalinchik, V.P. (2016). Energy-efficient control of the "crusher-mill" mechatronic complex using artificial neural networks / Kalinchik V.P., Rosen V.P., Shevchuk S.P., Meita A.V. // Energy: economics, technology, ecology, 3, 45-50.
• Komashinsky, V.I., Smirnov, D.A. (2002). Neural networks and their application in control and communication systems: Moscow: Hotline – Telecom, 94.
• Kruglov, V.V., Borisov, V.V. (2002). Artificial neural networks. Theory and practice. Moscow. Hotline – Telecom. 382.
• Medvedev, V.S., Potemkin, V.G. (2002). Neural networks. MATLAB 6. – Moscow: Dialogue, МIFE, 496.
• Neural networks. (2000). STATISTICA Neural Networks. – Moscow: Hotline – Telecom. 182.
• Picton, P. (2000). Neural networks. New York: Palgrave, 195.
• Prakhovnik, A.V. (1985). Energy-saving modes of power supply of mining enterprises / A.V. Prahovnik, V.P. Rosen, V.V. Degtyarev. – Moscow: Bosom, 232.
• Shumilova, G.P. (2008). Prediction of electrical loads in the operational control of electric power systems based on neural network structures / G.P. Shumilova, N.E. Gotman, T.B. Startseva. Syktyvkar: RAS, 78.
• Sukhbaataryn Munkhzhargal. (2004). Development and research of neural network algorithms for short-term forecasting of the load of the central electric power system of Mongolia: dissertation of the PhD: 05.14.02 / Sukhbaataryn Munkhzha. – Novosibirsk, 177.
• Surovtsev, I.S., Klyukin, V.I., Pivovarova, R.P. (1994). Neural networks. Voronezh: HSU, 224.
• Tikhonov, E.E. (2006). Forecasting methods in market conditions: textbook / E.E. Tikhonov – Nevinnomyssk: North Caucasian GTU, 221. ISBN 5895710778.
• Titterington, M. (2009). Neural networks. WIREs Computational Statistics, 2(1). 1-8.
• Vinoslavsky, V.N. (1974). Forecasting the power consumption of industrial facilities /V.N. Vinoslavsky, A.V. Prakhovnik, A.F. Bondarenko // Energy and electrification, 5, 30-31.
• Voloshko, A.V., Lutchin, T.M., Kladko, O.M. (2012). Short-term forecasting of electric load graphs based on wavelet transforms. Energosberezhenie, vol. Energy. Energy audit., 6. 35-42.
• Zaigraeva, Yu. B. (2008). Neural network models for assessing and planning energy losses in electrical systems: author. dis. for a job. scientific. degree of Cand. those. Sciences: spec. 05.14.02 "Power Plants and Electric Power Systems" / Zaigraeva Yulia Borisovna; Novosibirsk state technical university – Novosibirsk, 20.