Geodesic
Electrical energy consumption prediction of the federal district of Russia on the based of the reccurent neural network
Journal of computational and engineering mathematics, Tome 5 (2018) no. 2, pp. 3-15.

Voir la notice de l'article provenant de la source Math-Net.Ru

The paper considers the prediction of electrical energy consumption using the recurrent neural network. Neural network is built on the base of the energy consumption data of the major Russian federal districts over the past 13 years. When developing the model, the following dominant factors were taken into account: data on energy consumption over the forecast period; meteorological factors (air temperature, cloudiness, amount of precipitation, wind speed, length of daylight, etc.); date (day, month); data of production calendars (information on the day of the week: weekday / weekend / holiday / shortened); specificity of the industry in the district under consideration (combining statistical information on major centers of federal districts). The factor were selected on the basis of test runs through the neural network of fixed configuration. The relevance of the study is explained by the practical importance of searching for the most accurate methods for predicting the main parameters of the energy market conducted by scientists in most developed countries of the world. The constructed recurrent neural network has yielded more accurate prediction results than the widely used mathematical prediction models based on regression dependencies. The obtained scientific result will help to reduce costs and increase the energy efficiency of the electro-energy subjects in the wholesale electric energy and capacity in Russia.
Keywords: neural network, neural forecast, recurrent neural network, RNN, power industry. 
@article{JCEM_2018_5_2_a0,
     author = {V. G. Mokhov and V. I. Tsimbol},
     title = {Electrical energy consumption prediction of the federal district of {Russia} on the based of the reccurent neural network},
     journal = {Journal of computational and engineering mathematics},
     pages = {3--15},
     publisher = {mathdoc},
     volume = {5},
     number = {2},
     year = {2018},
     language = {en},
     url = {http://geodesic.mathdoc.fr/item/JCEM_2018_5_2_a0/}
}
TY  - JOUR
AU  - V. G. Mokhov
AU  - V. I. Tsimbol
TI  - Electrical energy consumption prediction of the federal district of Russia on the based of the reccurent neural network
JO  - Journal of computational and engineering mathematics
PY  - 2018
SP  - 3
EP  - 15
VL  - 5
IS  - 2
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/JCEM_2018_5_2_a0/
LA  - en
ID  - JCEM_2018_5_2_a0
ER  - 
%0 Journal Article
%A V. G. Mokhov
%A V. I. Tsimbol
%T Electrical energy consumption prediction of the federal district of Russia on the based of the reccurent neural network
%J Journal of computational and engineering mathematics
%D 2018
%P 3-15
%V 5
%N 2
%I mathdoc
%U http://geodesic.mathdoc.fr/item/JCEM_2018_5_2_a0/
%G en
%F JCEM_2018_5_2_a0
V. G. Mokhov; V. I. Tsimbol. Electrical energy consumption prediction of the federal district of Russia on the based of the reccurent neural network. Journal of computational and engineering mathematics, Tome 5 (2018) no. 2, pp. 3-15. http://geodesic.mathdoc.fr/item/JCEM_2018_5_2_a0/

[1] L. B. Melamed, N. I. Suslov, Ekonomika energetiki: osnovy teorii, Izdatelstvo SO RAN, Novosibirsk, 2000

[2] V. I. Mikhailov, Kontseptsiya rynochnykh reform v elektroenergetike Rossii, M-vo obrazovaniya Ros. Federatsii. Gos. un-t upr., M., 2001

[3] J. Nowotarski, E. Raviv, S. Trück, R. Weron, “An Empirical Comparison of Alternate Schemes for Combining Electricity Spot Price Forecasts”, Energy Economics, 46 (2014), 396–412 | DOI

[4] J. Bastian, J. Zhu, V. Banunarayanan, R. Mukerji, “Forecasting Energy Prices in a Competitive Market”, IEEE Computer Applications in Power, 12 (1999), 40–45 | DOI

[5] B. Yildiz, A. Yalama, M. Coskun, “Forecasting the Istanbul Stock Exchange National 100 Index Using an Artificial Neural Network”, An International Journal of Science, Engineering and Technology, 46 (2008), 36–39

[6] C. Robinson, “The Energy Market and Energy Planning”, Long Range Planning, 9:6 (1976), 30–38 | DOI

[7] A. Serletis, L. Xu, “Volatility and a Century of Energy Markets Dynamics”, Energy Economics, 55 (2016), 1–9 | DOI

[8] G. J. Osório, J. C. O. Matias, J. P. S. Catalão, “Electricity Prices Forecasting by a Hybrid Evolutionary-Adaptive Methodology”, Energy Conversion and Management, 80 (2014), 363–373 | DOI

[9] Y. Wang, C. Wu, “Forecasting Energy Market Volatility Using GARCH Models: Can Multivariate Models Beat Univariate Models?”, Energy Economics, 34:6 (2012), 2167–2181 | DOI

[10] O. Efimova, A. Serletis, “Energy Markets Volatility Modelling Using GARCH”, Energy Economics, 43 (2014), 264–273 | DOI

[11] C. Chiarella, L. Clewlow, B. Kang, “Modelling and Estimating the Forward Price Curve in the Energy Market”, Quantitative Finance Research Centre, 2009, no. 260, 1–17 | Zbl

[12] I. A. Chuchueva, Skolko stoit na OREM povyshenie tochnosti prognoza energopotrebleniya na 1 MVt, } (data obrascheniya: 11 maya 2018 g.) {\tt http://mbureau.ru/blog/skolko-stoit-na-orem-povyshenie-tochnosti-prognoza-energopotrebleniya-na-1-mvt

[13] I. A. Soloveva, Upravlenie zatratami na elektropotreblenie na promyshlennykh predpriyatiyakh v sovremennykh ekonomicheskikh usloviyakh, Izdatelskii tsentr YuUrGU, Chelyabinsk, 2017

[14] V. G. Mokhov, T. S. Demyanenko, “Modelling of the time series digressions by the example of the UPS of the Ural”, Bulletin of the South Ural State University. Series: Mathematical Modelling, Programming and Computer Software, 8:4 (2015), 127–130 | DOI

[15] C. Rodriguez, G. Anders, “Energy Price Forecasting in the Ontario Competitive Power System Market”, IEEE Transactions on Power Systems, 19:1 (2004), 366–374 | DOI

[16] S. Voronin, J. Partanen, “Price Forecasting in the Day-Ahead Energy Market by an Iterative Method with Separate Normal Price and Price Spike Frameworks”, Energies, 6:11 (2013), 5897–5920 | DOI

[17] J. Wang, J. Wang, “Forecasting Energy Market Indices with Recurrent Neural Networks: Case Study of Crude Oil Price Fluctuations”, Energy, 102 (2016), 365–374 | DOI

[18] A. Parida, R. Bisoi, P. Dash, “Chebyshev Polynomial Functions Based Locally Recurrent Neuro-Fuzzy Information System for Prediction of Financial and Energy Market Data”, Journal of Finance and Data Science, 2:3 (2016), 202–223 | DOI

[19] V. G. Mokhov, T. S. Demyanenko, K. V. Demyanenko, “Analysis of formalized methods for forecasting the volume of electricity consumption”, Journal of Computational and Engineering Mathematics, 4:4 (2017), 3–14 | DOI | MR

[20] Sistemnyi operator edinoi energeticheskoi sistemy, } (data obrascheniya: 11 maya 2018 g.) {\tt http://www.so-ups.ru

[21] National Oceanic and Atmospheric Administration } (accessed on May 11, 2018) {\tt http://www.noaa.gov

[22] Voskhod solntsa } (data obrascheniya: 11 maya 2018 g.) {\tt http://www.voshod-solnca.ru

[23] GARANT.RU Informatsionno-pravovoi portal } (data obrascheniya: 11 maya 2018 g.) {\tt https://www.garant.ru

[24] N. Sh. Kremer, B. A. Putko, Ekonometrika, Izd-vo YuNITI-DANA, M., 2010

[25] Python Data Analysis Library Pandas } (accessed on May 11, 2018) {\tt http://www.pandas.pydata.org

[26] TensorFlow } (accessed on May 11, 2018) {\tt https://www.tensorflow.org

[27] Keras Documentation } (accessed on May 11, 2018) {\tt http://www.keras.io

[28] I. A. Chuchueva, “Model ekstrapolyatsii vremennykh ryadov po vyborke maksimalnogo podobiya”, Informatsionnye tekhnologii, 2010, no. 12, 43–47