DEVELOPMENT OF NEURAL NETWORK MODELS TO PREDICT AND CONTROL POWER CONSUMPTION IN MINERAL MINING INDUSTRY

Control and prediction of power consumption regimes is one of the pressing problems in mineral mining industry. One of the heaviest expenditure items is connected with the electricity bills payment. Optimization of price brackets of power to be consumed and application of consumption controllers facilitates reduction in maximum energy consumption in the production rush hours, decreases energy loss in internal and external mains, reduction in electricity bills and creation of favorable operation conditions for electric power systems in the tightest periods of day. Efficiency of the adjustment measures towards electricity reduction and power consumption limitation in the time of peak demand and transfer to electric power consumption to a day time zone when the electricity bills are minimal is evaluated; the compound plots of actual and wattless power are drawn; one-part and two-part electricity tariffs are calculated and performance capability of using different power price brackets (3–6 price brackets) is appraised. The algorithm is put forward for electric energy consumption prediction for a month period based on artificial neural networks to determine optimum price brackets, including planning.

Keywords

Power consumption control, electricity tariff, consumer–controller, artificial neural networks, backpropagation algorithm.

Issue number: 5
Year: 2018
ISBN:
UDK: 621.314
DOI: 10.25018/0236-1493-2018-5-0-206-213
Authors: Abramovich B. N., Babanova I. S.

About authors: Abramovich B.N., Doctor of Technical Sciences, Professor, e-mail: babaramov@mail.ru, Babanova I.S., Graduate Student, e-mail: irina_babanova@mail.ru, Saint Petersburg Mining University, 199106, Saint-Petersburg, Russia.

REFERENCES:

1. Postanovlenie Pravitel'stva RF «Ob utverzhdenii pravil optovogo rynka elektricheskoy energii i moshchnosti i o vnesenii izmeneniy v nekotorye akty Pravitel'stva Rossiyskoy Federatsii po voprosam organizatsii funktsionirovaniya optovogo rynka elektricheskoy energii i moshchnosti» (utv. 27.12.2010 g. №1172, red. ot 29.02.2016 g). (Government regulations of wholesale market of electric energy and wattage and amendment of some governmental acts of Russian Federation on functioning of wholesale market of electric energy and wattage (approved as of Dec 27, 2010, No. 1172, edited as of Feb 29, 2016)).

2. Postanovlenie Pravitel'stva RF «O funktsionirovanii roznichnykh rynkov elektricheskoy energii, polnom i (ili) chastichnom ogranichenii rezhima potrebleniya elektricheskoy energii» (utv. 04.05.2012 g. № 442, red. 22.02.2016 g) (Functioning of retail markets of electric energy subject to complete and (or) partial limitation of power consumption (approved as of May 04, 2012, No. 442, edited as of Feb 22, 2016)).

3. Daut M. A.M.; Hassan M. Y.; Abdullah, H.; Rahman H. A.; Abdullah M. P.; Hussin, F. Building electrical energy consumption forecasting analysis using conventional and artificial intelligence methods:

A review. Renew. Sustain. Energy Rev. 2017, 70, pp. 1108—1118.

4. Chengdong Li, Zixiang Ding, Dongbin Zhao, Jianqiang Yi, Guiqing Zhang Building Energy Consumption Prediction. Extreme Deep Learning Approach Energies 2017, 10 (10)

5. Naji S., Keivani A., Shamshirband S, Alengaram U. J., Jumaat M. Z., Mansor Z., Lee M. Estimating building energy consumption using extreme learning machine method. Energy, 2016, 97, pp. 506—516.

6. Pérez-Chacón R., Talavera-Llames R. L., Martinez-Alvarez F., Troncoso A. Finding electric energy consumption patterns in big time series data. Proceedings of the13th International Conference Distributed Computing and Artificial Intelligence, Sevilla, Spain, 1—3 June 2016; Springer: Cham, Switzerland, 2016, pp. 231—238.

7. Khaykin S. Neyronnye seti: polnyy kurs (Neural networks: Full course), Moscow, Vil'yams, 2006, 781 p.

8. Shumilova G. P., Gotman N. E., Startseva T. B. Prognozirovanie elektricheskikh nagruzok pri operativnom upravlenii elektroenergeticheskimi sistemami na osnove neyrosetevykh struktur (Prediction of electric energy demands under operating control of power systems based on neural network structures), Syktyvkar, KNTs UrO RAN, 2008.

9. Abramovich B. N., Babanova I. S. Mining sciences and technologies. 2016, no 2, pp. 66—77.

10. Ustinov D. A., Babanova I. S. Promyshlennaya energetika.2016, no 11, pp. 9—16.

11. Abramovich B. N., Babanova I. S. Gornyy informatsionno-analiticheskiy byulleten'. 2017. Special edition 5—2, pp. 310—318.

12. Zhukovskiy Yu. L., Korolev N. A., Babanova I. S., Boikov A. V. The prediction of the residual life of electromechanical equipment based on the artificial neural network IOP Conf. Series: Earth and Environmental Science 87 (2017) 032056.

Subscribe for our dispatch