NEURAL NETWORK MODELING IN PROBLEMS OF PREDICTION MODES OF ELECTRICAL GRIDS

Authors

  • A. N. Moroz Kharkiv Petro Vasylenko National Technical University of Agriculture, Ukraine
  • N. M. Cheremisin Kharkiv Petro Vasylenko National Technical University of Agriculture, Ukraine
  • V. V. Cherkashina National Technical University «Kharkiv Polytechnic Institute», Ukraine
  • A. V. Kholod Company «ELAKS», Ukraine

DOI:

https://doi.org/10.20998/2074-272X.2016.1.12

Keywords:

electric grid, neural grid, neuro-fuzzy grid, temperature monitoring of air electric line, prediction modes of electric grid

Abstract

Purpose. Form a neuro-fuzzy network based on temperature monitoring of overhead transmission line for the prediction modes of the electrical network. Methodology. To predict the load capacity of the overhead line architecture provides the use of neuro-fuzzy network based on temperature monitoring of overhead line. The proposed neuro-fuzzy network has a four-layer architecture with direct transmission of information. To create a full mesh network architecture based on hybrid neural elements with power estimation accuracy of the following two stages of the procedure: - in the first stage a core network (without power estimation accuracy) is generated; - in the second stage architecture and network parameters are fixed obtained during the first stage, and it is added to the block estimation accuracy, the input signals which are all input, internal and output signals of the core network, as well as additional input signals. Results. Formed neuro-fuzzy network based on temperature monitoring of overhead line. Originality. A distinctive feature of the proposed network is the ability to process information specified in the different scales of measurement, and high performance for prediction modes mains. Practical value. The monitoring system will become a tool parameter is measuring the temperature of the wire, which will, based on a retrospective analysis of the accumulated information on the parameters to predict the thermal resistance of the HV line and as a result carry out the calculation of load capacity in real time.

Author Biographies

A. N. Moroz, Kharkiv Petro Vasylenko National Technical University of Agriculture

Doctor of Technical Science, Professor

N. M. Cheremisin, Kharkiv Petro Vasylenko National Technical University of Agriculture

Candidate of Technical Science, Professor

V. V. Cherkashina, National Technical University «Kharkiv Polytechnic Institute»

Candidate of Technical Science, Associate Professor

A. V. Kholod, Company «ELAKS»

Engineer

References

Naumov A.N., Vendrov A.M., Ivanov V.K. Sistemy upravleniia bazami dannykh i znanii [Database management systems and knowledge]. Moscow, Finansy i statistika Publ., 1991. 352 p. (Rus).

Kenneth C. Sevcik. Priority scheduling disciplines in queueing network models of computer systems. In Proceedings of IFIP Congress’77. August 8-12, 1977, Toronto, Canada, pp. 565-570.

V. Mainkar, K.S. Trivedi. Approximate analysis of priority scheduling systems using stochastic reward nets. In Proceedings of the 13th International Conference on Distributed Computing Systems ICDCS’93. May 1993, Pittsburgh, PA, USA, pp. 466-473. doi: 10.1109/icdcs.1993.287678.

Leonard Kleinrock. Queueing Systems. Volume 8: Computer Applications. John Wiley and Sons, New York, USA, 1976.

Popov S.V., Cheremisin M.M., Parkhomenko O.V., Shkuro K.A. Neural network method for predicting accidents due to formation of ice on power lines overhead. Visnyk Vinnytskoho politekhnichnoho instytutu – Visnyk of Vinnytsia Politechnical Institute, 2012, no.1, pp.161-163. (Ukr).

Popov S.V., Shkuro K.A., Cheremisin N.M., Parkhomenko O.V. A hybrid method of predicting ice load on power lines overhead. Enerhetyka ta elektryfikatsiia – Energetic and electrification, 2013, no.5, pp. 33-38. (Rus).

Kruglov V.V. Methods of forecasting multivariate time series. Pribory i sistemy. Upravlenie, kontrol', diagnostika – Devices and systems. Management, monitoring, diagnostics, 2005, no.2, pp. 62-66. (Rus).

Popov S.V., Shkuro K.A. Evolutionary neuro-fuzzy network based on hybrid neural elements. 17 mizhn. konf. z avtomatychnoho upravlinnia «Avtomatyka-2010». Tezy dopovidei [Proceedings of 17th Int. Conf. of Automatic Control «Automation 2010»]. Kharkiv (Ukraine), 2010, vol.2, pp. 193-194. (Rus).

Popov S.V. Specialized architecture of artificial neural networks based on hybrid neural elements. Zbirnyk naukovykh prats Natsionalnoho hirnychoho universytetu – The collection of scientific works of National Mining University, 2009, vol.2, no.33, pp. 76-82.

Titov N.N. Povyshenie nadezhnosti i kachestva funktsionirovaniia avtomatizirovannykh sistem dispetcherskogo upravleniia elektroenergeticheskimi sistemami [Improving the reliability and quality of the functioning of the automated systems of dispatching management of power systems]. Kharkov, Fakt Publ., 2013. 200 p. (Rus).

Published

2016-03-12

How to Cite

Moroz, A. N., Cheremisin, N. M., Cherkashina, V. V., & Kholod, A. V. (2016). NEURAL NETWORK MODELING IN PROBLEMS OF PREDICTION MODES OF ELECTRICAL GRIDS. Electrical Engineering & Electromechanics, (1), 65–68. https://doi.org/10.20998/2074-272X.2016.1.12

Issue

Section

Power Stations, Grids and Systems