NEURO-NETWORK MODEL FOR PROVIDING ELECTRICITY GENERATION BY RENEWABLE SOURCES IN ENERGY MANAGEMENT SYSTEM OF LOCAL OBJECT

Автор(и)

DOI:

https://doi.org/10.20535/1813-5420.2.2019.190002

Анотація

The paper provides continuation research related to the analysis of the structures of combined power systems. It’s considered with regard the choice of the model line of power traditional and renewable sources for forming energy balance microgrid system to increase the efficiency of management energy local objects.

The research is to substantiate and implement a neural network model to predict the generation of electricity from renewable sources to develop intelligent algorithms for the energy management system of local objects. Neural network modeling, theory of computational intelligence, and gradient optimization methods for analyzing the behavior of multicomponent systems were used to create an intelligent prognostic apparatus.
The principles of intelligent management combined power supply of local objects based on neural network prediction of electricity generation by renewable sources are substantiated. The paper is proposed basic algorithms for the system of energy management of local objects.
By means of neural network prediction electricity generation by renewable sources, the basic theoretical principles of creation of the system of intellectual control of the combined electric supply of local objects based on a conditional dynamic tariff are formulated.
It is given based to allow users conditional dynamic tariff to reconcile real-time power schedules with one parameter.
The propose a neural network model for a combined power system with a wind- solar power plant to develop algorithms and structural and logical diagram of intelligent management power consumption local object with heterogeneous sources is allowed. It’s based to use statistics of daily electricity generation with half-hour discrete energy.

Посилання

European Smart Grids Technology Platform. Vision and Strategy for Europe’s Electricity Networks of the Future. – Luxembourg: Office for Official Publications of the European Communities, 2006.

Kaplun V. V. Umovnyi dynamichnyi taryf yak kryterii efektyvnosti funktsionuvannia mikroenerhetychnykh system lokalnykh obiektiv / V. V. Kaplun // Visnyk Kyivskoho natsionalnoho universytetu tekhnolohii ta dyzainu. Seriia : Tekhnichni nauky. - 2016. - № 3. - S. 50-58.

Kaplun V.V. Resursno-protsessnыi podkhod k postroenyiu matematycheskoi modely mykroэnerhetycheskoi systemы / V. V. Kaplun, P. A. Pavlov, V. N. Shtepa // Visnyk Kyivskoho natsionalnoho universytetu tekhnolohii ta dyzainu. Seriia "Tekhnichni nauky" : retsenzovanyi naukovyi zhurnal. – 2016. – № 2. – S. 48-60.

Global Energy Forecasting Competition 2014: Probabilistic Solar Power Forecasting [Електронний ресурс]. URL: https://www.crowdanalytix.com/contests/global-energy-forecasting-competition-2014- probabilistic-solar-power-forecasting (дата звернення: 29.07.2019)

Brester Ch. Yu., Semenkin E. S. Development of adaptive genetic algorithms for neural network models multicriteria design // Вестник Сибирского государственного аэрокосмического университета им. академика М. Ф. Решетнева. 2013. № 4 (50). С. 99–103.

Cortes C., Vapnik V. N. Support-Vector Networks // Machine Learning, 20, 1995.

Smola A. J., Schoelkopf B. A tutorial on support vector regression. Statistics and Computing, 1998.

Y-K Wu, and J-S Hong, “A literature review of wind forecasting technology in the world,” IEEE Power Tech 2007, Lausanne , pp. 504-509, 1-5 July 2007.

“Load Forecasting” Chapter 12, E.A Feinberg and Dora Genethlio, Page 269 – 285

Kruhlov V.V. Yskusstvennыe neironnыe sety. Teoryia y praktyka / V.V. Kruhlov. – M.: Horiachaia lynyia – Telekom, 2002. – 382 s.

Neiromerezheve prohnozuvannia chasovykh riadiv temperatury navkolyshnoho pryrodnoho seredovyshcha / V.P. Lysenko, N.A. Zaiets, V.M. Shtepa, A.O. Dudnyk // Bioresursy i pryrodokorystuvannia: nauk. zhurn. – 2011. – T. 3, № 3-4. – S. 102-108.

##submission.downloads##

Опубліковано

2019-12-27

Номер

Розділ

ЕНЕРГЕТИЧНА ЕФЕКТИВНІСТЬ ТА ЕНЕРГОЗБЕРЕЖЕННЯ