MODEL OF ADAPTIVE CONTROL SYSTEM OF REACTIVE POWER FLOW AT THE BALANCE AFFILIATION BOUNDARY OF AN ENTERPRISE AND A GRID OPERATOR
https://doi.org/10.21285/1814-3520-2018-12-185-201
Abstract
The paper proposes the structure of the reactive power flow control system at a balance affiliation boundary of an enterprise and a grid operator. It deals with the features of neural networks and presents a numerical mathematical model based on an artificial neural network for adaptive control of reactive power flow. Training of the neural network is automated and implemented in software. Levenberg-Marquardt method is used for neural network training. The structure of the control system of reactive power flow and voltage levels is designed. A Levenberg-Marquardt method-based algorithm for neural network training is developed and implemented in software. The authors have proposed an adaptive control system of reactive power flow at the balance affiliation boundary of an enterprise and a grid operator based on the synthesis of the artificial neural network and STATCOM own logic.
About the Authors
R. A. Petukhov
Siberian Federal University
Russian Federation
Russian Federation
E. Yu. Sizganova
Siberian Federal University
Russian Federation
Russian Federation
N. V. Sizganov
Scientific Production Center of Magnetic Hydrodynamics LLC
Russian Federation
Russian Federation
A. N. Filatov
Siberian Federal University
Russian Federation
Russian Federation
References
1. Петухов Р.А., Сизганова Е.Ю., Сизганов Н.В., Филатов А.Н. К вопросу автоматизации управления потоками реактивной мощности в системах электроснабжения // Вестник Иркутского государственного технического университета. 2018. Т. 22. № 7. С. 123-146. https://doi.org/10.21285/1814-3520-2018-7-123-146
2. Guo Z. et al. (2019) Cloud Computing Platform Design and Machine Learning-Based Fault Location Method in Automatic Dispatching System of Smart Grid. In: Liang Q., Mu J., Jia M., Wang W., Feng X., Zhang B. (eds) Communications, Signal Processing, and Systems. CSPS. Lecture Notes in Electrical Engineering. 2017. Vol. 463. Springer, Singapore DOIhttps://doi.org/10.1007/978-981-10-6571-2_259
3. Han D., Sun W., FanX. Dynamic energy management in smart grid: a fast randomized first-order optimization algorithm IJEPES, 94 (2018), 10.1016/j.ijepes.2017.07.003
4. Gwang W.K., Lee K.Y. Coordination control of ULTC transformer and STATCOM based on an artificial neural network, IEEE Trans. on Power System. 2005. Vol. 20 (2). P. 580-586.
5. Медведев В.С., Потемкин В.Г. Нейронные сети. MATLAB 6.М.: ДИАЛОГ-МИФИ, 2002. 496 с.
6. Anil K. Jain, Jianchang Mao, K.M. Mohiuddin - Artificial Neural Networks: A Tutorial, Computer.1996. Vol. 29.No. 3.P. 31-44.
7. Комякова О.А. Возможности искусственных нейронных сетей как аппарата для прогнозирования расхода электрической энергии на предприятиях железнодорожного транспорта // Омский научный вестник. Серия: Приборы, машины и технологии. 2013. № 2. С. 264-266.
8. Хайкин С. Нейронные сети: полный курс. 2-е изд. / пер. с англ. М.: Изд. Дом «Вильямс», 2006. 1104 с.
9. Пархоменко С.С., Леденева Т.М. Обучение нейронных сетей методом Левенберга-Марквардта в условиях большого количества данных // Вестник Воронежского государственного университета. Серия: Системный анализ и информационные технологии. 2014. № 2.С. 98-106.
10. Кохонен Т. Толковый словарь «нейронных» терминов. Самоорганизующиеся карты / пер. с англ. М.: БИНОМ. Лаборатория знаний, 2013. С. 532.
11. Хайкин С. Преимущества и ограничения обучения методом обратного распространения // Нейронные сети. М.: Вильямс, 2006.С. 304-314.
12. Sousa C. Neural network learning by the Levenberg-Marquardt algorithm with Bayesian regularization (part 1). 2009. URL: http:// crsouza.blogspot.com/2009/11/neural-networklearning-by-levenberg_18.html.
13. Suratgar A.A., Tavakoli M.B., Hoseinabadi A. Modified Levenberg-Marquardt method for neural networks training.
14. Transtrum M.K., Sethna J.P. Improvements to the levenberg-marquardt algorithm for nonlinear least-squares minimization // Journal of Computational Physics. 2012.
15. Sousa C. Neural network learning by the Levenberg-Marquardt algorithm with Bayesian regularization (part 2). 2009. URL: http:// crsouza.blogspot.com/2009/11/neural-networklearning-by-levenberg.html.
Review
For citations:
Petukhov R.A., Sizganova E.Yu., Sizganov N.V., Filatov A.N. MODEL OF ADAPTIVE CONTROL SYSTEM OF REACTIVE POWER FLOW AT THE BALANCE AFFILIATION BOUNDARY OF AN ENTERPRISE AND A GRID OPERATOR. Proceedings of Irkutsk State Technical University. 2018;22(12):185-201. (In Russ.) https://doi.org/10.21285/1814-3520-2018-12-185-201
Views:
263
Email this article 