Keywords
electrical load
short-term forecasting
regression models
artificial neural networks
neurofuzzy network енергосистема
електричне навантаження
короткострокове прогнозування
регресійні моделі
штучні нейронні мережі
нейро-фаззі мережі
How to Cite
Abstract
This paper deals with the solution of the problem of short-term forecasting of the power system active load (PSAL) in two ways. First, to build a mathematical model using parametric method of analysis and prediction of non-stationary time series. The second - the neuro-fuzzy network. The additive mathematical model of PSAL, algorithms of modelling and prediction of its components are presented. The architecture of the neuro-fuzzy network and learning algorithm are described. With the purpose of adequate comparing of results, using the same informations, the forecasting of PSAL for a week are performed. The advantages of hierarchical problem solving short-term forecasting electrical load of united power systems with using the mathematical models load of regional power systems are demonstrated. The ways of further improving of the accuracy and reliability results of the short-term forecasting of PSAL are formulated. References 15, tables 4, figures 9.
References
Gross E., Galiana F. Short term load forecasting // ТIIER. Temat. vyp. “EVM v upravlenii energosistemami”. – 1987. – Т.75. – №12. – Pр. 6–23. (Rus)
Chernenko P. Tiered interconnected electric load forecasting of united power system // Pratsi Instytutu Elektrodynamiky Natsionalnoi Akademii Nauk Ukrainy. Enerhoefektyvnist. – 2000. – Pp. 99–104. (Rus)
Chernenko P. Parameter identification, modeling and multilevel forecasting of electrical loads of united power system // Tekhnichna elektrodynamika. Temat. vypusk ''Problemy suchasnoi elektrotekhnіky''. – 2010. – Vol.3. – Pp. 57–64. (Rus)
Martyniuk O., Chernenko P. Algorithms and software for three-level short-term electric load forecasting of united power system of Ukraine // Enerhetyka ta elektryfikatsiia. – № 7. – 2012. – Pp. 3–8. (Ukr)
Chernenko P., Kuznetsov G. Definition of informativeness and short-term forecasting periodically nonstationary random processes in power systems // Kyiv: IED AN USSR, Preprint 157. – 1977. – 38 p. (Rus)
Hippert H.S., Pedreira C.E., Souza R.C. Neural networks for short-term load forecasting: a review and evaluation // IEEE Trans. Power Systems. – 2001. – Vol. 16. – № 1. – Pp. 44–55.
Danyliuk O., Mayorov A., Batiuk N., Mykhailiuk M. Prediction modes load power systems based on the technology of artificial neural networks // Informatsiini tekhnologii i systemy. – 2001. – Vol. 4. – № 1/2. – Pp. 100–103. (Ukr)
Chernenko P., Martyniuk O. Multi-level short-term forecasting of electric load of united power system // Visnyk Vinnytskoho politekhnichnoho instytutu. – 2011. – №2. – Pp. 74–80. (Ukr)
Chernenko P., Martyniuk O. Improving the effectiveness of short-term electric load forecasting of united power system // Tekhnichna elektrodynamika. – № 1. – 2012. – Pp. 63–70. (Ukr)
Bodyanskiy Ye., Popov S., Chepenko T. Predictive adaptive neural network with dynamic neuronfilters // Radioelektronika i informatika. – 2003. – №2. – Pp. 48–51. (Rus)
Bodyanskiy Ye., Popov S. Neuro-Fuzzy Unit for Real-Time Signal Processing // Proc. IEEE East-West Design & Test Workshop (EWDTW’06). – Sochi, Russia, September 15-19, 2006. – Pp. 403–406.
Bodyanskiy Ye., Popov S. Multilayer Network of Neuro-Fuzzy Units in Forecasting Applications // Research Papers of Wroclaw University of Economics. Knowledge Acquisition and Management. – 2008. – №25. – Pp. 9–14.
Bodyanskiy Ye., Popov S., Rybalchenko T. Determine the effect of temperature on energy consumption using neural network technology // Zbіrnyk Naukovykh Prats Natsіonalnoho hіrnychoho unіversytetu. – 2008. – №31. – Pp. 169–173. (Rus)
Bodyanskiy Ye., Popov S., Rybalchenko T. Feedforward neural network with a specialized architecture for estimation of the temperature influence on the electric load // Proc. 4th International IEEE Conference "Intelligent Systems". – Varna, 2008. – Vol. I. – Pp. 714–718.
Bodyanskiy Ye., Popov S., Titov M. Robust Learning Algorithm for Networks of Neuro-Fuzzy Units // Innovations and Advances in Computer Sciences and Engineering / Ed. by T. Sobh. – Dordrecht: Springer, 2010. – Pp. 343–346.
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Copyright (c) 2023 Tekhnichna Elektrodynamika