Abstract
Problems of neural network forecasting system, invariant to type of energy consumption schedule are solved. Minimum length input vector structure is explained; neural network ensemble structures are determined; selection of the most effective neural network types in the ensemble is held. Original three-level structure of neural network ensemble is developed. Its high forecasting capability makes network perspective for solving information statistical analysis problems.
Similar content being viewed by others
References
Benn, D.V. and Farmer, E.D., Sravnitel’nye modeli prog-nozirovaniya elektricheskoy nagruzki (Comparative Models of Power Load Forecasting), Moscow: Energoatomizdat, 1987 [in Russian].
Shumilova, G.P., Gotman, N.E., and Startseva, T.B., Prognozirovanie elektricheskikh nagruzok pri operativnom upravlenii elektroenergeticheskimi sistemami na osnove neyrosetevykh struktur (Forecasting of Electric Loads in Operational Control of Electric Power Systems Based on Neural Networks), Syktyvkar: KNTs UrO RAN, 2008 [in Russian].
Buyankin, V.M., Razrabotka metoda sinteza mnogoparametricheskoy neyroprognoziruyuschey identifikacii s ispolzovaniem ansamblya neironnih setey s nachetkoy logikoy dlya slognih tehnologicheskih ustanovok (Development of the method of synthesis of the multiparameter neural based forecasting identification using an ensemble of neural networks with fuzzy logic for the complex technological installations), Promishlennie ASU i Controlleri, 2012, no. 6, pp. 31–35 [in Russian].
Staroverov, B.A. and Gnatyuk, B.A., Improving of the efficiency of the automatic system for commercial measurement of power consumption by introducing forecasting functions, Vestnik IGEU, 2013, issue 5, pp. 43–46.
Osovsky, S., Neironnye seti dlya obrabotki informatsii (Artificial Neural Networks for Information Handling), Moscow: Finansy I Statistika, 2002 [in Russian].
Author information
Authors and Affiliations
Corresponding author
About this article
Cite this article
Staroverov, B.A., Gnatyuk, B.A. Universal energy consumption forecasting system based on neural network ensemble. Opt. Mem. Neural Networks 25, 198–202 (2016). https://doi.org/10.3103/S1060992X16030097
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S1060992X16030097