hrcak mascot   Srce   HID

Izvorni znanstveni članak

SHORT-TERM POWER SYSTEM HOURLY LOAD FORECASTING USING ARTIFICIAL NEURAL NETWORKS

NINOSLAV HOLJEVAC   ORCID icon orcid.org/0000-0001-6570-2757 ; Faculty of Electrical Engineering and Computing, University of Zagreb Unska 3, 10000 Zagreb, Croatia
CATARINA SOARES ; Faculty of Electrical Engineering and Computing, University of Zagreb Unska 3, 10000 Zagreb, Croatia
IGOR KUZLE   ORCID icon orcid.org/0000-0001-8992-4098 ; Faculty of Electrical Engineering and Computing, University of Zagreb Unska 3, 10000 Zagreb, Croatia

Puni tekst: engleski, pdf (850 KB) str. 0-0 preuzimanja: 59* citiraj
APA 6th Edition
HOLJEVAC, N., SOARES, C. i KUZLE, I. (2017). SHORT-TERM POWER SYSTEM HOURLY LOAD FORECASTING USING ARTIFICIAL NEURAL NETWORKS. Journal of Energy, 66 (1-4), 0-0. Preuzeto s https://hrcak.srce.hr/199752
MLA 8th Edition
HOLJEVAC, NINOSLAV, et al. "SHORT-TERM POWER SYSTEM HOURLY LOAD FORECASTING USING ARTIFICIAL NEURAL NETWORKS." Journal of Energy, vol. 66, br. 1-4, 2017, str. 0-0. https://hrcak.srce.hr/199752. Citirano 26.05.2020.
Chicago 17th Edition
HOLJEVAC, NINOSLAV, CATARINA SOARES i IGOR KUZLE. "SHORT-TERM POWER SYSTEM HOURLY LOAD FORECASTING USING ARTIFICIAL NEURAL NETWORKS." Journal of Energy 66, br. 1-4 (2017): 0-0. https://hrcak.srce.hr/199752
Harvard
HOLJEVAC, N., SOARES, C., i KUZLE, I. (2017). 'SHORT-TERM POWER SYSTEM HOURLY LOAD FORECASTING USING ARTIFICIAL NEURAL NETWORKS', Journal of Energy, 66(1-4), str. 0-0. Preuzeto s: https://hrcak.srce.hr/199752 (Datum pristupa: 26.05.2020.)
Vancouver
HOLJEVAC N, SOARES C, KUZLE I. SHORT-TERM POWER SYSTEM HOURLY LOAD FORECASTING USING ARTIFICIAL NEURAL NETWORKS. Journal of Energy [Internet]. 2017 [pristupljeno 26.05.2020.];66(1-4):0-0. Dostupno na: https://hrcak.srce.hr/199752
IEEE
N. HOLJEVAC, C. SOARES i I. KUZLE, "SHORT-TERM POWER SYSTEM HOURLY LOAD FORECASTING USING ARTIFICIAL NEURAL NETWORKS", Journal of Energy, vol.66, br. 1-4, str. 0-0, 2017. [Online]. Dostupno na: https://hrcak.srce.hr/199752. [Citirano: 26.05.2020.]

Sažetak
Artificial neural networks (ANN) have been used for many application in
various sectors. The learning property of an ANN algorithm in solving both linear
and non-linear problems can be utilized and applied to different forecasting
problems. In the power system operation load forecasting plays a key role in the
process of operation and planning.
This paper present the development of an ANN based short-term hourly load
forecasting model applied to a real data from MIBEL – Iberian power market test
case. The historical data for 2012 and 2013 ware used for a Multilayer Feed
Forward ANN trained by Levenberg-Marquardt algorithm. The forecasted next day
24 hourly peak loads and hourly consumptions are generated based on the
stationary output of the ANN with a performance measured by Mean Squared Error
(MSE) and MAPE (Mean Absolute Percentage Error). The results have shown good
alignment with the actual power system data and have shown proposed method is
robust in forecasting future (short-term) hourly loads/consumptions for the daily
operational planning.

Ključne riječi
Artificial neural networks; Short-term load forecasting; Electric power system operation and planning

Hrčak ID: 199752

URI
https://hrcak.srce.hr/199752

Posjeta: 99 *