Naslov
Application of Neural Networks for Zagreb Load Forecasting

Autori
Mileta, Dino ; Milešević, Boško ; Sučić, Stjepan

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
5th Dubrovnik Conference on Sustainable Development of Energy, Water and Environment Systems : CD proceedings / Guzović, Zvonimir ; Duić, Neven ; Ban, Marko - Zagreb : Fakultet strojarstva i brodogradnje Sveučilišta u Zagrebu, 2009

ISBN
9789536313983

Skup
Dubrovnik Conference on Sustainable Development of Energy, Water and Environment Systems (5 ; 2009)

Mjesto i datum
Dubrovnik, Hrvatska, 30.09.2009. - 03.10.2009

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Load Forecasting ; Neural Networks ; Energy-efficient

Sažetak
Load forecasting is needful to the operation of electricity companies. This paper presents a study of short-term load forecasting using Artificial Neural Networks (ANNs) and applied it to city of Zagreb (Croatia). The goal of it is to enhance the energy-efficient, reliable operation of a power system and better planning of energy production. Historical load and weather data obtained for the month January 2006 were used. The main stages are the pre-processing of the data sets, network training, and forecasting. Inputs for ANN are hour of the day, day of the week, temperature forecast and the output is load forecast for a given hour.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika

POVEZANOST RADA