Recurrent neural network technique for one-day ahead load forecasting

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F00%3A43300020" target="_blank" >RIV/00216305:26220/00:43300020 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Recurrent neural network technique for one-day ahead load forecasting

Popis výsledku v původním jazyce

Multilayer perceptron networks (MLP) have constituted the preferred architecture, achieving successful results for the load forecasting problem during recent years. However, this model generally fails to deal with the temporal pattern of the load signal,being more suitable for static pattern recognition tasks. Recurrent or dynamic networks have shown better capabilities for time signals modeling and forecasting. This paper presents the application of a recurrent neural network model for short-term loadforecasting problem. Particularly, the Elman recurrent model was applied to one-day ahead load forecasting for the Czech Electric Power System (ČEZ). The load values are considered as a time series, , taking advantage of the temporal processing capabilities of this neural network model. The strength of this technique lies in its ability to forecast the load effectively on weekdays, on weekends and as well as, on special days/public holidays.

Název v anglickém jazyce

Recurrent neural network technique for one-day ahead load forecasting

Popis výsledku anglicky

Multilayer perceptron networks (MLP) have constituted the preferred architecture, achieving successful results for the load forecasting problem during recent years. However, this model generally fails to deal with the temporal pattern of the load signal,being more suitable for static pattern recognition tasks. Recurrent or dynamic networks have shown better capabilities for time signals modeling and forecasting. This paper presents the application of a recurrent neural network model for short-term loadforecasting problem. Particularly, the Elman recurrent model was applied to one-day ahead load forecasting for the Czech Electric Power System (ČEZ). The load values are considered as a time series, , taking advantage of the temporal processing capabilities of this neural network model. The strength of this technique lies in its ability to forecast the load effectively on weekdays, on weekends and as well as, on special days/public holidays.

Druh

D - Stať ve sborníku

CEP obor

JA - Elektronika a optoelektronika, elektrotechnika

OECD FORD obor

—

Projekt

—

Návaznosti

Z - Vyzkumny zamer (s odkazem do CEZ)

Rok uplatnění

2000

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

3rd International Conference on Prediction (NOSTRADAMUS)

ISBN

80-214-1668-8

ISSN

—

e-ISSN

—

Počet stran výsledku

7

Strana od-do

—

Název nakladatele

TU Zlín

Místo vydání

Zlín

Místo konání akce

—

Datum konání akce

—

Typ akce podle státní příslušnosti

—

Kód UT WoS článku

—