Recurrent neural network technique for one-day ahead load forecasting

Result code in 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>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Recurrent neural network technique for one-day ahead load forecasting
Original language description
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.
Czech name
—
Czech description
—

Publication year
2000
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
3rd International Conference on Prediction (NOSTRADAMUS)
ISBN
80-214-1668-8
ISSN
—
e-ISSN
—
Number of pages
7
Pages from-to
—
Publisher name
TU Zlín
Place of publication
Zlín
Event location
—
Event date
—
Type of event by nationality
—
UT code for WoS article
—

Similar results(10)