Title :
ANN backpropagation power consumption forecasting
Author :
Raluca Schiopu;Constantin Barbulescu;Stefan Kilyeni;Antheia Deacu;Alin Vernica
Author_Institution :
Power Systems Department, Power Systems Analysis and Optimization Research Center, Politehnica University Timisoara, Romania
Abstract :
The paper is focusing on artificial neural networks (ANN) based load forecasting. It is applied for hourly load and daily load curves forecasting. The backpropagation algorithm is presented. The basic propagation algorithm is completed with conjugated gradient and parabolic interpolation. A software tool has been developed in Matlab environment. The results are compared with the ones provided by classic forecasting methods.
Keywords :
"Artificial neural networks","Standards","Forecasting","Neurons","Load forecasting","Training","Backpropagation"
Conference_Titel :
EUROCON 2015 - International Conference on Computer as a Tool (EUROCON), IEEE
DOI :
10.1109/EUROCON.2015.7313774
