DocumentCode :
2752853
Title :
The effect of neural network parameters on the performance of neural network forecasting
Author :
Azadeh, A. ; Behshtipour, Behshtipour
Author_Institution :
Dept. of Ind. Eng., Tehran Univ., Tehran
fYear :
2008
fDate :
13-16 July 2008
Firstpage :
1498
Lastpage :
1505
Abstract :
This paper deal first with artificial neural networks for demand forecasting, neural networks have successfully been used for demand forecasting, however, due to a large number of parameters to be estimated empirically, it is not a simple task to select the appropriate neural network architecture for a demand forecasting problem. Researchers often overlook the effect of neural network parameters on the performance of neural network forecasting. This paper examines the effects of the number of input and hidden nodes and hidden layers as well as the size of the training sample on the in-sample and out-of-sample performance. The second objective of this paper is to describe a new forecasting approach inspired from regression method for weekly demand forecasting, we have used this approach for demand forecasting as a benchmark for comparison. This method performs an extensive search in order to select the appropriate transformation functions of input variables, the weighting factors and the training periods to be used, by taking into consideration the correlation analysis of the selected input variables. With this procedure the best forecasting model is formed.
Keywords :
correlation methods; demand forecasting; forecasting theory; multilayer perceptrons; neural net architecture; regression analysis; artificial neural networks; correlation analysis; multilayer perceptron; neural network architecture; regression method; transformation functions; weekly demand forecasting; Artificial intelligence; Artificial neural networks; Demand forecasting; Energy management; Industrial engineering; Input variables; Load forecasting; Neural networks; Power engineering and energy; Predictive models; multi-layer perceptron (MLP); neural networks; regression; time series forecasting;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Industrial Informatics, 2008. INDIN 2008. 6th IEEE International Conference on
Conference_Location :
Daejeon
ISSN :
1935-4576
Print_ISBN :
978-1-4244-2170-1
Electronic_ISBN :
1935-4576
Type :
conf
DOI :
10.1109/INDIN.2008.4618341
Filename :
4618341
Link To Document :
بازگشت