Application of Neural Network for Forecasting Gas Price in America


Authors

Mehdi Sotoudeh - South pars gas complex, Iran, Assaluyeh Elahe Farshad - Applied science comprehensive university of Kangan, Iran


Abstract

This paper presents a neuro-base approach for gas price forecasting of American consumers. in order to forming a neural network structure, effecting parameters on gas price are analyzed and gas production and consumption, import and export gas ,natural gas supplies held in storage,oil price are selected as inputs. this approach is structured as multi-level artificial neural net work(ANN)base on supervised muliti-layer perceptron (MLP),train with the levbergenberg-marquard algorithm .actual data from 1949-2010 is extracted from American energy information administration (EIA) .samples from 1949-2005 are used to train the multi-level ANN and the rest from 2005 to 2010 are used for network test. Result shows multi-level ANN is train well.


Share and Cite

  • Share on Facebook
  • Share on Twitter
  • Share on LinkedIn
ISRP Style

Mehdi Sotoudeh, Elahe Farshad, Application of Neural Network for Forecasting Gas Price in America, Journal of Mathematics and Computer Science, 4 (2012), no. 2, 216--226

AMA Style

Sotoudeh Mehdi, Farshad Elahe, Application of Neural Network for Forecasting Gas Price in America. J Math Comput SCI-JM. (2012); 4(2):216--226

Chicago/Turabian Style

Sotoudeh, Mehdi, Farshad, Elahe. "Application of Neural Network for Forecasting Gas Price in America." Journal of Mathematics and Computer Science, 4, no. 2 (2012): 216--226


Keywords


MSC


References