You can view the full text of this article for free using the link below.

Title: Computational intelligence for gas imports forecasting

Authors: George Atsalakis; Sofia Evangelia Ioannou; Constantin Zopounidis

Addresses: School of Production Engineering and Management, Technical University of Crete, Crete, Greece ' School of Production Engineering and Management, Technical University of Crete, Crete, Greece ' School of Production Engineering and Management, Technical University of Crete, Crete, Greece

Abstract: This paper investigates the ability to forecast the natural gas imports in Greece, using artificial intelligent methods. The Adaptive Neuro-Fuzzy Inference System (ANFIS) model and Artificial Neural Networks (ANN) model were developed. The overall gas import data required for the model were collected from Greek gas imports. The results of the developed models were compared with the actual data imports. Main statistical errors have been calculated in order to examine the forecasting accuracy of the proposed models. Further evaluation of the proposed models took place in comparison to the results with those of Autoregressive (AR) and Autoregressive Moving Average (ARMA). The results showed that gas import forecasting estimations using the ANFIS and ANN model were very encouraged. In terms of forecasting performance, it is clear from the empirical evidence that the ANFIS model outperforms artificial neural network and two other conventional models (AR and ARMA).

Keywords: adaptive neuro-fuzzy inference system; ANFIS; artificial neural networks; ANNs; fuzzy logic; imported gas forecasts; forecasting performance; gas imports; natural gas; Greece; modelling.

DOI: 10.1504/IJFERM.2015.068854

International Journal of Financial Engineering and Risk Management, 2015 Vol.2 No.1, pp.17 - 29

Available online: 13 Apr 2015 *

Full-text access for editors Access for subscribers Free access Comment on this article