DocumentCode
3251881
Title
A novel modification of ARX to generalize crude oil consumption model
Author
Awaludin, Iwan ; Ibrahim, Rosdiazli ; Rama Rao, K.S.
Author_Institution
Electr. & Electron. Eng. Dept., UTP, Malaysia
fYear
2009
fDate
23-26 Jan. 2009
Firstpage
1
Lastpage
6
Abstract
A general model of oil consumption is investigated in this study. This model should be applicable to different countries even with different characteristics. Conventional model that works very well for Malaysia is tested with seven developing Asian countries: China, India, Indonesia, Malaysia, Pakistan, Philippines, and Thailand. The results have shown that this model can not produce a good fit to original data. A modification of Autoregressive Exogenous (ARX) model is proposed and tested. Data are separated into training and validation dataset where the number of validation dataset is higher than the number of training dataset. The results have shown that the proposed model can be considered as a general model where all countries except Philippines can produce a good fit to original data.
Keywords
crude oil; learning (artificial intelligence); regression analysis; Asian countries; autoregressive exogenous model; crude oil consumption model; training dataset; validation dataset; Artificial neural networks; Decision making; Energy consumption; Extrapolation; Gallium nitride; Mathematical model; Petroleum; Predictive models; Root mean square; Testing; ARX; Asian Countries; Oil Consumption;
fLanguage
English
Publisher
ieee
Conference_Titel
TENCON 2009 - 2009 IEEE Region 10 Conference
Conference_Location
Singapore
Print_ISBN
978-1-4244-4546-2
Electronic_ISBN
978-1-4244-4547-9
Type
conf
DOI
10.1109/TENCON.2009.5395846
Filename
5395846
Link To Document