Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Crude Oil Consumption Forecasting Using Classical and Machine Learning Methods


Affiliations
1 Department of Computer Science & Engineering. Maharaja Agrasen Institute of Technology, GGSIPU, New Delhi, India
     

   Subscribe/Renew Journal


The global oil market is the most important of all the world energy markets. Since crude oil is a non-renewable source, its quantity is fixed and limited. To manage the available oil reserves, it will be helpful if we have estimation about the future consumption requirements of this resource beforehand. This paper describes methods to forecast crude oil consumption of next 5 years using past 17 years data (2000-2017). The decision making process comprised of: (1) Preprocessing of dataset, (2) Designing forecasting model, (3) Training model, (4) Testing model on test set, (5) Forecasting results for next 5 years. The proposed methods are divided into two categories: (a) Classical methods, (b) Machine Learning methods. These were applied on global data as well as on three major countries: (a) the USA, (b) China, (c) India. The results showed that the best accuracy was obtained for polynomial regression. An accuracy of 97.8% was obtained.

Keywords

Accuracy, Machine Learning, Oil Consumption Prediction, Time Series Forecasting.
Subscription Login to verify subscription
User
Notifications
Font Size


  • “World energy resources,” www.worldenergy.org, 2016. [Online]. Available: https://www.worldenergy.org/wp-content/uploads/2016/10/World-Energy-Resources-Full-report-2016.10.03.pdf
  • “World oil outlook 2040,” www.opec.org, 2017. [Online]. Available: https://www.opec.org/opec_web/flipbook/WOO2017/WOO2017/assets/common/downloads/WOO%202017.pdf
  • “BP statistical review of world energy,” www.bp.com, 2018. Available: https://www.bp.com/content/dam/bp/en/corporate/pdf/energy-economics/statistical-review/bp-stats-review-2018-full-report.pdf
  • “Global energy statistical yearbook,” Enerdata, 2018. Available: https://yearbook.enerdata.net/crude-oil/world-refineries-data.html
  • V. S. Ediger, S. Akar, and B. Uğurlu, “Forecasting production of fossil fuel sources in Turkey using a comparative regression and ARIMA model,” Energy Policy, vol. 34, no. 18, pp. 3836-3846, 2006.
  • H. H. Landsberg, L. L. Fischman, and J. L. Fisher, “Resources in America’s future: Patterns of requirements and availabilities 1960-2000,” Johns Hopkins Press for Resources for the Future, Baltimore, 1963.
  • V. Smil, “Perils of long-range energy forecasting: Reflections on looking far ahead,” Technological Forecasting and Social Change, vol. 65, no. 3, pp. 251-264, 2000.
  • V. Smil, Energy at the Crossroads: Global Perspectives and Uncertainties, The MIT Press, 2003.
  • J. Li, R. Wang, J. Wang, and Y. Li, “Analysis and forecasting of the oil consumption in China based on combination models optimized by artificial intelligence algorithms,” Energy, vol. 144, pp. 243-264, 2018.

Abstract Views: 43

PDF Views: 0




  • Crude Oil Consumption Forecasting Using Classical and Machine Learning Methods

Abstract Views: 43  |  PDF Views: 0

Authors

Zameer Fatima
Department of Computer Science & Engineering. Maharaja Agrasen Institute of Technology, GGSIPU, New Delhi, India
Alok Kumar
Department of Computer Science & Engineering. Maharaja Agrasen Institute of Technology, GGSIPU, New Delhi, India
Lakshita Bhargava
Department of Computer Science & Engineering. Maharaja Agrasen Institute of Technology, GGSIPU, New Delhi, India
Ayushi Saxena
Department of Computer Science & Engineering. Maharaja Agrasen Institute of Technology, GGSIPU, New Delhi, India

Abstract


The global oil market is the most important of all the world energy markets. Since crude oil is a non-renewable source, its quantity is fixed and limited. To manage the available oil reserves, it will be helpful if we have estimation about the future consumption requirements of this resource beforehand. This paper describes methods to forecast crude oil consumption of next 5 years using past 17 years data (2000-2017). The decision making process comprised of: (1) Preprocessing of dataset, (2) Designing forecasting model, (3) Training model, (4) Testing model on test set, (5) Forecasting results for next 5 years. The proposed methods are divided into two categories: (a) Classical methods, (b) Machine Learning methods. These were applied on global data as well as on three major countries: (a) the USA, (b) China, (c) India. The results showed that the best accuracy was obtained for polynomial regression. An accuracy of 97.8% was obtained.

Keywords


Accuracy, Machine Learning, Oil Consumption Prediction, Time Series Forecasting.

References