CPSO-SVM Based Petroleum Demand Prediction

Abstract:

Study of oil demand, oil demand uncertainty, leading to its strong non-linear, sudden change characteristic, causes the linear modeling of traditional method and neural network prediction precision is low. In order to accurately forecast demand, presents a chaos particle swarm optimization of support vector machine oil demand forecasting method (CPSO-SVM). The CPSO SVM parameter optimization, and then using SVM to petroleum demand nonlinear variation modeling, finally to 1989~ 2007 oil demand data for simulation, the results show that, compared with other oil demand forecast algorithm, CPSO-SVM raised oil demand forecast accuracy, as demand for oil to provide a new method for predicting.

• Periodical: Applied Mechanics and Materials (Volume 273)
• Pages: 91-96
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.273.91
• Online since: January 2013
• Authors: Li Fang Tang
• Keywords: Chaotic Particle Swarm Optimization, Petroleum Demand, Prediction Model, Support Vector Machine (SVM)

References

[1] Han Keqi, Wang Yujun. Development Trend and Prospect of Energy Consumption in China in Journal of China University of Mining and Technology, 2004, 33(1), pp.45-50.

[2] Yang Xiaolong, Liu Xisong. Predictive Analysis of China's Petroleum Supply Using Gray System Theory. in Journal of Daqing Petroleum Institute, 2003, 27(4), pp.11-13.

[3] Gao Shoubai. Latest Prediction of World Petroleum Demand and Price between 2010 and 2020 by International Energy Agency. in Acta Petrolei Sinica, 2001, 22 (3), pp.26-26.

[4] Xu Mingde, Li Weijie. Linear Rin egression Analysis and Energy Demand Projection. in Journal of Inner Mongolia Normal University, 2003, 32(1), pp.17-20.

[5] Xu Ping, Wang Ben, Fan Ying. BP Neural Network Based Petroleum Demand Prediction in Our Country. Journal of Daqing Petroleum Institute, 2007, 31(2), pp.82-84.