Data Driven Natural Gas Spot Price Prediction Models Using Machine Learning Methods

Moting Su,Wenying Wen,Donglan Zha,Ye Zhu,Zongyi Zhang

doi:10.3390/en12091680

Abstract

Natural gas has been proposed as a solution to increase the security of energy supply and reduce environmental pollution around the world. Being able to forecast natural gas price benefits various stakeholders and has become a very valuable tool for all market participants in competitive natural gas markets. Machine learning algorithms have gradually become popular tools for natural gas price forecasting. In this paper, we investigate data-driven predictive models for natural gas price forecasting based on common machine learning tools, i.e., artificial neural networks (ANN), support vector machines (SVM), gradient boosting machines (GBM), and Gaussian process regression (GPR). We harness the method of cross-validation for model training and monthly Henry Hub natural gas spot price data from January 2001 to October 2018 for evaluation. Results show that these four machine learning methods have different performance in predicting natural gas prices. However, overall ANN reveals better prediction performance compared with SVM, GBM, and GPR.

Highlights

The world total primary energy supply (TPES) by fuel in 2016 was as follows: oil (31.9%), coal (27.1%), natural gas (22.1%), biofuels and waste (9.8%), nuclear (4.9%), hydro (1.8%), and other (0.1%) [1]
Observing data of four criteria can find that the forecasting performance of artificial neural networks (ANN) and support vector machines (SVM) is better than that of gradient boosting machines (GBM) and Gaussian process regression (GPR)
ANN is obviously superior to other methods while GBM has the worst behaviour

Summary

Introduction

The world total primary energy supply (TPES) by fuel in 2016 was as follows: oil (31.9%), coal (27.1%), natural gas (22.1%), biofuels and waste (9.8%), nuclear (4.9%), hydro (1.8%), and other (0.1%) [1]. Natural gas has the third-largest share among the TPES. Natural gas production continues to grow at a higher pace, most notably with a 3.6% increase in 2017 compared to 2016 that constitutes the largest increase since 2010. Power, and mobility with fewer emissions, including both carbon-dioxide (CO2 ) emissions and air pollutants, than the other fossil fuels, helping to address widespread concerns over air quality. Because the natural gas energy causes less pollution to the environment than other kinds of energy resource, it has received much more recognition recently

Objectives

Results

Conclusion