In accordance with the regulations of the Energy Agency of the Republic of Slovenia, each natural gas supplier regulates and determines the charges for the differences between the ordered (predicted) and the actually supplied quantities of natural gas. Yearly charges for these differences represent up to 2% of supplied natural gas costs. All the natural gas users, especially industry, have huge problems finding the proper method for efficient natural gas consumption prediction and, consequently, the decreasing of mentioned costs. In this study, prediction of the natural gas consumption in Štore Steel Ltd. (steel plant) is presented. On the basis of production data, several models for natural gas consumption have been developed using linear regression, genetic programming and artificial neural network methods. The genetic programming approach outperformed linear regression and artificial neural networks.
Keywords
- natural gas
- consumption
- modeling
- linear regression
- genetic programming
- artificial neural networks
- industry
An analysis of coal consumption, CO2 emissions and economic growth in Slovenia Valuation of Rubber Waste and Dune Sand: Mortar for Construction and Environmental Protection Field Observations, Petrography, and Microstructures of Granite from Abeokuta Southwestern Nigeria Lateral squeezing effects on cement-slag-bentonite slurry wall performance Determining the Enthalpy of an Fe-Ni Alloy at Various Temperatures Using the ‘STA’ PT 1600 Equipment Hydrocarbon Potential and Biomarker Studies of EE-1 Well, Offshore Eastern Dahomey Basin, SW Nigeria Regression methods for evaluation of the underwater noise levels in the Slovenian Sea Physico-Chemical Trends in the Sediments of Agbede Wetlands, Nigeria Copper tailings reprocessing Returning Electrostatic Precipitators to the Fe-Ni Production Process