Akademik Veri Yönetim Sistemi
SN Applied Sciences, cilt.1, sa.1138, 2019 (ESCI)
Natural gas is one of the most important energy sources in the world because it is cheaper and cleaner than most of its alternatives. Therefore, natural gas is used for residential and industrial purposes such as heating, electricity generation and manufacturing. Although Turkey has its own resources to meet the demand for natural gas, most of the needed natural gas amount is imported from other countries. The produced or imported natural gas has been used for heating, electricity generation and manufacturing in Turkey. Therefore approximate forecasting with a less statistical error of vital energy sources such as natural gas is extremely significant for countries having an imbalance between export and import values. The main purpose of this study is to determine the best coefficients with less statistical error for the forecasting equation for natural gas demand of Turkey. This paper suggests an Artificial Bee Colony (ABC) algorithm for forecasting natural gas consumption in billion cubic meters (bcm) for the years between 2018 and 2030 by using some historical indicators between 1998 and 2017. ABC algorithm is firstly used for determining coefficients of a forecasting equation for natural gas demand of Turkey. ABC algorithm was originally designed for continuous optimization problems and with its simple structure and applicability can be useful for decision or policymakers. Therefore such a strong meta heuristic algorithm in the literature should be used for a vital problem of the countries having current account deficit like Turkey. Annual gross domestic product at chained volume index, population, export and import of Turkey are selected as historical indicators and independent variables for forecasting in this study. Furthermore, a linear regression model is also created to compare the proposed forecasting model. Both models are used to forecast Turkey future natural gas consumption for two different scenarios. The proposed algorithm outperforms the linear regression model in view of total absolute relative errors from previous natural gas consumptions of Turkey.