Forecasting of Turkey natural gas demand using a hybrid algorithm

ABSTRACT

The basis of the energy management constitutes the forecasting of the need for energy as much as accurate. In this study, a hybrid genetic algorithm-simulated annealing (GA-SA) algorithm based on linear regression has been developed and coded as software to forecast natural gas demand of Turkey. The linear models, which are constructed by using the amounts of natural gas consumption for years between 1985 and 2000 as dependent variable, and gross national product, population, and growth rate as independent variables, are used to forecast the amount of natural gas consumption for years between 2001 and 2009. Then, the forecasts are compared with real amounts of consumptions and are analyzed statistically.

Consequentially, it is observed that the GA-SA hybrid algorithm made forecasts with less statistical error against linear regression. The models were used to forecast Turkey’s natural gas demand under two different scenarios for years between 2010 and 2030.

KEYWORDS:

• Forecasting
• genetic algorithm
• linear regression
• natural gas demand
• simulated annealing