An adaptive search equation-based artificial bee colony algorithm for transportation energy demand forecasting

Abstract

This study aimed to develop a new adaptive artificial bee colony (A-ABC) algorithm that can adaptively select an appropriate search equation to more accurately estimate transport energy demand (TED). Also, A-ABC and canonical artificial bee colony (C-ABC) algorithms were compared in terms of efficiency and performance. The input parameters used in the proposed TED model were the official economic indicators of Turkey, including gross domestic product (GDP), population, and total vehicle kilometer per year (TKM). Three mathematical models, linear (A-ABCL), exponential (A-ABCE), and quadratic (A-ABCQ) were developed and tested. Also, economic variables were generated using the "curve fitting" technique to see TED's projections for the year 2034, under two different scenarios. In the first scenario, the results of linear, exponential, and quadratic models according to 2034 TED estimates were 40.1, 31.6, and 70.5 million tons of oil equivalent (Mtoe), respectively. In the second scenario, the results of linear, exponential, and quadratic models according to the TED estimates for 2034 were found as 40.0, 31.5, and 66.5 Mtoe, respectively. The presented models, A-ABCL, A-ABCE, A-ABCQ for the solution of the TED problem, produced successful results compared to the studies in the literature. Besides that, according to global error metrics, developed models generated lower error values than C-ABC. Furthermore, consumption estimation values of A-ABCL and A-ABCE were lower than A-ABCQ. According to A-ABCQ model estimations for both scenarios, the TED value would increase approximately three times from 2013 to 2034.