A method for performance analysis of a genetic algorithm applied to the problem of fuel consumption minimization for heavy-duty vehicles

Artikel i vetenskaplig tidskrift, 2019

This paper presents a general method for assessment of the performance of a genetic algorithm (GA)in cases where the global optimum of the objective function is unknown. The method involves discretization of the search space, making it possible to apply a brute force calculation to find the global optimum for the discretized case. Then, this method is used to study the performance of a GA applied to the problem of speed profile optimization for heavy-duty vehicles, in which the optimization must be carried out within a rather short time. In this performance analysis, the discretization involves generating speed profiles as piecewise linear functions. It is demonstrated that the GA is able to find near-optimal solutions for the cases considered here: The speed profiles generated by the GA have objective function values that are typically within 2% of the global optimum.