Parenting Fitness in Genetic Algorithms: Empirical Advantages Over NSGA-II in Logistics Optimization

Abstract

Genetic algorithms (GAs) are population-based metaheuristics widely employed to solve complex real-world problems such as networking and resource allocation. These algorithms evolve a population of candidate solutions through iterative processes of selection, crossover, and mutation. The composition of the next generation is determined by either a general approach, where only offspring are retained, or an elitist approach, which selects fit solutions from the current generation. While elitism enhances solution quality, it is susceptible to premature convergence. This article presents a comparative study between the parenting fitness mechanism and the crowding distance approach used in the Non-dominated Sorting Genetic Algorithm II (NSGA-II) for solving the Vehicle Routing Problem with Drones (VRPD). Experimental evaluations demonstrate that the proposed parenting fitness method yields consistent improvements in solution quality. Relative improvements range from 27.30% to 43.83% for small problem instances, 6.36% to 11.41% for medium instances, and 0.54% to 1.90% for large instances, with performance variations influenced by the population size. These results validate the effectiveness of parenting fitness as a diversity-preservation strategy in mono-objective optimization.