Neural network applied to the coevolution of the memetic algorithm for solving the makespan minimization problem in parallel machine scheduling

Abstract

The problem discussed here is one of scheduling the tasks in identical parallel machines. In this problem, we deal with a set of n tasks and m identical parallel machines, with the objective of minimizing the makespan. The makespan is the total processing time of the most busy machine. This work presents an implementation of a memetic-neuro scheduler for solving this scheduling problem. The memetic algorithm, which is an hybrid version of genetic algorithm with local search, has been used to evolve good scheduling forms; and the neural network has been used to calculate the fitness for each individual of the population.