Parallel machine scheduling optimization based on roulette probability assignment encoding

Evolutionary strategy algorithm is employed to optimize the parallel machine scheduling problem, and a new kinds of the encoding method based on roulette probability assignment is introduced. The individual gene is sequenced and the probability of each gene is evaluated. Then, the solution of the parallel scheduling would be obtained while the machine assignment is achieved by the roulette. The initialization condition of the encoding based on roulette probability assignment is analyzed. A kind of recombination operation based on three-point crossover and interchange is used to generate the offspring individuals, and a kind of mutation operation is designed that some gene in the encoding is stochastically generated. From the computational results of two parallel machine scheduling problems, particle swam optimization algorithm based on roulette probability assignment encoding can effectively optimize the parallel machine scheduling problems, the encoding method based on roulette probability assignment can effectively avoid the infeasible schedule solution.