Abstract: To solve the problem of unbalanced resource requirements and low resource utilization when the same type of tasks are executed in parallel in the cloud manufacturing system, a task resource scheduling model with the goal of minimizing cost, minimizing time, maximizing reliability and optimizing quality is established. A non-dominated sorting genetic algorithm based on reference points (NSGA-III) is adopted to solve the model by combining real number matrix coding and crossover and mutation based on real number coding instead of common evolutionary strategy. And an optimal decision strategy based on combination of analytic hierarchy process and entropy value method is used to evaluate the solutions. The performance of the scheduling system with sufficient and limited resources is discussed respectively. The example proves that method is feasible.

Key words: cloud manufacturing, parallel tasks, virtual resource, optimal scheduling, NSGA-Ⅲ