A Game-Theoretic Approach to Multiobjective Job Scheduling in Cloud Computing Systems

This paper presents a distributed and security driven solution to multiobjective job scheduling problem in the Cloud Computing infrastructures. The goal of this scheme is allocating a limited quantity of resources to a specific number of jobs minimizing their execution failure probability and job completion time. As this problem is NP-hard in the strong sense, a meta-heuristic NSGA-II is proposed to solve it. To select the best strategy from the resulting Pareto frontier we develop decision-making mechanisms based on the game theoretic model of Spatial Prisoner's Dilemma and realized by independent, selfish brokering agents. Their behavior is conditioned by objectives of the various entities involved in the scheduling process and driven towards a Nash equilibrium solution by the employed social welfare criteria. The performance of the applied scheduler is verified by a number of numerical experiments. The related results show the effectiveness of the proposed solution for medium and large-sized scheduling problems.