Endocrine-based coevolutionary multi-swarm for multi-objective workflow scheduling in a cloud system

The workflow scheduling with multiple objectives is a well-known NP-complete problem, and even more complex and challenging when the workflow is executed in cloud computing system. In this study, an endocrine-based coevolutionary multi-swarm for multi-objective optimization algorithm (ECMSMOO) is proposed to satisfy multiple scheduling conflicting objectives, such as the total execution time (makespan), cost, and energy consumption. To avoid the influence of elastic available resources, a manager server is adopted to collect the available resources for scheduling. In ECMSMOO, multi-swarms are adopted and each swarm employs improved multi-objective particle swarm optimization to find out non-dominated solutions with one objective. To avoid falling into local optima which is common in traditional heuristic algorithms, an endocrine-inspired mechanism is embedded in the particles’ evolution process. Furthermore, a competition and cooperation technique among swarms is designed in the ECMSMOO. All these strategies effectively improve the performance of ECMSMOO. We compare the quality of the proposed method with other algorithms for multi-objective task scheduling by hybrid and parallel workflow jobs. The results highlight the better performance of the proposed approach than that of the compared algorithms.