Multi-Objective Optimization of Cloud Resource Scheduling

Abstract

The research on cloud resource scheduling has become a hotspot in the field of cloud computing. At present, many intelligent optimization algorithms have been proposed to handle the cloud computing resource scheduling problem, but they all focus solely on the execution time of tenant tasks or the energy consumption of load resources in the cloud data center, and there is no comprehensive scheduling algorithm. In the actual application, the execution time of tenant tasks and the energy consumption of cloud data center are not compatible. This paper establishes a multi-objective scheduling model in a cloud resource environment, which not only considers the execution time of tenant task, but also reduces the load energy consumption of the cloud data center, and tries to achieve the best balance between the tenant and the data center. In order to solve this multi-objective scheduling model, this paper proposes a Multi-Optimization joint evolution genetic algorithm (MOOV-GA). The experimental results show that the MOOV-GA algorithm has a better performance on dealing with the multi-objective scheduling model than other genetic algorithms.