An improved genetic algorithm for task scheduling in cloud computing
Shuang Yin, Peng Ke, Ling Tao · 2018
In cloud computing environment, task scheduling is one of the most critical issues to be solved. Efficient task scheduling mechanism not only meets users' requirements but also ensures cloud resources' high utilization, so as to improve the overall performance of the cloud computing environment. Aiming at this problem, a new scheduling algorithm based on double-fitness algorithm-load balancing and task completion cost genetic algorithm(LCGA) is proposed. The scheduling guarantees load balancing and makes task completion cost less. At the same time, this paper brings in not just variance to represent the load among computing workers but weights multi-fitness function. Through the simulation experiment, the proposed algorithm is being compared with the genetic algorithm based on load balancing (LGA) and the genetic algorithm based on task completion cost (CGA). It proves the effectiveness of the scheduling algorithm and the availability of the optimization method.