A look-ahead algorithm for online multiple workflow scheduling problem in heterogeneous systems

Abstract

A look-ahead algorithm is proposed to solve the online multiple workflow scheduling problem with two constraints in heterogeneous system. In this problem, workflows come to the system online when they are released, and each workflow is composed of multiple tasks which can be executed on heterogeneous processors, according to their types. Considered two constrains including the non-preemptive processor and the task order in a workflow, the proposed algorithm utilizes the information contained in the list of the submitted workflows and optimizes the scheduling of current task according to subsequent tasks. It can keep the subsequent tasks from waiting for a long time due to the occupation of the limited resource by the current task. The simulation results show that the proposed look-ahead algorithm outperforms four classical online scheduling algorithms, and the algorithm can get better performance when the look-ahead value L = 1 than L ≥ 2.

An evolutionary approach for optimal multi-objective resource allocation in distributed computing systems

“…The performance of the distributed system is dependent on the allocation of users' jobs on computing resources. The problem of effectively managing the utilization of resources is referred to as a resource allocation problem, which is very common in production, agriculture, and computer industries (Comito et al, 2013;Deng et al, 2018;Kaur and Bala, 2019;Xu et al, 2017).…”

An efficient resource prediction–based scheduling technique for scientific applications in cloud environment

“…Each client connection occurs at different time with different resource requirements. The varying interactions exert unique challenges for cloud resource usage (Xu et al, 2017).…”