Multi-resource fair allocation with bandwidth requirement compression in the cloud–edge system

Li, Xingxing; Li, Weidong; Zhang, Xuejie

doi:10.1016/j.compeleceng.2022.108510

Cited by 10 publications

(2 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…EnergyFairShare [3] is a fair scheduling algorithm that uses statistics on user job power consumption to ensure fairness in user power consumption. DRF-CE [4] is committed to solving the problem of fair allocation of multiple resources in cloud-edge collaborative computing systems.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

SAUFEE: a datacenter task scheduling algorithm considering user fairness and energy efficiency

Peng,

Yan,

et al. 2024

International Conference on Communication, Information, and Digital Technologies (CIDT2024)

View full text Add to dashboard Cite

The data center uses virtualization and isolation technologies to provide flexible and efficient services for multi-tenants. One of the most challenging aspect of resource sharing is task scheduling. During the scheduling process, it is crucial to ensure fairness in user resource usage and achieve high cluster utilization and energy efficiency. However, the heterogeneity of resources and the variations in user demands make it extremely difficult to provide an effective scheduling solution. In this paper, we propose an efficient heuristic scheduling algorithm called SAUFEE, which trades off the resource requirement of multi-tenants and cluster power consumption. First, we introduce a user fairness model, which prioritizes the tasks of users with the least resource allocation in each scheduling round, ensuring fairness among them. Next, we propose a resource utilization model to schedule user tasks to reduce resource waste. Additionally, idle machines are shut down to save overall cluster energy consumption. The simulation experiment results show that our algorithm increases the number of running tasks by 3.3% and the CPU utilization by 3.4% while ensuring fairness. Our algorithm plays an important role in improving cluster energy efficiency and user fairness.

show abstract

Section: Related Workmentioning

confidence: 99%

“…The first challenge is the fairness among users during the scheduling process [1][2][3][4], and the second challenge is the energy-efficient of the cluster [5][6][7]. The scheduler, acting as a bridge between user tasks and cluster nodes, plays a crucial role for the challenges.…”

Section: Introductionmentioning

confidence: 99%