PYTHIA: Admission Control for Multi-Framework, Deadline- Driven, Big Data Workloads

Dimopoulos, Stratos; Krintz, Chandra; Wolski, Rich

doi:10.1109/cloud.2017.69

Cited by 7 publications

(1 citation statement)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This decision is taken with profit optimization in mind. A deadline-aware admission control mechanism (PYTHIA) is proposed in [10]. PYTHIA admits the tasks if their deadlines can be met with the estimated resources; otherwise, it rejects the tasks.…”

Section: Literature Reviewmentioning

confidence: 99%

A Deadline-Budget Constrained Task Admission Control for a Software-as-a-Service Provider in Cloud Computing

Jain,

Sharma

2023

Iraqi Journal of Science

View full text Add to dashboard Cite

Cloud computing is a pay-as-you-go model that provides users with on-demand access to services or computing resources. It is a challenging issue to maximize the service provider's profit and, on the other hand, meet the Quality of Service (QoS) requirements of users. Therefore, this paper proposes an admission control heuristic (ACH) approach that selects or rejects the requests based on budget, deadline, and penalty cost, i.e., those given by the user. Then a service level agreement (SLA) is created for each selected request. The proposed work uses Particle Swarm Optimization (PSO) and the Salp Swarm Algorithm (SSA) to schedule the selected requests under budget and deadline constraints. Performances of PSO and SSA with and without ACH are evaluated and compared using CloudSim. The simulation results prove that admission control maximizes profit by minimizing the number of task rejections and SLA violations. It also improves resource utilization while balancing makespan.

show abstract

Section: Literature Reviewmentioning

confidence: 99%