Emerging Paradigms and Practices in Cloud Resource Management

Sharma, Durga Prasad; Singh, Bhupesh Kumar; Gure, Amin Tuni; Choudhury, Tanupriya

doi:10.1007/978-3-030-71756-8_2

Cited by 2 publications

(1 citation statement)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The SLAs that are signed between the cloud customers and cloud service providers are required to be maintained on each call of request processing and executions. Generally, marketbased resource management strategies are more focused on customer satisfaction and service provider profits [19,20]. Therefore, the development of a framework that can satisfy www.ijacsa.thesai.org both the service providers and customers is of utmost need [21].…”

Section: Introductionmentioning

confidence: 99%

An Autonomous Multi-Agent Framework using Quality of Service to prevent Service Level Agreement Violations in Cloud Environment

Singh¹,

Goraya²

2023

IJACSA

View full text Add to dashboard Cite

Cloud is a specialized computing technology accommodating several million users to provide seamless services via the internet. The extension of this reverenced technology is growing abruptly with the increase in the number of users. One of the major issues with the cloud is that it receives a huge volume of workloads requesting resources to complete their executions. While executing these workloads, the cloud suffers from the issue of service level agreement (SLA) violations which impacts the performance and reputation of the cloud. Therefore, there is a requirement for an effective design that supports faster and optimal execution of workloads without any violation of SLA. To fill this gap, this article proposes an automatic multiagent framework that ensures the minimization of the SLA violation rate in workload execution. The proposed framework includes seven major agents such as user agent, system agent, negotiator agent, coordinator agent, monitoring agent, arbitrator agent and the history agent. All these agents work cooperatively to enable the effective execution of workloads irrespective of their dynamic nature. With effective execution of workloads, the proposed model also resulted in an advantage of minimized energy consumption in data centres. The inclusion of a history agent within the framework enabled the model to predict future requirements based on the records of resource utilization. The proposed model followed the Poisson distribution to generate random numbers that are further used for evaluation purposes. The simulations of the model proved that model is more reliable in reducing SLA violations compared to the existing works. The proposed method resulted in an average SLA violation rate of 55.71% for 1200 workloads and resulted in an average energy consumption of 47.84kWh for 1500 workloads.

show abstract

Section: Introductionmentioning

confidence: 99%