QoS Aware Resource Scheduling and Performance Assessment of Heuristics for Processing Jobs on Cloud
Krunal Vaghela1, Amit Lathigara2, Paresh Tanna3
1Krunal Vaghela*, Research Scholar, Faculty of Technology, RK University, Rajkot, India.
2Dr. Amit Lathigara, Computer Engineering, Marwadi University, Rajkot, India.
3Dr. Paresh Tanna, MCA, RK University, Rajkot, India.
Manuscript received on March 15, 2020. | Revised Manuscript received on March 30, 2020. | Manuscript published on April 10, 2020. | PP: 2202-2207 | Volume-9 Issue-6, April 2020. | Retrieval Number: F4638049620/2020©BEIESP | DOI: 10.35940/ijitee.F4638.049620
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Cloud computing or in other words, shared computing is a unique way of sharing resources via the Internet. It combines and extends features of parallel processing, grid computing, and distributed computing. Cloud Computing environments provide a competent way to schedule and process various jobs on remote machines. Rather than relying on local machines, Cloud users access services remotely via high-speed networks. Various users submitting jobs to be processed to Cloud would expect Quality of Service (QoS). So, currently, many researchers are proposing various heuristics that provide QoS to cloud users. The job scheduler is responsible for scheduling various jobs to its best-matched resource to achieve desired QoS. There are Service Level Agreements (SLAs) between Cloud Service Providers (CSPs) and Cloud users, which need to be followed by both the parties. Benefits would be affected in case of not complying with SLAs. In this paper various SLAs like Hard SLA, Best Effort SLA and Soft SLA are proposed. Jobs with required QoS parameters like Reliability, Execution Time and Priority are submitted to the scheduler. QoS of resources is determined by parameters like Reliability, Job Completion Time and the Cost of the resource. Schedulers then assign the Job to the best-matched resource according to specified SLA. Simulation is performed for First Fit and Best Fit heuristic approaches. Performances of both the heuristic approaches are evaluated with performance parameters like Average Resource Utilization (ARU), Success Rate of Jobs (SR) and Total Completion Time (TCT). This research work is useful for various organizations that provide various Cloud services to users who seek different levels of QoS for various applications.
Keywords: Average Resource Utilization (ARU), Best Fit (BF), First Fit (FF), Success Rate of Jobs (SR), Total Completion Time (TCT).
Scope of the Article: Cloud Resources Utilization in IoT