Cloud Data Center Design using Delay Tolerant Based Priority Queuing Model
Journal: The International Arab Journal of Information Technology (Vol.16, No. 3)Publication Date: 2019-05-01
Authors : Meera Annamalai Swamynathan Sankaranarayanan;
Page : 482-491
Keywords : Cloud data center; (IaaS) and M/M/S priority queuing model;
Abstract
Infrastructure as a Service (IaaS) that occupies the bottom tier in the cloud pyramid is a recently developed technology in cloud computing. Organizations can move their applications to a cloud data center without remodelling it. Cloud providers and consumers need to take into account the performance factors such as resource utilization of computing resources, availability of resources caused by scheduling algorithms. Thus, an effective scheduling algorithm must strive to maximize these performance factors. Designing a cloud data center that schedules computing resources and monitoring their performances plays a leading challenge among the cloud researches. In this paper, we propose a data center design using delay tolerant based priority queuing model for resource provisioning, by paying attention to individual customer attributes. Priority selection process defines how to select the next customer to be served. The system has a priority based task classifier and allocator that accept the customer's request. Based on the rules defined in the rule engine, task classifier classifies each request to a workload Priority classifier is modeled as M/M/S priority queue. The resource monitoring agent provides the resource utilization scenario of cloud infrastructure in the form of dashboard to the task classifier for further resource optimization.
Other Latest Articles
- New Class-based Dynamic Scheduling Strategy for Self-Management of Packets at the Internet Routers
- Offline Isolated Arabic Handwriting Character Recognition System Based on SVM
- Multi-Level Improvement for a Transcription Generated by Automatic Speech Recognition System for Arabic
- Improving Classification Performance Using Genetic Programming to Evolve String Kernels
- Parallel Optimized Pearson Correlation Condition (PO-PCC) for Robust Cosmetic Makeup Facial Recognition
Last modified: 2019-04-28 20:22:59