Efficient cloud system for scientific communities

The main idea behind cloud system is to provide the unlimited resources. Existing DawningCloud is an efficient cloud system for scientific communities. It reduced the total resource consumption of cloud resource provider and cloud users. However, DawningCloud simply used First Come First Served (FCFS) scheduling Policy and did not investigate the effect of different scheduling techniques on them. Therefore, we are proposing a novel scheduling algorithm, "Priority Scheduling based on Users Activities (PS-UA)" to handle the large amount of requests on the existing DawningCloud system. The contribution of this paper is to compare the performance of the existing DawningCloud system with "First Come First Served (FCFS)", "Earlier Account Expire Prioritized with Round Robin (EAEP-RR)" and proposed "Priority Scheduling based on Users Activities (PS-UA)" scheduling algorithm. The conclusion of this paper is that existing DawningCloud with EAEP-RR algorithm gives better performance as compared to a FCFS scheduling algorithm. However, existing DawningCloud with proposed PS-UA scheduling algorithm provides less waiting time for resources as compared to FCFS and EAEP-RR. Therefore, we conclude that proposed PS-UA is more efficient than FCFS and EAEP-RR.

[1]  Yi Liang,et al.  In Cloud, Can Scientific Communities Benefit from the Economies of Scale? , 2010, IEEE Transactions on Parallel and Distributed Systems.

[2]  Mohamed Othman,et al.  A priority based job scheduling algorithm in cloud computing , 2012 .

[3]  Rajkumar Buyya,et al.  Evaluating the cost-benefit of using cloud computing to extend the capacity of clusters , 2009, HPDC '09.

[4]  Miron Livny,et al.  The cost of doing science on the cloud: The Montage example , 2008, 2008 SC - International Conference for High Performance Computing, Networking, Storage and Analysis.

[5]  Anindya Jyoti Pal,et al.  Design, Development and Performance Analysis of Deadline Based Priority Heuristic for Job Scheduling on a Grid , 2012 .

[6]  T. Ravichandran,et al.  Non-Preemptive Real Time Scheduling using Checkpointing Algorithm for Cloud Computing , 2013 .

[7]  Constantinos Evangelinos,et al.  Cloud Computing for parallel Scientific HPC Applications: Feasibility of Running Coupled Atmosphere- , 2008 .

[8]  Li Yang,et al.  A New Class of Priority-based Weighted Fair Scheduling Algorithm , 2012 .

[9]  Seema Verma,et al.  A survey on the impact of economies of scale on scientific communities , 2015, 2015 International Conference on Advances in Computer Engineering and Applications.

[10]  Weisong Shi,et al.  PhoenixCloud: Provisioning Resources for Heterogeneous Cloud Workloads , 2010, ArXiv.

[11]  Dan Meng,et al.  Phoenix Cloud : Consolidating Heterogeneous Workloads of Large Organizations on Cloud Computing Platforms , 2009, ArXiv.