Abstract

In this paper, we will present a scheduling algorithm for batch pipeline resources using GA. BGPS algorithms for resource allocation with variable processing power to the jobs is offered. In previous algorithms, a source could select and run one job at a time. New techniques can batch jobs and perform them in parallel. so after the first job is completed, second job is started simultaneously. The BGPS algorithm can reduce wasting time of sweeping jobs. And we can have the optimal use of existing resources. The new algorithm, in comparison to a similar algorithm with a bunch of jobs, can run them in a pipline. It will be able to request and confirmation of job after the end of previous job, and also allocate resources to perform jobs in parallel. The system is capable to accelerate of processing tasks with different parameters in function and increase system efficiency.

References

• An ant algorithm for balanced job scheduling in grids Ruay-Shiung Chang_, Jih-Sheng Chang, Po-Sheng Lin Department of Computer Science and Information Engineering, National Dong Hwa University, Shoufeng Hualien, 974 Taiwan, ROC
• New Self-Scheduling Schemes for Internet-Based Grids of Computers Javier Díaz, Sebastián Reyes, Alfonso Niño, and Camelia Muñoz-Caro
• A general model for the generation and scheduling of parameter sweep experiments in Computational Grid Environments- International Conference on Computational Science, ICCS 2010- Javier Díaza,?, Sebastián Reyesa, Rosa M. Badiab, Alfonso Niñoa, Camelia Muñoz-Caroa
• I. Foster and C. Kesselman(editors), The Grid: Blueprint for a Future Computing Infrastructure, Morgan Kaufmann Publishers, USA, 1999.
• DSQGG: An optimized genetic-based algorithm for scheduling in distributed grid Delavar, A. G. ; Rahmany, M. ; Halaakouie, A. ; Sookhtsaraei, R. ; Payam Noor Univ. , Tehran, Iran 29 November 2010
• An improved rank-based genetic algorithm with limited iterations for grid scheduling Abdulal, W. CSE Dept. , Osmania Univ. , Hyderabad, India Al Jadaan, O. ; Jabas, A. ; Ramachandram, S. Industrial Electronics & Applications, 2009. ISIEA 2009. IEEE Symposium on
• On the Design of Fault-Tolerant Scheduling Strategies Using Primary-Backup Approach for Computational Grids with Low Replication Costs Qin Zheng Inst. of High Performance Comput. , Agency for Sci. , Singapore Veeravalli, B. ; Chen-Khong Tham March 2009
• A genetic algorithm for task scheduling in network computing environment Dongmei Liu State Key Lab. of Software Eng. , Wuhan Univ. , China Yuanxiang Li ; Mingzhao Yu 23-25 Oct. 2002
• GABased Job Scheduling Strategies for FaultTolerant Grid Systems Chao-Chin Wu; Kuan-Chou Lai; Ren-Yi Sun Asia-Pacific Services Computing Conference, 2008. APSCC '08. IEEE
• Arash Ghorbannia Delavar, Ali Reza Khalili Boroujeni and Javad Bayrampoor. Article: A Balanced Scheduling Algorithm with Fault Tolerant and Task Migration based on Primary Static Mapping (PSM) in Grid. International Journal of Computer Applications52(8):10-21, August 2012. Published by Foundation of Computer Science, New York, USA.