A hybrid load balancing algorithm for coarse-grained applications

Authors:
Aggarwal Akshai;Gan Xinyu
Affiliations:
School of Computer Science, University of Windsor, Windsor, Ontario, Canada;School of Computer Science, University of Windsor, Windsor, Ontario, Canada
Venue:
ICCOMP'06 Proceedings of the 10th WSEAS international conference on Computers
Year:
2006

Citing 8
Cited 0

Metasystems: an approach combining parallel processing and heterogeneous distributed computing systems

Journal of Parallel and Distributed Computing - Special issue on heterogeneous processing
Dynamic load balancing of data parallel applications on a distributed network

ICS '95 Proceedings of the 9th international conference on Supercomputing
Diffusive Load-Balancing Policies for Dynamic Applications

IEEE Concurrency
Load Distributing for Locally Distributed Systems

Computer
Fast Allocation of Processes in Distributed and Parallel Systems

IEEE Transactions on Parallel and Distributed Systems
Web Enabled Client-Server Model for Development Environment of Distributed Image Processing

GRID '00 Proceedings of the First IEEE/ACM International Workshop on Grid Computing
Practical Dynamic Load Balancing for Irregular Problems

IRREGULAR '96 Proceedings of the Third International Workshop on Parallel Algorithms for Irregularly Structured Problems
Load Balancing in a Heterogeneous Computing Environment

HICSS '98 Proceedings of the Thirty-First Annual Hawaii International Conference on System Sciences-Volume 7 - Volume 7

Quantified Score

Hi-index	0.00

Visualization

Abstract

A non-preemptive hybrid load balancing algorithm is proposed for heterogeneous distributed computing environment. The hybrid model initially classifies the compute elements and jobs into different types. The algorithm maps the tasks of various jobs onto compute elements of the same type. Based on historical experience, the centralized load balancer can dynamically change the parameters in order to improve the overall performance during runtime. The algorithm balances the work load of coarse-grained applications with interdependent processes. Its working has been compared with other similar algorithms by extensive testing on a test-bed. The Hybrid Load Balancing algorithm is found to give consistently better results.