A Fuzzy Approach to Load Balancing in a Distributed Object Computing Network

Authors:
Lap-Sun Cheung
Affiliations:
-
Venue:
CCGRID '01 Proceedings of the 1st International Symposium on Cluster Computing and the Grid
Year:
2001

Citing 0
Cited 4

Fault-Tolerant Parallel Scheduling of Tasks on a Heterogeneous High-Performance Workstation Cluster

The Journal of Supercomputing
References

Grid resource management
IP layer load balance using fuzzy logic under IPv6 anycast mechanism

International Journal of Network Management
A novel adaptive fuzzy load balancer for heterogeneous LAM/MPI clusters applied to evolutionary learning in neuro-fuzzy systems

FUZZ-IEEE'09 Proceedings of the 18th international conference on Fuzzy Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

Distributed Object Computing (DOC) environments are widely considered as important platforms for building practical network computing applications. To efficiently manage such environments, load balancing technique can be applied to balance system processing load among multiple server hosts. However, due to the global state uncertainty, there is no suitable mathematical model to characterize network behavior such that accurate task placement decision can be predicted. Fuzzy Logic is one of the most powerful paradigms in solving problems that are difficult to model mathematically. In this paper, the design and implementation of a dynamic fuzzy load balancing service running a DOC environment is described. We have chosen Jini (Sun Microsystems) as our experimental platform on which our proposed approach and random and round-robin approaches are implemented and compared.