Background:
In grid computing, several computing nodes work together to accomplish a common goal. During
computation some nodes get overloaded and some nodes sit idle without any job, which degrades the overall grid
performance. For better resource utilization, the load balancing strategy of a grid must be improved.
Objective:
A good load balancing strategy intelligently perceives grid information and finds the best node to transfer jobs
from an overloaded node. In our study, we found that the good load balancing strategies have two prominent needs while
decision making i.e. consider multiple parameters and handle uncertainty presents in the grid environment.
Methods:
This paper proposed a model, an intelligent fuzzy middleware for load balancing in a grid computing
environment (IFMLBG) which fulfilled both the needs. The processing of IFMLBG is based on Chang’s extent analysis
for the fuzzy analytical hierarchy process (FAHP). FAHP hierarchically structured the load-balancing problem and used
the non-crisp input to handle the uncertainty of the grid environment. Chang’s analysis is performed to generate weights
to prioritize nodes and find the best one.
Results:
The results show that the IFMLBG Model assigned more weight to the best-selected node as compared to the
AHP model and performs well with prudent nodes and criteria.
Conclusion:
This paper comprehensively described the design of an Intelligent Fuzzy middleware for Load Balancing in
Grid computing (IFMLBG) which used Chang’s extent analysis for FAHP and implemented using four parameters and
four computing nodes. The Chang’s extent analysis for FAHP takes triangular fuzzy numbers as input and generates
weights for nodes. We compared IFMLBG with the classical AHP model on thirteen datasets and concluded that
IFMLBG gives more weight to select the node as compare to the AHP model. The results also show that IFMLBG would
work better with the number of parameters and computing nodes.