Advanced Scheduling Techniques with the Pliant System for High-Level Grid Brokering

Abstract

Here we will present advanced scheduling techniques with a weighted fitness function for an adaptive grid meta-brokering using the Pliant system, in order to cope with the high uncertainty ruling current Grid systems. The algorithms are based on the Pliant concept, which is a specific part of fuzzy logic theory. This tool is also capable of creating functions, classifying sets and making decisions. We construct and show how well our new algorithms perform in a grid simulation environment. The results obtained demonstrate that these novel scheduling techniques produce better performance scores, hence the load of Grid systems can be more balanced.