In the computational grid environment, there is usually a general
framework focusing on the interaction between grid resource
broker, domain resource manager and the grid information server
[9]. Computational grids usually assume that the physical and virtual
levels are completely split but there is a mapping between
resources and users of the two layers [10]. Han and Berry [11] proposed
a novel semantic-supported and agent-based decentralized
grid resource discovery mechanism.
Without overheads of negotiation,
the algorithm allows individual resource agents to semantically
interact with neighboring agents based on local knowledge
and to dynamically form a resource service chain to complete the
tasks. Chung and Chang [12] presented a Grid Resource Information
Monitoring (GRIM) prototype to manage large scale grid resources
for dynamic access and resource management in the grid
environment. In a grid environment it is usually easy to obtain information
about the speed of the available grid nodes but quite
complicated to know the computational processing time requirements
from the user. To conceptualize the problem as an algorithm,
we need to dynamically estimate the job lengths from user application
specifications or historical data. For clarity, some key terminologies
are defined as follows:
نوشته شده توسط BoOghz
جواب بصورت نقل قول
