Today there is an acceptable situation for any increase in resources connected to grid and providing great low-cost calculation power. Regarding the active and heterogeneous situation of connected resources to grid and diffusion of these resources in wide geographical situation, one of the most important problems of grid is discover the required resources. There are two major groups of grid resource discovery methods meaning centralized & non-centralized methods with some special and personal problems. The current presented methods are resulted from combination of above-mentioned methods. The fundamental problem in these new methods is going towards various problems in centralized or non-centralized methods including hierarchy method, tree method, and virtual organization and so on. For instance in tree methods we have servers with a fixed and constructional role. Any damages of them may cause a lot of costs. There is also another worrying factor such as gradual greatness of group and various problems of non-centralized methods like non-defined distribution of messages and non-damping situation of the message. This paper intends to propose a new method based upon active grouping of nodes. In this method we have independent groups of nodes with a separate server for management of domestic resources of group. Then group server may call other groups for further relations upon recognition of territorial nodes of groups and finding group servers. We should create server and territorial nodes in a way not to bear a fixed role and could replace with other nodes. The proposed method in this paper has been compared with other resource discovery methods on analytical basis and also through simulation of grid environment for small & great environments as well. According to the obtained results, this method has a more harmonized application in speed factors, reducing of network traffic and also better application in damping of quick wasted messages.
[1]
Rafael Moreno-Vozmediano.
A hybrid mechanism for resource/service discovery in ad-hoc grids
,
2009,
Future Gener. Comput. Syst..
[2]
Amos Brocco,et al.
Enabling efficient information discovery in a self-structured grid
,
2010,
Future Gener. Comput. Syst..
[3]
K. Siu,et al.
XXXXXXXXXX An O ( log n ) Randomized Resource Discovery Algorithm
,
2000
.
[4]
Takahiro Katagiri,et al.
A time-to-live based reservation algorithm on fully decentralized resource discovery in Grid computing
,
2005,
Parallel Comput..
[5]
Wilson Rivera,et al.
Grid-HSI: Using grid computing to enable hyperspectral imaging analysis
,
2004,
Communications, Internet, and Information Technology.
[6]
Domenico Talia,et al.
Design and Implementation of a Hybrid P2P-based Grid Resource Discovery System
,
2007,
CoreGRID Workshop - Making Grids Work.
[7]
R. Buyya,et al.
A Study on Peer-to-Peer Based Discovery of Grid Resource Information
,
2006
.
[8]
Juan Li,et al.
Grid resource discovery based on semantically linked virtual organizations
,
2010,
Future Gener. Comput. Syst..
[9]
Leili Mohammad Khanli,et al.
FRDT: Footprint Resource Discovery Tree for grids
,
2011,
Future Gener. Comput. Syst..
[10]
Ruay-Shiung Chang,et al.
A resource discovery tree using bitmap for grids
,
2010,
Future Gener. Comput. Syst..
[11]
Shaowen Wang,et al.
Sog: a self-organized grouping infrastructure for grid resource discovery
,
2006
.