A Genetic Algorithm based approach for designing multi-state computational grid with cost and bandwidth constraints

A computational grid needs to be cost-effective and highly reliable. It must have the ability to transfer maximum amount of data for end-to-end delivery. Many research works on computational grids conclude with a binary state of operation. Although some research reveals that, the grids operate with...

Full description

Saved in:
Bibliographic Details
Published in:Journal of King Saud University. Computer and information sciences Vol. 34; no. 2; pp. 443 - 456
Main Authors: Debashreet Das, C.R. Tripathy, P.K. Tripathy, M.R. Kabat
Format: Journal Article
Language:English
Published: Springer 01.02.2022
Subjects:
Bandwidth
Cost
Genetic Algorithm
Multi-state computational grids
Reliability
ISSN:1319-1578
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A computational grid needs to be cost-effective and highly reliable. It must have the ability to transfer maximum amount of data for end-to-end delivery. Many research works on computational grids conclude with a binary state of operation. Although some research reveals that, the grids operate with multiple states of connections and operations, they are silent about the mentioned constraints. Since there are multi-state operations, the reliability depends on the load, bandwidth and cost. This paper proposes a Genetic Algorithm (GA) based approach for optimization of reliability of computational grid with desired reliability under cost and bandwidth constraints. The method is well explained through illustration and its implementation on some Grid networks. The efficient encoding, cross-over, mutation and selection operation of the proposed scheme ensures the fast convergence to the optimal solution. On comparison, the proposed method is observed to be more efficient than the existing ones.
ISSN:1319-1578
DOI:10.1016/j.jksuci.2018.10.006