UTHM Institutional Repository

Neighbor-replica distribution technique model for availability prediction in distributed interdependent environment

Mohd Noor, Ahmad Shukri and Herawan, Tutut and Mat Deris, Mustafa (2012) Neighbor-replica distribution technique model for availability prediction in distributed interdependent environment. International Journal of Cloud Applications and Computing, 2 (3). pp. 98-109. ISSN 2156-1834

Full text not available from this repository.

Abstract

High availability is important for large scale distributed systems. Replication provides effective ways to enhance performance, high availability and fault tolerance in distributed systems. An efficient and effective replication technique is the key to improve the availability performance. Data and processes can be replicated for failures recovery. There are currently projects successfully implemented in two-replica distribution technique (TRDT) or primary–backup technique. However, these projects have their weaknesses of increasing cost overhead and inherit irrecoverable scenarios from TRDT such as double faults when both copies of replicated components are damaged. The authors propose the Neighbor Replica Distributed Technique (NRDT) availability prediction model. Focusing on improving high availability in which it predicts future expectation of interdependent server’s availability in a distributed online system over an extended period of time. The results and discussion are explored further in the article.

Item Type: Article
Uncontrolled Keywords: distributed computing; distributed systems; fault failure recovery; high availability; replication technique
Subjects: Q Science > QA Mathematics > QA76 Computer software
Divisions: Faculty of Computer Science and Information Technology > Department of Software Engineering
Depositing User: Normajihan Abd. Rahman
Date Deposited: 03 Jan 2016 07:18
Last Modified: 03 Jan 2016 07:18
URI: http://eprints.uthm.edu.my/id/eprint/3612
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item