A data mining correlated patterns-based periodic decentralized replication strategy for data grids

Hamrouni, Tarek; Slimani, Sarra; Charrada, Faouzi Ben

doi:10.1016/j.jss.2015.08.019

Cited by 24 publications

(23 citation statements)

References 56 publications

(111 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They chose all the confidence as correlation measure. In [2] TarekHamrouni, Sarra Slimani, et al, proposed new dynamic periodic decentralized data replication strategy as well as they introduced new pattern mining algorithm to find out frequent correlated pattern. Using OptorSim simulator they proved the performance with compared to other strategies.…”

Section: A Related Workmentioning

confidence: 99%

“…Most of the existing replication techniques, neglects correlation among different data files as well as those are all based on the single file granularity. In fact, in most of the applications, data files may be correlated for accessing and to consider together to reduce access cost [2]. By analysing Coadd, which is a actual data intensive grid application, found that there is strong correlation between jobs tend to demand groups of correlated files and requested files.…”

Section: Introductionmentioning

confidence: 99%

“…Even though data mining has been applied for sectors, the applications of data mining in the context of replication is limited. In this regard, data mining techniques are used by several works to explore file correlations in data grids [2]. The main approaches to mining file correlations can be classified into two categories: access sequence mining and association rule mining [3].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Efficient Data Management in Grid Computing using DMDR Algorithm

Prema.¹

2019

IJRASET

View full text Add to dashboard Cite

Replication is a widely used method in data grid which aims to reduce bandwidth consumption, improve response time and maintain reliability. In data grid, for performance enhancement file correlations become an important consideration. The scrutiny of actual data intensive grid applications suggests that correlations can be broken for improving the efficiency of replication strategies and acknowledge that job requests for group of correlated files. In this paper an algorithm namely, Data mining based dynamic replication algorithm (DMDR) has been implemented, which consider a set of files as granularity. This work collects files based on a relationship of concurrent accesses between files by jobs as well as stores related files at the same time. So DM (Data Mining) is introduced to find out these correlations. All confidence measure is chosen for correlation measure.

show abstract

Section: A Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Efficient Data Management in Grid Computing using DMDR Algorithm

Prema.¹

2019

IJRASET

View full text Add to dashboard Cite

show abstract

“…ARRA is indeed introduced in two parts. In first part, access behaviours of data intensive jobs are analyzed based on the APRIORI algorithm [13]. In another part, replica replacement rules are generated and applied.…”

Section: A Arra (Associated Replica Replacement Algorithm Based On Amentioning

confidence: 99%

“…A pre-fetching based dynamic data replication algorithm strategy consists of 3 steps [13]: 1) Storing file accessing patterns: In this step, file accessing sequences and data accessing patterns are stored in a database. A prefetching based dynamic data replication algorithm uses a structure for storing access sequences.…”

Section: Pddra (A Pre-fetching Based Dynamic Data Replication Algomentioning

confidence: 99%

A Survey of Dynamic Replication Strategies based on Data Mining Techniques

Prema¹

2019

IJRASET

View full text Add to dashboard Cite

Grid Computing is an emerging research field which is mainly concentrates on enterprise information systems. To improve the dynamic data management in grid computing the efficient replication strategy needs to be followed. In this paper, we focused on various data mining based replication strategies to enhance data replication which are important data management techniques commonly used in data grids.

show abstract

Popularity and correlation aware data replication strategy based on half‐life concept and clustering in cloud system

Chellouf

Hamrouni

2020

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

Summary In the new millennium, a myriad of large‐scale applications (e.g., social networks, ecommerce, internet of things, and scientific experiments) often generate large volumes of data. Given their volumes, their heterogeneous and distributed nature, the management of such data constitutes a challenge for distributed systems, particularly cloud computing. In this regard, data replication is a well‐known and effective data management technique that consists in creating multiple copies of the same data in different storage resources. In this article, we propose a popularity and correlation based data replication strategy, called PCDR. The main idea of our strategy is to replicate a set of the most popular correlated file groups based on files access history analysis. In this respect, the popularity of the files in each group is determined while taking into consideration temporal locality. Moreover, a clustering technique is used to find groups of correlated files. Using the CloudSim simulator, extensive experimentations show that our proposed strategy outperforms other strategies for several evaluation metrics.

show abstract

A data mining correlated patterns-based periodic decentralized replication strategy for data grids

Cited by 24 publications

References 56 publications

Efficient Data Management in Grid Computing using DMDR Algorithm

Efficient Data Management in Grid Computing using DMDR Algorithm

A Survey of Dynamic Replication Strategies based on Data Mining Techniques

Popularity and correlation aware data replication strategy based on half‐life concept and clustering in cloud system

Contact Info

Product

Resources

About