Probabilistic Replication Based on Access Frequencies in Unstructured Peer-to-Peer Networks

Hara, Takahiro; Kido, Yuki; Nishio, Shojiro

doi:10.1007/11827405_77

Cited by 3 publications

(7 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [4], we have shown that this method can achieve replica allocation which is closer to the square-root allocation than path replication.…”

Section: A Probabilistic Replication Methodsmentioning

confidence: 94%

“…In this section, we briefly present the probabilistic replication method which we proposed in [4] and show the results of preliminary experiments to analyze the characteristics of this method.…”

Section: Our Previous Methodsmentioning

confidence: 99%

“…The probabilistic replication method proposed in [4] uses the rank of each item's access frequency for achieving the square-root allocation. In this method, the requested data item is replicated at peers on the query path when a search succeeds.…”

Section: A Probabilistic Replication Methodsmentioning

confidence: 99%

“…In an unstructured P2P network, it is common that data items are replicated on multiple peers in the network for efficient data retrieval and improving data availability [3], [4], [5], [6], [7]. In [3], the authors discussed the optimal ratios of numbers of replicas of data items allocated in the network.…”

Section: Introductionmentioning

confidence: 98%

“…In [4], we proposed a probabilistic replication method based on access frequencies of data items for achieving the squareroot allocation. As described in Section III, this method replicates the requested data with the probability determined based on the rank of the item's access frequency, and achieves better replica allocation than path replication.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A Replica Relocation Method for Improving Search Efficiency in P2P Networks

Watanabe

Zhao

Kanzaki

et al. 2009

2009 First International Conference on Advances in P2P Systems

Self Cite

View full text Add to dashboard Cite

In P2P networks, it is effective to allocate replicas of each data item to multiple peers for improving search efficiency and data availability. It has been mathematically proved that the square-root allocation, in which the ratios of numbers of replicas are proportional to the square-root of their access frequencies, is optimal in terms of search efficiency. In this paper, we propose a replica relocation method that not only nearly achieves the square-root allocation but also distributes replicas uniformly in the network as much as possible. Our method creates replicas at each peer on the path along which a query is successfully forwarded. Here, each peer on the path determines whether it creates the replica or not based on the access frequency of the data item. In addition, for creating a new replica when a cache memory space is full, our method preferentially deletes a replica of a data item which has been replicated at a large number of peers.

show abstract

“…In [4], we have shown that this method can achieve replica allocation which is closer to the square-root allocation than path replication.…”

Section: A Probabilistic Replication Methodsmentioning

confidence: 94%

Section: Our Previous Methodsmentioning

confidence: 99%

Section: A Probabilistic Replication Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 98%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Replica Relocation Method for Improving Search Efficiency in P2P Networks

Watanabe

Zhao

Kanzaki

et al. 2009

2009 First International Conference on Advances in P2P Systems

Self Cite

View full text Add to dashboard Cite

show abstract

A Generalized File Replication Scheme with Diffusion-Based Storage Load Balancing Function in Unstructured P2P File-Sharing Networks

Takaoka

Uchida

Oie

2010

2010 International Conference on Intelligent Networking and Collaborative Systems

View full text Add to dashboard Cite

In this paper, we provide a generalized file replication scheme with a storage load balancing function in unstructured P2P file-sharing networks. The generalized file replication scheme is expressed as a weighted mixture of the concepts introduced in existing schemes. A mathematical analysis shows that the system behavior realized by the generalized file replication scheme can be described by a thermal diffusion equation composed of heat, reaction and diffusion terms, the weights of which are controlled by a parameter of the mixing rate. Here, the heat term represents a function to enhance file search performance by making replicas on specific peers. The reaction term represents a function to avoid concentrations of storage loads on specific peers. The diffusion term represents a function to uniform the storage loads among peers. The simulation results show that the generalized file replication scheme enables us to control the trade-off between search and storage load balancing performances extensively and intuitively by controlling the parameter of the mixing rate. In addition, the simulation results show that the generalized file replication scheme can adapt to dynamic P2P file-sharing environments.

show abstract