BaRT, Balanced Randomized Tree: A scalable and distributed protocol for lookup in peer-to-peer networks

Angelo Spognardi; Roberto Di Pietro; Luigi V. Mancini

BaRT, Balanced Randomized Tree: A scalable and distributed protocol for lookup in peer-to-peer networks

Angelo Spognardi, Roberto Di Pietro, Luigi V. Mancini

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper proposes a new scheme for p2p networks. The main contributions are an extensive use of randomization techniques and a novel usage of tree-data structure. The combination of these two ingredients allows a great flexibility of network parameters, such as: load balance among the peers, fast lookups and reduced memory usage. For instance, with routing tables of size (d - 1) log d n, the average number of hops for a lookup is of the order of 1/d ((d - 1) logd n + 1), where n is the number of peers in the network and d is the ariety of the tree data structure. Further, we propose a few new optimization mechanisms that can be adopted in DHT. Extensive simulations support these results. © 2005 IEEE.

Original language	English (US)
Title of host publication	Proceedings of the First International Workshop on Hot Topics in Peer-to-Peer Systems, HOT-P2P '04
Pages	22-30
Number of pages	9
State	Published - Dec 1 2004
Externally published	Yes

Bibliographical note

Generated from Scopus record by KAUST IRTS on 2023-09-20

Cite this

@inproceedings{2fce19bef33c4590a826a21434175d55,

title = "BaRT, Balanced Randomized Tree: A scalable and distributed protocol for lookup in peer-to-peer networks",

abstract = "This paper proposes a new scheme for p2p networks. The main contributions are an extensive use of randomization techniques and a novel usage of tree-data structure. The combination of these two ingredients allows a great flexibility of network parameters, such as: load balance among the peers, fast lookups and reduced memory usage. For instance, with routing tables of size (d - 1) log d n, the average number of hops for a lookup is of the order of 1/d ((d - 1) logd n + 1), where n is the number of peers in the network and d is the ariety of the tree data structure. Further, we propose a few new optimization mechanisms that can be adopted in DHT. Extensive simulations support these results. {\textcopyright} 2005 IEEE.",

author = "Angelo Spognardi and {Di Pietro}, Roberto and Mancini, {Luigi V.}",

note = "Generated from Scopus record by KAUST IRTS on 2023-09-20",

year = "2004",

month = dec,

day = "1",

language = "English (US)",

isbn = "0769522696",

pages = "22--30",

booktitle = "Proceedings of the First International Workshop on Hot Topics in Peer-to-Peer Systems, HOT-P2P '04",

}

TY - GEN

T1 - BaRT, Balanced Randomized Tree: A scalable and distributed protocol for lookup in peer-to-peer networks

AU - Spognardi, Angelo

AU - Di Pietro, Roberto

AU - Mancini, Luigi V.

N1 - Generated from Scopus record by KAUST IRTS on 2023-09-20

PY - 2004/12/1

Y1 - 2004/12/1

N2 - This paper proposes a new scheme for p2p networks. The main contributions are an extensive use of randomization techniques and a novel usage of tree-data structure. The combination of these two ingredients allows a great flexibility of network parameters, such as: load balance among the peers, fast lookups and reduced memory usage. For instance, with routing tables of size (d - 1) log d n, the average number of hops for a lookup is of the order of 1/d ((d - 1) logd n + 1), where n is the number of peers in the network and d is the ariety of the tree data structure. Further, we propose a few new optimization mechanisms that can be adopted in DHT. Extensive simulations support these results. © 2005 IEEE.

AB - This paper proposes a new scheme for p2p networks. The main contributions are an extensive use of randomization techniques and a novel usage of tree-data structure. The combination of these two ingredients allows a great flexibility of network parameters, such as: load balance among the peers, fast lookups and reduced memory usage. For instance, with routing tables of size (d - 1) log d n, the average number of hops for a lookup is of the order of 1/d ((d - 1) logd n + 1), where n is the number of peers in the network and d is the ariety of the tree data structure. Further, we propose a few new optimization mechanisms that can be adopted in DHT. Extensive simulations support these results. © 2005 IEEE.

UR - http://www.scopus.com/inward/record.url?scp=24644512702&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0769522696

SP - 22

EP - 30

BT - Proceedings of the First International Workshop on Hot Topics in Peer-to-Peer Systems, HOT-P2P '04

ER -

BaRT, Balanced Randomized Tree: A scalable and distributed protocol for lookup in peer-to-peer networks

Abstract

Bibliographical note

Other files and links

Fingerprint

Cite this