Load balancing in peer-to-peer networks based on sampling system states

Hung-Chang Hsiao, I. Ta Lin, Hao Liao

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Virtual servers provide an abstraction layer to exploit the heterogeneity of peers (or nodes) that participate in a peer-to-peer (P2P) network based on the distributed hash table (DHT). In this paper, we present a load-balancedDHT network based on virtual servers. In our proposal, participating peers accept loads proportional to their capacities. By sampling the capacities of peers and workloads of virtual servers in the system, our design approximates the probability distributions for the capacities and workloads. Each node is based on the probability distributions to match their local virtual servers and other peers. Our proposal is developed through rigorous performance analysis, and is evaluated in extensive simulations.

Original languageEnglish
Title of host publicationProceedings of The 5th International Conference on Embedded and Ubiquitous Computing, EUC 2008
Pages417-423
Number of pages7
DOIs
Publication statusPublished - 2008 Dec 1
Event5th International Conference on Embedded and Ubiquitous Computing, EUC 2008 - Shanghai, China
Duration: 2008 Dec 172008 Dec 20

Publication series

NameProceedings of The 5th International Conference on Embedded and Ubiquitous Computing, EUC 2008
Volume1

Other

Other5th International Conference on Embedded and Ubiquitous Computing, EUC 2008
CountryChina
CityShanghai
Period08-12-1708-12-20

Fingerprint

Peer to peer networks
Resource allocation
Computer systems
Servers
Sampling
workload
Probability distributions
abstraction
simulation
performance

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Software
  • Communication

Cite this

Hsiao, H-C., Lin, I. T., & Liao, H. (2008). Load balancing in peer-to-peer networks based on sampling system states. In Proceedings of The 5th International Conference on Embedded and Ubiquitous Computing, EUC 2008 (pp. 417-423). [4756369] (Proceedings of The 5th International Conference on Embedded and Ubiquitous Computing, EUC 2008; Vol. 1). https://doi.org/10.1109/EUC.2008.12
Hsiao, Hung-Chang ; Lin, I. Ta ; Liao, Hao. / Load balancing in peer-to-peer networks based on sampling system states. Proceedings of The 5th International Conference on Embedded and Ubiquitous Computing, EUC 2008. 2008. pp. 417-423 (Proceedings of The 5th International Conference on Embedded and Ubiquitous Computing, EUC 2008).
@inproceedings{fd525e95b2404225bfa3793740d68978,
title = "Load balancing in peer-to-peer networks based on sampling system states",
abstract = "Virtual servers provide an abstraction layer to exploit the heterogeneity of peers (or nodes) that participate in a peer-to-peer (P2P) network based on the distributed hash table (DHT). In this paper, we present a load-balancedDHT network based on virtual servers. In our proposal, participating peers accept loads proportional to their capacities. By sampling the capacities of peers and workloads of virtual servers in the system, our design approximates the probability distributions for the capacities and workloads. Each node is based on the probability distributions to match their local virtual servers and other peers. Our proposal is developed through rigorous performance analysis, and is evaluated in extensive simulations.",
author = "Hung-Chang Hsiao and Lin, {I. Ta} and Hao Liao",
year = "2008",
month = "12",
day = "1",
doi = "10.1109/EUC.2008.12",
language = "English",
isbn = "9780769534923",
series = "Proceedings of The 5th International Conference on Embedded and Ubiquitous Computing, EUC 2008",
pages = "417--423",
booktitle = "Proceedings of The 5th International Conference on Embedded and Ubiquitous Computing, EUC 2008",

}

Hsiao, H-C, Lin, IT & Liao, H 2008, Load balancing in peer-to-peer networks based on sampling system states. in Proceedings of The 5th International Conference on Embedded and Ubiquitous Computing, EUC 2008., 4756369, Proceedings of The 5th International Conference on Embedded and Ubiquitous Computing, EUC 2008, vol. 1, pp. 417-423, 5th International Conference on Embedded and Ubiquitous Computing, EUC 2008, Shanghai, China, 08-12-17. https://doi.org/10.1109/EUC.2008.12

Load balancing in peer-to-peer networks based on sampling system states. / Hsiao, Hung-Chang; Lin, I. Ta; Liao, Hao.

Proceedings of The 5th International Conference on Embedded and Ubiquitous Computing, EUC 2008. 2008. p. 417-423 4756369 (Proceedings of The 5th International Conference on Embedded and Ubiquitous Computing, EUC 2008; Vol. 1).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Load balancing in peer-to-peer networks based on sampling system states

AU - Hsiao, Hung-Chang

AU - Lin, I. Ta

AU - Liao, Hao

PY - 2008/12/1

Y1 - 2008/12/1

N2 - Virtual servers provide an abstraction layer to exploit the heterogeneity of peers (or nodes) that participate in a peer-to-peer (P2P) network based on the distributed hash table (DHT). In this paper, we present a load-balancedDHT network based on virtual servers. In our proposal, participating peers accept loads proportional to their capacities. By sampling the capacities of peers and workloads of virtual servers in the system, our design approximates the probability distributions for the capacities and workloads. Each node is based on the probability distributions to match their local virtual servers and other peers. Our proposal is developed through rigorous performance analysis, and is evaluated in extensive simulations.

AB - Virtual servers provide an abstraction layer to exploit the heterogeneity of peers (or nodes) that participate in a peer-to-peer (P2P) network based on the distributed hash table (DHT). In this paper, we present a load-balancedDHT network based on virtual servers. In our proposal, participating peers accept loads proportional to their capacities. By sampling the capacities of peers and workloads of virtual servers in the system, our design approximates the probability distributions for the capacities and workloads. Each node is based on the probability distributions to match their local virtual servers and other peers. Our proposal is developed through rigorous performance analysis, and is evaluated in extensive simulations.

UR - http://www.scopus.com/inward/record.url?scp=63149128733&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=63149128733&partnerID=8YFLogxK

U2 - 10.1109/EUC.2008.12

DO - 10.1109/EUC.2008.12

M3 - Conference contribution

SN - 9780769534923

T3 - Proceedings of The 5th International Conference on Embedded and Ubiquitous Computing, EUC 2008

SP - 417

EP - 423

BT - Proceedings of The 5th International Conference on Embedded and Ubiquitous Computing, EUC 2008

ER -

Hsiao H-C, Lin IT, Liao H. Load balancing in peer-to-peer networks based on sampling system states. In Proceedings of The 5th International Conference on Embedded and Ubiquitous Computing, EUC 2008. 2008. p. 417-423. 4756369. (Proceedings of The 5th International Conference on Embedded and Ubiquitous Computing, EUC 2008). https://doi.org/10.1109/EUC.2008.12