DATALITE

A Distributed Architecture for Traffic Analysis via Light-weight Traffic digEst

Wing Cheong Lau, Murali Kodialam, T. V. Lakshman, H. Jonathan Chao

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

Abstract

In this paper, we propose DATALITE, a Distributed Architecture for Traffic Analysis via Lightweight Traffic digEst, which introduces a set of new distributed algorithms and protocols to support general Traffic Measurement and Analysis (TMA) functions for large-scale, 10Gbps+ packet-switched networks. We formulate the network-wide traffic measurement/analysis problem as a series of set-cardinality-determination (SCD) problems. By leveraging recent advances in probabilistic distinct sample counting techniques, the set-cardinalities, and thus, the network-wide traffic measurements of interest can be computed in a distributed manner via the exchange of extremely light-weight traffic digests (TD's) amongst the network nodes. A TD for N packets only requires O(loglog N) bits of memory storage.

Original languageEnglish (US)
Title of host publicationProceedings of the 4th International Conference on Broadband Communications, Networks, Systems, BroadNets
Pages622-630
Number of pages9
DOIs
StatePublished - 2007
Event4th International Conference on Broadband Communications, Networks, Systems, BroadNets - Raleigh, NC, United States
Duration: Sep 10 2007Sep 14 2007

Other

Other4th International Conference on Broadband Communications, Networks, Systems, BroadNets
CountryUnited States
CityRaleigh, NC
Period9/10/079/14/07

Fingerprint

Packet networks
Parallel algorithms
Network protocols
Data storage equipment

Keywords

  • Digest
  • Traceback
  • Traffic Measurement and Analysis

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Lau, W. C., Kodialam, M., Lakshman, T. V., & Chao, H. J. (2007). DATALITE: A Distributed Architecture for Traffic Analysis via Light-weight Traffic digEst. In Proceedings of the 4th International Conference on Broadband Communications, Networks, Systems, BroadNets (pp. 622-630). [4550492] https://doi.org/10.1109/BROADNETS.2007.4550492

DATALITE : A Distributed Architecture for Traffic Analysis via Light-weight Traffic digEst. / Lau, Wing Cheong; Kodialam, Murali; Lakshman, T. V.; Chao, H. Jonathan.

Proceedings of the 4th International Conference on Broadband Communications, Networks, Systems, BroadNets. 2007. p. 622-630 4550492.

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

Lau, WC, Kodialam, M, Lakshman, TV & Chao, HJ 2007, DATALITE: A Distributed Architecture for Traffic Analysis via Light-weight Traffic digEst. in Proceedings of the 4th International Conference on Broadband Communications, Networks, Systems, BroadNets., 4550492, pp. 622-630, 4th International Conference on Broadband Communications, Networks, Systems, BroadNets, Raleigh, NC, United States, 9/10/07. https://doi.org/10.1109/BROADNETS.2007.4550492
Lau WC, Kodialam M, Lakshman TV, Chao HJ. DATALITE: A Distributed Architecture for Traffic Analysis via Light-weight Traffic digEst. In Proceedings of the 4th International Conference on Broadband Communications, Networks, Systems, BroadNets. 2007. p. 622-630. 4550492 https://doi.org/10.1109/BROADNETS.2007.4550492
Lau, Wing Cheong ; Kodialam, Murali ; Lakshman, T. V. ; Chao, H. Jonathan. / DATALITE : A Distributed Architecture for Traffic Analysis via Light-weight Traffic digEst. Proceedings of the 4th International Conference on Broadband Communications, Networks, Systems, BroadNets. 2007. pp. 622-630
@inproceedings{34340be8480f414696639503223d6525,
title = "DATALITE: A Distributed Architecture for Traffic Analysis via Light-weight Traffic digEst",
abstract = "In this paper, we propose DATALITE, a Distributed Architecture for Traffic Analysis via Lightweight Traffic digEst, which introduces a set of new distributed algorithms and protocols to support general Traffic Measurement and Analysis (TMA) functions for large-scale, 10Gbps+ packet-switched networks. We formulate the network-wide traffic measurement/analysis problem as a series of set-cardinality-determination (SCD) problems. By leveraging recent advances in probabilistic distinct sample counting techniques, the set-cardinalities, and thus, the network-wide traffic measurements of interest can be computed in a distributed manner via the exchange of extremely light-weight traffic digests (TD's) amongst the network nodes. A TD for N packets only requires O(loglog N) bits of memory storage.",
keywords = "Digest, Traceback, Traffic Measurement and Analysis",
author = "Lau, {Wing Cheong} and Murali Kodialam and Lakshman, {T. V.} and Chao, {H. Jonathan}",
year = "2007",
doi = "10.1109/BROADNETS.2007.4550492",
language = "English (US)",
isbn = "1424414334",
pages = "622--630",
booktitle = "Proceedings of the 4th International Conference on Broadband Communications, Networks, Systems, BroadNets",

}

TY - GEN

T1 - DATALITE

T2 - A Distributed Architecture for Traffic Analysis via Light-weight Traffic digEst

AU - Lau, Wing Cheong

AU - Kodialam, Murali

AU - Lakshman, T. V.

AU - Chao, H. Jonathan

PY - 2007

Y1 - 2007

N2 - In this paper, we propose DATALITE, a Distributed Architecture for Traffic Analysis via Lightweight Traffic digEst, which introduces a set of new distributed algorithms and protocols to support general Traffic Measurement and Analysis (TMA) functions for large-scale, 10Gbps+ packet-switched networks. We formulate the network-wide traffic measurement/analysis problem as a series of set-cardinality-determination (SCD) problems. By leveraging recent advances in probabilistic distinct sample counting techniques, the set-cardinalities, and thus, the network-wide traffic measurements of interest can be computed in a distributed manner via the exchange of extremely light-weight traffic digests (TD's) amongst the network nodes. A TD for N packets only requires O(loglog N) bits of memory storage.

AB - In this paper, we propose DATALITE, a Distributed Architecture for Traffic Analysis via Lightweight Traffic digEst, which introduces a set of new distributed algorithms and protocols to support general Traffic Measurement and Analysis (TMA) functions for large-scale, 10Gbps+ packet-switched networks. We formulate the network-wide traffic measurement/analysis problem as a series of set-cardinality-determination (SCD) problems. By leveraging recent advances in probabilistic distinct sample counting techniques, the set-cardinalities, and thus, the network-wide traffic measurements of interest can be computed in a distributed manner via the exchange of extremely light-weight traffic digests (TD's) amongst the network nodes. A TD for N packets only requires O(loglog N) bits of memory storage.

KW - Digest

KW - Traceback

KW - Traffic Measurement and Analysis

UR - http://www.scopus.com/inward/record.url?scp=51249083269&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51249083269&partnerID=8YFLogxK

U2 - 10.1109/BROADNETS.2007.4550492

DO - 10.1109/BROADNETS.2007.4550492

M3 - Conference contribution

SN - 1424414334

SN - 9781424414338

SP - 622

EP - 630

BT - Proceedings of the 4th International Conference on Broadband Communications, Networks, Systems, BroadNets

ER -