Small active counters

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

33 Citations (Scopus)

Abstract

The need for efficient counter architecture has arisen for the following two reasons. Firstly, a number of data streaming algorithms and network management applications require a large number of counters in order to identify important traffic characteristics. And secondly, at high speeds, current memory devices have significant limitations in terms of speed (DRAM) and size (SRAM). For some applications no information on counters is needed on a per-packet basis and several methods have been proposed to handle this problem with low SRAM memory requirements. However, for a number of applications it is essential to have the counter information on every packet arrival. In this paper we propose two, computationally and memory efficient, randomized algorithms for approximating the counter values. We prove that proposed estimators are unbiased and give variance bounds. A case study on Multistage Filters (MSF) over the real Internet traces shows a significant improvement by using the active counters architecture.

Original languageEnglish
Title of host publicationProceedings - IEEE INFOCOM 2007: 26th IEEE International Conference on Computer Communications
Pages2153-2161
Number of pages9
DOIs
Publication statusPublished - 2007
Externally publishedYes
EventIEEE INFOCOM 2007: 26th IEEE International Conference on Computer Communications - Anchorage, AK, United States
Duration: 6 May 200712 May 2007

Other

OtherIEEE INFOCOM 2007: 26th IEEE International Conference on Computer Communications
CountryUnited States
CityAnchorage, AK
Period6/5/0712/5/07

Fingerprint

Static random access storage
Data storage equipment
Dynamic random access storage
Network management
Internet

Keywords

  • Counter architecture
  • Data streaming algorithms
  • High-speed measurements
  • Router

ASJC Scopus subject areas

  • Computer Science(all)
  • Electrical and Electronic Engineering

Cite this

Stanojevic, R. (2007). Small active counters. In Proceedings - IEEE INFOCOM 2007: 26th IEEE International Conference on Computer Communications (pp. 2153-2161). [4215831] https://doi.org/10.1109/INFCOM.2007.249

Small active counters. / Stanojevic, Rade.

Proceedings - IEEE INFOCOM 2007: 26th IEEE International Conference on Computer Communications. 2007. p. 2153-2161 4215831.

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

Stanojevic, R 2007, Small active counters. in Proceedings - IEEE INFOCOM 2007: 26th IEEE International Conference on Computer Communications., 4215831, pp. 2153-2161, IEEE INFOCOM 2007: 26th IEEE International Conference on Computer Communications, Anchorage, AK, United States, 6/5/07. https://doi.org/10.1109/INFCOM.2007.249
Stanojevic R. Small active counters. In Proceedings - IEEE INFOCOM 2007: 26th IEEE International Conference on Computer Communications. 2007. p. 2153-2161. 4215831 https://doi.org/10.1109/INFCOM.2007.249
Stanojevic, Rade. / Small active counters. Proceedings - IEEE INFOCOM 2007: 26th IEEE International Conference on Computer Communications. 2007. pp. 2153-2161
@inproceedings{2c5e909d02e24dc285419e64a0a12e9f,
title = "Small active counters",
abstract = "The need for efficient counter architecture has arisen for the following two reasons. Firstly, a number of data streaming algorithms and network management applications require a large number of counters in order to identify important traffic characteristics. And secondly, at high speeds, current memory devices have significant limitations in terms of speed (DRAM) and size (SRAM). For some applications no information on counters is needed on a per-packet basis and several methods have been proposed to handle this problem with low SRAM memory requirements. However, for a number of applications it is essential to have the counter information on every packet arrival. In this paper we propose two, computationally and memory efficient, randomized algorithms for approximating the counter values. We prove that proposed estimators are unbiased and give variance bounds. A case study on Multistage Filters (MSF) over the real Internet traces shows a significant improvement by using the active counters architecture.",
keywords = "Counter architecture, Data streaming algorithms, High-speed measurements, Router",
author = "Rade Stanojevic",
year = "2007",
doi = "10.1109/INFCOM.2007.249",
language = "English",
isbn = "1424410479",
pages = "2153--2161",
booktitle = "Proceedings - IEEE INFOCOM 2007: 26th IEEE International Conference on Computer Communications",

}

TY - GEN

T1 - Small active counters

AU - Stanojevic, Rade

PY - 2007

Y1 - 2007

N2 - The need for efficient counter architecture has arisen for the following two reasons. Firstly, a number of data streaming algorithms and network management applications require a large number of counters in order to identify important traffic characteristics. And secondly, at high speeds, current memory devices have significant limitations in terms of speed (DRAM) and size (SRAM). For some applications no information on counters is needed on a per-packet basis and several methods have been proposed to handle this problem with low SRAM memory requirements. However, for a number of applications it is essential to have the counter information on every packet arrival. In this paper we propose two, computationally and memory efficient, randomized algorithms for approximating the counter values. We prove that proposed estimators are unbiased and give variance bounds. A case study on Multistage Filters (MSF) over the real Internet traces shows a significant improvement by using the active counters architecture.

AB - The need for efficient counter architecture has arisen for the following two reasons. Firstly, a number of data streaming algorithms and network management applications require a large number of counters in order to identify important traffic characteristics. And secondly, at high speeds, current memory devices have significant limitations in terms of speed (DRAM) and size (SRAM). For some applications no information on counters is needed on a per-packet basis and several methods have been proposed to handle this problem with low SRAM memory requirements. However, for a number of applications it is essential to have the counter information on every packet arrival. In this paper we propose two, computationally and memory efficient, randomized algorithms for approximating the counter values. We prove that proposed estimators are unbiased and give variance bounds. A case study on Multistage Filters (MSF) over the real Internet traces shows a significant improvement by using the active counters architecture.

KW - Counter architecture

KW - Data streaming algorithms

KW - High-speed measurements

KW - Router

UR - http://www.scopus.com/inward/record.url?scp=34548359269&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34548359269&partnerID=8YFLogxK

U2 - 10.1109/INFCOM.2007.249

DO - 10.1109/INFCOM.2007.249

M3 - Conference contribution

SN - 1424410479

SN - 9781424410477

SP - 2153

EP - 2161

BT - Proceedings - IEEE INFOCOM 2007: 26th IEEE International Conference on Computer Communications

ER -