A Method for Evaluation of Quality of Service in Computer Networks

Tomasz Bujlow, Sara Ligaard Hald, M. Tahir Riaz, Jens Myrup Pedersen

Research output: Contribution to journalConference article in JournalResearchpeer-review

1 Citation (Scopus)
1205 Downloads (Pure)

Abstract

Monitoring of Quality of Service (QoS) in high-speed Internet infrastructures is a challenging task. However, precise assessments must take into account the fact that the requirements for the given quality level are service-dependent. The backbone QoS monitoring and analysis requires processing of large amounts of data and knowledge of which kinds of applications the traffic is generated by. To overcome the drawbacks of existing methods for traffic classification, we proposed and evaluated a centralized solution based on the C5.0 Machine Learning Algorithm (MLA) and decision rules. The first task was to collect and to provide to C5.0 high-quality training data divided into groups, which correspond to different types of applications. It was found that the currently existing means of collecting data (classification by ports, Deep Packet Inspection, statistical classification, public data sources) are not sufficient and they do not comply with the required standards. We developed a new system
to collect training data, in which the major role is performed by volunteers. Client applications installed on volunteers' computers collect the detailed data about each flow passing through the network interface, together with the application name taken from the description of system sockets. This paper proposes a new method for measuring the level of Quality of Service in broadband networks. It is based on our Volunteer-Based System to collect the training data, Machine Learning Algorithms to generate the classification rules and the application-specific rules for assessing the QoS level. We combine both passive and active monitoring technologies. The paper evaluates different possibilities of implementation, presents the current implementation of particular parts of the system, their initial runs and the obtained results, highlighting parts relevant from the QoS point of view.
Original languageEnglish
JournalICACT Transactions on the Advanced Communications Technology
Number of pages9
Publication statusPublished - 17 Jul 2012
Event2012 14th International Conference on Advanced Communication Technology - PyeongChang, Korea, Republic of
Duration: 19 Feb 201222 Feb 2012

Conference

Conference2012 14th International Conference on Advanced Communication Technology
CountryKorea, Republic of
CityPyeongChang
Period19/02/201222/02/2012

Fingerprint

Computer networks
Quality of service
Learning algorithms
Learning systems
Monitoring
Broadband networks
Interfaces (computer)
Inspection
Internet
Processing

Keywords

  • broadband networks
  • data collecting
  • Machine Learning Algorithms
  • performance monitoring
  • Quality of Service
  • traffic classification
  • volunteer-based system

Cite this

@inproceedings{38dcfbb7323144658234d91bd6528c2f,
title = "A Method for Evaluation of Quality of Service in Computer Networks",
abstract = "Monitoring of Quality of Service (QoS) in high-speed Internet infrastructures is a challenging task. However, precise assessments must take into account the fact that the requirements for the given quality level are service-dependent. The backbone QoS monitoring and analysis requires processing of large amounts of data and knowledge of which kinds of applications the traffic is generated by. To overcome the drawbacks of existing methods for traffic classification, we proposed and evaluated a centralized solution based on the C5.0 Machine Learning Algorithm (MLA) and decision rules. The first task was to collect and to provide to C5.0 high-quality training data divided into groups, which correspond to different types of applications. It was found that the currently existing means of collecting data (classification by ports, Deep Packet Inspection, statistical classification, public data sources) are not sufficient and they do not comply with the required standards. We developed a new system to collect training data, in which the major role is performed by volunteers. Client applications installed on volunteers' computers collect the detailed data about each flow passing through the network interface, together with the application name taken from the description of system sockets. This paper proposes a new method for measuring the level of Quality of Service in broadband networks. It is based on our Volunteer-Based System to collect the training data, Machine Learning Algorithms to generate the classification rules and the application-specific rules for assessing the QoS level. We combine both passive and active monitoring technologies. The paper evaluates different possibilities of implementation, presents the current implementation of particular parts of the system, their initial runs and the obtained results, highlighting parts relevant from the QoS point of view.",
keywords = "broadband networks, data collecting, Machine Learning Algorithms, performance monitoring, Quality of Service, traffic classification, volunteer-based system",
author = "Tomasz Bujlow and Hald, {Sara Ligaard} and Riaz, {M. Tahir} and Pedersen, {Jens Myrup}",
note = "Paper ID 112",
year = "2012",
month = "7",
day = "17",
language = "English",
journal = "ICACT Transactions on the Advanced Communications Technology",
issn = "2288-0003",
publisher = "IEEE",

}

A Method for Evaluation of Quality of Service in Computer Networks. / Bujlow, Tomasz; Hald, Sara Ligaard; Riaz, M. Tahir; Pedersen, Jens Myrup.

In: ICACT Transactions on the Advanced Communications Technology, 17.07.2012.

Research output: Contribution to journalConference article in JournalResearchpeer-review

TY - GEN

T1 - A Method for Evaluation of Quality of Service in Computer Networks

AU - Bujlow, Tomasz

AU - Hald, Sara Ligaard

AU - Riaz, M. Tahir

AU - Pedersen, Jens Myrup

N1 - Paper ID 112

PY - 2012/7/17

Y1 - 2012/7/17

N2 - Monitoring of Quality of Service (QoS) in high-speed Internet infrastructures is a challenging task. However, precise assessments must take into account the fact that the requirements for the given quality level are service-dependent. The backbone QoS monitoring and analysis requires processing of large amounts of data and knowledge of which kinds of applications the traffic is generated by. To overcome the drawbacks of existing methods for traffic classification, we proposed and evaluated a centralized solution based on the C5.0 Machine Learning Algorithm (MLA) and decision rules. The first task was to collect and to provide to C5.0 high-quality training data divided into groups, which correspond to different types of applications. It was found that the currently existing means of collecting data (classification by ports, Deep Packet Inspection, statistical classification, public data sources) are not sufficient and they do not comply with the required standards. We developed a new system to collect training data, in which the major role is performed by volunteers. Client applications installed on volunteers' computers collect the detailed data about each flow passing through the network interface, together with the application name taken from the description of system sockets. This paper proposes a new method for measuring the level of Quality of Service in broadband networks. It is based on our Volunteer-Based System to collect the training data, Machine Learning Algorithms to generate the classification rules and the application-specific rules for assessing the QoS level. We combine both passive and active monitoring technologies. The paper evaluates different possibilities of implementation, presents the current implementation of particular parts of the system, their initial runs and the obtained results, highlighting parts relevant from the QoS point of view.

AB - Monitoring of Quality of Service (QoS) in high-speed Internet infrastructures is a challenging task. However, precise assessments must take into account the fact that the requirements for the given quality level are service-dependent. The backbone QoS monitoring and analysis requires processing of large amounts of data and knowledge of which kinds of applications the traffic is generated by. To overcome the drawbacks of existing methods for traffic classification, we proposed and evaluated a centralized solution based on the C5.0 Machine Learning Algorithm (MLA) and decision rules. The first task was to collect and to provide to C5.0 high-quality training data divided into groups, which correspond to different types of applications. It was found that the currently existing means of collecting data (classification by ports, Deep Packet Inspection, statistical classification, public data sources) are not sufficient and they do not comply with the required standards. We developed a new system to collect training data, in which the major role is performed by volunteers. Client applications installed on volunteers' computers collect the detailed data about each flow passing through the network interface, together with the application name taken from the description of system sockets. This paper proposes a new method for measuring the level of Quality of Service in broadband networks. It is based on our Volunteer-Based System to collect the training data, Machine Learning Algorithms to generate the classification rules and the application-specific rules for assessing the QoS level. We combine both passive and active monitoring technologies. The paper evaluates different possibilities of implementation, presents the current implementation of particular parts of the system, their initial runs and the obtained results, highlighting parts relevant from the QoS point of view.

KW - broadband networks

KW - data collecting

KW - Machine Learning Algorithms

KW - performance monitoring

KW - Quality of Service

KW - traffic classification

KW - volunteer-based system

M3 - Conference article in Journal

JO - ICACT Transactions on the Advanced Communications Technology

JF - ICACT Transactions on the Advanced Communications Technology

SN - 2288-0003

ER -