Neural modeling of link occupancy for wireless transmissions using Markov reward models

Izabella Lokshina, Michael R. Bartolacci

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

Abstract

The paper is devoted to neural modeling of link occupancy distribution. Multi-service (i.e., bandwidth sharing between different traffic classes) models of a single, possibly wireless transmission link for rigid, adaptive and elastic traffic are developed based on Markov reward models. Link occupancy distribution is introduced as embedded, discrete time Markov chain researched with vector quantization. Link occupancy performance is simulated as a combination of single queues with random distributions of arrival processes and holding times in service phases. Link occupancy probability density is determined using learning vector quantization in a two-layered neural structure. Simulation and numerical results are shown.

Original languageEnglish (US)
Title of host publication2014 4th International Conference on Wireless Communications, Vehicular Technology, Information Theory and Aerospace and Electronic Systems, VITAE 2014 - Co-located with Global Wireless Summit
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781479946266
DOIs
StatePublished - Oct 22 2014
Event2014 4th International Conference on Wireless Communications, Vehicular Technology, Information Theory and Aerospace and Electronic Systems, VITAE 2014 - Co-located with Global Wireless Summit - Aalborg, Denmark
Duration: May 11 2014May 14 2014

Other

Other2014 4th International Conference on Wireless Communications, Vehicular Technology, Information Theory and Aerospace and Electronic Systems, VITAE 2014 - Co-located with Global Wireless Summit
CountryDenmark
CityAalborg
Period5/11/145/14/14

Fingerprint

Telecommunication links
Vector quantization
Telecommunication traffic
Markov processes
Bandwidth

All Science Journal Classification (ASJC) codes

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

Cite this

Lokshina, I., & Bartolacci, M. R. (2014). Neural modeling of link occupancy for wireless transmissions using Markov reward models. In 2014 4th International Conference on Wireless Communications, Vehicular Technology, Information Theory and Aerospace and Electronic Systems, VITAE 2014 - Co-located with Global Wireless Summit [6934396] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/VITAE.2014.6934396
Lokshina, Izabella ; Bartolacci, Michael R. / Neural modeling of link occupancy for wireless transmissions using Markov reward models. 2014 4th International Conference on Wireless Communications, Vehicular Technology, Information Theory and Aerospace and Electronic Systems, VITAE 2014 - Co-located with Global Wireless Summit. Institute of Electrical and Electronics Engineers Inc., 2014.
@inproceedings{eb2e322dce864c359b72f690da5b8769,
title = "Neural modeling of link occupancy for wireless transmissions using Markov reward models",
abstract = "The paper is devoted to neural modeling of link occupancy distribution. Multi-service (i.e., bandwidth sharing between different traffic classes) models of a single, possibly wireless transmission link for rigid, adaptive and elastic traffic are developed based on Markov reward models. Link occupancy distribution is introduced as embedded, discrete time Markov chain researched with vector quantization. Link occupancy performance is simulated as a combination of single queues with random distributions of arrival processes and holding times in service phases. Link occupancy probability density is determined using learning vector quantization in a two-layered neural structure. Simulation and numerical results are shown.",
author = "Izabella Lokshina and Bartolacci, {Michael R.}",
year = "2014",
month = "10",
day = "22",
doi = "10.1109/VITAE.2014.6934396",
language = "English (US)",
booktitle = "2014 4th International Conference on Wireless Communications, Vehicular Technology, Information Theory and Aerospace and Electronic Systems, VITAE 2014 - Co-located with Global Wireless Summit",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Lokshina, I & Bartolacci, MR 2014, Neural modeling of link occupancy for wireless transmissions using Markov reward models. in 2014 4th International Conference on Wireless Communications, Vehicular Technology, Information Theory and Aerospace and Electronic Systems, VITAE 2014 - Co-located with Global Wireless Summit., 6934396, Institute of Electrical and Electronics Engineers Inc., 2014 4th International Conference on Wireless Communications, Vehicular Technology, Information Theory and Aerospace and Electronic Systems, VITAE 2014 - Co-located with Global Wireless Summit, Aalborg, Denmark, 5/11/14. https://doi.org/10.1109/VITAE.2014.6934396

Neural modeling of link occupancy for wireless transmissions using Markov reward models. / Lokshina, Izabella; Bartolacci, Michael R.

2014 4th International Conference on Wireless Communications, Vehicular Technology, Information Theory and Aerospace and Electronic Systems, VITAE 2014 - Co-located with Global Wireless Summit. Institute of Electrical and Electronics Engineers Inc., 2014. 6934396.

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

TY - GEN

T1 - Neural modeling of link occupancy for wireless transmissions using Markov reward models

AU - Lokshina, Izabella

AU - Bartolacci, Michael R.

PY - 2014/10/22

Y1 - 2014/10/22

N2 - The paper is devoted to neural modeling of link occupancy distribution. Multi-service (i.e., bandwidth sharing between different traffic classes) models of a single, possibly wireless transmission link for rigid, adaptive and elastic traffic are developed based on Markov reward models. Link occupancy distribution is introduced as embedded, discrete time Markov chain researched with vector quantization. Link occupancy performance is simulated as a combination of single queues with random distributions of arrival processes and holding times in service phases. Link occupancy probability density is determined using learning vector quantization in a two-layered neural structure. Simulation and numerical results are shown.

AB - The paper is devoted to neural modeling of link occupancy distribution. Multi-service (i.e., bandwidth sharing between different traffic classes) models of a single, possibly wireless transmission link for rigid, adaptive and elastic traffic are developed based on Markov reward models. Link occupancy distribution is introduced as embedded, discrete time Markov chain researched with vector quantization. Link occupancy performance is simulated as a combination of single queues with random distributions of arrival processes and holding times in service phases. Link occupancy probability density is determined using learning vector quantization in a two-layered neural structure. Simulation and numerical results are shown.

UR - http://www.scopus.com/inward/record.url?scp=84911866641&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84911866641&partnerID=8YFLogxK

U2 - 10.1109/VITAE.2014.6934396

DO - 10.1109/VITAE.2014.6934396

M3 - Conference contribution

AN - SCOPUS:84911866641

BT - 2014 4th International Conference on Wireless Communications, Vehicular Technology, Information Theory and Aerospace and Electronic Systems, VITAE 2014 - Co-located with Global Wireless Summit

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Lokshina I, Bartolacci MR. Neural modeling of link occupancy for wireless transmissions using Markov reward models. In 2014 4th International Conference on Wireless Communications, Vehicular Technology, Information Theory and Aerospace and Electronic Systems, VITAE 2014 - Co-located with Global Wireless Summit. Institute of Electrical and Electronics Engineers Inc. 2014. 6934396 https://doi.org/10.1109/VITAE.2014.6934396