Detail publikace

Intelligent Channel Assignment for WI-FI System Based on Reinforcement Learning

URBAN, R. DREXLER, P.

Originální název

Intelligent Channel Assignment for WI-FI System Based on Reinforcement Learning

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

This paper focuses on enhanced channel planning for WI-FI systems. Based on a real measurement of the frequency spectrum background, the quality of each channel has been classified. Machine learning algorithms are used to process these data and control the system. Reinforcement learning (a special example of machine learning) is used due to its complexity as a test-trial agents system. In the proposed system punishment and reward schema are utilized making it possible to change channels during the transmission and use the one with minimal interference. The promising increase of SINR up to 5% for outdoor scenarios and up to 30% for indoor scenarios should be applied to improve modulation schemas and increase data throughput.

Klíčová slova

machine learning, channel assignment, WI-FI

Autoři

URBAN, R.; DREXLER, P.

Rok RIV

2014

Vydáno

21. 3. 2014

ISBN

978-1-934142-28-8

Kniha

Proceedings of PIERS 2014 in Guangzhou

ISSN

1559-9450

Periodikum

Progress In Electromagnetics

Stát

Spojené státy americké

Strany od

2322

Strany do

2325

Strany počet

4

BibTex

@inproceedings{BUT109330,
  author="Robert {Urban} and Petr {Drexler}",
  title="Intelligent Channel Assignment for WI-FI System Based on Reinforcement Learning",
  booktitle="Proceedings of PIERS 2014 in Guangzhou",
  year="2014",
  journal="Progress In Electromagnetics",
  pages="2322--2325",
  isbn="978-1-934142-28-8",
  issn="1559-9450"
}