Q-Learning Based Two-Timescale Power Allocation for Multi-Homing Hybrid RF/VLC Networks

Justin Kong, Zi Yang Wu, Muhammad Ismail, Erchin Serpedin, Khalid A. Qaraqe

Research output: Contribution to journalArticle

Abstract

This letter investigates hybrid networks composed of a radio frequency (RF) access point (AP) and multiple visible light communication (VLC) APs. We consider mobile multi-homing users that can aggregate resources from both RF and VLC APs. In hybrid RF/VLC networks, RF channel gains vary faster than VLC channels due to small scale fading. By leveraging multi-agent Q-learning to interact with the dynamics of wireless environments, we develop an online two-timescale power allocation strategy that optimizes the transmit powers at the RF and VLC APs to ensure quality-of-service satisfaction. Simulation results demonstrate the effectiveness of the proposed Q-learning based strategy.

Original languageEnglish
JournalIEEE Wireless Communications Letters
DOIs
Publication statusAccepted/In press - 1 Jan 2019

Fingerprint

Telecommunication networks
Visible light communication
Quality of service
Networks (circuits)

Keywords

  • Fading channels
  • hybrid networks
  • Hybrid power systems
  • Light emitting diodes
  • optimization
  • Q-learning.
  • Quality of service
  • Radio frequency
  • reinforcement learning
  • Resource management
  • two-timescale
  • Visible light communication
  • Wireless communication

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Q-Learning Based Two-Timescale Power Allocation for Multi-Homing Hybrid RF/VLC Networks. / Kong, Justin; Wu, Zi Yang; Ismail, Muhammad; Serpedin, Erchin; Qaraqe, Khalid A.

In: IEEE Wireless Communications Letters, 01.01.2019.

Research output: Contribution to journalArticle

@article{326c0dcbdc2549f1bf7d2eb72d0a4d35,
title = "Q-Learning Based Two-Timescale Power Allocation for Multi-Homing Hybrid RF/VLC Networks",
abstract = "This letter investigates hybrid networks composed of a radio frequency (RF) access point (AP) and multiple visible light communication (VLC) APs. We consider mobile multi-homing users that can aggregate resources from both RF and VLC APs. In hybrid RF/VLC networks, RF channel gains vary faster than VLC channels due to small scale fading. By leveraging multi-agent Q-learning to interact with the dynamics of wireless environments, we develop an online two-timescale power allocation strategy that optimizes the transmit powers at the RF and VLC APs to ensure quality-of-service satisfaction. Simulation results demonstrate the effectiveness of the proposed Q-learning based strategy.",
keywords = "Fading channels, hybrid networks, Hybrid power systems, Light emitting diodes, optimization, Q-learning., Quality of service, Radio frequency, reinforcement learning, Resource management, two-timescale, Visible light communication, Wireless communication",
author = "Justin Kong and Wu, {Zi Yang} and Muhammad Ismail and Erchin Serpedin and Qaraqe, {Khalid A.}",
year = "2019",
month = "1",
day = "1",
doi = "10.1109/LWC.2019.2958121",
language = "English",
journal = "IEEE Wireless Communications Letters",
issn = "2162-2337",
publisher = "IEEE Communications Society",

}

TY - JOUR

T1 - Q-Learning Based Two-Timescale Power Allocation for Multi-Homing Hybrid RF/VLC Networks

AU - Kong, Justin

AU - Wu, Zi Yang

AU - Ismail, Muhammad

AU - Serpedin, Erchin

AU - Qaraqe, Khalid A.

PY - 2019/1/1

Y1 - 2019/1/1

N2 - This letter investigates hybrid networks composed of a radio frequency (RF) access point (AP) and multiple visible light communication (VLC) APs. We consider mobile multi-homing users that can aggregate resources from both RF and VLC APs. In hybrid RF/VLC networks, RF channel gains vary faster than VLC channels due to small scale fading. By leveraging multi-agent Q-learning to interact with the dynamics of wireless environments, we develop an online two-timescale power allocation strategy that optimizes the transmit powers at the RF and VLC APs to ensure quality-of-service satisfaction. Simulation results demonstrate the effectiveness of the proposed Q-learning based strategy.

AB - This letter investigates hybrid networks composed of a radio frequency (RF) access point (AP) and multiple visible light communication (VLC) APs. We consider mobile multi-homing users that can aggregate resources from both RF and VLC APs. In hybrid RF/VLC networks, RF channel gains vary faster than VLC channels due to small scale fading. By leveraging multi-agent Q-learning to interact with the dynamics of wireless environments, we develop an online two-timescale power allocation strategy that optimizes the transmit powers at the RF and VLC APs to ensure quality-of-service satisfaction. Simulation results demonstrate the effectiveness of the proposed Q-learning based strategy.

KW - Fading channels

KW - hybrid networks

KW - Hybrid power systems

KW - Light emitting diodes

KW - optimization

KW - Q-learning.

KW - Quality of service

KW - Radio frequency

KW - reinforcement learning

KW - Resource management

KW - two-timescale

KW - Visible light communication

KW - Wireless communication

UR - http://www.scopus.com/inward/record.url?scp=85076314410&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85076314410&partnerID=8YFLogxK

U2 - 10.1109/LWC.2019.2958121

DO - 10.1109/LWC.2019.2958121

M3 - Article

AN - SCOPUS:85076314410

JO - IEEE Wireless Communications Letters

JF - IEEE Wireless Communications Letters

SN - 2162-2337

ER -