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

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

38 Citations (Scopus)

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
Article number8926487
Pages (from-to)443-447
Number of pages5
JournalIEEE Wireless Communications Letters
Volume9
Issue number4
DOIs
Publication statusPublished - 1 Apr 2020
Externally publishedYes

Keywords

  • hybrid networks
  • optimization
  • Q-learning
  • reinforcement learning
  • two-timescale
  • Visible light communication

Fingerprint

Dive into the research topics of 'Q-Learning Based Two-Timescale Power Allocation for Multi-Homing Hybrid RF/VLC Networks'. Together they form a unique fingerprint.

Cite this