Multi-agent double deep Q-Learning for beamforming in mmWave MIMO networks

Xueyuan Wang, M. Cenk Gursoy

Research output: Chapter in Book/Entry/PoemConference contribution

4 Scopus citations

Abstract

Beamforming is one of the key techniques in millimeter wave (mmWave) multi-input multi-output (MIMO) communications. Designing appropriate beamforming not only improves the quality and strength of the received signal, but also can help reduce the interference, consequently enhancing the data rate. In this paper, we propose a distributed multi-agent double deep Q-learning algorithm for beamforming in mmWave MIMO networks, where multiple base stations (BSs) can automatically and dynamically adjust their beams to serve multiple highly-mobile user equipments (UEs). In the analysis, largest received power association criterion is considered for UEs, and a realistic channel model is taken into account. Simulation results demonstrate that the proposed learning-based algorithm can achieve comparable performance with respect to exhaustive search while operating at much lower complexity.

Original languageEnglish (US)
Title of host publication2020 IEEE 31st Annual International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728144900
DOIs
StatePublished - Aug 2020
Event31st IEEE Annual International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC 2020 - Virtual, London, United Kingdom
Duration: Aug 31 2020Sep 3 2020

Publication series

NameIEEE International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC
Volume2020-August

Conference

Conference31st IEEE Annual International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC 2020
Country/TerritoryUnited Kingdom
CityVirtual, London
Period8/31/209/3/20

Keywords

  • Beamforming
  • Deep reinforcement learning
  • MIMO
  • MmWave communications
  • Multi-agent systems

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Multi-agent double deep Q-Learning for beamforming in mmWave MIMO networks'. Together they form a unique fingerprint.

Cite this