Application of Reinforcement Learning and Deep Learning in Multiple-Input and Multiple-Output (MIMO) Systems.

Muddasar Naeem, Giuseppe De Pietro, Antonio Coronato
Author Information
  1. Muddasar Naeem: Institute of High Performance Computing and Networking, National Research Council of Italy, 80131 Napoli, Italy. ORCID
  2. Giuseppe De Pietro: Institute of High Performance Computing and Networking, National Research Council of Italy, 80131 Napoli, Italy. ORCID
  3. Antonio Coronato: Institute of High Performance Computing and Networking, National Research Council of Italy, 80131 Napoli, Italy. ORCID

Abstract

The current wireless communication infrastructure has to face exponential development in mobile traffic size, which demands high data rate, reliability, and low latency. MIMO systems and their variants (i.e., Multi-User MIMO and Massive MIMO) are the most promising 5G wireless communication systems technology due to their high system throughput and data rate. However, the most significant challenges in MIMO communication are substantial problems in exploiting the multiple-antenna and computational complexity. The recent success of RL and DL introduces novel and powerful tools that mitigate issues in MIMO communication systems. This article focuses on RL and DL techniques for MIMO systems by presenting a comprehensive review on the integration between the two areas. We first briefly provide the necessary background to RL, DL, and MIMO. Second, potential RL and DL applications for different MIMO issues, such as detection, classification, and compression; channel estimation; positioning, sensing, and localization; CSI acquisition and feedback, security, and robustness; mmWave communication and resource allocation, are presented.

Keywords

References

  1. IEEE Trans Cybern. 2017 Oct;47(10):3110-3123 [PMID: 28362599]
  2. IEEE Trans Neural Netw Learn Syst. 2012 Jan;23(1):138-49 [PMID: 24808463]
  3. IEEE Trans Neural Netw. 2010 May;21(5):796-812 [PMID: 20236884]
  4. IEEE Trans Neural Netw Learn Syst. 2021 Jun 10;PP: [PMID: 34111009]
  5. Insights Imaging. 2018 Aug;9(4):611-629 [PMID: 29934920]
  6. IEEE Trans Neural Netw Learn Syst. 2015 Jan;26(1):165-76 [PMID: 25438326]
  7. IEEE Trans Neural Netw Learn Syst. 2012 Jul;23(7):1163-9 [PMID: 24807142]
  8. Sensors (Basel). 2021 Jul 16;21(14): [PMID: 34300599]
  9. Sensors (Basel). 2020 May 12;20(10): [PMID: 32408531]
  10. Artif Intell Med. 2020 Sep;109:101964 [PMID: 34756216]
  11. J Indian Inst Sci. 2020;100(2):369-382 [PMID: 32624647]
  12. Ann Telecommun. 2021 Jun 14;:1-13 [PMID: 34149057]
  13. IEEE Trans Neural Netw Learn Syst. 2017 Jun;28(6):1318-1330 [PMID: 27008679]
  14. SN Comput Sci. 2021;2(6):420 [PMID: 34426802]
  15. Sensors (Basel). 2020 Mar 20;20(6): [PMID: 32244857]

MeSH Term

Communication
Deep Learning
Feedback
Reproducibility of Results

Word Cloud

Created with Highcharts 10.0.0MIMOcommunicationsystemsRLDLwirelesshighdatarateissuesdetectionchannelestimationpositioninglocalizationCSImmWaveresourceallocationLearninglearningcurrentinfrastructurefaceexponentialdevelopmentmobiletrafficsizedemandsreliabilitylowlatencyvariantsieMulti-UserMassivepromising5GtechnologyduesystemthroughputHoweversignificantchallengessubstantialproblemsexploitingmultiple-antennacomputationalcomplexityrecentsuccessintroducesnovelpowerfultoolsmitigatearticlefocusestechniquespresentingcomprehensivereviewintegrationtwoareasfirstbrieflyprovidenecessarybackgroundSecondpotentialapplicationsdifferentclassificationcompressionsensingacquisitionfeedbacksecurityrobustnesspresentedApplicationReinforcementDeepMultiple-InputMultiple-OutputSystemsBSdeepreinforcementsignal

Similar Articles

Cited By