Deep Reinforcement Learning for Joint Spectrum and Power Allocation in Cellular Networks

Yasar Sinan Nasir, Dongning Guo

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A wireless network operator typically divides its radio spectrum into a number of subbands and reuse them to serve traffic in many cells. To mitigate co-channel interference, allocation of spectrum and power resources needs to be adapted to time-varying channel and traffic conditions throughout the network. Standard model-based network utility maximization is severely limited by the computational complexity and the difficulty of acquiring instantaneous global channel state information. In this paper, a learning-based method is proposed to optimize discrete subband allocations and continuous power allocations using (generally delayed and inaccurate) channel state information in local and nearby cells. For these two types of allocations, two complementary deep reinforcement learning algorithms are designed to be executed and trained simultaneously to maximize a joint objective. Simulation results show that the proposed method outperforms a state-of-the-art fractional programming algorithm as well as a previous solution based on deep reinforcement learning.

Original languageEnglish (US)
Title of host publication2021 IEEE Globecom Workshops, GC Wkshps 2021 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665423908
DOIs
StatePublished - 2021
Event2021 IEEE Globecom Workshops, GC Wkshps 2021 - Madrid, Spain
Duration: Dec 7 2021Dec 11 2021

Publication series

Name2021 IEEE Globecom Workshops, GC Wkshps 2021 - Proceedings

Conference

Conference2021 IEEE Globecom Workshops, GC Wkshps 2021
Country/TerritorySpain
CityMadrid
Period12/7/2112/11/21

Keywords

  • Cloud Radio Access Network
  • Deep Reinforcement Learning
  • Dynamic Environment

ASJC Scopus subject areas

  • Information Systems
  • Signal Processing
  • Software
  • Information Systems and Management
  • Artificial Intelligence
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'Deep Reinforcement Learning for Joint Spectrum and Power Allocation in Cellular Networks'. Together they form a unique fingerprint.

Cite this