Deep Reinforcement Learning for Interference Management in UAV-based 3D Networks: Potentials and Challenges Mojtaba

Mojtaba Vaezi, Xingqin Lin, Hongliang Zhang, Walid Saad, H. Vincent Poor

Research output: Contribution to journalArticlepeer-review

Abstract

Modern cellular networks are multi-cell and use universal frequency reuse to maximize spectral efficiency. This results in high inter-cell interference. This problem is growing as cellular networks become three-dimensional with the adoption of unmanned aerial vehicles (UAVs). This is because the strength and number of interference links rapidly increase due to the lineof- sight channels in UAV communications. Existing interference management solutions need each transmitter to know the channel information of interfering signals, rendering them impractical due to excessive signaling overhead. In this paper, we propose leveraging deep reinforcement learning for interference management to tackle this shortcoming. In particular, we show that interference can still be effectively mitigated even without knowing its channel information. We then discuss novel approaches to scale the algorithms with linear/sublinear complexity and decentralize them using multi-agent reinforcement learning. By harnessing interference, the proposed solutions enable the continued growth of civilian UAVs.

Original languageEnglish (US)
Pages (from-to)1-7
Number of pages7
JournalIEEE Communications Magazine
DOIs
StateAccepted/In press - 2023

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Computer Networks and Communications
  • Electrical and Electronic Engineering

Keywords

  • Autonomous aerial vehicles
  • Cellular networks
  • Deep learning
  • Intercell interference
  • Interference
  • Sensors
  • Three-dimensional displays

Fingerprint

Dive into the research topics of 'Deep Reinforcement Learning for Interference Management in UAV-based 3D Networks: Potentials and Challenges Mojtaba'. Together they form a unique fingerprint.

Cite this