Reinforcement Learning-Based Downlink Interference Control for Ultra-Dense Small Cells

Liang Xiao, Hailu Zhang, Yilin Xiao, Xiaoyue Wan, Sicong Liu, Li Chun Wang, H. Vincent Poor

Research output: Contribution to journalArticlepeer-review

65 Scopus citations


The dense deployment of small cells in 5G cellular networks raises the issue of controlling downlink inter-cell interference under time-varying channel states. In this paper, we propose a reinforcement learning based power control scheme to suppress downlink inter-cell interference and save energy for ultra-dense small cells. This scheme enables base stations to schedule the downlink transmit power without knowing the interference distribution and the channel states of the neighboring small cells. A deep reinforcement learning based interference control algorithm is designed to further accelerate learning for ultra-dense small cells with a large number of active users. Analytical convergence performance bounds including throughput, energy consumption, inter-cell interference, and the utility of base stations are provided and the computational complexity of our proposed scheme is discussed. Simulation results show that this scheme optimizes the downlink interference control performance after sufficient power control instances and significantly increases the network throughput with less energy consumption compared with a benchmark scheme.

Original languageEnglish (US)
Article number8868117
Pages (from-to)423-434
Number of pages12
JournalIEEE Transactions on Wireless Communications
Issue number1
StatePublished - Jan 2020
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Electrical and Electronic Engineering
  • Applied Mathematics


  • Ultra-dense small cells
  • interference control
  • power control
  • reinforcement learning


Dive into the research topics of 'Reinforcement Learning-Based Downlink Interference Control for Ultra-Dense Small Cells'. Together they form a unique fingerprint.

Cite this