Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Reconfigurable Intelligent Surface Assisted Device-to-Device Communications

Zelin Ji, Zhijin Qin, Clive G. Parini

Abstract

Reconfigurable intelligent surface (RIS) technology is a promising method to enhance wireless communications services and to realize the smart radio environment. In this paper, we investigate the application of RIS in D2D communications, and maximize the sum of the transmission rate of the D2D underlaying networks in a new perspective. Instead of solving similarly formulated resource allocation problems for D2D communications, this paper treats the wireless environment as a variable by adjusting the position and phase shift of the RIS. To solve this non-convex problem, we propose a novel double deep Q-network (DDQN) based structure which is able to achieve the near-optimal performance with lower complexity and enhanced robustness. Simulation results illustrate that the proposed DDQN based structure can achieve a higher uplink rate compared to the benchmarks, meanwhile meeting the quality of service (QoS) requirements at the base station (BS) and D2D receivers.

Reconfigurable Intelligent Surface Assisted Device-to-Device Communications

Abstract

Reconfigurable intelligent surface (RIS) technology is a promising method to enhance wireless communications services and to realize the smart radio environment. In this paper, we investigate the application of RIS in D2D communications, and maximize the sum of the transmission rate of the D2D underlaying networks in a new perspective. Instead of solving similarly formulated resource allocation problems for D2D communications, this paper treats the wireless environment as a variable by adjusting the position and phase shift of the RIS. To solve this non-convex problem, we propose a novel double deep Q-network (DDQN) based structure which is able to achieve the near-optimal performance with lower complexity and enhanced robustness. Simulation results illustrate that the proposed DDQN based structure can achieve a higher uplink rate compared to the benchmarks, meanwhile meeting the quality of service (QoS) requirements at the base station (BS) and D2D receivers.

Paper Structure

This paper contains 24 sections, 21 equations, 8 figures, 1 table, 2 algorithms.

Table of Contents

  1. Introduction
  2. Related work
  3. Resource allocation in D2D
  4. RIS enhanced wireless communications
  5. Motivation and Contribution
  6. System Model
  7. System settings
  8. Problem formulation
  9. Resource allocation optimization by multi-agent reinforcement learning
  10. System description
  11. Concept of Reinforcement learning and deep Q-network
  12. Double DQN algorithm
  13. Multi-agent observation state
  14. Actions and rewards definition
  15. Training algorithm
  16. ...and 9 more sections

Figures (8)

  • Figure 1: System model of the of RIS enhanced D2D network.
  • Figure 2: The interaction of the DQN with the environment.
  • Figure 3: Architecture of the proposed DDQN algorithm.
  • Figure 4: Training performance comparison.
  • Figure 5: Testing performance of proposed algorithm.
  • ...and 3 more figures