Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

DRL-Based Resource Allocation for Energy-Efficient IRS-Assisted UAV Spectrum Sharing Systems

Yiheng Wang

TL;DR

This work tackles energy-efficient resource allocation in an IRS-assisted UAV-enabled spectrum-sharing system using OFDM. It jointly optimizes SBS beamforming, IRS phase shifts, and UAV trajectory by formulating an EE objective with a propulsion-energy model and solving a non-convex, time-coupled problem via a constrained, hybrid DRL framework that combines D3QN for discrete scheduling and SAC for continuous control. The approach uses explicit EE-based rewards with penalties for constraint violations and analytic projections to enforce feasibility, achieving substantial gains over baselines in both sum rate and energy efficiency while maintaining robustness to mobility. The results highlight the practical viability of DRL for real-time, mobility-aware, energy-efficient spectrum sharing in IRS-assisted UAV networks.

Abstract

Intelligent reflecting surface (IRS) assisted unmanned aerial vehicle (UAV) systems provide a new paradigm for reconfigurable and flexible wireless communications. To enable more energy efficient and spectrum efficient IRS assisted UAV wireless communications, this paper introduces a novel IRS-assisted UAV enabled spectrum sharing system with orthogonal frequency division multiplexing (OFDM). The goal is to maximize the energy efficiency (EE) of the secondary network by jointly optimizing the beamforming, subcarrier allocation, IRS phase shifts, and the UAV trajectory subject to practical transmit power and passive reflection constraints as well as UAV physical limitations. A physically grounded propulsion-energy model is adopted, with its tight upper bound used to form a tractable EE lower bound for the spectrum sharing system. To handle highly non convex, time coupled optimization problems with a mixed continuous and discrete policy space, we develop a deep reinforcement learning (DRL) approach based on the actor critic framework. Extended experiments show the significant EE improvement of the proposed DRL-based approach compared to several benchmark schemes, thus demonstrating the effectiveness and robustness of the proposed approach with mobility.

DRL-Based Resource Allocation for Energy-Efficient IRS-Assisted UAV Spectrum Sharing Systems

TL;DR

This work tackles energy-efficient resource allocation in an IRS-assisted UAV-enabled spectrum-sharing system using OFDM. It jointly optimizes SBS beamforming, IRS phase shifts, and UAV trajectory by formulating an EE objective with a propulsion-energy model and solving a non-convex, time-coupled problem via a constrained, hybrid DRL framework that combines D3QN for discrete scheduling and SAC for continuous control. The approach uses explicit EE-based rewards with penalties for constraint violations and analytic projections to enforce feasibility, achieving substantial gains over baselines in both sum rate and energy efficiency while maintaining robustness to mobility. The results highlight the practical viability of DRL for real-time, mobility-aware, energy-efficient spectrum sharing in IRS-assisted UAV networks.

Abstract

Intelligent reflecting surface (IRS) assisted unmanned aerial vehicle (UAV) systems provide a new paradigm for reconfigurable and flexible wireless communications. To enable more energy efficient and spectrum efficient IRS assisted UAV wireless communications, this paper introduces a novel IRS-assisted UAV enabled spectrum sharing system with orthogonal frequency division multiplexing (OFDM). The goal is to maximize the energy efficiency (EE) of the secondary network by jointly optimizing the beamforming, subcarrier allocation, IRS phase shifts, and the UAV trajectory subject to practical transmit power and passive reflection constraints as well as UAV physical limitations. A physically grounded propulsion-energy model is adopted, with its tight upper bound used to form a tractable EE lower bound for the spectrum sharing system. To handle highly non convex, time coupled optimization problems with a mixed continuous and discrete policy space, we develop a deep reinforcement learning (DRL) approach based on the actor critic framework. Extended experiments show the significant EE improvement of the proposed DRL-based approach compared to several benchmark schemes, thus demonstrating the effectiveness and robustness of the proposed approach with mobility.
Paper Structure (14 sections, 35 equations, 3 figures, 1 algorithm)

This paper contains 14 sections, 35 equations, 3 figures, 1 algorithm.

Table of Contents

  1. Introduction
  2. System Model and Problem Formulation
  3. System Model
  4. Problem Formulation
  5. DRL-Based Energy-Efficient Transmission Framework
  6. MDP Formulation
  7. Reward Design with Explicit EE Constraint Penalties
  8. Policy Parameterization and Analytic Projections
  9. Learning Objective
  10. Overall Algorithm
  11. Simulation and Results
  12. Simulation Setup
  13. Simulation Results
  14. Conclusion

Figures (3)

  • Figure 1: The considered system model of UAV-IRS spectrum sharing systems.
  • Figure 2: Achievable sum rate versus transmit power.
  • Figure 3: Energy efficiency versus mission duration.