Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Deep Reinforcement Learning for Energy Efficiency Maximization in RSMA-IRS-Assisted ISAC System

Zhangfeng Ma, Ruichen Zhang, Bo Ai, Zhuxian Lian, Linzhou Zeng, Dusit Niyato

TL;DR

This work develops a 3D geometry-based channel model for RSMA-IRS-assisted ISAC systems and formulates an EE maximization problem under QoS and hardware constraints. A PPO-based DRL framework is introduced to jointly optimize the common-rate split, beamforming, IRS phase shifts, and radar beampointer with a robust MDP formulation. Numerical results show that the proposed approach enhances energy efficiency, with performance degraded at higher carrier frequencies and improved by richer fading (double-Rician) and larger IRS size; RSMA offers clear gains over SDMA in this setting. The findings highlight the practical value of integrating RSMA, IRS, and DRL for energy-efficient, QoS-compliant ISAC systems in urban environments.

Abstract

This paper proposes a three-dimensional (3D) geometry-based channel model to accurately represent intelligent reflecting surfaces (IRS)-enhanced integrated sensing and communication (ISAC) networks using rate-splitting multiple access (RSMA) in practical urban environments. Based on this model, we formulate an energy efficiency (EE) maximization problem that incorporates transceiver beamforming constraints, IRS phase adjustments, and quality-of-service (QoS) requirements to optimize communication and sensing functions. To solve this problem, we use the proximal policy optimization (PPO) algorithm within a deep reinforcement learning (DRL) framework. Our numerical results confirm the effectiveness of the proposed method in improving EE and satisfying QoS requirements. Additionally, we observe that system EE drops at higher frequencies, especially under double-Rayleigh fading.

Deep Reinforcement Learning for Energy Efficiency Maximization in RSMA-IRS-Assisted ISAC System

TL;DR

This work develops a 3D geometry-based channel model for RSMA-IRS-assisted ISAC systems and formulates an EE maximization problem under QoS and hardware constraints. A PPO-based DRL framework is introduced to jointly optimize the common-rate split, beamforming, IRS phase shifts, and radar beampointer with a robust MDP formulation. Numerical results show that the proposed approach enhances energy efficiency, with performance degraded at higher carrier frequencies and improved by richer fading (double-Rician) and larger IRS size; RSMA offers clear gains over SDMA in this setting. The findings highlight the practical value of integrating RSMA, IRS, and DRL for energy-efficient, QoS-compliant ISAC systems in urban environments.

Abstract

This paper proposes a three-dimensional (3D) geometry-based channel model to accurately represent intelligent reflecting surfaces (IRS)-enhanced integrated sensing and communication (ISAC) networks using rate-splitting multiple access (RSMA) in practical urban environments. Based on this model, we formulate an energy efficiency (EE) maximization problem that incorporates transceiver beamforming constraints, IRS phase adjustments, and quality-of-service (QoS) requirements to optimize communication and sensing functions. To solve this problem, we use the proximal policy optimization (PPO) algorithm within a deep reinforcement learning (DRL) framework. Our numerical results confirm the effectiveness of the proposed method in improving EE and satisfying QoS requirements. Additionally, we observe that system EE drops at higher frequencies, especially under double-Rayleigh fading.
Paper Structure (9 sections, 23 equations, 4 figures, 1 algorithm)

This paper contains 9 sections, 23 equations, 4 figures, 1 algorithm.

Table of Contents

  1. Introduction
  2. System Model and Problem Formulation
  3. System Model
  4. Problem Formulation
  5. Algorithm Design
  6. MDP
  7. PPO
  8. Numerical Results
  9. Conclusions

Figures (4)

  • Figure 1: System model of an IRS-enhanced ISAC network with RSMA. In this setup, user messages are split into common and private parts for efficient interference management. The PPO-based DRL framework is used to enhance the system EE and meet QoS requirements.
  • Figure 2: Convergence performance, where ${f_c} = 2.4$ GHz, ${K_{{\rm{BI}}}} = {K_{{\rm{IU}}}}= 10$, $\sigma = 20$${{\rm{m}}^{\rm{2}}}$, $M = 4$, $N = 9$.
  • Figure 3: EE comparison of systems with various baseline approaches and channel conditions, where $\sigma = 10$${{\rm{m}}^{\rm{2}}}$, $N = 9$.
  • Figure 4: Comparison of EE achieved by RSMA with SDMA, where ${f_c} = 2.4$ GHz, ${K_{{\rm{BI}}}} = {K_{{\rm{IU}}}}= 10$, $M = 4$.