Intelligent ISAC-Enabled RIS-Assisted Hybrid 6G and Wi-Fi 8 Networks: A Multi-Objective EE–SE–Sensing Optimization Framework

Abstract

The migration of wireless networks towards sixth-generation (6G) cellular communications and Wi-Fi 8 is targeting ultra-high data rates, massive connectivity, and in-built sensing. However, these sophisticated applications introduce new challenges in achieving high levels of energy efficiency, spectral efficiency, and sensing accuracy in ultra-dense and heterogeneous wireless networks. The existing literature has mainly addressed energy efficiency or spectral efficiency in hybrid multi-radio access technology (multi-RAT)-based wireless communications. Therefore, in this manuscript, an intelligent Integrated Sensing and Communication (ISAC) solution for hybrid 6G and Wi-Fi 8 communications is proposed to concurrently maximize energy efficiency (EE), spectral efficiency (SE), and sensing performance. The system model used in this manuscript utilizes Reconfigurable Intelligent Surfaces (RIS) and formulates a multi-objective problem considering communications quality of service and sensing constraints. For this non-convex problem, an optimized deep reinforcement learning (DRL)-based controller to dynamically control RIS phases, beamforming, as well as power allocation in multiple radio communications links has been proposed. The simulation results indicate that the proposed method significantly enhances EE and SE while maintaining reliable environmental sensing accuracy under the simulated conditions, attaining a spectral efficiency of 7.1 bits/s/Hz with 32 RIS elements and 12.3 bits/s/Hz with 128 RIS elements. This work proposes novel framework that performs joint energy efficiency, spectral efficiency, and sensing performance optimization for hybrid 6G and Wi-Fi 8 networks. The proposed approach utilizes RIS-aided ISAC to enable intelligent multi-objective optimization using deep reinforcement learning.