Semantic-Aware Resource Allocation Based on Deep Reinforcement Learning for 5G-V2X HetNets

2024-06-12

IEEE Communications Letters

AI Summary

In high-mobility 5G-V2X heterogeneous networks, V2X and WiFi users contend for resources in the NR-U unlicensed spectrum, leading to severe interference and inefficiency. To address this, we propose SARADC—a Semantic-Aware Resource Allocation framework for Dynamic Coexistence. SARADC is the first to integrate semantic communication into V2X resource management, jointly optimizing base station selection, spectrum allocation, and cross-technology coexistence strategies via a flexible duty-cycle coexistence mechanism and Proximal Policy Optimization (PPO)-based deep reinforcement learning. We introduce two novel semantic metrics: High-Speed Semantic Rate (HSR) and High-Speed Semantic Spectral Efficiency (HSSE), shifting optimization from bit-level to semantic-level paradigms. Experimental results demonstrate that SARADC significantly improves HSSE and Semantic Throughput (ST), outperforming state-of-the-art bit-level approaches in both V2X-only and V2X-WiFi coexistence scenarios.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Game Theory and Economic Paradigms: Adversarial Learning
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Virtualization and resource management in Web systems and infrastructures
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Vertical and domain-specific search

Abstract

This letter proposes a semantic-aware resource allocation (SARA) framework with flexible duty cycle (DC) coexistence mechanism (SARADC) for 5G-V2X Heterogeneous Network (HetNets) based on deep reinforcement learning (DRL) proximal policy optimization (PPO). Specifically, we investigate V2X networks within a three-tiered HetNets structure. To meet the demands of high-speed vehicular networking in urban environments, we design a semantic communication system and introduce two resource allocation metrics: high-speed semantic transmission rate (HSR) and semantic spectrum efficiency (HSSE). Additionally, we address the coexistence of vehicular users and WiFi users in 5G New Radio Unlicensed (NR-U) networks. Our approach jointly optimizes the DC coexistence mechanism and the allocation of resources and base stations (BSs). Unlike traditional bit-based transmission methods, our approach integrates the semantic communication into the communication system. Experimental results show that our proposed framework significantly improves HSSE and semantic throughput (ST) for both vehicular and WiFi users compared to conventional methods.

Problem

• Optimize resource allocation in 5G-V2X HetNets using DRL
• Maximize semantic spectrum efficiency for high-speed vehicular networks
• Enable coexistence of vehicular and WiFi users in 5G NR-U

Innovation

• DRL-based semantic-aware resource allocation
• Flexible duty cycle coexistence mechanism
• Semantic metrics HSR and HSSE optimization