Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Semantic-Aware Cooperative Communication and Computation Framework in Vehicular Networks

Jingbo Zhang, Maoxin Ji, Qiong Wu, Pingyi Fan, Kezhi Wang, Wen Chen

TL;DR

The paper tackles ultra-low-latency semantic offloading in high-m mobility IoV by introducing a Tripartite Cooperative Semantic Communication framework that leverages V2I and V2V links among vehicles, RSUs, and service vehicles. It decouples the optimization into semantic-symbol selection via MAPPO-PDN and offloading-rate allocation via linear programming, forming a MAPPO-PDN-LP solution that outperforms traditional schemes. The key contributions include a detailed system model for semantic VEC on highways, a novel MAPPO-PDN-based approach for discrete symbol optimization with PDN regularization, and a LP-based method to compute optimal offloading ratios, validated by simulations showing reduced latency and robust convergence. The work demonstrates significant potential for enabling efficient, low-latency semantic processing in dynamic vehicular networks and points toward future multimodal semantic communication extensions.

Abstract

Semantic Communication (SC) combined with Vehicular edge computing (VEC) provides an efficient edge task processing paradigm for Internet of Vehicles (IoV). Focusing on highway scenarios, this paper proposes a Tripartite Cooperative Semantic Communication (TCSC) framework, which enables Vehicle Users (VUs) to perform semantic task offloading via Vehicle-to-Infrastructure (V2I) and Vehicle-to-Vehicle (V2V) communications. Considering task latency and the number of semantic symbols, the framework constructs a Mixed-Integer Nonlinear Programming (MINLP) problem, which is transformed into two subproblems. First, we innovatively propose a multi-agent proximal policy optimization task offloading optimization method based on parametric distribution noise (MAPPO-PDN) to solve the optimization problem of the number of semantic symbols; second, linear programming (LP) is used to solve offloading ratio. Simulations show that performance of this scheme is superior to that of other algorithms.

Semantic-Aware Cooperative Communication and Computation Framework in Vehicular Networks

TL;DR

The paper tackles ultra-low-latency semantic offloading in high-m mobility IoV by introducing a Tripartite Cooperative Semantic Communication framework that leverages V2I and V2V links among vehicles, RSUs, and service vehicles. It decouples the optimization into semantic-symbol selection via MAPPO-PDN and offloading-rate allocation via linear programming, forming a MAPPO-PDN-LP solution that outperforms traditional schemes. The key contributions include a detailed system model for semantic VEC on highways, a novel MAPPO-PDN-based approach for discrete symbol optimization with PDN regularization, and a LP-based method to compute optimal offloading ratios, validated by simulations showing reduced latency and robust convergence. The work demonstrates significant potential for enabling efficient, low-latency semantic processing in dynamic vehicular networks and points toward future multimodal semantic communication extensions.

Abstract

Semantic Communication (SC) combined with Vehicular edge computing (VEC) provides an efficient edge task processing paradigm for Internet of Vehicles (IoV). Focusing on highway scenarios, this paper proposes a Tripartite Cooperative Semantic Communication (TCSC) framework, which enables Vehicle Users (VUs) to perform semantic task offloading via Vehicle-to-Infrastructure (V2I) and Vehicle-to-Vehicle (V2V) communications. Considering task latency and the number of semantic symbols, the framework constructs a Mixed-Integer Nonlinear Programming (MINLP) problem, which is transformed into two subproblems. First, we innovatively propose a multi-agent proximal policy optimization task offloading optimization method based on parametric distribution noise (MAPPO-PDN) to solve the optimization problem of the number of semantic symbols; second, linear programming (LP) is used to solve offloading ratio. Simulations show that performance of this scheme is superior to that of other algorithms.

Paper Structure

This paper contains 17 sections, 19 equations, 4 figures.

Table of Contents

  1. Introduction
  2. System Model
  3. System Scenario
  4. Semantic Communication Model
  5. Computation Model
  6. Local computing
  7. Processed on the RSU
  8. Processed on the SV
  9. Problem Formulation
  10. Problem Formulation and Solution
  11. Semantic Symbol Optimization Based on MAPPO-PDN
  12. State space
  13. Action space
  14. Reward function
  15. Offloading Rate Based on Linear Programming
  16. ...and 2 more sections

Figures (4)

  • Figure 1: System overview.
  • Figure 2: Convergence performance comparisons.
  • Figure 3: Average transmission delay versus vehicular number.
  • Figure 4: Average task delay versus vehicular number.