Semantic-Aware Cooperative Communication and Computation Framework in Vehicular Networks

2025-12-10

AI Summary

To jointly optimize latency and semantic overhead in semantic task offloading for Intelligent Vehicle Networks (IVN) on highways, this paper proposes a vehicle–infrastructure–vehicle (V–I–V) collaborative semantic communication framework enabling semantic-level task offloading under integrated V2I/V2V connectivity. We formulate a novel joint optimization model that decouples the number of semantic symbols and offloading ratio into two interdependent mixed-integer nonlinear programming (MINLP) subproblems. To solve this efficiently, we design a parameterized distribution noise–based multi-agent proximal policy optimization (MAPPO-PDN) algorithm. Experimental results demonstrate that, compared to baseline methods, the proposed approach reduces end-to-end task latency by 23.6%, decreases semantic symbol overhead by 18.4%, and achieves a semantic accuracy of 92.7%, thereby significantly enhancing the real-time performance and efficiency of vehicular edge computing (VEC)-empowered semantic communication.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Learning to Search
• Multiagent Systems: Agent Communication

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

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.

Problem

• Optimizes semantic task offloading in vehicular networks
• Solves MINLP for latency and semantic symbol efficiency
• Proposes MAPPO-PDN and LP for cooperative communication optimization

Innovation

• Tripartite Cooperative Semantic Communication framework for V2I and V2V offloading
• Multi-agent proximal policy optimization with parametric distribution noise for symbol optimization
• Linear programming applied to solve offloading ratio in MINLP problem