Green Probabilistic Semantic Communication over Wireless Networks

TL;DR

This paper introduces a multi-user green semantic communication system using probabilistic knowledge graphs, optimizing energy efficiency through semantic compression and rate-splitting multiple access technology.

Contribution

It proposes a novel probabilistic semantic communication framework with a semantic compression model and an optimization algorithm for energy-efficient multi-user wireless networks.

Findings

System outperforms SDMA and NOMA methods in simulations.

Semantic compression improves transmission efficiency.

Optimization reduces overall energy consumption.

Abstract

In this paper, we propose a multi-user green semantic communication system facilitated by a probabilistic knowledge graph (PKG). By integrating probability into the knowledge graph, we enable probabilistic semantic communication (PSC) and represent semantic information accordingly. On this basis, a semantic compression model designed for multi-user downlink task-oriented communication is introduced, utilizing the semantic compression ratio (SCR) as a parameter to connect the computation and communication processes of information transmission. Based on the rate-splitting multiple access (RSMA) technology, we derive mathematical expressions for system transmission energy consumption and related formulations. Subsequently, the multi-user green semantic communication system is modeled and the optimal problem with the goal of minimizing system energy consumption comprehensively considering the computation and communication process under given constrains is formulated. In order to address the optimal problem, we propose an alternating optimization algorithm that tackles sub-problems of power allocation and beamforming design, semantic compression ratio, and computation capacity allocation. Simulation results validate the effectiveness of our approach, demonstrating the superiority of our system over methods using Space Division Multiple Access (SDMA) and non-orthogonal multiple access (NOMA) instead of RSMA, and highlighting the benefits of our PSC compression model.