Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Joint User Association and Bandwidth Allocation in Semantic Communication Networks

Le Xia, Yao Sun, Dusit Niyato, Xiaoqian Li, Muhammad Ali Imran

TL;DR

This article identifies two general SC-Net scenarios, namely perfect knowledge matching-based SC-Net and imperfect knowledge matching-based SC-Net, and formulate a joint STM-maximization problem of UA and BA for each SC-Net scenario, followed by a corresponding optimal solution proposed.

Abstract

Semantic communication (SemCom) has recently been considered a promising solution to guarantee high resource utilization and transmission reliability for future wireless networks. Nevertheless, the unique demand for background knowledge matching makes it challenging to achieve efficient wireless resource management for multiple users in SemCom-enabled networks (SC-Nets). To this end, this paper investigates SemCom from a networking perspective, where two fundamental problems of user association (UA) and bandwidth allocation (BA) are systematically addressed in the SC-Net. First, considering varying knowledge matching states between mobile users and associated base stations, we identify two general SC-Net scenarios, namely perfect knowledge matching-based SC-Net and imperfect knowledge matching-based SC-Net. Afterward, for each SC-Net scenario, we describe its distinctive semantic channel model from the semantic information theory perspective, whereby a concept of bit-rate-to-message-rate transformation is developed along with a new semantics-level metric, namely system throughput in message (STM), to measure the overall network performance. In this way, we then formulate a joint STM-maximization problem of UA and BA for each SC-Net scenario, followed by a corresponding optimal solution proposed. Numerical results in both scenarios demonstrate significant superiority and reliability of our solutions in the STM performance compared with two benchmarks.

Joint User Association and Bandwidth Allocation in Semantic Communication Networks

TL;DR

This article identifies two general SC-Net scenarios, namely perfect knowledge matching-based SC-Net and imperfect knowledge matching-based SC-Net, and formulate a joint STM-maximization problem of UA and BA for each SC-Net scenario, followed by a corresponding optimal solution proposed.

Abstract

Semantic communication (SemCom) has recently been considered a promising solution to guarantee high resource utilization and transmission reliability for future wireless networks. Nevertheless, the unique demand for background knowledge matching makes it challenging to achieve efficient wireless resource management for multiple users in SemCom-enabled networks (SC-Nets). To this end, this paper investigates SemCom from a networking perspective, where two fundamental problems of user association (UA) and bandwidth allocation (BA) are systematically addressed in the SC-Net. First, considering varying knowledge matching states between mobile users and associated base stations, we identify two general SC-Net scenarios, namely perfect knowledge matching-based SC-Net and imperfect knowledge matching-based SC-Net. Afterward, for each SC-Net scenario, we describe its distinctive semantic channel model from the semantic information theory perspective, whereby a concept of bit-rate-to-message-rate transformation is developed along with a new semantics-level metric, namely system throughput in message (STM), to measure the overall network performance. In this way, we then formulate a joint STM-maximization problem of UA and BA for each SC-Net scenario, followed by a corresponding optimal solution proposed. Numerical results in both scenarios demonstrate significant superiority and reliability of our solutions in the STM performance compared with two benchmarks.
Paper Structure (18 sections, 1 theorem, 30 equations, 11 figures)

This paper contains 18 sections, 1 theorem, 30 equations, 11 figures.

Table of Contents

  1. Introduction
  2. Semantic Communication Model
  3. Background Knowledge Matching in SemCom
  4. Semantic Channel Model in the PKM-based SC-Net
  5. Semantic Channel Model in the IKM-based SC-Net
  6. Basic Network Topology of SC-Net
  7. Resource Management in the PKM-based SC-Net
  8. Problem Formulation
  9. Optimal Solution for UA
  10. Optimization Solution for BA
  11. Resource Management in the IKM-based SC-Net
  12. Problem Formulation
  13. Problem Transformation with Semantic Confidence Level
  14. Solution Finalization for UA and BA
  15. Numerical Results and Discussions
  16. ...and 3 more sections

Key Result

Proposition 1

Given the knowledge matching degree, denoted as $\tau_{ij}$, between MU $i$ and BS $j$ in the IKM case, the random knowledge matching coefficient $\beta_{ij}$ obeys a Gaussian distribution with mean $\tau_{ij}$ and variance $\sigma^{2}_{ij}$, i.e., $\beta_{ij}\sim \mathcal{N}\left(\tau_{ij},\sigma^{

Figures (11)

  • Figure 1: An overview of SC-Net.
  • Figure 2: Example illustration of the PKM-based SC-Net (on the left) and the IKM-based SC-Net (on the right) with respect to a single SemCom-enabled link.
  • Figure 3: A SemCom diagram of information source and destination.
  • Figure 4: The BLEU score (1-gram) vs. bit rates under four different SINRs of $0$, $3$, $6$, and $9$ dB in the PKM-based SC-Net.
  • Figure 5: Demonstration of B2M transformation under four SINRs of Transformer-powered SemCom-enabled links in the PKM-based SC-Net.
  • ...and 6 more figures

Theorems & Definitions (4)

  • Definition 1
  • Definition 2
  • Definition 3
  • Proposition 1