Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Wireless Resource Management in Intelligent Semantic Communication Networks

Le Xia, Yao Sun, Xiaoqian Li, Gang Feng, Muhammad Ali Imran

TL;DR

This paper introduces the auxiliary knowledge base (KB) into the system model, and develops a new performance metric for the ISCHetNet, named system throughput in message (STM), and proposes joint optimization of UA and BA with the aim of STM maximization subject to KB matching and wireless bandwidth constraints.

Abstract

The prosperity of artificial intelligence (AI) has laid a promising paradigm of communication system, i.e., intelligent semantic communication (ISC), where semantic contents, instead of traditional bit sequences, are coded by AI models for efficient communication. Due to the unique demand of background knowledge for semantic recovery, wireless resource management faces new challenges in ISC. In this paper, we address the user association (UA) and bandwidth allocation (BA) problems in an ISC-enabled heterogeneous network (ISC-HetNet). We first introduce the auxiliary knowledge base (KB) into the system model, and develop a new performance metric for the ISC-HetNet, named system throughput in message (STM). Joint optimization of UA and BA is then formulated with the aim of STM maximization subject to KB matching and wireless bandwidth constraints. To this end, we propose a two-stage solution, including a stochastic programming method in the first stage to obtain a deterministic objective with semantic confidence, and a heuristic algorithm in the second stage to reach the optimality of UA and BA. Numerical results show great superiority and reliability of our proposed solution on the STM performance when compared with two baseline algorithms.

Wireless Resource Management in Intelligent Semantic Communication Networks

TL;DR

This paper introduces the auxiliary knowledge base (KB) into the system model, and develops a new performance metric for the ISCHetNet, named system throughput in message (STM), and proposes joint optimization of UA and BA with the aim of STM maximization subject to KB matching and wireless bandwidth constraints.

Abstract

The prosperity of artificial intelligence (AI) has laid a promising paradigm of communication system, i.e., intelligent semantic communication (ISC), where semantic contents, instead of traditional bit sequences, are coded by AI models for efficient communication. Due to the unique demand of background knowledge for semantic recovery, wireless resource management faces new challenges in ISC. In this paper, we address the user association (UA) and bandwidth allocation (BA) problems in an ISC-enabled heterogeneous network (ISC-HetNet). We first introduce the auxiliary knowledge base (KB) into the system model, and develop a new performance metric for the ISC-HetNet, named system throughput in message (STM). Joint optimization of UA and BA is then formulated with the aim of STM maximization subject to KB matching and wireless bandwidth constraints. To this end, we propose a two-stage solution, including a stochastic programming method in the first stage to obtain a deterministic objective with semantic confidence, and a heuristic algorithm in the second stage to reach the optimality of UA and BA. Numerical results show great superiority and reliability of our proposed solution on the STM performance when compared with two baseline algorithms.
Paper Structure (11 sections, 21 equations, 5 figures)

This paper contains 11 sections, 21 equations, 5 figures.

Table of Contents

  1. Introduction
  2. System Model
  3. Network Topology of the ISC-HetNet
  4. KB-enabled Semantic Model
  5. Problem Formulation
  6. Solutions to UA and BA in the ISC-HetNet
  7. STM Maximization with Semantic Confidence Level
  8. Optimal UA Solutions under Relaxation
  9. Association Approximation and Allocation Adjustment
  10. Numerical Results
  11. Conclusions

Figures (5)

  • Figure 1: The structure diagram of an ISC system.
  • Figure 2: The transformation diagram between received bits and recovered messages in semantic communication.
  • Figure 3: The BLEU score (1-gram) vs. bit-rates obtained by MUs in the ISC-HetNet under four different SINRs of $0$, $3$, $6$, and $9$ dB.
  • Figure 4: The STM performance against number of MUs under three different semantic confidence levels of $\alpha=55\%$, $75\%$, and $95\%$.
  • Figure 5: The STM performance against number of KB-enabled BSs under two different mean values of $\tau=0.3$ and $0.7$ for knowledge matching coefficients.