Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Semantic Extraction Model Selection for IoT Devices in Edge-assisted Semantic Communications

Hong Chen, Fang Fang, Xianbin Wang

TL;DR

The paper addresses SE model selection for IoT devices in edge-assisted semantic communications, where an edge server co-located with an AP supports multiple SE models. It formulates an NP-complete problem to maximize the total semantic rate, $\sum_{i,j,k} x_{i,j,k} \gamma_{i,j,k}$, under per-task accuracy, delay, and ES capacity constraints. The authors transform the problem into a Typed Knapsack and develop a dynamic-programming based FPTAS with guaranteed near-optimal performance. Simulations demonstrate that the proposed method closely tracks the optimum and scales efficiently with ES resources, enabling practical deployment of edge-enabled semantic networks.

Abstract

Semantic communications offer the potential to alleviate communication loads by exchanging meaningful information. However, semantic extraction (SE) is computationally intensive, posing challenges for resource-constrained Internet of Things (IoT) devices. To address this, leveraging computing resources at the edge servers (ESs) is essential. ESs can support multiple SE models for various tasks, making it crucial to select appropriate SE models based on diverse requirements of IoT devices and limited ES computing resources. In this letter, we study an SE model selection problem, where the ES co-located at the access point can provide multiple SE models to execute the uploaded SE tasks of associated IoT devices. We aim to maximize the total semantic rate of all SE tasks by selecting appropriate SE models, while considering SE delay and ES capacity constraints, and SE accuracy requirements. The formulated NP-complete integer programming problem is transformed into a modified Knapsack problem. The proposed efficient approximation algorithm using dynamic programming can yield a guaranteed near-optimum solution. Simulation results demonstrate the superior performance of proposed solution.

Semantic Extraction Model Selection for IoT Devices in Edge-assisted Semantic Communications

TL;DR

The paper addresses SE model selection for IoT devices in edge-assisted semantic communications, where an edge server co-located with an AP supports multiple SE models. It formulates an NP-complete problem to maximize the total semantic rate, , under per-task accuracy, delay, and ES capacity constraints. The authors transform the problem into a Typed Knapsack and develop a dynamic-programming based FPTAS with guaranteed near-optimal performance. Simulations demonstrate that the proposed method closely tracks the optimum and scales efficiently with ES resources, enabling practical deployment of edge-enabled semantic networks.

Abstract

Semantic communications offer the potential to alleviate communication loads by exchanging meaningful information. However, semantic extraction (SE) is computationally intensive, posing challenges for resource-constrained Internet of Things (IoT) devices. To address this, leveraging computing resources at the edge servers (ESs) is essential. ESs can support multiple SE models for various tasks, making it crucial to select appropriate SE models based on diverse requirements of IoT devices and limited ES computing resources. In this letter, we study an SE model selection problem, where the ES co-located at the access point can provide multiple SE models to execute the uploaded SE tasks of associated IoT devices. We aim to maximize the total semantic rate of all SE tasks by selecting appropriate SE models, while considering SE delay and ES capacity constraints, and SE accuracy requirements. The formulated NP-complete integer programming problem is transformed into a modified Knapsack problem. The proposed efficient approximation algorithm using dynamic programming can yield a guaranteed near-optimum solution. Simulation results demonstrate the superior performance of proposed solution.
Paper Structure (7 sections, 1 theorem, 9 equations, 4 figures, 1 table, 2 algorithms)

This paper contains 7 sections, 1 theorem, 9 equations, 4 figures, 1 table, 2 algorithms.

Table of Contents

  1. Introduction
  2. System Model and Problem Formulation
  3. Approximation Algorithm for the Problem
  4. Problem Transformation
  5. An FPTAS for Typed Knapsack
  6. Simulation Results
  7. Conclusions

Key Result

Theorem 3.1

For any given constant $\varepsilon \in (0,1]$, the FPTAS algorithm achieves an approximate solution (when feasible) of total value at least $(1-\varepsilon)OBJ^*$, where $OBJ^*$ is the optimal objective value, and the computation complexity is in polynomial time $O(M^4 {N_{\max}}^2/\varepsilon)$.

Figures (4)

  • Figure 1: Edge-assisted semantic-aware network for IoT devices.
  • Figure 2: Total semantic rate versus ES computation capacity.
  • Figure 3: Total semantic rate versus wireless channel bandwidth.
  • Figure 4: Total semantic rate versus maximum SE delay tolerance.

Theorems & Definitions (2)

  • Theorem 3.1
  • proof