Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Joint User Association and Resource Allocation for Multi-Cell Networks with Adaptive Semantic Communication

Xingqiu He, Chaoqun You, Tony Q. S. Quek

TL;DR

This work addresses joint user association and resource allocation in multi‑cell networks where devices employ adaptive semantic transmitters. By modeling semantic workloads and a task‑driven utility, the authors decompose the problem into scheduling, RB allocation, and user association, and develop near‑optimal polynomial‑time algorithms for each stage. Across concave and general utility settings, the proposed three‑stage approach outperforms traditional benchmarks, illustrating the benefits of combining adaptive semantics with load‑balanced resource management. The results highlight the practical potential of adaptive semantic communication to reduce data transmission while meeting latency and energy constraints in dense wireless networks.

Abstract

Semantic communication is a promising communication paradigm that utilizes Deep Neural Networks (DNNs) to extract the information relevant to downstream tasks, hence significantly reducing the amount of transmitted data. In current practice, the semantic communication transmitter for a specific task is typically pre-trained and shared by all users. However, due to user heterogeneity, it is desirable to use different transmitters according to the available computational and communication resources of users. In this paper, we first show that it is possible to dynamically adjust the computational and communication overhead of DNN-based transmitters, thereby achieving adaptive semantic communication. After that, we investigate the user association and resource allocation problem in a multi-cell network where users are equipped with adaptive semantic communication transmitters. To solve this problem, we decompose it into three subproblems involving the scheduling of each user, the resource allocation of each base station (BS), and the user association between users and BSs. Then we solve each problem progressively based on the solution of the previous subproblem. The final algorithm can obtain near-optimal solutions in polynomial time. Numerical results show that our algorithm outperforms benchmarks under various situations.

Joint User Association and Resource Allocation for Multi-Cell Networks with Adaptive Semantic Communication

TL;DR

This work addresses joint user association and resource allocation in multi‑cell networks where devices employ adaptive semantic transmitters. By modeling semantic workloads and a task‑driven utility, the authors decompose the problem into scheduling, RB allocation, and user association, and develop near‑optimal polynomial‑time algorithms for each stage. Across concave and general utility settings, the proposed three‑stage approach outperforms traditional benchmarks, illustrating the benefits of combining adaptive semantics with load‑balanced resource management. The results highlight the practical potential of adaptive semantic communication to reduce data transmission while meeting latency and energy constraints in dense wireless networks.

Abstract

Semantic communication is a promising communication paradigm that utilizes Deep Neural Networks (DNNs) to extract the information relevant to downstream tasks, hence significantly reducing the amount of transmitted data. In current practice, the semantic communication transmitter for a specific task is typically pre-trained and shared by all users. However, due to user heterogeneity, it is desirable to use different transmitters according to the available computational and communication resources of users. In this paper, we first show that it is possible to dynamically adjust the computational and communication overhead of DNN-based transmitters, thereby achieving adaptive semantic communication. After that, we investigate the user association and resource allocation problem in a multi-cell network where users are equipped with adaptive semantic communication transmitters. To solve this problem, we decompose it into three subproblems involving the scheduling of each user, the resource allocation of each base station (BS), and the user association between users and BSs. Then we solve each problem progressively based on the solution of the previous subproblem. The final algorithm can obtain near-optimal solutions in polynomial time. Numerical results show that our algorithm outperforms benchmarks under various situations.
Paper Structure (18 sections, 3 theorems, 27 equations, 8 figures, 1 table, 3 algorithms)

This paper contains 18 sections, 3 theorems, 27 equations, 8 figures, 1 table, 3 algorithms.

Table of Contents

  1. Introduction
  2. Related Work
  3. System Model and Problem Formulation
  4. Network Model
  5. Adaptive Semantic Communication Model
  6. Computation and Transmission Model
  7. Problem Formulation
  8. Algorithm Design and Performance Analysis
  9. Scheduling Subproblem for Each WD
  10. RB Allocation Subproblem for Each BS
  11. RB Allocation with Concave Utility
  12. RB Allocation with General Utility
  13. User Association Subproblem
  14. Numerical Results
  15. Conclusion
  16. ...and 3 more sections

Key Result

Theorem 1

Problem problem is strongly NP-hard even if (i) there is only one WD for each running application and its utility function is binary, (ii) the energy budget $E^{max}_n$ is sufficiently large, and (iii) the channel gain $h^m_n$ and interference $I_m$ for different BS $m$ is equal.

Figures (8)

  • Figure 1: A simple example of the considered system.
  • Figure 2: Utility of each BS under the concave utility function.
  • Figure 3: Utility of each BS under the general utility function.
  • Figure 4: Total utility of different algorithms.
  • Figure 5: Total utility under different numbers of BSs.
  • ...and 3 more figures

Theorems & Definitions (6)

  • Theorem 1
  • proof
  • Theorem 2
  • proof
  • Theorem 3
  • proof