Joint Semantic Transmission and Resource Allocation for Intelligent Computation Task Offloading in MEC Systems

TL;DR

The paper tackles intelligent computation task offloading in MEC by integrating semantic transmission with early exit of inference (EEoI) across a multi-BS, multi-terminal setting. It develops a joint optimization framework that maximizes a delay-based system reward, and solves it via a BCD approach that decouples communication and computation: the communication subproblem is addressed with 3D and two-sided matching, while the computation subproblem uses convex optimization for resource allocation and a binary decision for semantic transmission. The proposed method demonstrates significant delay reductions and substantial reward improvements over benchmark schemes, validating the benefits of EEoI and semantic compression in intelligent MEC tasks. The work offers a scalable resource-management paradigm for intelligent edge services, enabling more efficient use of communication and computation resources in heterogeneous networks.

Abstract

Mobile edge computing (MEC) enables the provision of high-reliability and low-latency applications by offering computation and storage resources in close proximity to end-users. Different from traditional computation task offloading in MEC systems, the large data volume and complex task computation of artificial intelligence involved intelligent computation task offloading have increased greatly. To address this challenge, we propose a MEC system for multiple base stations and multiple terminals, which exploits semantic transmission and early exit of inference. Based on this, we investigate a joint semantic transmission and resource allocation problem for maximizing system reward combined with analysis of semantic transmission and intelligent computation process. To solve the formulated problem, we decompose it into communication resource allocation subproblem, semantic transmission subproblem, and computation capacity allocation subproblem. Then, we use 3D matching and convex optimization method to solve subproblems based on the block coordinate descent (BCD) framework. The optimized feasible solutions are derived from an efficient BCD based joint semantic transmission and resource allocation algorithm in MEC systems. Our simulation demonstrates that: 1) The proposed algorithm significantly improves the delay performance for MEC systems compared with benchmarks; 2) The design of transmission mode and early exit of inference greatly increases system reward during offloading; and 3) Our proposed system achieves efficient utilization of resources from the perspective of system reward in the intelligent scenario.

Figures (6)

• Figure 1: The system scenario of image semantic transmission.
• Figure 2: Convergence of all algorithms.
• Figure 3: Terminal average system reward with varying number of terminals under 3 exit points and 1 exit point.
• Figure 4: System reward with varying computing capacity of edge under 3 exit points and 1 exit point.
• Figure 5: System reward with varying bandwidth of subcarriers under 3 exit points and 1 exit point.