Flexible Semantic-Aware Resource Allocation: Serving More Users Through Similarity Range Constraints

TL;DR

The paper tackles resource allocation under semantic constraints in SemCom by formulating a non convex MINLP that jointly optimizes bandwidth, power, and compression rates to maximize the number of semantically satisfied users. It introduces semantic similarity ranges to add flexibility and decomposes the problem into a GP solvable power-bandwidth subproblem and a compression rate subproblem handled via a semantic similarity lookup table, iterating to a suboptimal solution. Empirical results on CIFAR-10 with UDeepSC show the proposed method increases the number of satisfied users by up to 17.1% and total network semantic similarity by about 14% compared with baselines, demonstrating improved resource efficiency. The approach offers practical gains for scalable semantic aware networks and opens avenues for extending to multi-task and diverse data types.

Abstract

Semantic communication (SemCom) aims to enhance the resource efficiency of next-generation networks by transmitting the underlying meaning of messages, focusing on information relevant to the end user. Existing literature on SemCom primarily emphasizes learning the encoder and decoder through end-to-end deep learning frameworks, with the objective of minimizing a task-specific semantic loss function. Beyond its influence on the physical and application layer design, semantic variability across users in multi-user systems enables the design of resource allocation schemes that incorporate user-specific semantic requirements. To this end, \emph{a semantic-aware resource allocation} scheme is proposed with the objective of maximizing transmission and semantic reliability, ultimately increasing the number of users whose semantic requirements are met. The resulting resource allocation problem is a non-convex mixed-integer nonlinear program (MINLP), which is known to be NP-hard. To make the problem tractable, it is decomposed into a set of sub-problems, each of which is efficiently solved via geometric programming techniques. Finally, simulations demonstrate that the proposed method improves user satisfaction by up to $17.1\%$ compared to state of the art methods based on quality of experience-aware SemCom methods.

Figures (4)

• Figure 1: Number of satisfied users VS maximum available bandwidth.
• Figure 2: Semantic similarity of the satisfied users.
• Figure 3: Average similarity VS maximum available bandwidth.
• Figure : Proposed algorithm for bandwidth, power allocation, and compression rate adjustment.