Semantic-Aware Power Allocation for Generative Semantic Communications with Foundation Models

TL;DR

This paper introduces a semantic-aware power allocation framework for generative semantic communications using foundation models, optimizing power use while maintaining semantic and perceptual quality of images.

Contribution

It proposes a novel generative SemCom framework with foundation models and develops two power allocation methods to minimize power consumption under semantic performance constraints.

Findings

Semantic-aware methods reduce power consumption compared to conventional approaches.

The framework effectively balances transmission reliability and image perceptual quality.

Numerical simulations validate the superiority of the proposed methods.

Abstract

Recent advancements in diffusion models have made a significant breakthrough in generative modeling. The combination of the generative model and semantic communication (SemCom) enables high-fidelity semantic information exchange at ultra-low rates. A novel generative SemCom framework for image tasks is proposed, wherein pre-trained foundation models serve as semantic encoders and decoders for semantic feature extractions and image regenerations, respectively. The mathematical relationship between the transmission reliability and the perceptual quality of the regenerated image and the semantic values of semantic features are modeled, which are obtained by conducting numerical simulations on the Kodak dataset. We also investigate the semantic-aware power allocation problem, with the objective of minimizing the total power consumption while guaranteeing semantic performance. To solve this problem, two semanticaware power allocation methods are proposed by constraint decoupling and bisection search, respectively. Numerical results show that the proposed semantic-aware methods demonstrate superior performance compared to the conventional one in terms of total power consumption.