Enabling Distributed Generative Artificial Intelligence in 6G: Mobile Edge Generation

TL;DR

This paper introduces a novel mobile edge generation (MEG) framework for distributed text-to-image AI tasks in 6G networks, optimizing transmission and image quality through compression and reinforcement learning.

Contribution

It proposes a new MEG model with seed-based compression, a deep RL power optimization, and demonstrates improved transmission efficiency and image quality in edge-based GAI.

Findings

Reduced transmission overhead compared to centralized schemes

Enhanced image quality under low SNR conditions

Effective power management via deep reinforcement learning

Abstract

Mobile edge generation (MEG) is an emerging technology that allows the network to meet the challenging traffic load expectations posed by the rise of generative artificial intelligence~(GAI). A novel MEG model is proposed for deploying GAI models on edge servers (ES) and user equipment~(UE) to jointly complete text-to-image generation tasks. In the generation task, the ES and UE will cooperatively generate the image according to the text prompt given by the user. To enable the MEG, a pre-trained latent diffusion model (LDM) is invoked to generate the latent feature, and an edge-inferencing MEG protocol is employed for data transmission exchange between the ES and the UE. A compression coding technique is proposed for compressing the latent features to produce seeds. Based on the above seed-enabled MEG model, an image quality optimization problem with transmit power constraint is formulated. The transmitting power of the seed is dynamically optimized by a deep reinforcement learning agent over the fading channel. The proposed MEG enabled text-to-image generation system is evaluated in terms of image quality and transmission overhead. The numerical results indicate that, compared to the conventional centralized generation-and-downloading scheme, the symbol number of the transmission of MEG is materially reduced. In addition, the proposed compression coding approach can improve the quality of generated images under low signal-to-noise ratio (SNR) conditions.