Mobile Edge Generation-Enabled Digital Twin: Architecture Design and Research Opportunities

TL;DR

This paper introduces a new mobile edge generation-enabled digital twin architecture that decentralizes AI models to edge devices for real-time, privacy-preserving, and customizable digital twin applications, with protocols for efficient distributed generation.

Contribution

It proposes a novel MEG-DT architecture with decentralized AI models, new generation mechanisms, and transmission protocols, advancing real-time digital twin capabilities at the edge.

Findings

MEG-DT reduces latency compared to centralized systems.

Protocols enable efficient feature transmission between edge servers and devices.

Numerical case studies demonstrate superiority over centralized generation.

Abstract

A novel paradigm of mobile edge generation (MEG)-enabled digital twin (DT) is proposed, which enables distributed on-device generation at mobile edge networks for real-time DT applications. First, an MEG-DT architecture is put forward to decentralize generative artificial intelligence (GAI) models onto edge servers (ESs) and user equipments (UEs), which has the advantages of low latency, privacy preservation, and individual-level customization. Then, various single-user and multi-user generation mechanisms are conceived for MEG-DT, which strike trade-offs between generation latency, hardware costs, and device coordination. Furthermore, to perform efficient distributed generation, two operating protocols are explored for transmitting interpretable and latent features between ESs and UEs, namely sketch-based generation and seed-based generation, respectively. Based on the proposed protocols, the convergence between MEG and DT are highlighted. Considering the seed-based image generation scenario, numerical case studies are provided to reveal the superiority of MEG-DT over centralized generation. Finally, promising applications and research opportunities are identified. Code is available at https://github.com/xiaoxiaxusummer/MEG_DT