Deploying On-Device AIGC Inference Services in 6G via Optimal MEC-Device Offloading

Authors

Changshi Zhou, Newark College of Engineering
Weiqi Liu, Auburn University at Montgomery
Tao Han, Newark College of Engineering
Nirwan Ansari, Newark College of Engineering

Document Type

Article

Publication Date

1-1-2024

Abstract

From AI-assisted art creation to large language model (LLM)-powered ChatGPT, AI-generated contents and services are becoming a transforming force. It calls for the telecom industry to embrace the prospects of AIGC services and face the unique challenges posed by incorporating generative model services into the AI-native 6G wireless network paradigm. We propose enabling AIGC inference services on mobile devices by optimizing MEC-device computing offloading, through which AIGC task latency is minimized by reinforcement learning based policy agent in a computing resource constrained and bandwidth limited wireless environment. Simulation results are presented to demonstrate the performance advantage.

Identifier

85209464414 (Scopus)

Publication Title

IEEE Networking Letters

External Full Text Location

https://doi.org/10.1109/LNET.2024.3490954

e-ISSN

25763156

First Page

232

Last Page

236

Issue

4

Volume

6

Recommended Citation

Zhou, Changshi; Liu, Weiqi; Han, Tao; and Ansari, Nirwan, "Deploying On-Device AIGC Inference Services in 6G via Optimal MEC-Device Offloading" (2024). Faculty Publications. 804.
https://digitalcommons.njit.edu/fac_pubs/804