Open-Source Edge AI for 6G Wireless Networks

Liqiang Zhao; Yunfeng Wang; Xiaoli Chu; Shenghui Song; Yansha Deng; Arumugam Nallanathan; George K. Karagiannidis

doi:10.1109/MNET.2024.3411772

Open-Source Edge AI for 6G Wireless Networks

Liqiang Zhao, Yunfeng Wang, Xiaoli Chu, Shenghui Song, Yansha Deng, Arumugam Nallanathan, George K. Karagiannidis

Research output: Contribution to journal › Article › peer-review

Abstract

Multi-access Edge Computing (MEC) has been recognized as a key enabler for next-generation networks in supporting a large variety of compelling applications with challenging requirements. With its widely proved strength and successes, AI has to become an integral part of MEC. In this paper, we present a novel open-source edge AI (OpenEAI) framework that introduces a native AI plane into the recently proposed open-source MEC framework. The AI plane is designed based on two principles: decoupling the edge AI services into independent AI functions; and recomposing the independent edge AI functions into customized OpenEAI instances based on users’ specific requirements. Typical use cases of OpenEAI are characterized with the aid of a small-scale test network. Finally, we discuss the opportunities and challenges facing OpenEAI.

Original language	English
Pages (from-to)	1
Number of pages	1
Journal	IEEE NETWORK
DOIs	https://doi.org/10.1109/MNET.2024.3411772
Publication status	Accepted/In press - 2024

Keywords

6G
Artificial Intelligence
Central Processing Unit
Data models
Edge AI
Graphics processing units
Hardware
Multi-access Edge Computing
Open Source
Training
Uniform resource locators
Virtualization

Access to Document

10.1109/MNET.2024.3411772

Cite this

@article{fb5fd5e8b1ee413484716197edd66555,

title = "Open-Source Edge AI for 6G Wireless Networks",

abstract = "Multi-access Edge Computing (MEC) has been recognized as a key enabler for next-generation networks in supporting a large variety of compelling applications with challenging requirements. With its widely proved strength and successes, AI has to become an integral part of MEC. In this paper, we present a novel open-source edge AI (OpenEAI) framework that introduces a native AI plane into the recently proposed open-source MEC framework. The AI plane is designed based on two principles: decoupling the edge AI services into independent AI functions; and recomposing the independent edge AI functions into customized OpenEAI instances based on users{\textquoteright} specific requirements. Typical use cases of OpenEAI are characterized with the aid of a small-scale test network. Finally, we discuss the opportunities and challenges facing OpenEAI.",

keywords = "6G, Artificial Intelligence, Central Processing Unit, Data models, Edge AI, Graphics processing units, Hardware, Multi-access Edge Computing, Open Source, Training, Uniform resource locators, Virtualization",

author = "Liqiang Zhao and Yunfeng Wang and Xiaoli Chu and Shenghui Song and Yansha Deng and Arumugam Nallanathan and Karagiannidis, {George K.}",

note = "Publisher Copyright: IEEE",

year = "2024",

doi = "10.1109/MNET.2024.3411772",

language = "English",

pages = "1",

journal = "IEEE NETWORK",

issn = "0890-8044",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Open-Source Edge AI for 6G Wireless Networks

AU - Zhao, Liqiang

AU - Wang, Yunfeng

AU - Chu, Xiaoli

AU - Song, Shenghui

AU - Deng, Yansha

AU - Nallanathan, Arumugam

AU - Karagiannidis, George K.

N1 - Publisher Copyright: IEEE

PY - 2024

Y1 - 2024

N2 - Multi-access Edge Computing (MEC) has been recognized as a key enabler for next-generation networks in supporting a large variety of compelling applications with challenging requirements. With its widely proved strength and successes, AI has to become an integral part of MEC. In this paper, we present a novel open-source edge AI (OpenEAI) framework that introduces a native AI plane into the recently proposed open-source MEC framework. The AI plane is designed based on two principles: decoupling the edge AI services into independent AI functions; and recomposing the independent edge AI functions into customized OpenEAI instances based on users’ specific requirements. Typical use cases of OpenEAI are characterized with the aid of a small-scale test network. Finally, we discuss the opportunities and challenges facing OpenEAI.

AB - Multi-access Edge Computing (MEC) has been recognized as a key enabler for next-generation networks in supporting a large variety of compelling applications with challenging requirements. With its widely proved strength and successes, AI has to become an integral part of MEC. In this paper, we present a novel open-source edge AI (OpenEAI) framework that introduces a native AI plane into the recently proposed open-source MEC framework. The AI plane is designed based on two principles: decoupling the edge AI services into independent AI functions; and recomposing the independent edge AI functions into customized OpenEAI instances based on users’ specific requirements. Typical use cases of OpenEAI are characterized with the aid of a small-scale test network. Finally, we discuss the opportunities and challenges facing OpenEAI.

KW - 6G

KW - Artificial Intelligence

KW - Central Processing Unit

KW - Data models

KW - Edge AI

KW - Graphics processing units

KW - Hardware

KW - Multi-access Edge Computing

KW - Open Source

KW - Training

KW - Uniform resource locators

KW - Virtualization

UR - http://www.scopus.com/inward/record.url?scp=85196097047&partnerID=8YFLogxK

U2 - 10.1109/MNET.2024.3411772

DO - 10.1109/MNET.2024.3411772

M3 - Article

AN - SCOPUS:85196097047

SN - 0890-8044

SP - 1

JO - IEEE NETWORK

JF - IEEE NETWORK

ER -

Open-Source Edge AI for 6G Wireless Networks

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this