AI-Driven Next-Generation Edge Computing: Current and Future Trends
Al Ridhawi, Ismaeel Aloqaily, Moayad
Al Ridhawi, Ismaeel
Aloqaily, Moayad
Supervisor
Department
Machine Learning
Embargo End Date
Type
Journal article
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Traditional edge computing architectures envisioned for the Sixth Generation (6G) network cannot meet the ever-increasing task and processing demands of immersive services due to their limited ability to adapt to highly dynamic and resource-intensive scenarios. The absence of a robust Space-Air-Ground Integrated Network (SAGIN) framework in 6G for dynamic task allocation and resource management provides an obstacle to the realization of a true 6G network. In this article, we discuss some of the edge computing obstacles and challenges facing the provisioned upcoming 6G network and introduce a framework designed to optimize task and resource management in edge computing devices within SAGIN. The solution leverages contemporary technologies including metaverse-enabled Digital Twin (DT) and a plethora of Artificial Intelligence (AI) techniques that collectively enhance the adaptability, scalability, and computational efficiency of the network. The solution supports autonomous decision-making and coordination among distributed network entities, predict entity demands and network dynamics, facilitating real-time, proactive resource allocation, and optimize task offloading and load balancing by identifying efficient resource distribution paths across hierarchical network layers. Decentralized optimization and entity privacy preservation is maintained through Federated Learning (FL) and Blockchain. This work establishes a transformative pathway for the integration of the aforementioned technologies into 6G and lays the foundations for next-generation cooperative edge computing. © 1986-2012 IEEE.
Citation
I. A. Ridhawi and M. Aloqaily, "AI-Driven Next-Generation Edge Computing: Current and Future Trends," in IEEE Network, doi: 10.1109/MNET.2025.3580540
Source
IEEE Network
Conference
Keywords
6G, Agentic AI, Deep Learning, Digital Twin, Edge Computing, Federated Learning, Generative AI, Metaverse
Subjects
Source
Publisher
IEEE