.png){kind=icon}
.png){kind=icon}
Return
AI-Driven Next-Generation Edge Computing: Current and Future Trends
.png){kind=icon}
PRE
AI
DOI：10.1109/MNET.2025.3580540.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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.
Keywords:
6G
Edge Computing
Metaverse
Digital Twin
Federated Learning
Generative AI
Agentic AI
Deep Learning
Journal
IF:
6.3
Papers:
2.6K
Citations:
1.1W