Cross-Domain AI Towards 6G: Requirements, Solution, and Validation | |
---|---|
Author | |
Abstract |
With the continuous enrichment of intelligent applications, it is anticipated that 6G will evolve into a ubiquitous intelligent network. In order to achieve the vision of full-scenarios intelligent services, how to collaborate AI capabilities in different domains is an urgent issue. After analyzing potential use cases and technological requirements, this paper proposes an endto-end (E2E) cross-domain artificial intelligence (AI) collaboration framework for next-generation mobile communication systems. Two potential technical solutions, namely cross-domain AI management and orchestration and RAN-CN convergence, are presented to facilitate intelligent collaboration in both E2E scenarios and the edge network. Furthermore, we have validated the performance of a cross-domain federated learning algorithm in a simulated environment for the prediction of received signal power. While ensuring the security and privacy of terminal data, we have analyzed the communication overhead caused by cross-domain training. |
Year of Publication |
2024
|
Date Published |
may
|
URL |
https://ieeexplore.ieee.org/document/10592394
|
DOI |
10.1109/IWCMC61514.2024.10592394
|
Google Scholar | BibTeX | DOI |