基於基礎模型與聯邦學習賦能無線接入網智慧控制器人工智慧
Abstract
This project focuses on advancing Radio Access Network (RAN) intelligent controllers through the integration of foundation models and federated learning techniques. The research aims to develop AI-enabled systems that can efficiently manage and optimize wireless network resources while maintaining data privacy and security. Key areas of investigation include foundation model adaptation for telecommunications, federated learning protocols for distributed RAN optimization, and intelligent resource allocation algorithms. The proposed framework will enable RAN controllers to learn from distributed network data without compromising privacy, supporting next-generation wireless communication systems including 5G and beyond. This research contributes to the development of more intelligent, adaptive, and efficient wireless networks capable of handling the increasing complexity and demands of modern telecommunications infrastructure.