Three-three-three network architecture and learning optimization mechanism for B5G/6G

Aiming at the problem that the future B5G/6G network is a complex intelligent network with large connections, coupled with the comprehensive application of 3G, 4G, 5G and even 6G, the future networks will inevitably become extremely complex, a three-three-three network architecture was proposed that...

Mô tả đầy đủ

Chi tiết về thư mục
Những tác giả chính: Jinkang ZHU, Mingyang CHAI, Wuyang ZHOU
Định dạng: Bài viết
Ngôn ngữ:zho
Được phát hành: Editorial Department of Journal on Communications 2021-04-01
Loạt:Tongxin xuebao
Những chủ đề:
Truy cập trực tuyến:http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2021095/
Miêu tả
Tóm tắt:Aiming at the problem that the future B5G/6G network is a complex intelligent network with large connections, coupled with the comprehensive application of 3G, 4G, 5G and even 6G, the future networks will inevitably become extremely complex, a three-three-three network architecture was proposed that was a network that includes three types of networks (core network, access network and terminal network), three resources (frequency band, power and time consumptions) and three requirements (active, work and service), which was a three-dimensional comprehensive optimization system architecture, referred to as the three-three-three network.Furthermore, the mathematical basic formulas of the three-dimensional complex network were analyzed, the knowledge + data-driven learning model and the optimization method of intelligent processing using the knowledge learning mechanism were presented.Finally, the numerical example and reachable performance of the three-three-three network were given.Those results demonstrate that the proposed network architecture and the learning optimization mechanism are beneficial for designing future large-connected complex intelligent networks.
số ISSN:1000-436X