CRII: CNS: Towards Robust RAN Slicing: Theories, Algorithms, and Applications

CRII：CNS：迈向稳健的 RAN 切片：理论、算法和应用

• 批准号: 2103405
• 负责人: Tu Nguyen
• 金额: $ 17.5万
• 依托单位: Kennesaw State University Research and Service Foundation
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-10-01 至 2024-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2103405&HistoricalAwards=false
• 关键词: CRII; CNS; Towards; Robust; RAN

With the rapid growth of new services and Internet applications, traditional cellular networks are now faced with a major challenge of supporting diverse applications. To address the various application demands, Radio Access Network (RAN) slicing has become one of the most promising architectural technologies for the forthcoming 5G era. RAN slicing allows the physical infrastructure resources to be shared across many RAN slices, with each slice built on top of the underlying physical RAN (substrate) is a separate logical network, which provides a set of services. Each RAN slice is constituted by various virtual network functions (VNFs) distributed geographically in numerous substrate nodes. Failures may occasionally arise from substrate. RAN configuration schemes for the network are imperative to relieve VNFs from substrate node failures (remapping/re-embedding VNFs onto live substrate nodes). This project aims to explore a new scheme and algorithms to enhance the robustness of RAN slicing by addressing the RAN configuration issue for slice recovery in a unified framework, referred to as RS-configuration. This project will build a theoretical and computational scheme that formalizes this insight and provides efficient and practical techniques for RAN slice recovery by mapping VNFs efficiently in the RAN slicing. This research program will also be integrated with education to develop new courses and a new series of case-study class modules in an advanced networking course as well as the design and analysis of algorithm courses at Kennesaw State University. Outreach programs through the university will be utilized to ensure the dissemination of the results. The PI will also release the implementation of the proposed scheme and algorithms in public domains. The goal of this project is to develop optimization models and methods for 1) establishing the theoretical foundation for using RS-configuration to construct a VNF mapping plan for RAN slice recovery optimization; 2) developing a new scheme and algorithms needed to map VNFs efficiently and finally 3) applying our theoretical and algorithmic development to investigate the robustness of RAN slicing and trade-offs between RAN slice recovery and RAN configuration in the RAN-related networking environment. Methodologies will be developed in the context of mathematical programing and graph theory that will help obtain more efficient and fast solutions performing within reasonable bounds of computational complexity. Hence, this research on new scheme and algorithms for RAN slicing will provide the computational basis towards building a robust RAN slicing and contribute to the development of new networking technologies.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

随着新业务和互联网应用的快速增长，传统蜂窝网络面临着支持多样化应用的重大挑战。为了满足各种应用需求，无线接入网络（RAN）切片已成为即将到来的5G时代最有前途的架构技术之一。 RAN 切片允许在多个 RAN 切片之间共享物理基础设施资源，每个切片构建在底层物理 RAN（底层）之上，是一个独立的逻辑网络，提供一组服务。每个 RAN 切片由分布在众多底层节点中的各种虚拟网络功能 (VNF) 构成。故障有时可能是由基板引起的。网络的 RAN 配置方案对于缓解 VNF 底层节点故障（将 VNF 重新映射/重新嵌入到活动底层节点上）至关重要。该项目旨在探索一种新的方案和算法，通过在统一框架（称为RS配置）中解决切片恢复的RAN配置问题来增强RAN切片的鲁棒性。该项目将构建一个理论和计算方案，将这一见解形式化，并通过在 RAN 切片中有效映射 VNF 来为 RAN 切片恢复提供高效且实用的技术。该研究计划还将与教育相结合，在肯尼索州立大学的高级网络课程以及算法课程的设计和分析中开发新课程和一系列新的案例研究课程模块。将利用大学的外展计划来确保成果的传播。 PI 还将在公共领域发布所提议方案和算法的实现。该项目的目标是开发优化模型和方法，以实现以下目的：1）为使用 RS 配置构建用于 RAN 切片恢复优化的 VNF 映射计划奠定理论基础； 2) 开发有效映射 VNF 所需的新方案和算法，最后 3) 应用我们的理论和算法开发来研究 RAN 切片的鲁棒性以及 RAN 相关网络环境中 RAN 切片恢复和 RAN 配置之间的权衡。将在数学编程和图论的背景下开发方法，这将有助于在计算复杂性的合理范围内获得更高效、更快速的解决方案。因此，这项关于 RAN 切片新方案和算法的研究将为构建强大的 RAN 切片提供计算基础，并有助于新网络技术的开发。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力价值和更广泛的影响审查标准。

项目成果

5G network slicing and drone-assisted applications: a deep reinforcement learning approach

5G网络切片和无人机辅助应用：深度强化学习方法

• DOI: 10.1145/3555661.3560873
• 发表时间: 2022-10
• 期刊: ACM MobiCom Conference: Proceedings of the 5th International ACM Mobicom Workshop on Drone Assisted Wireless Communications for 5G and Beyond
• 作者: Le, Linh;Nguyen, Tu N.;Suo, Kun;He, Jing
• 通讯作者: He, Jing

Entanglement Routing For Quantum Networks: A Deep Reinforcement Learning Approach

量子网络的纠缠路由：一种深度强化学习方法

• DOI: 10.1109/icc45855.2022.9839240
• 发表时间: 2022-05
• 期刊: ICC 2022 - IEEE International Conference on Communications
• 作者: Le, Linh;Nguyen, Tu N.;Lee, Ahyoung;Dumba, Braulio
• 通讯作者: Dumba, Braulio

Robust Efficient License Plate and Character Detection System Based on Simplified CNN

• DOI: 10.1145/3564746.3587108
• 发表时间: 2023-04-12
• 期刊: Proceedings of the 2023 ACM Southeast Conference
• 作者: Selena He;Tu N. Nguyen;Kun Suo
• 通讯作者: Kun Suo

Maximizing Key Distribution Capability: An Application in Quantum Cryptography

最大化密钥分发能力：量子密码学中的应用

• DOI: 10.1109/qce57702.2023.00134
• 发表时间: 2023-09-17
• 期刊: 2023 IEEE International Conference on Quantum Computing and Engineering (QCE)
• 作者: Tu N. Nguyen;Dung H. P. Nguyen;Manh V. Nguyen;Thinh V. Le;Bing;Thang N. Dinh
• 通讯作者: Thang N. Dinh

Towards Fidelity-Optimal Qubit Mapping on NISQ Computers

在 NISQ 计算机上实现保真度最优的量子位映射

• 发表时间: 2023-01
• 期刊: IEEE International Conference on Quantum Computing and Engineering (QCE
• 作者: Khandavilli, Sri;Palanisamy, Indu;Nguyen, Manh V.;Le, Thinh V.;Nguyen, Tu N.;Dinh, Thang N.
• 通讯作者: Dinh, Thang N.