Collaborative Research: CCRI: New: Open AI Cellular (OAIC): Prototyping Artificial Intelligence-Enabled Control and Testing Systems for Cellular Communications Research

合作研究：CCRI：新：开放人工智能蜂窝 (OAIC)：为蜂窝通信研究构建人工智能控制和测试系统原型

• 批准号: 2120442
• 负责人: Vuk Marojevic
• 金额: $ 84.35万
• 依托单位: Mississippi State University
• 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=2120442&HistoricalAwards=false
• 关键词: Collaborative; Research; CCRI; New; Open

This collaborative project brings together investigators from Mississippi State University (MSU) and Virginia Tech (VT) to develop a software infrastructure that spurs research and development on artificial intelligence (AI)-enabled cellular radio networks. The main contribution is Open AI Cellular (OAIC), the first fully open-source software architecture, library, and toolset that encompass both the AI controllers (OAIC-C) as well as an AI testing framework (OAIC-T) for enabling research on 6G Open Radio Access Networks. This project puts the U.S. in the leading position of research, development, and testing of AI-enhanced cellular networks, initiated and organized by a group of academics and their collaborators and maintained by the wireless research community. The project (1) specifies the methodology along with the technical requirements, a reference architecture and design to facilitate collaborative software development; (2) designs and develops the fundamental OAIC-C software library for common software-defined radio (SDR) platforms; (3) facilitates systematic and exhaustive testing with the OAIC-T framework on community wireless research testbeds that are accessible to researchers; (4) develops verification tools and resources to facilitate rapid prototyping and testing as well as offers a variety of user services, such as mailing lists, code repositories, and learning material; and (5) implements a variety of community engagement and outreach processes, including the organization of workshops to engage with and leverage the community for long-term maintenance and sustainability.OAIC enhances lecture material by introducing hands-on laboratory sessions at MSU, VT, and collaborating universities. Industry, standardization bodies, and regulators are regularly informed about OAIC resources and projects, which can be leveraged for determining important standardization and regulatory decisions related to 6G. Other US agencies will be able to leverage OAIC and the community around it to develop AI-enhanced cellular technology and systems for purposes such as transportation and smart grid applications. The code repositories, documentation, and other material are maintained by the OAIC team with contributions from the research community. The project website (https://sites.google.com/msstate.edu/oaic) consolidates the OAIC project information and provides links to all project deliverables and related resources. The project repository/website maintenance is planned for several years beyond the initial project timeline through the community ecosystem and follow-up projects.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.

这个合作项目汇集了来自密西西比州立大学（MSU）和弗吉尼亚理工大学（VT）的研究人员，以开发一个软件基础设施，促进人工智能（AI）蜂窝无线电网络的研究和开发。主要贡献是开放AI蜂窝（OAIC），这是第一个完全开源的软件架构，库和工具集，包括AI控制器（OAIC-C）以及AI测试框架（OAIC-T），用于支持6 G开放无线电接入网络的研究。该项目使美国在人工智能增强型蜂窝网络的研究、开发和测试方面处于领先地位，该项目由一群学者及其合作者发起和组织，并由无线研究界维护。该项目（1）规定了方法沿着技术要求、参考体系结构和设计，以促进协作软件开发;（2）设计和开发用于通用软件定义无线电（SDR）平台的基本OAIC-C软件库;（3）促进在社区无线研究测试平台上使用OAIC-T框架进行系统和详尽的测试，研究人员可以使用这些测试平台;（4）开发验证工具和资源，以促进快速原型设计和测试，并提供各种用户服务，如邮件列表、代码库和学习材料;和（5）实施各种社区参与和外展流程，包括组织研讨会，以长期参与和利用社区-OAIC通过在MSU，VT和合作大学引入实践实验室课程来增强讲座材料。行业、标准化机构和监管机构定期了解OAIC的资源和项目，这些资源和项目可用于确定与6 G相关的重要标准化和监管决策。其他美国机构将能够利用OAIC及其周围的社区开发用于交通和智能电网应用等目的的AI增强型蜂窝技术和系统。代码存储库、文档和其他材料由OAIC团队维护，并由研究社区提供。项目网站（https：//sites.google.com/msstate.edu/oaic）整合了独立审计办公室的项目信息，并提供了所有项目交付成果和相关资源的链接。项目库/网站维护计划在最初项目时间轴之后的几年内通过社区生态系统和后续项目进行。该奖项反映了NSF的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

O-RAN Perspective on Industrial Internet of Things: A SWOT Analysis

• DOI: 10.1109/icit58465.2023.10143032
• 发表时间: 2023-04
• 期刊: 2023 IEEE International Conference on Industrial Technology (ICIT)
• 作者: T. Rahman;Minglong Zhang;V. Marojevic

Actor-Critic Network for O-RAN Resource Allocation: xApp Design, Deployment, and Analysis

用于 O-RAN 资源分配的 Actor-Critic 网络：xApp 设计、部署和分析

• DOI: 10.1109/gcwkshps56602.2022.10008713
• 发表时间: 2022
• 期刊: 2022 IEEE Globecom Workshops (GC Wkshps
• 作者: Kouchaki, Mohammadreza;Marojevic, Vuk
• 通讯作者: Marojevic, Vuk

Toward Secure and Efficient O-RAN Deployments: Secure Slicing xApp Use Case

实现安全高效的 O-RAN 部署：安全切片 xApp 用例

• 发表时间: 2023
• 期刊: IEEE Future Networks World Forum (FNWF
• 作者: Moore, Joshua;Adhikari, Nisha;Abdalla, Aly S.;Marojevic, Vuk
• 通讯作者: Marojevic, Vuk

AI Testing Framework for Next-G O-RAN Networks: Requirements, Design, and Research Opportunities

Next-G O-RAN 网络的人工智能测试框架：要求、设计和研究机会

• DOI: 10.1109/mwc.001.2200213
• 发表时间: 2023
• 期刊: IEEE Wireless Communications
• 影响因子: 12.9
• 作者: Tang, Bo;Shah, Vijay K.;Marojevic, Vuk;Reed, Jeffrey H.
• 通讯作者: Reed, Jeffrey H.

Deep Q-Network for 5G NR Downlink Scheduling

• DOI: 10.1109/iccworkshops53468.2022.9814547
• 发表时间: 2022-05
• 期刊: 2022 IEEE International Conference on Communications Workshops (ICC Workshops)
• 作者: Walaa AlQwider;T. Rahman;V. Marojevic