CNS Core: Small: Application-Oriented Scheduling for Optimizing Information Freshness in Wireless Networks

CNS 核心：小型：面向应用的调度，用于优化无线网络中的信息新鲜度

• 批准号: 2008092
• 负责人: Yu Cheng
• 金额: $ 42.05万
• 依托单位: Illinois Institute of Technology
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-10-01 至 2024-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2008092&HistoricalAwards=false
• 关键词: CNS; Core; Small; Application; Oriented

The significant advancement in wireless networking technologies as well as the proliferation of mobile devices have enabled information-centric Internet of Things (IoT) systems, where timely information updating is normally required or preferred by users. Age of Information (AoI) has recently been introduced to quantify the freshness of the knowledge the controller has about the remote information sources. While AoI is information-centric, in the present state of the art, the evaluation of information freshness has been conducted mainly in a transmission-centric manner. This project aims to bridge the gap between transmission-level information freshness and application-level decision making by revealing involved fundamental research issues, developing generic modeling tools, and generating effective network protocols in some important practical scenarios. This proposed research integrates theoretical studies in the areas of wireless networking, optimization theory, control theory, information theory, and machine learning. Such an interdisciplinary project will not only provide various training projects to undergraduate and graduate students, but also inspire students to pursue high-quality research with a creative and open-minded perspective. Information freshness based wireless scheduling algorithms are of critical importance to next generation wireless networks and mobile applications, with a good potential to be transformed into practical solutions.The proposed research is expected to contribute to innovative information freshness optimization techniques with some fundamental intellectual merits. This study is to show that optimizing information freshness from an application-oriented angle (that is, incorporating user query patterns, correlations across different information sources, or cooperative decision-making among distributed agents) requires brand-new modeling/analysis techniques. Effective decomposition techniques and low-complexity algorithms for information freshness optimization are to be developed through predicting user query patterns and incorporating delay-tolerant responses at the application level. When multiple correlated information sources present, a fundamental obstacle to information freshness optimization is the lack of a well-defined application-level freshness metric; this issue will be tackled. Moreover, it is to be demonstrated that the intricacies raised by the correlations can be addressed efficiently through integrating domain knowledge and deep reinforcement learning techniques. With recent studies confirming the inadequacy of CSMA-based scheduling in terms of freshness optimization, a decentralized TDMA-based medium access control (MAC) protocol is to be developed and mathematically analyzed. Such a new MAC protocol is expected to provision quantitative information freshness guarantee in the scenario of multi-agent decision making; the outcome in this part hopefully can contribute an important component for freshness-oriented network design in the system level.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.

无线联网技术的显著进步以及移动的设备的激增已经实现了以信息为中心的物联网（IoT）系统，其中用户通常需要或偏好及时的信息更新。信息时代（AoI）最近被引入以量化控制器具有的关于远程信息源的知识的新鲜度。虽然AoI是以信息为中心的，但在现有技术中，信息新鲜度的评估主要以传输为中心的方式进行。该项目旨在通过揭示所涉及的基础研究问题，开发通用建模工具，并在一些重要的实际场景中生成有效的网络协议，来弥合传输级信息新鲜度和应用级决策之间的差距。这项研究整合了无线网络、优化理论、控制理论、信息论和机器学习等领域的理论研究。这样一个跨学科的项目不仅将为本科生和研究生提供各种培训项目，还将激励学生以创造性和开放的视角追求高质量的研究。基于信息新鲜度的无线调度算法对于下一代无线网络和移动的应用具有重要意义，具有很好的应用前景，本文的研究将为信息新鲜度优化技术的创新提供理论基础。这项研究表明，优化信息新鲜度从面向应用的角度（即，将用户查询模式，不同的信息源之间的相关性，或分布式代理之间的合作决策）需要全新的建模/分析技术。有效的分解技术和低复杂度的信息新鲜度优化算法是通过预测用户的查询模式，并在应用程序级的延迟容忍响应。当存在多个相关信息源时，信息新鲜度优化的一个根本障碍是缺乏定义良好的应用程序级新鲜度度量;这个问题将得到解决。此外，还需要证明的是，通过整合领域知识和深度强化学习技术，可以有效地解决相关性带来的复杂性。随着最近的研究证实CSMA为基础的调度在新鲜度优化方面的不足，一个分散的基于TDMA的媒体访问控制（MAC）协议的开发和数学分析。这样一个新的MAC协议，预计将提供定量的信息新鲜度保证的情况下，多智能体的决策，在这一部分的成果，希望可以有助于新鲜度为导向的网络设计的重要组成部分，在系统level.This奖项反映了NSF的法定使命，并已被认为是值得通过评估使用基金会的智力价值和更广泛的影响审查标准的支持。

项目成果

A Self-Supervised Learning Approach for Accelerating Wireless Network Optimization

• DOI: 10.1109/tvt.2023.3244043
• 发表时间: 2023-06
• 期刊: IEEE Transactions on Vehicular Technology
• 影响因子: 6.8
• 作者: Shuai Zhang;O. Ajayi;Yu-long Cheng

Machine Learning Assisted Capacity Optimization for B5G/6G Integrated Access and Backhaul Networks

• DOI: 10.1109/infocomwkshps57453.2023.10225946
• 发表时间: 2023-05
• 期刊: IEEE INFOCOM 2023 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)
• 作者: O. Ajayi;Shuai Zhang;Yu-long Cheng

Age of Local Information for Fusion Freshness in Internet of Things

• DOI: 10.1109/iccc57788.2023.10233592
• 发表时间: 2023-08
• 期刊: 2023 IEEE/CIC International Conference on Communications in China (ICCC)
• 作者: Taige Chang;Xianghui Cao;Y. Cheng

Deep Reinforcement Learning for Scheduling in Multi-Hop Wireless Networks : Invited Paper

• DOI: 10.1109/mass52906.2021.00010
• 发表时间: 2021-10
• 期刊: 2021 IEEE 18th International Conference on Mobile Ad Hoc and Smart Systems (MASS)
• 作者: Shuai Zhang;Bo Yin;Yu Cheng

Optimal Sleep Scheduling for Energy-Efficient AoI Optimization in Industrial Internet of Things

• DOI: 10.1109/jiot.2023.3234582
• 发表时间: 2023-06
• 期刊: IEEE Internet of Things Journal
• 影响因子: 10.6
• 作者: Xianghui Cao;Jia Wang;Yu Cheng;Jiong Jin