CAREER: Towards Networked Airborne Computing in Uncertain Airspace: A Control and Networking Facilitated Distributed Computing Framework

职业：走向不确定空域的网络机载计算：控制和网络促进的分布式计算框架

• 批准号: 2048266
• 负责人: Junfei Xie
• 金额: $ 55.67万
• 依托单位: San Diego State University Foundation
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-02-15 至 2026-01-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2048266&HistoricalAwards=false
• 关键词: CAREER; Towards; Networked; Airborne; Computing

Networked airborne computing is a new computing paradigm that relies on the airborne network formed by aerial vehicles with direct flight-to-flight communication links to achieve computing in the air. It can not only benefit a wide range of existing applications (e.g., drone show, precision agriculture and emergence response), but also give rise to a variety of new applications (e.g., next-generation air traffic control, Internet of Things and real-time 3-dimensional mapping). Despite the exciting applications, enabling networked airborne computing requires overcoming many formidable challenges such as 3-dimensional node mobility, highly uncertain operating environment and strict safety requirements. This project aims to develop an innovative theoretical framework that conquers these challenges to enable networked airborne computing. Unlike traditional mobile computing systems that treat mobility, uncertainty and communication as constraints for computing, the proposed framework exploits their benefits to facilitate robust, efficient and scalable computing in the uncertain, dynamic and heterogeneous airspace. The proposed framework, featured by fast response, resilience to uncertain disturbances and failures, scalability, and adaptivity to system and environmental changes, will advance the fundamental Computer and Network Systems (CNS) science and engineering on mobile computing and produce broader civilian and economic impacts related to unmanned systems based applications. The findings of this project will also contribute to fields such as distributed computing, stochastic optimal control, networking, real-time decision-making under uncertainty and experiment design. Innovative education and outreach activities (e.g., virtual lab modules, summer camps and internships) will produce a profound impact on the community and significantly benefit students, especially underrepresented minorities, at different levels in San Diego county and beyond. The proposed dissemination activities (e.g., workshops and tutorials) will further broaden the impact of the proposed research and benefit the general public.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.

网络机载计算是一种新的计算范式，它依赖于带有直接飞行飞行器通信链接的航空车形成的机载网络，以实现空气中的计算。它不仅可以使广泛的现有应用程序受益（例如，无人机展示，精密农业和出现响应），还可以带来各种新应用程序（例如，下一代空中交通控制，物联网和实时3维映射）。尽管应用了令人兴奋的应用程序，但启用网络机载计算仍需要克服许多艰巨的挑战，例如三维节点移动性，高度不确定的操作环境和严格的安全要求。该项目旨在开发一个创新的理论框架，以征服这些挑战以实现网络机载计算。与传统的移动计算系统不同，将移动性，不确定性和通信作为计算的限制不同，所提出的框架利用了其收益，以促进不确定，动态和异构空间中的稳健，高效且可扩展的计算。提出的框架具有快速响应，对不确定的干扰和失败的弹性，可伸缩性以及对系统和环境变化的适应性，将推动移动计算机上的基本计算机和网络系统（CNS）科学和工程，并产生与基于无人系统的应用程序有关的更广泛的平民和经济影响。该项目的发现还将有助于在不确定性和实验设计下进行分布式计算，随机最佳控制，网络，实时决策制定等领域。创新的教育和外展活动（例如，虚拟实验室模块，夏令营和实习）将对社区产生深远的影响，并在圣地亚哥县及以后的不同层次上对学生，尤其是代表性不足的少数群体受益。拟议的传播活动（例如，讲习班和教程）将进一步扩大拟议研究的影响，并使公众受益。该奖项反映了NSF的法定任务，并被认为是值得通过基金会的智力优点和更广泛的影响来通过评估来支持的。

项目成果

On Batch-Processing Based Coded Computing for Heterogeneous Distributed Computing Systems

• DOI: 10.1109/tnse.2021.3095040
• 发表时间: 2019-12
• 期刊: IEEE Transactions on Network Science and Engineering
• 影响因子: 6.6
• 作者: Baoqian Wang;Junfei Xie;K. Lu;Yan Wan;Shengli Fu

Joint Task Scheduling, Routing, and Charging for Multi-UAV Based Mobile Edge Computing

• DOI: 10.1109/icc45855.2022.9839040
• 发表时间: 2022-05
• 期刊: ICC 2022 - IEEE International Conference on Communications
• 作者: Jun Chen;Junfei Xie

CFL-HC: A Coded Federated Learning Framework for Heterogeneous Computing Scenarios

CFL-HC：异构计算场景的编码联邦学习框架

• DOI: 10.1109/globecom46510.2021.9685962
• 发表时间: 2021
• 期刊: 2021 IEEE Global Communications Conference (GLOBECOM
• 作者: Wang, Dong;Wang, Baoqian;Zhang, Jinran;Lu, Kejie;Xie, Junfei;Wan, Yan;Fu, Shengli
• 通讯作者: Fu, Shengli

Multi-Agent Reinforcement Learning Based Coded Computation for Mobile Ad Hoc Computing

• DOI: 10.1109/icc42927.2021.9500600
• 发表时间: 2021-04
• 期刊: ICC 2021 - IEEE International Conference on Communications
• 作者: Baoqian Wang;Junfei Xie;K. Lu;Yan Wan;Shengli Fu

An SDR-based LTE System for Unmanned Aerial Systems

用于无人机系统的基于 SDR 的 LTE 系统

• DOI: 10.1109/icuas54217.2022.9836117
• 发表时间: 2022
• 期刊: 2022 International Conference on Unmanned Aircraft Systems (ICUAS
• 作者: Zhang, Jinran;Wang, Baoqian;Wang, Dong;Fu, Shengli;Lu, Kejie;Wan, Yan;Xie, Junfei
• 通讯作者: Xie, Junfei