arXivDaily arXiv每日学术速递 周一至周五更新
看起来今天可以划水了
arXiv 2011.03169cs.NI
收藏

无线网络的实时的控制

Real-Time Control over Wireless Networks

Venkata Prashant Modekurthy

摘要:

工业物联网(IIoT)正在大规模应用中越来越受欢迎,例如油田管理(例如,$74\times 8$ km $^2$ East Texas Oil-field)、智能农业、智能制造、智能电网和数据中心电源管理。这些应用要求无线堆栈提供可扩展、可靠、低功耗和低延迟的通信。为了在高度不可靠的无线环境中实现可预测和可靠的通信,工业无线标准使用集中式无线堆栈设计。在集中式无线堆栈设计中,中央管理器为基于多信道时分多址通信(TDMA)的媒体访问控制(MAC)生成路由和通信调度。然而,集中式无线堆栈设计是高能耗的,不可扩展的,并且不支持对网络或工作负载的频繁改变。为了应对这些挑战,本文做出了以下贡献:(2)本地和在线调度算法,其是可扩展的、节能的,并且支持网络/工作负载动态,同时确保可靠性和实时的【形】性能,(3)最小化多个低功率网络的带内集成的延迟的方法,(4)确定应用是否满足给定网络拓扑的实时的【形】性能要求的可扩展性的快速且有效的测试,以及(5)分布式调度和控制协同设计,其平衡工业物联网的控制性能要求和实时的【形】性能。

英文摘要:

Industrial internet of Things (IIoT) are gaining popularity for use in large-scale applications such as oil-field management (e.g., $74\times 8$km$^2$ East Texas Oil-field), smart farming, smart manufacturing, smart grid, and data center power management. These applications require the wireless stack to provide a scalable, reliable, low-power and low-latency communication. To realize a predictable and reliable communication in a highly unreliable wireless environment, industrial wireless standards use a centralized wireless stack design. In a centralized wireless stack design, a central manager generates routes and a communication schedule for a multi-channel time division multiple access communication (TDMA) based medium access control (MAC). However, a centralized wireless stack design is highly energy consuming, not scalable, and does not support frequent changes to networks or workloads. To address these challenges, the following contributions are made in this dissertation: (1) A scalable and distributed routing algorithm for industrial IoT which generates graph routes, which offer a high degree of redundancy, (2) A local and online scheduling algorithm that is scalable, energy-efficient, and supports network/workload dynamics while ensuring reliability and real-time performance, (3) An approach to minimize latency for in-band integration of multiple low-power networks, (4) A fast and efficient test of schedulability that determines if an application meets the real-time performance requirement for given network topology, and (5) A distributed scheduling and control co-design that balances the control performance requirement and real-time performance for industrial IoT.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑