2019/06/14 by Mark Eisen, Mohammad Mamunur Rashid, Eisen, Mark +5 · 1 citation
Computer Science · Engineering · #Advanced Wireless Network Optimization #Age of Information Optimization #FOS: Electrical engineering #Signal Processing (eess.SP) #Stability and Control of Uncertain Systems #Systems and Control (eess.SY) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1906.06225
openalex publication_date 2019/06/14 · openalex created_date 2022/07/28 · openalex updated_date 2026/07/28
We consider the problem of scheduling transmissions over low-latency wireless\ncommunication links to control various control systems. Low-latency\nrequirements are critical in developing wireless technology for industrial\ncontrol and Tactile Internet, but are inherently challenging to meet while also\nmaintaining reliable performance. An alternative to ultra reliable low latency\ncommunications is a framework in which reliability is adapted to control system\ndemands. We formulate the control-aware scheduling problem as a constrained\nstatistical optimization problem in which the optimal scheduler is a function\nof current control and channel states. The scheduler is parameterized with a\ndeep neural network, and the constrained problem is solved using techniques\nfrom primal-dual learning, which have a necessary model-free property in that\nthey do not require explicit knowledge of channels models, performance metrics,\nor system dynamics to execute. The resulting control-aware deep scheduler is\nevaluated in empirical simulations and strong performance is shown relative to\nother model-free heuristic scheduling methods.\n