Abstract
This article studies the joint problem of uplink-downlink scheduling and power allocation for controlling a large number of control systems that upload their states to remote controllers and download control actions over wireless links. To overcome the lack of wireless resources, we propose a machine learning-based solution, where only one control system is controlled, while the rest of the control systems are actuated by locally predicting the missing state and/or action information using the previous uplink and/or downlink receptions via a Gaussian process regression (GPR). This GPR prediction credibility is determined using the age-of-information (AoI) of the latest reception. Moreover, the successful reception is affected by the transmission power, mandating a co-design of the communication and control operations. To this end, we formulate a network-wide minimization problem of the average AoI and transmission power under communication reliability and control stability constraints. To solve the problem, we propose a dynamic control algorithm using the Lyapunov drift-plus-penalty optimization framework. Numerical results corroborate that the proposed algorithm can stably control <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$2\times$ </tex-math></inline-formula> more number of actuators compared to an event-triggered scheduling baseline with Kalman filtering and frequency division multiple access, which is <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$18\times$ </tex-math></inline-formula> larger than a round-robin scheduling baseline.
Highlights
U LTRA-RELIABLE and low-latency communication (URLLC) is a key enabler for ensuring the stability of Manuscript received January 27, 2021; revised June 5, 2021; accepted July 13, 2021
Control-aware scheduling in [22] carries out the scheduling decisions, based on communication reliability reflecting both control and channel states, thereby minimizing the overall transmission latency of the scheduled control systems. Motivated by these prior works and recent advances in machine learning, in this paper we aspire to further improve the scalability and communication efficiency of wireless networked control systems (WNCS) to support a larger number of control systems under limited wireless bandwidth and transmit power. To this end, departing from the existing methods [15]–[24] whose control operations and scheduling decisions are reactive to the current control stability and channel state information (CSI), we develop a predictive WNCS where the controller and each actuator locally predict their future states and actions, respectively, based on previously received data by individually running the Gaussian process regression (GPR) mechanisms at the controller and actuator, a Bayesian machine learning framework [25]
The results show that the proposed predictive control algorithm is more communication efficient while achieving faster control stability than the time-triggered and event-triggered control baselines, highlighting the effectiveness of the UL-DL decoupled scheduling and the use of two-way GPRs at both controller and actuator sides
Summary
U LTRA-RELIABLE and low-latency communication (URLLC) is a key enabler for ensuring the stability of Manuscript received January 27, 2021; revised June 5, 2021; accepted July 13, 2021. Date of publication July 26, 2021; date of current version October 18, 2021. 318927) and project SMARTER, projects EUICT IntellIoT and EUCHISTERA LearningEdge, and CONNECT, InfotechNOOR, and NEGEIN. This article was presented at the Proceedings of IEEE SPAWC-2020 [1]. The associate editor coordinating the review of this article and approving it for publication was S.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
