Predictive Control and Communication Co-Design via Two-Way Gaussian Process Regression and AoI-Aware Scheduling

TL;DR

This paper introduces a machine learning-based co-design of communication and control for wireless actuator networks, leveraging Gaussian process regression and AoI-aware scheduling to enhance stability and scalability.

Contribution

It proposes a novel joint optimization framework combining GPR-based prediction, AoI-aware scheduling, and power control to improve control stability and network efficiency.

Findings

Can control twice as many actuators compared to event-triggered baseline.

Achieves 18 times larger scale than round-robin scheduling.

Demonstrates stable control with reduced communication resources.

Abstract

This article studies the joint problem of uplink-downlink scheduling and power allocation for controlling a large number of actuators 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 a fraction of actuators is controlled, while the rest of the actuators 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 $2$x more number of actuators compared to an event-triggered scheduling baseline with Kalman filtering and frequency division multiple access, which is $18$x larger than a round-robin scheduling baseline.