Resource Optimization for Tail-Based Control in Wireless Networked Control Systems

TL;DR

This work addresses resource optimization in Wireless Networked Control Systems by introducing tail-based stability, which relaxes classical stability to accommodate extreme state conditions. It proposes a three-component co-design—Lyapunov optimization for uplink scheduling, Gaussian Process Regression for missing-state prediction, and Reinforcement Learning for tail-based control—to decouple and solve the joint scheduling-prediction-control problem. Using Moore’s mountain car as a testbed, the framework achieves a 22% reduction in total cost compared with state-of-the-art baselines, highlighting significant gains in communication and control resource efficiency. The approach offers a practical pathway to maintain stability under tight resources and can be extended to heterogeneous systems and multi-antenna networks.

Abstract

Achieving control stability is one of the key design challenges of scalable Wireless Networked Control Systems (WNCS) under limited communication and computing resources. This paper explores the use of an alternative control concept defined as tail-based control, which extends the classical Linear Quadratic Regulator (LQR) cost function for multiple dynamic control systems over a shared wireless network. We cast the control of multiple control systems as a network-wide optimization problem and decouple it in terms of sensor scheduling, plant state prediction, and control policies. Toward this, we propose a solution consisting of a scheduling algorithm based on Lyapunov optimization for sensing, a mechanism based on Gaussian Process Regression (GPR) for state prediction and uncertainty estimation, and a control policy based on Reinforcement Learning (RL) to ensure tail-based control stability. A set of discrete time-invariant mountain car control systems is used to evaluate the proposed solution and is compared against four variants that use state-of-the-art scheduling, prediction, and control methods. The experimental results indicate that the proposed method yields 22% reduction in overall cost in terms of communication and control resource utilization compared to state-of-the-art methods.

Figures (3)

• Figure 1: An illustration of $M$ number of where sensor-controller communication takes place over a shared wireless network.
• Figure 2: RL convergence of the tail-based control and LQR problems.
• Figure 3: Performance of total cost, cost related to controlling, and cost related to stability per control system for different $M$.