Statistical learning for analysis of networked control systems over unknown channels

DOI10.1016/J.AUTOMATICA.2020.109386MaRDI QIDQ2663884zbMATH OpenOpenAlexFDO

Authors Konstantinos Gatsis, George Pappas

Publication date 20 April 2021

Published in Automatica (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1911.03422

zbMATH Keywords

communication channelslearning algorithmsnetworked control systemsstability analysisstatistical analysis

Mathematics Subject Classification ID

Applications of statistics in engineering and industry; control charts (62P30) Networked control (93B70) Lyapunov and other classical stabilities (Lagrange, Poisson, (L^p, l^p), etc.) in control theory (93D05)

Abstract: Recent control trends are increasingly relying on communication networks and wireless channels to close the loop for Internet-of-Things applications. Traditionally these approaches are model-based, i.e., assuming a network or channel model they are focused on stability analysis and appropriate controller designs. However the availability of such wireless channel modeling is fundamentally challenging in practice as channels are typically unknown a priori and only available through data samples. In this work we aim to develop algorithms that rely on channel sample data to determine the stability and performance of networked control tasks. In this regard our work is the first to characterize the amount of channel modeling that is required to answer such a question. Specifically we examine how many channel data samples are required in order to answer with high confidence whether a given networked control system is stable or not. This analysis is based on the notion of sample complexity from the learning literature and is facilitated by concentration inequalities. Moreover we establish a direct relation between the sample complexity and the networked system stability margin, i.e., the underlying packet success rate of the channel and the spectral radius of the dynamics of the control system. This illustrates that it becomes impractical to verify stability under a large range of plant and channel configurations. We validate our theoretical results in numerical simulations.

Recommendations

• Analysis and design of networked control systems
• Stability analysis of stochastic networked control systems
• Improved sample complexity estimates for statistical learning control of uncertain systems
• On the model-based control of networked systems
• Design of Information Channels for Optimization and Stabilization in Networked Control

Cites work

• Advanced Lectures on Machine Learning
• Control Under Communication Constraints
• Decentralized Event-Triggered Control Over Wireless Sensor/Actuator Networks
• Deep reinforcement learning for wireless sensor scheduling in cyber-physical systems
• Dynamic programming and optimal control. Vol. 2
• scientific article; zbMATH DE number 2136426 (Why is no real title available?)
• Learning in Wireless Control Systems Over Nonstationary Channels
• On Kalman filtering over fading wireless channels with controlled transmission powers
• Opportunistic Control Over Shared Wireless Channels
• Optimal Power Management in Wireless Control Systems
• Probability. Theory and examples.
• The Necessity and Sufficiency of Anytime Capacity for Stabilization of a Linear System Over a Noisy Communication Link—Part I: Scalar Systems

Cited in

(3)

• Separation of learning and control for cyber-physical systems
• Learning for Decision and Control in Stochastic Networks
• Thompson sampling for networked control over unknown channels

This page was built for publication: Statistical learning for analysis of networked control systems over unknown channels

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2663884)