Ergodicity of Controlled Stochastic Nonlinear Systems under Information Constraints: Refined Bounds via Splitting

TL;DR

This paper refines the bounds on the minimum channel capacity needed to stabilize controlled stochastic nonlinear systems by focusing on unstable components, using stabilization entropy to improve existing theoretical limits.

Contribution

It introduces a refined lower bound on channel capacity for stabilizing systems with stable and unstable parts, focusing only on the unstable dimensions, advancing the theoretical understanding.

Findings

Lower bound on channel capacity considering only unstable dimensions

Refinement of existing bounds using stabilization entropy

Applicable to systems with decomposable stable and unstable components

Abstract

This paper considers the problem of stabilizing a discrete-time non-linear stochastic system over a finite capacity noiseless channel. Our focus is on systems which decompose into a stable and unstable component, and the stability notion considered is asymptotic ergodicity of the $\mathbb{R}^N$-valued state process. We establish a necessary lower bound on channel capacity for the existence of a coding and control policy which renders the closed-loop system stochastically stable. In the literature, it has been established that under technical assumptions, the channel capacity must not be smaller than the logarithm of the determinant of the system linearization, averaged over the noise and ergodic state measures. In this paper, we establish that for systems with a stable component, it suffices to consider only the unstable dimensions, providing a refinement on the general channel capacity bound for a large class of systems. The result is established using the notion of stabilization entropy, a notion adapted from invariance entropy, used in the study of noise-free systems under information constraints.