Stochastic Stability of Discrete-time Phase-coupled Oscillators over Uncertain and Random Networks

TL;DR

This paper investigates the stochastic stability of discrete-time phase-coupled oscillators over uncertain networks, providing conditions for phase-cohesiveness and phase-locking under various stochastic uncertainties and network models.

Contribution

It introduces new sufficient conditions for stochastic phase-cohesiveness and phase-locking in uncertain oscillator networks, including those with Bernoulli-based uncertainties.

Findings

Conditions for stochastic phase-cohesiveness in in-phase and anti-phase sets.

Phase-locking occurs with positive probability in Erdős-Rényi networks.

Analytical results are validated through numerical simulations.

Abstract

This article studies stochastic relative phase stability, i.e., stochastic phase-cohesiveness, of discrete-time phase-coupled oscillators. Stochastic phase-cohesiveness in two types of networks is studied. First, we consider oscillators coupled with 2{\pi}-periodic odd functions over underlying undirected graphs subject to both multiplicative and additive stochastic uncertainties. We prove stochastic phase-cohesiveness of the network with respect to two specific, namely in-phase and anti-phase, sets by deriving sufficient coupling conditions. We show the dependency of these conditions on the size of the mean values of additive and multiplicative uncertainties, as well as the sign of the mean values of multiplicative uncertainties. Furthermore, we discuss the results under a relaxation of the odd property of the coupling function. Second, we study an uncertain network in which the multiplicative uncertainties are governed by the Bernoulli process representing the well-known Erdos-Renyi network. We assume constant exogenous frequencies and derive sufficient conditions for achieving both stochastic phase-cohesive and phase-locked solutions, i.e., stochastic phase-cohesiveness with respect to the origin. For the latter case, where identical exogenous frequencies are assumed, we prove that any positive probability of connectivity leads to phase-locking. Thorough analyses are provided, and insights obtained from stochastic analysis are discussed, along with numerical simulations to validate the analytical results.