Regions of Attraction Estimation using Level SetMethod for Complex Network System

TL;DR

This paper introduces a novel approach using Level Set Methods to estimate the Region of Attraction in complex, dynamic network systems, enabling better stability control through topology adjustments.

Contribution

It applies Level Set Methods to high-dimensional, dynamic network systems to estimate ROA, advancing stability analysis beyond linearized models.

Findings

ROA can be estimated using Level Set Methods in complex networks.

Network topology influences the size of the ROA.

Controlling local network degree can preserve stability.

Abstract

Many complex engineering systems network together functional elements and balance demand loads (e.g.information on data networks, electric power on grids). This allows load spikes to be shifted and avoid a local overload. In mobile wireless networks, base stations(BSs) receive data demand and shift high loads to neighbouring BSs to avoid the outage. The stability of cascade load balancing is important because unstable networks can cause high inefficiency. The research challenge is to prove the stability conditions for any arbitrarily large, complex, and dynamic network topology, and for any balancing dynamic function. Our previous work has proven the conditions for stability for stationary networks near equilibrium for any load balancing dynamic and topology. Most current analyses in dynamic complex networks linearize the system around the fixed equilibrium solutions. This approach is insufficient for dynamic networks with changing equilibrium and estimating the Region of Attraction(ROA) is needed. The novelty of this paper is that we compress this high-dimensional system and use Level Set Methods (LSM) to estimate the ROA. Our results show how we can control the ROA via network topology (local degree control) as a way to configure the mobility of transceivers to ensure the preservation of stable load balancing.