A Survey on the Network Models applied in the Industrial Network Optimization

TL;DR

This survey reviews various network models used in industrial network optimization, analyzing their mathematical properties and introducing a novel performance metric called system entropy for comprehensive network comparison.

Contribution

It summarizes existing graph theory-based network modeling methods and proposes a new general performance metric applicable across different network types.

Findings

System entropy covers regular, random, small-world, and scale-free networks.

Simulation shows system entropy effectively compares diverse industrial networks.

Mathematical analysis confirms desirable properties of the new metric.

Abstract

Network architecture design is very important for the optimization of industrial networks. The type of network architecture can be divided into small-scale network and large-scale network according to its scale. Graph theory is an efficient mathematical tool for network topology modeling. For small-scale networks, its structure often has regular topology. For large-scale networks, the existing research mainly focuses on the random characteristics of network nodes and edges. Recently, popular models include random networks, small-world networks and scale-free networks. Starting from the scale of network, this survey summarizes and analyzes the network modeling methods based on graph theory and the practical application in industrial scenarios. Furthermore, this survey proposes a novel network performance metric - system entropy. From the perspective of mathematical properties, the analysis of its non-negativity, monotonicity and concave-convexity is given. The advantage of system entropy is that it can cover the existing regular network, random network, small-world network and scale-free network, and has strong generality. The simulation results show that this metric can realize the comparison of various industrial networks under different models.