Hybrid complex network topologies are preferred for component-subscription in large-scale data-centres

TL;DR

This study investigates how hybrid complex network topologies, combining small-world and scale-free features, influence the robustness and scalability of large-scale data-centres, revealing that hybrid configurations outperform pure types.

Contribution

It introduces the use of the Klemm-Eguiliz model to generate hybrid network topologies and demonstrates their superior performance in data-centre robustness and scaling.

Findings

Hybrid network topologies yield better system performance.

Pure small-world or scale-free networks are less optimal.

Hybrid configurations significantly improve robustness and scalability.

Abstract

We report on experiments exploring the interplay between the topology of the complex network of dependent components in a large-scale data-centre, and the robustness and scaling properties of that data-centre. In a previous paper [1] we used the SPECI large-scale data-centre simulator [2] to compare the robustness and scaling characteristics of data-centres whose dependent components are connected via Strogatz-Watts small-world (SW) networks [3], versus those organized as Barabasi-Albert scale-free (SF) networks [4], and found significant differences. In this paper, we present results from using the Klemm-Eguiliz (KE) construction method [5] to generate complex network topologies for data-centre component dependencies. The KE model has a control parameter {\mu}\in[0,1]\inR that determines whether the networks generated are SW (0<{\mu}<<1) or SF ({\mu}=1) or a "hybrid" network topology part-way between SW and SF (0<{\mu}<1). We find that the best scores for system-level performance metrics of the simulated data-centres are given by "hybrid" values of {\mu} significantly different from pure-SW or pure-SF.