Graph-Based Evaluation of Structural Metrics and Simulated Performance in Synthetic Microservice Topologies

Graph representation aids the evaluation of microservice dependencies, yet a distinction is required between structural links and performance links that are enforced by simulator. A documented simulation experiment was conducted with 1,350 records from 450 synthetic architecture instances in three undirected topology families, five sizes (20–100 services), 30 seeds and three arrival rates. When the two parameters are computed, they satisfy the identity with no arbitrary constant. Average path length latency is related with r = 0.9994 and adjusted coefficient of 2.045 ms per SD (95% CI: 2.035 to 2.055). Confirming the additive model is that the latency follows 5(hops + 1). Based on a controlled experiment that used approximate edge matching, Scale-Free instances have the lowest latency for every size. The edge-adjusted advantage of Scale-Free instances over Clustered was between −1.70 and −2.97 ms (Holm p < 1e-10). The offered rate is tracked by the throughput; no saturation is established.

Authors

Institutions

Publication Details

Journal
Muthanna Journal of Engineering and Technology
Published
2026-11-06
DOI
https://doi.org/10.52113/3/eng/mjet/2026-14-04-/272-281
Primary Topic
Software System Performance and Reliability
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Graph-Based Evaluation of Structural Metrics and Simulated Performance in Synthetic Microservice Topologies

Abbas Ghaleb Talib
1 links
Muthanna Journal of Engineering and Technology
Software System Performance and Reliability
article

Graph-Based Evaluation of Structural Metrics and Simulated Performance in Synthetic Microservice Topologies

Abbas Ghaleb Talib
article en

Abstract

Graph representation aids the evaluation of microservice dependencies, yet a distinction is required between structural links and performance links that are enforced by simulator. A documented simulation experiment was conducted with 1,350 records from 450 synthetic architecture instances in three undirected topology families, five sizes (20–100 services), 30 seeds and three arrival rates. When the two parameters are computed, they satisfy the identity with no arbitrary constant. Average path length latency is related with r = 0.9994 and adjusted coefficient of 2.045 ms per SD (95% CI: 2.035 to 2.055). Confirming the additive model is that the latency follows 5(hops + 1). Based on a controlled experiment that used approximate edge matching, Scale-Free instances have the lowest latency for every size. The edge-adjusted advantage of Scale-Free instances over Clustered was between −1.70 and −2.97 ms (Holm p < 1e-10). The offered rate is tracked by the throughput; no saturation is established.

Muthanna Journal of Engineering and TechnologyVol. 14(04)
Islamic Azad University, Isfahan (IR), Al-Muthanna University (IQ), Islamic Azad University of Najafabad (IR)
Industry, innovation and infrastructure
Openalex Percentile: Top 16%
Software System Performance and Reliability
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon