LQ-GNN: A Graph Neural Network Model for Response Time Prediction of Microservice-Based Applications in the Computing Continuum

To address the challenges posed by the deployment of microservices of future end-user applications in the cloud continuum, a performance prediction model working together with a network elasticity controller will be needed. With that aim, this work introduces Layered Queuing-Graph Neural Networks (L...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on parallel and distributed systems Vol. 36; no. 12; pp. 2566 - 2577
Main Authors: Richart, Matias, Gorricho, Juan-Luis, Baliosian, Javier, Contreras, Luis M., Muniz, Alejandro, Serrat, Joan
Format: Journal Article
Language:English
Published: IEEE 01.12.2025
Subjects:
Cloud computing
Computational modeling
Computing continuum
Elasticity
Graph neural networks
Machine learning
Microservice architectures
microservice-based applications
Predictive models
Quality of service
Resource management
Time factors
ISSN:1045-9219, 1558-2183
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:To address the challenges posed by the deployment of microservices of future end-user applications in the cloud continuum, a performance prediction model working together with a network elasticity controller will be needed. With that aim, this work introduces Layered Queuing-Graph Neural Networks (LQ-GNN), a novel Machine Learning (ML) approach to develop a generalized performance prediction model for microservice-based applications. Unlike previous works focused on individual applications, our proposal aims for a versatile model applicable to any microservice-based application, integrating the Layered Queueing Network (LQN) modeling with Graph Neural Networks (GNN). LQ-GNN allows to efficiently estimate the response time of applications under different resource allocations and placements on the computing continuum. The obtained evaluation results indicate that the proposed model achieves a prediction error below 10% when considering different evaluation scenarios. Compared to existing methodologies, our approach balances prediction accuracy and computational efficiency, making it viable for real-time deployments. Consequently, ML-based performance prediction can significantly enhance the resource management and elasticity control of microservice-based architectures, leading to more resilient and efficient systems.
ISSN:1045-9219
1558-2183
DOI:10.1109/TPDS.2025.3564214