Abstract
dc:description.abstractMicroservices are a fundamental component of modern distributed systems, enabling scalability, flexibility, and resilience. However, understanding and predicting the interactions between microservices, which evolve over time, remains a significant challenge. Traditional static models fail to capture the dynamic nature of these interactions, prompting the use of dynamic graph-based models, such as Graph Neural Networks (GNNs) and transformer-based architectures, for link prediction tasks. Despite their success, these models struggle with large-scale, temporal data and limited generalization capabilities. This research addresses these challenges by developing a diffusion-based model that incorporates advanced negative sampling and temporal graph representations. The goal is to enhance link prediction accuracy while maintaining scalability in real-world microservice networks. The study evaluates various predictive models, including Random Walk, GNNs, LSTMs, and Transformer Models, and explores the impact of time windowing strategies, dataset variations, and scalability. Additionally, the research investigates the feasibility of real-time predictions and the identification of recurring patterns in microservice interactions. Through extensive analysis and real-world case studies, this work contributes to the optimization of microservice systems by improving fault tolerance, resource allocation, and system efficiency.
Degree
thesis:*- Name thesis:degree_name
- M.Sc. Computer Science
- Level thesis:degree_level
- Master
- Discipline thesis:degree_discipline
- Faculty of Mathematics and Science
- Department dc:contributor.department
- Department of Computer Science
- Grantor dc:publisher
- Brock University
- Year dc:date.issued
- 2025
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Khodabandeh, Ghazal
- Advisor dc:contributor.advisor
-
- Ezzati-Jivan, Naser
Subjects
dc:subject × 2Rights
- Language dc:language.iso
- eng
Identifiers
dc:identifier.*- Handle dc:identifier.uri
- https://hdl.handle.net/10464/19596
- OAI identifier oai:identifier
- oai:brocku.scholaris.ca:10464/19596