Back to search

Institutional Repository of Vilnius University

Dirbtinio intelekto modeliais grįstas Kubernetes išteklių valdymas /

Abstract

dc:description

The main objective of this bachelor work is to analyze unexpected load and cold start problems in Kubernetes clusters. Traditional tools of managing pod resources and its replicas count HPA and VPA are working reactively and manages resources only when load appears. In order to solve this problem, machine learning frameworks LightGBM and XGBoost models are used, which are predicting replica count based on historical data: those predictions are being automatically integrated into Kubernetes cluster’s configuration. By using metrics monitoring system Prometheus resource management of each model are being analyzed which model uses CPU and memory less. By analysing results of each model, it is clear that both models are using 20% less of CPU and memory resources and also increases replica count 1 minute earlier compared to HPA. Also, when comparing model to each other it is clear that XGBoost based model uses less resources, but the response rate of HTTP requests and p95 latency are bigger than LightGBM based model.

Degree

thesis:*
Grantor dc:publisher
Institutional Repository of Vilnius University
Year dc:date
2026

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Šilingas, Marius,

Rights

dc:rights
Statement dc:rights
  • info:eu-repo/semantics/openAccess
Language dc:language
lit

Identifiers

dc:identifier.*

Chain of custody

source
Harvested from
Vilnius University
Base URL
epublications.vu.lt/oai
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
related terms
citation

Šilingas, Marius,. Dirbtinio intelekto modeliais grįstas Kubernetes išteklių valdymas /. Institutional Repository of Vilnius University, 2026. https://repository.vu.lt/VU:ELABAETD308338902&prefLang=en_US