{"id":{"repo_id":"vilnius","oai_identifier":"oai:vu.lt:elaba:308338902"},"canonical_url":"https://search.ndltd.org/etd/vilnius/oai:vu.lt:elaba:308338902","repository":{"repo_id":"vilnius","name":"Vilnius University","base_url":"https://epublications.vu.lt/oai"},"display":{"title":"Dirbtinio intelekto modeliais grįstas Kubernetes išteklių valdymas /","abstract":"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.","abstract_html":"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.","abstract_has_math":false,"creators":["Šilingas, Marius,"],"institution":"Institutional Repository of Vilnius University","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026","date_published":"2026","updated_at":"2026-11-19T10:12:59Z","subjects":[],"languages":["lit"],"rights":["info:eu-repo/semantics/openAccess"],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://repository.vu.lt/VU:ELABAETD308338902&prefLang=en_US","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://repository.vu.lt/VU:ELABAETD308338902&prefLang=en_US","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":"open","embargo_until":null,"access_note":null},"source_record":{"url":"https://epublications.vu.lt/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai%3Avu.lt%3Aelaba%3A308338902","prefix":"oai_dc"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Šilingas, Marius,"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2026"]},{"key":"dc:publisher","label":"Institution","values":["Institutional Repository of Vilnius University"]},{"key":"dc:relation","label":"Dc Relation","values":["https://epublications.vu.lt/object/elaba:308338902/308338902.pdf"]},{"key":"dc:type","label":"Dc Type","values":["info:eu-repo/semantics/bachelorThesis"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["lit"]},{"key":"dc:rights","label":"Dc Rights","values":["info:eu-repo/semantics/openAccess"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://repository.vu.lt/VU:ELABAETD308338902&prefLang=en_US"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["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."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Dirbtinio intelekto modeliais grįstas Kubernetes išteklių valdymas /","Kubernetes resource management based on artificial intelligence models."]}]}],"canonical_facts":{"dc:creator":["Šilingas, Marius,"],"dc:date":["2026"],"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."],"dc:format":["application/pdf"],"dc:identifier":["https://repository.vu.lt/VU:ELABAETD308338902&prefLang=en_US"],"dc:language":["lit"],"dc:publisher":["Institutional Repository of Vilnius University"],"dc:relation":["https://epublications.vu.lt/object/elaba:308338902/308338902.pdf"],"dc:rights":["info:eu-repo/semantics/openAccess"],"dc:title":["Dirbtinio intelekto modeliais grįstas Kubernetes išteklių valdymas /","Kubernetes resource management based on artificial intelligence models."],"dc:type":["info:eu-repo/semantics/bachelorThesis"]},"updated_at":"2026-11-19T10:12:59Z"}