International Journal of Leading Research Publication

E-ISSN: 2582-8010   •   Impact Factor: 9.56

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Call for Paper Volume 6 Issue 7 July 2025 Submit your research before last 3 days of to publish your research paper in the issue of July.
Submit Research Paper Join as a Reviewer

Plagiarism is checked by the leading plagiarism checker TurnItIn

Call for Paper

Volume 6 Issue 7
July 2025

Submit your research paper

Indexing Partners
Academia Advanced Sciences Index Bielefeld Academic Search Engine CiteSeer DRJI Google Scholar Independent Search Engine & Directory Network ISI (International Scientific Indexing) Issuu Mendeley Research Networks
RefSeek ResearcherId - Thomson Reuters ResearchGate Scirus Scribd Semantic Scholar UTeM - Universiti Teknikal Malaysia Melaka Wiki for Call for Papers WorldCat Zenodo

Reinforcement Learning Scheduler to Improve Kubernetes Performance and Scalability

Author(s) Kanagalakshmi Murugan
Country United States
Abstract Kubernetes is an open-source container orchestration platform designed to automate the deployment, scaling, and management of containerized applications. It provides a powerful and extensible architecture that enables organizations to run complex, distributed systems reliably and efficiently. One of the core components that drives Kubernetes' operational efficiency is its scheduler, which is responsible for assigning newly created pods to suitable nodes within a cluster. The Kubernetes scheduler plays a critical role in balancing workloads across the available resources to ensure performance, reliability, and optimal resource utilization. The default scheduler in Kubernetes, known as the kube-scheduler, follows a multi-step process to make scheduling decisions. First, it filters nodes based on resource requirements and constraints such as CPU, memory, affinity rules, taints, and tolerations. Once the set of feasible nodes is identified, a scoring mechanism is applied to rank these nodes. Factors such as resource balance, data locality, and pod affinity are taken into account. The node with the highest score is then selected, and the pod is bound to it. This decision-making process is designed to be pluggable, allowing custom schedulers or policy extensions to be added for more specific use cases. In such scenarios, alternative scheduling approaches are explored, including heuristics, constraint solvers, and increasingly, machine learning and reinforcement learning (RL) techniques. RL-based schedulers, for instance, learn optimal scheduling policies by interacting with the environment and receiving feedback in the form of rewards or penalties based on outcomes such as pod latency, resource utilization, or SLA compliance. RL-based schedulers can outperform traditional approaches by identifying non-obvious patterns and continuously evolving their policies based on operational data. Kubernetes scheduler is a foundational element of the platform that significantly influences application performance and cluster efficiency. With the growing complexity of containerized workloads, there is a clear need to explore intelligent scheduling mechanisms that go beyond rule-based methods. Reinforcement learning provides a promising direction for future innovation, enabling smarter and more adaptable scheduling strategies for next-generation Kubernetes deployments. This paper shows the perf improvement at scheduler.
Keywords Kubernetes, scheduler, containers, orchestration, deployment, clustering, scalability, latency, scheduling, automation, reinforcement, learning, optimization, resources, performance.
Published In Volume 3, Issue 5, May 2022
Published On 2022-05-06
Cite This Reinforcement Learning Scheduler to Improve Kubernetes Performance and Scalability - Kanagalakshmi Murugan - IJLRP Volume 3, Issue 5, May 2022. DOI 10.70528/IJLRP.v3.i5.1641
DOI https://doi.org/10.70528/IJLRP.v3.i5.1641
Short DOI https://doi.org/g9rv6t
View / Download PDF File

Share this



CrossRef

CrossRef DOI is assigned to each research paper published in our journal.

IJLRP DOI prefix is
10.70528/IJLRP

Downloads
Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 6 Isu 7 Cover Page Vol 6 Isu 6 Cover Page Vol 6 Isu 5

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA Open Access

About IJLRP
Fees & Payment
Current Issue
Publication Archive 		Submit Research Paper
Track Submission Status
Publication Guidelines
Publication Ethics
Peer Review & Plagiarism 		Join as a Reviewer
Editors & Reviewers
Reviewer Referral Program
Get Reviewer Membership Certi. 		Website/Journal Policies
Usage Policy
Content Policies
Privacy Policy
Contact Us +91-9687-828-838 editor@ijlrp.com