Next Article in Journal
A Framework for Communication–Compute–Control Co-Design in Cyber–Physical Systems
Previous Article in Journal
Performance Comparison of Wired and Wireless Electrodermal Activity Sensors During a Simulated Port Approach Maneuver
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Electronics
Volume 14
Issue 5
10.3390/electronics14050863
electronics-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Optimizing Kubernetes Scheduling for Web Applications Using Machine Learning

by
Vedran Dakić
1,*,
Goran Đambić
2,*,
Jurica Slovinac
1 and
Jasmin Redžepagić
1
1
Department of System Engineering and Cybersecurity, Algebra University, 10000 Zagreb, Croatia
2
Department of Software Engineering, Algebra University, 10000 Zagreb, Croatia
*
Authors to whom correspondence should be addressed.
Electronics 2025, 14(5), 863; https://doi.org/10.3390/electronics14050863
Submission received: 16 December 2024 / Revised: 18 February 2025 / Accepted: 20 February 2025 / Published: 21 February 2025
Browse Figures
Versions Notes

Abstract

Machine learning (ML) has significantly enhanced computing and optimization, offering solutions to complex challenges. This paper investigates the development of a custom Kubernetes scheduler employing ML to optimize web application placement. A cluster of five nodes was established for evaluation, utilizing Python and TensorFlow to create and train a neural network that forecasts scheduling times for various configurations. The dataset, generated via scripts, encompassed multiple scenarios to ensure thorough model training. The results indicate that the custom scheduler with ML consistently surpasses the default Kubernetes scheduler in scheduling time by 1–18%, depending on the scenario. As expected, the difference between the built-in and ML-based scheduler becomes more evident with higher loads, underscoring opportunities for future research by using other ML algorithms and considering energy efficiency.
Keywords: Kubernetes; scheduler; machine learning; neural network; Tensorflow; performance; Python Kubernetes; scheduler; machine learning; neural network; Tensorflow; performance; Python

Share and Cite

MDPI and ACS Style

Dakić, V.; Đambić, G.; Slovinac, J.; Redžepagić, J. Optimizing Kubernetes Scheduling for Web Applications Using Machine Learning. Electronics 2025, 14, 863. https://doi.org/10.3390/electronics14050863

AMA Style

Dakić V, Đambić G, Slovinac J, Redžepagić J. Optimizing Kubernetes Scheduling for Web Applications Using Machine Learning. Electronics. 2025; 14(5):863. https://doi.org/10.3390/electronics14050863

Chicago/Turabian Style

Dakić, Vedran, Goran Đambić, Jurica Slovinac, and Jasmin Redžepagić. 2025. "Optimizing Kubernetes Scheduling for Web Applications Using Machine Learning" Electronics 14, no. 5: 863. https://doi.org/10.3390/electronics14050863

APA Style

Dakić, V., Đambić, G., Slovinac, J., & Redžepagić, J. (2025). Optimizing Kubernetes Scheduling for Web Applications Using Machine Learning. Electronics, 14(5), 863. https://doi.org/10.3390/electronics14050863

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop