Skip to main content

ORIGINAL RESEARCH article

Front. Comput. Sci.
Sec. Software
Volume 7 - 2025 | doi: 10.3389/fcomp.2025.1509165
This article is part of the Research Topic Machine Learning for Software Engineering View all 3 articles

Time Series Forecasting Based Kubernetes Autoscaler using Facebook Prophet and Long Short-Term Memory

Provisionally accepted
  • 1 University of Westminster, London, United Kingdom
  • 2 Kyoto University of Advanced Science (KUAS), Kyoto, Kyōto, Japan

The final, formatted version of the article will be published soon.

    The advancement of cloud computing technologies has increased the usage in application deployment in recent years. Kubernetes, a popular container orchestration platform for deploying applications on cloud systems, offers advantages such as autoscaling to meet the changing workload while keeping the quality of service and availability. In this research, we designed and evaluated a proactive Kubernetes autoscaler using Facebook Prophet and Long-Short Term Memory hybrid model to predict the HTTP requests and calculate required pod counts based on Monitor-Analyze-Plan-Execute loop. The proposed model not only captures seasonal data patterns effectively but also proactively predicts the pod requirements for timely and efficient resource allocation to reduce resource wastage while enhancing application performance in cloud computing applications. The proposed hybrid model was evaluated using real-world datasets from NASA and FIFA World Cup in order to benchmark and compare with existing literature. Evaluation results show that the proposed novel hybrid model outperforms single-model proactive autoscalers with a maximum margin of 65-90% accuracy against NASA and FIFA World Cup datasets. This work contributes to the areas of cloud computing and container orchestration by providing a refined proactive autoscaling mechanism that enhances application availability, efficient resource usage, and reduced costs and paves the way for further exploration in increased prediction speed, integrated with vertical scaling and implementations with Kubernetes.

    Keywords: Kubernetes, Proactive auto-scaling, LSTM, time series forecasting, Facebook Prophet, Kubernetes autoscaling

    Received: 10 Oct 2024; Accepted: 29 Jan 2025.

    Copyright: © 2025 Guruge and Yapa. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Pasan Bhanu Guruge, University of Westminster, London, United Kingdom

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.