CPU Usage Forecasting for Load Balancing in Kubernetes Using LSTM: A Synthetic Traffic Simulation Approach

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Kubernetes offers automatic scaling; however, the accuracy of predicting resource requirements remains a challenge in dynamic workload environments. This research proposes LSTM to predict CPU usage in real-time on Kubernetes. The dataset was obtained from e-commerce server logs, and a distribution that identified the beta distribution as the best choice (AIC & BIC). Synthetic data based on the Beta distribution is then simulated using k6, resulting in a time series of CPU usages. The results show that LSTM outperforms ARIMA and GRU with the lowest MSE (0.00001053) and RMSE (0.00324451). The proposed approach can enhance resource allocation efficiency and application stability, as well as provide opportunities to develop real-time workload predictions for more adaptive auto-scaling on Kubernetes.

Original languageEnglish
Title of host publicationProceedings of the 2025 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology, IAICT 2025
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages277-282
Number of pages6
ISBN (Electronic)9798331586492
DOIs
Publication statusPublished - 2025
Event2025 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology, IAICT 2025 - Hybrid, Bali, Indonesia
Duration: 3 Jul 20255 Jul 2025

Publication series

NameProceedings of the 2025 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology, IAICT 2025

Conference

Conference2025 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology, IAICT 2025
Country/TerritoryIndonesia
CityHybrid, Bali
Period3/07/255/07/25

Keywords

  • CPU usage
  • Kubernetes
  • LSTM
  • and Beta distribution
  • auto-scaling
  • workload prediction

Fingerprint

Dive into the research topics of 'CPU Usage Forecasting for Load Balancing in Kubernetes Using LSTM: A Synthetic Traffic Simulation Approach'. Together they form a unique fingerprint.

Cite this