Abstract

This study aims to explore predictive scaling algorithms used to predict and manage workloads
in a containerized system. The goal is to identify which predictive scaling approach delivers the
most effective results, contributing to research on cloud elasticity and resource management.
This potentially leads to reduced infrastructure costs while maintaining efficient performance,
enabling a more sustainable cloud-computing technology. The work involved the development
and comparison of three different autoscaling algorithms with an interchangeable prediction
component. For the predictive part, three different time-series analysis methods were used:
XGBoost, ARIMA, and Prophet. A simulation system with the necessary modules was
developed, as well as a designated target service to experience the load. Each algorithm’s
scaling accuracy was evaluated by comparing its suggested number of instances to the optimal
number, with each instance representing a simulated CPU core. The results showed varying
efficiency: XGBoost and Prophet excelled with richer datasets, while ARIMA performed better
with limited data. Although XGBoost and Prophet maintained 100% uptime, this could lead to
resource wastage, whereas ARIMA’s lower uptime percentage possibly suggested a more
resource-efficient, though less reliable, approach. Further analysis, particularly experimental
investigation is required to deepen the understanding of these predictors’ influence on resource
allocation.