Resource utilization forecasting for predictive autoscaling

Abstract

Certain aspects of the disclosure provide techniques for predictive autoscaling. A method includes determining resource utilization metrics for a plurality of instances of a service running in a container-based cluster for a plurality of timestamps over a period of time; applying a smoothing filter to the resource utilization metrics to obtain smoothed resource utilization metrics; adjusting each of the smoothed resource utilization metrics by a nominal value; calculating a plurality of ratio metrics for the smoothed resource utilization metrics; processing, with a machine learning (ML) model trained to perform resource utilization forecasting, the plurality of ratio metrics and to predict a future ratio metric for the service after a prediction time window; determining a future resource utilization for the service after the prediction time window based on the future ratio metric; and automatically adjusting configuration parameter(s) to modify a state of the container-based cluster based on the future resource utilization.