Scalable capacity forecasting in storage systems using a machine learning model

Abstract

Methods, apparatus, and processor-readable storage media for scalable capacity forecasting in storage systems using a machine learning model are provided herein. An example computer-implemented method includes obtaining historical capacity data for storage objects; partitioning the obtained data into categories, wherein at least a first category comprises data from storage objects associated with a first capacity-related condition, and at least a second category comprises data from storage objects associated with a second capacity-related condition different than the first capacity-related condition; selecting a time series sequence of a designated time interval, and labeling, accordingly, portions of the data in the first category and portions of the data in the second category; training a machine learning model using the labeled data; performing capacity forecasting by processing input capacity data for at least one of the storage objects using the machine learning model; and performing automated actions based on results of the capacity forecasting.