inputting Self-Monitoring, Analysis, and Reporting Technology (SMART) data of the storage device obtained in real time, into each of a plurality of base classification models;

obtaining a plurality of classification results from the plurality of base classification models, for the SMART data of the storage device, wherein each of the plurality of base classification models is obtained by training using at least one of historical SMART data of a plurality of storage devices or SMART data of the plurality of storage devices obtained through a network;

determining whether the SMART data of the storage device obtained in real time indicates healthy data or erroneous data, based on the plurality of classification results of the plurality of base classification models; and

predicting whether the storage device will fail, based on a number of SMART data that is determined as the healthy data and a number of SMART data that is determined as the erroneous data among SMART data of the storage device obtained within a predetermined time window.