Disk failure prediction using machine learning

An apparatus comprising:

• a processing device operatively coupled to a memory and configured:
• to collect operational data of a plurality of disks;
• to identify at least one disk of the plurality of disks as failing based at least in part on a portion of the operational data associated with the at least one disk;
• to predict, using one or more machine learning algorithms, a time period when the at least one disk will remain operational based at least in part on the portion of the operational data associated with the at least one disk;
• and
• to execute an operation to write contents of the at least one disk on at least one replacement disk, wherein in executing the operation, the processing device is configured:
• to compare the predicted time period to a designated threshold time period;
• and
• to initiate the operation to write the contents of the at least one disk on the at least one replacement disk in response to the predicted time period being less than the designated threshold time period.

An article of manufacture comprising a non-transitory processor-readable storage medium having stored therein program code of one or more software programs, wherein the program code when executed by at least one processing device causes said at least one processing device to perform steps of:

• collecting operational data of a plurality of disks;
• identifying at least one disk of the plurality of disks as failing based at least in part on a portion of the operational data associated with the at least one disk;
• predicting, using one or more machine learning algorithms, a time period when the at least one disk will remain operational based at least in part on the portion of the operational data associated with the at least one disk;
• and
• executing an operation to write contents of the at least one disk on at least one replacement disk, wherein the executing comprises:
• comparing the predicted time period to a designated threshold time period;
• and
• initiating the operation to write the contents of the at least one disk on the at least one replacement disk in response to the predicted time period being less than the designated threshold time period.