Determine recovery mechanism in a storage system by training a machine learning module

摘要

A machine learning module receives inputs comprising attributes of a storage controller, where the attributes affect failures that occur in the storage controller. In response to a failure occurring in the storage controller, a plurality of output values corresponding to a plurality of recovery mechanisms to recover from the failure in the storage controller are generated via forward propagation through a plurality of layers of the machine learning module. A margin of error is calculated based on comparing the generated output values to expected output values corresponding to the plurality of recovery mechanisms, where the expected output values are generated from an indication of a correct recovery mechanism for the failure. An adjustment is made of weights of links that interconnect nodes of the plurality of layers via back propagation to reduce the margin of error, to improve a determination of a recovery mechanism for the failure.