Automatic failure recovery system, control device, procedure creation device, and computer-readable storage medium

A control device to be applied to an automatic failure recovery system that, using machine learning, creates an operation procedure for recovering from a network failure or corrects the created operation procedure, the control device comprising:

• at least one processor circuit with a memory comprising instructions, that when executed by the processor circuit, causes the processor circuit to at least:
• maintain a plurality of recovery tasks for recovering from the network failure;
• output failure data indicating network configuration information and failure information acquired upon occurrence of the network failure;
• and
• after an execution procedure of the recovery tasks that has been selected based on the failure data and a recovery model acquired in advance is executed, determine whether or not recovery from the network failure was achieved by the execution procedure,
• wherein, if the network is not capable of communication, a notification that an execution procedure that is next most probable, with respect to the execution procedure, is to be executed, is performed by the control device.

A procedure creation device to be applied to an automatic failure recovery system that, using machine learning, creates an operation procedure for recovering from a network failure or corrects the created operation procedure, the procedure creation device characterized by comprising:

• at least one processor circuit with a memory comprising instructions, that when executed by the processor circuit, causes the processor circuit to at least:
• select an execution procedure of a plurality of recovery tasks for recovering from the network failure, based on a recovery model acquired in advance and failure data indicating network configuration information and failure information acquired upon occurrence of the network failure;
• execute the selected execution procedure when the network failure occurs;
• and
• notify that the procedure is to be corrected, depending upon a recovery level of the network failure and the result of a determination as to whether or not recovery from the network failure was achieved by the execution procedure,
• wherein, if the network is not capable of communication, a notification that an execution procedure that is next most probable, with respect to the execution procedure, is to be executed, is received by the procedure creation device,
• the execution procedure that is next most probable, with respect to the execution procedure, is selected, and
• the selected execution procedure is executed.

A computer-readable storage medium storing a program to be executed by one or more processors of a control device to be applied to an automatic failure recovery system that, using machine learning, creates an operation procedure for recovering from a network failure or corrects the created operation procedure,

• wherein, when executed by the one or more processors, the program causes the control device to execute:
• processing for outputting failure data indicating network configuration information and failure information acquired upon occurrence of the network failure;
• and
• processing for, after an execution procedure of a plurality of recovery tasks for recovering from the network failure is executed, the execution procedure having been selected based on the failure data and a recovery model acquired in advance, determining whether or not recovery from the network failure was achieved by the execution procedure,
• wherein, if the network is not capable of communication, a notification that an execution procedure that is next most probable, with respect to the execution procedure, is to be executed, is received in the processing for determining.

A computer-readable storage medium storing a program to be executed by one or more processors of a procedure creation device to be applied to an automatic failure recovery system that, using machine learning, creates an operation procedure for recovering from a network failure or corrects the created operation procedure,

• wherein, when executed by the one or more processors, the program causes the procedure creation device to execute:
• processing for selecting an execution procedure of a plurality of recovery tasks for recovering from the network failure based on a recovery model acquired in advance and failure data indicating network configuration information and failure information acquired upon occurrence of the network failure;
• processing for executing the selected execution procedure when the network failure occurs;
• and
• processing for providing a notification that the procedure is to be corrected, depending upon a recovery level of the network failure and the result of a determination as to whether or not recovery from the network failure was achieved by the execution procedure,
• wherein, if the network is not ca able of communication, a notification that an execution procedure that is next most probable, with respect to the execution procedure, is to be executed, is provided in the processing for providing,
• the execution procedure that is next most probably, with respect to the executing procedure is selected in the processing for selecting, and
• the selected execution procedure is executed in the processing for executing.