Failure influence estimation apparatus, failure influence estimation method and program

1. A failure effects estimating device, comprising:

an input unit configured to input a log and a traffic amount obtained from a communication system when an abnormality occurs;

an estimating unit, including one or more processors, configured to estimate a failure effects amount in the communication system, on the basis of the log and the traffic amount, wherein estimating the failure effects amount comprises:

(i) estimating, based on the log and the traffic amount, a failure effects time that represents a time length during which one or more user terminals are affected by abnormality occurring in the communication system,

(ii) estimating a traffic change amount that represents an amount of decrease in network traffic during the estimated failure effects time, and

(iii) estimating the failure effects amount, comprising: estimating a network index value as the failure effects amount based on the log and the estimated traffic change amount, wherein the network index value represents a round trip delay time (RTT) observed at user terminals receiving services; and

an output unit configured to output the failure effects amount estimated by the estimating unit.

2. The failure effects estimating device according to claim 1 , wherein

the estimating unit is configured to estimate the number of affected users as the failure effects amount, on the basis of the log and the traffic change amount, wherein the number of affected user represents the number of user terminals at which network throughput relating to services deteriorated by at least a predetermined threshold value at the user terminals.

3. The failure effects estimating device according to claim 1 , wherein

the estimating unit is a model trained by machine learning, on the basis of a past log, a past traffic amount, and a past failure effects amount.

4. A failure effects estimating method executed by a failure effects estimating device, the method comprising:

an input step of inputting a log and a traffic amount obtained from a communication system when an abnormality occurs;

an estimating step of estimating a failure effects amount in the communication system, on the basis of the log and the traffic amount, wherein estimating the failure effects amount comprises:

(i) estimating, based on the log and the traffic amount, a failure effects time that represents a time length during which one or more user terminals are affected by abnormality occurring in the communication system,

(ii) estimating a traffic change amount that represents an amount of decrease in network traffic during the estimated failure effects time, and

(iii) estimating the failure effects amount, comprising: estimating a network index value as the failure effects amount based on the log and the estimated traffic change amount wherein the network index value represents a round trip delay time (RTT) observed at user terminals receiving services; and

an output step of outputting the failure effects amount estimated in the estimating step.

5. The failure effects estimating method according to claim 4 , wherein the estimating step comprises:

estimating the number of affected users as the failure effects amount, on the basis of the log and the traffic change amount, wherein the number of affected user represents the number of user terminals at which network throughput relating to services deteriorated by at least a predetermined threshold value at the user terminals.

6. The failure effects estimating method according to claim 4 , wherein the estimating step comprises:

estimating the failure effects amount in the communication system using a model trained by machine learning, on the basis of a past log, a past traffic amount, and a past failure effects amount.

7. A non-transitory computer readable medium storing a program causing a computer to function as parts of a failure effects estimating device to perform:

an input step of inputting a log and a traffic amount obtained from a communication system when an abnormality occurs;

an estimating step of estimating a failure effects amount in the communication system, on the basis of the log and the traffic amount, wherein estimating the failure effects amount comprises:

(i) estimating, based on the log and the traffic amount, a failure effects time that represents a time length during which one or more user terminals are affected by abnormality occurring in the communication system,

(ii) estimating a traffic change amount that represents an amount of decrease in network traffic during the estimated failure effects time, and

(iii) estimating the failure effects amount, comprising: estimating a network index value as the failure effects amount based on the log and the estimated traffic change amount, wherein the network index value represents a round trip delay time (RTT) observed at user terminals receiving services; and

an output step of outputting the failure effects amount estimated in the estimating step.

8. The non-transitory computer readable medium according to claim 7 , wherein the estimating step comprises:

estimating the number of affected users as the failure effects amount, on the basis of the log and the traffic change amount, wherein the number of affected user represents the number of user terminals at which network throughput relating to services deteriorated by at least a predetermined threshold value at the user terminals.

9. The non-transitory computer readable medium according to claim 7 , wherein the estimating step comprises:

estimating the failure effects amount in the communication system using a model trained by machine learning, on the basis of a past log, a past traffic amount, and a past failure effects amount.