Safe window for creating a firmware update package

1. An Information Handling System (IHS), comprising:

a processor; and

a memory coupled to the processor, the memory having program instructions stored thereon that, upon execution, cause the IHS to:

generate tokens based upon a log of historical firmware update package creation events;

identify a plurality of workflows based upon the tokens;

predict, based upon the plurality of workflows, a future workload of a firmware update package creation service; and

indicate, based upon the future workload, a time window for creating a firmware update package using the firmware update package creation service that increases a probability of successful creation.

2. The IHS of claim 1 , wherein the log comprises one or more operations performed by one or more software applications during an update package creation event and a time stamp for each operation.

3. The IHS of claim 2 , wherein to identify the plurality of workflows, the program instructions, upon execution, cause the IHS to create a hierarchical tree structure having nodes corresponding to a start and an end of each operation, and edges corresponding to a time taken to complete each respective operation.

4. The IHS of claim 3 , wherein to predict the future workload, the program instructions, upon execution, cause the IHS to use elements of the hierarchical tree structure as inputs into a neural network.

5. The IHS of claim 4 , wherein the neural network comprises a radial basis function neural network with unsupervised clustering.

6. The IHS of claim 4 , wherein the program instructions, upon execution, further cause the IHS to predict a workload for each of the software applications and an overall workload of the firmware update package creation service.

7. The IHS of claim 6 , wherein to indicate the time window, the program instructions, upon execution, further cause the IHS to arrange the predicted workloads into timelines and to identify the time window as having a lowest predicted aggregate workload.

8. The IHS of claim 1 , wherein the program instructions, upon execution, further cause the IHS to calculate a difference between the predicted future load with an actual future load and, in response to the difference being greater than a threshold value, re-train the neural network.

9. A memory storage device having program instructions stored thereon that, upon execution by one or more processors of an Information Handling System (IHS), cause the IHS to:

generate tokens based upon a log of historical firmware update package creation events;

identify a plurality of workflows based upon the tokens;

predict, based upon the plurality of workflows, a future workload of a firmware update package creation service; and

indicate, based upon the future workload, a time window for creating a firmware update package using the firmware update package creation service that increases a probability of successful creation.

10. The memory storage device of claim 9 , wherein the log comprises one or more operations performed by one or more software applications during an update package creation event and a time stamp for each operation.

11. The memory storage device of claim 10 , wherein to identify the plurality of workflows, the program instructions, upon execution, cause the IHS to create a hierarchical tree structure having nodes corresponding to a start and an end of each operation, and edges corresponding to a time taken to complete each respective operation.

12. The memory storage device of claim 11 , wherein to predict the future workload, the program instructions, upon execution, cause the IHS to use elements of the hierarchical tree structure as inputs into a neural network.

13. The memory storage device of claim 12 , wherein the program instructions, upon execution, cause the IHS to predict a workload for each of the software applications and an overall workload of the firmware update package creation service.

14. The memory storage device of claim 13 , wherein to indicate the time window, the program instructions, upon execution, further cause the IHS to arrange the predicted workloads into timelines and to identify the time window as having a lowest predicted aggregate workload.

15. A method, comprising:

generating tokens based upon a log of historical firmware update package creation events;

identifying a plurality of workflows based upon the tokens;

predicting, based upon the plurality of workflows, a future workload of a firmware update package creation service; and

indicating, based upon the future workload, a time window for creating a firmware update package using the firmware update package creation service that increases a probability of successful creation.

16. The method of claim 15 , wherein the log comprises one or more operations performed by one or more software applications during an update package creation event and a time stamp for each operation.

17. The method of claim 16 , wherein identifying the plurality of workflows, comprises creating a hierarchical tree structure having nodes corresponding to a start and an end of each operation, and edges corresponding to a time taken to complete each respective operation.

18. The method of claim 17 , wherein predicting the future workload comprises using elements of the hierarchical tree structure as inputs into a neural network.

19. The method of claim 18 , further comprising predicting a workload for each of the software applications and an overall workload of the firmware update package creation service.

20. The method of claim 19 , wherein indicating the time window comprises arranging the predicted workloads into timelines and to identify the time window as having a lowest predicted aggregate workload.