Method and system for predicting and mitigating failures in VDI system

1. A method for predicting and mitigating failures in Virtual Desktop Infrastructure (VDI) systems, the method comprising:

receiving, by a computing system, a plurality of system logs from a plurality of VDI systems;

segregating, by the computing system, one or more error logs from the plurality of system logs;

generating, by the computing system, a prediction score for each of the plurality of VDI systems based on respective one or more error logs, using a machine learning model, wherein the prediction score of a VDI system among the plurality of VDI systems is indicative of a possible failure in the VDI system, wherein the machine learning model is trained by performing steps of:

receiving a plurality of feature vectors associated with a plurality of training error logs and one or more rules; and

determining a failure in the plurality of VDI systems and a value associated with the plurality of training error logs, based on the plurality of feature vectors and the one or more rules;

determining a correlation between the one or more rules, the determined failure and the plurality of feature vectors to train the machine learning model;

wherein the trained machine learning model is used to predict failures in the plurality of VDI systems in real-time;

predicting, by the computing system, a failure in at least one VDI system from the plurality of VDI systems based on the prediction score of the at least one VDI system and the respective one or more error logs using the trained machine learning model; and

determining, by the computing system, at least one response action associated with the predicted failure, thereby mitigating the failure in the plurality of VDI systems.

2. The method of claim 1 , wherein segregating the one or more error logs from the plurality of system logs comprises:

parsing the plurality of system logs into a structured data sequence;

identifying the one or more error logs by comparing the structured data sequence with a VDI data repository comprising the plurality of training error logs;

segregating the one or more error logs from the plurality of system logs.

3. The method of claim 1 , wherein the one or more error logs is aggregated in a time-sequence format based on a timestamp associated with the one or more error logs.

4. The method of claim 1 , wherein generating the prediction score comprises:

comparing the one or more error logs with a VDI data repository based at least on a plurality of predetermined thresholds;

generating the prediction score based on the comparison.

5. The method of claim 4 , wherein the prediction score represents a probability of occurrence of the failure.

6. The method of claim 1 , wherein the training further comprises providing state data of software services and hardware assets associated with the plurality of VDI systems.

7. The method of claim 1 , wherein the at least one response action associated with the predicted failure is determined from a plurality of response actions in a VDI data repository.

8. The method of claim 1 , wherein the at least one response action is based on a severity level of at least one of, the predicted failure and a root cause of the predicted failure.

9. The method of claim 8 , wherein the root cause of the predicted failure is determined based on one or more historical failure points.

10. A computing system for predicting and mitigating failures in Virtual Desktop Infrastructure (VDI) systems, the computing system comprising:

one or more processors; and

a memory, wherein the memory stores processor-executable instructions, which, on execution, cause the one or more processors to:

receive a plurality of system logs from a plurality of VDI systems;

segregate one or more error logs from the plurality of system logs;

generate a prediction score for each of the plurality of VDI systems based on respective one or more error logs, using a machine learning model, wherein the prediction score of a VDI system among the plurality of VDI systems is indicative of a possible failure in the VDI system, wherein the machine learning model is trained by performing steps of:

receiving a plurality of feature vectors associated with a plurality of training error logs and one or more rules; and

determining a failure and a value associated with the plurality of training error logs in the plurality of VDI systems, based on the plurality of feature vectors and the one or more rules;

determining a correlation between the one or more rules, the determined failure and the plurality of feature vectors to train the machine learning model;

wherein the trained machine learning model is used to predict failures in the plurality of VDI systems in real-time;

predict a failure in at least one VDI system from the plurality of VDI systems based on the prediction score of the at least one VDI system and the respective one or more error logs using the trained machine learning model; and

determine at least one response action associated with the predicted failure, thereby mitigating the failure in the plurality of VDI systems.

11. The computing system of claim 10 , wherein the one or more processors segregates the one or more error logs from the plurality of system logs by:

parsing the plurality of system logs into a structured data sequence;

identifying the one or more error logs by comparing the structured data sequence with a VDI data repository comprising the plurality of training error logs;

segregating the one or more error logs from the plurality of system logs.

12. The computing system of claim 10 , wherein the one or more processors aggregates the one or more error logs in a time-sequence format based on a timestamp associated with the one or more error logs.

13. The computing system of claim 10 , wherein the one or more processors generates the prediction score by:

comparing the one or more error logs with a VDI data repository based at least on a plurality of predetermined thresholds;

generating the prediction score based on the comparison.

14. The computing system of claim 10 , wherein the training further comprises providing state data of software services and hardware assets associated with the plurality of VDI systems.

15. The computing system of claim 10 , wherein the one or more processors determines the at least one response action associated with the predicted failure from a plurality of response actions in a VDI data repository.

16. The computing system of claim 10 , wherein the at least one response action is based on a severity level of at least one of, the predicted failure and a root cause of the predicted failure.

17. The computing system of claim 16 , wherein the root cause of the predicted failure is determined based on one or more historical failure points.

18. A non-transitory computer readable medium including instructions stored thereon that when processed by one or more processors, wherein the instructions cause a computing system to:

receive a plurality of system logs from a plurality of VDI systems;

segregate one or more error logs from the plurality of system logs;

generate a prediction score for each of the plurality of VDI systems based on respective one or more error logs, using a machine learning model, wherein the prediction score of a VDI system among the plurality of VDI systems is indicative of a possible failure in the VDI system, wherein the machine learning model is trained by performing steps of:

receiving a plurality of feature vectors associated with a plurality of training error logs and one or more rules; and

determining a failure and a value associated with the plurality of training error logs in the plurality of VDI systems, based on the plurality of feature vectors and the one or more rules;

determining a correlation between the one or more rules, the determined failure and the plurality of feature vectors to train the machine learning model;

wherein the trained machine learning model is used to predict failures in the plurality of VDI systems in real-time;

predict a failure in at least one VDI system from the plurality of VDI systems based on the prediction score of the at least one VDI system and the respective one or more error logs using the trained machine learning model; and

determine at least one response action associated with the predicted failure, thereby mitigating the failure in the plurality of VDI systems.

19. The medium of claim 18 , wherein the one or more processors segregates the one or more error logs from the plurality of system logs by:

parsing the plurality of system logs into a structured data sequence;

identifying the one or more error logs by comparing the structured data sequence with a VDI data repository comprising the plurality of training error logs;

segregating the one or more error logs from the plurality of system logs.

20. The medium of claim 18 , wherein the one or more processors aggregates the one or more error logs in a time-sequence format based on a timestamp associated with the one or more error logs.

21. The medium of claim 18 , wherein the one or more processors generates the prediction score by:

comparing the one or more error logs with a VDI data repository based at least on a plurality of predetermined thresholds;

generating the prediction score based on the comparison.

22. The medium of claim 18 , wherein the training further comprises providing state data of software services and hardware assets associated with the plurality of VDI systems.

23. The medium of claim 18 , wherein the one or more processors determines the at least one response action associated with the predicted failure from a plurality of response actions in a VDI data repository.

24. The medium of claim 18 , wherein the at least one response action is based on a severity level of at least one of, the predicted failure and a root cause of the predicted failure.

25. The medium of claim 24 , wherein the root cause of the predicted failure is determined based on one or more historical failure points.