Optimizing radio cell quality for capacity and quality of service using machine learning techniques

1. A method for optimizing a radio access network, the method comprising steps of:

receiving at least one area of the radio access network to be analyzed from a user and receiving a desired outcome from a user;

identifying a plurality of network monitoring parameters related to a user requested analysis including user data and control plane data;

correlating the identified plurality of network monitoring parameters;

performing a root cause analysis using an automated classification model based on the correlated plurality of network monitoring parameters;

generating a recommendation related to the desired outcome based on the performed root cause analysis;

confirming with the user one or more aspects of the recommendation via a Graphical User Interface (GUI) which confirmation includes repeating the performance of the root cause analysis based upon a user entered numerical value indicative of the user's percentage certainty of the performed root cause analysis; and

updating the generated recommendation based upon the user confirmation and wherein the generated recommendation includes a confidence factor of a root cause by combining corresponding individual probabilities of preconditions.

2. The method of claim 1 , wherein the automated classification model comprises at least one of a Bayesian network model and an expert system model, wherein the Bayesian network model is a machine-learned Bayesian network with a seed for training the Bayesian network model provided from an expert in a network domain and wherein the seed represents relationships between the plurality of network monitoring parameters.

3. The method of claim 2 , wherein the step of performing the root cause analysis includes calculating confidence probability.

4. The method of claim 3 , wherein the generated recommendation includes the calculated confidence probability.

5. The method of claim 2 , wherein the automated classification model comprises one or more decision trees.

6. The method of claim 2 , wherein the expert system model comprises a rules based model having a plurality of rules based on knowledge developed from one or more experts relating to interpreting values of the identified plurality of network monitoring parameters with respect to the desired outcome.

7. The method of claim 1 , further comprising storing the correlated network monitoring parameters in a data repository.

8. The method of claim 1 , further comprising automatically adjusting configuration of the radio access network based on the generated recommendation.

9. A system for optimizing a radio access network, the system comprising:

a processor and a memory device coupled to the processor, the memory device containing a set of instructions that, when executed by the processor, cause the processor to:

receive at least one area of the radio access network to be analyzed from a user and receive a desired outcome from a user;

identify a plurality of network monitoring parameters related to a user requested analysis including user data and control plane data;

correlate the identified plurality of network monitoring parameters;

perform a root cause analysis using an automated classification model based on the correlated plurality of network monitoring parameters;

generate a recommendation related to the desired outcome based on the performed root cause analysis;

confirm with the user one or more aspects of the recommendation via a Graphical User Interface (GUI) which confirmation includes repeating the performance of the root cause analysis based upon a user entered numerical value indicative of the the user's percentage certainty of the performed root cause analysis; and

update the generated recommendation based upon the user confirmation and wherein the generated recommendation includes a confidence factor of a root cause by combining corresponding individual probabilities of preconditions.

10. The system of claim 9 , wherein the automated classification model comprises at least one of a Bayesian network model and an expert system model, wherein the Bayesian network model is a machine-learned Bayesian network with a seed for training the Bayesian network model provided from an expert in a network domain and wherein the seed represents relationships between the plurality of network monitoring parameters.

11. The system of claim 10 , wherein the set of instructions to perform the root cause analysis that, when executed by the processor, further cause the processor to calculate confidence probability.

12. The system of claim 11 , wherein the generated recommendation includes the calculated confidence probability.

13. The system of claim 10 , wherein the automated classification model comprises one or more decision trees.

14. The system of claim 9 , wherein the set of instructions that, when executed by the processor, further cause the processor to store the correlated network monitoring parameters in a data repository.

15. The system of claim 9 , wherein the set of instructions that, when executed by the processor, further cause the processor to automatically adjust configuration of the radio access network based on the generated recommendation.

16. The system of claim 10 , wherein the expert system model comprises a rules based model having a plurality of rules based on knowledge developed from one or more experts relating to interpreting values of the identified plurality of network monitoring parameters with respect to the desired outcome.

17. A tangible, non-transitory, computer-readable media having software encoded thereon, the software, when executed by a processor, operable to:

receive at least one area of the radio access network to be analyzed from a user and receive a desired outcome from a user;

identify a plurality of network monitoring parameters related to a user requested analysis including user data and control plane data;

correlate the identified plurality of network monitoring parameters;

perform a root cause analysis using an automated classification model based on the correlated plurality of network monitoring parameters;

generate a recommendation related to the desired outcome based on the performed root cause analysis;

confirm with the user one or more aspects of the recommendation via a Graphical User Interface (GUI) which confirmation includes repeating the performance of the root cause analysis based upon a user entered numerical value indicative of the the user's percentage certainty of the performed root cause analysis; and

update the generated recommendation based upon the user confirmation and wherein the generated recommendation includes a confidence factor of a root cause by combining corresponding individual probabilities of preconditions.

18. The computer-readable media of claim 17 , wherein the automated classification model comprises at least one of a Bayesian network model and an expert system model, wherein the Bayesian network model is a machine-learned Bayesian network with a seed for training the Bayesian network model provided from an expert in a network domain and wherein the seed represents relationships between the plurality of network monitoring parameters.

19. The computer-readable media of claim 18 , wherein the software to perform the root cause analysis that, when executed by the processor, operable to calculate confidence probability.

20. The computer-readable media of claim 19 , wherein the generated recommendation includes the calculated confidence probability.