PROACTIVE IMPACT ANALYSIS IN A 5G TELCO NETWORK

1 . A method for impact assessment in a Telco network, comprising:

receiving, at an impact assessment engine, a scenario that specifies a symptom for a network resource, wherein the symptom describes a state of the network resource;

constructing failure signatures in a codebook matrix, wherein the codebook matrix correlates problems at impacted network resources to symptoms at other network resources;

generating synthetic failure signatures by identifying problems in the codebook matrix that include the symptom and network resource of the scenario;

isolating a subset of the synthetic failure signatures that meet a ranking threshold, wherein the failure signatures are ranked based on at least problem occurrence frequency; and

identifying, on a graphical user interface (“GUI”), potentially impacted tenants and services for the scenario, wherein the tenants and services correspond to the impacted network resources of the subset of synthetic failure signatures.

2 . The method of claim 1 , wherein generating synthetic failure signatures includes creating a correlation matrix of problems and symptoms based on columns from the codebook matrix that include the symptom of the scenario.

3 . The method of claim 2 , wherein isolating the subset includes:

determining that first and second problems do not exceed a threshold difference in problem occurrence frequency;

for each of the symptoms of the first and second problems, creating symptom counts that represent the number of times the symptom exists in the correlation matrix; and

for each of the first and second problems, creating problem sums by summing the symptom counts for symptoms corresponding to the problem; and

ranking the first and second problems based which has a highest problem sum.

4 . The method of claim 2 , wherein the correlation matrix is reduced by removing rows that represent no active symptoms.

5 . The method of claim 1 , wherein identifying tenants and services includes using a network topology graph to determine tenants and services that use the impacted network resources.

6 . The method of claim 1 , wherein the impacted tenants and services are identified in an alert on the GUI.

7 . The method of claim 1 , wherein the scenario and a maximum number of synthetic failure signatures are specified by inputs on the GUI, and wherein the ranking threshold of the isolated subset is based on the maximum number.

8 . A non-transitory, computer-readable medium comprising instructions that, when executed by a processor, perform stages for impact assessment in a Telco network, the stages comprising:

receiving, at an impact assessment engine, a scenario that specifies a symptom for a network resource, wherein the symptom describes a state of the network resource;

constructing failure signatures in a codebook matrix, wherein the codebook matrix correlates problems at impacted network resources to symptoms at other network resources;

generating synthetic failure signatures by identifying problems in the codebook matrix that include the symptom and network resource of the scenario;

isolating a subset of the synthetic failure signatures that meet a ranking threshold, wherein the failure signatures are ranked based on at least problem occurrence frequency; and

identifying, on a graphical user interface (“GUI”), potentially impacted tenants and services for the scenario, wherein the tenants and services correspond to the impacted network resources of the subset of synthetic failure signatures.

9 . The non-transitory, computer-readable medium of claim 8 , wherein generating synthetic failure signatures includes creating a correlation matrix of problems and symptoms based on columns from the codebook matrix that include the symptom of the scenario.

10 . The non-transitory, computer-readable medium of claim 9 , wherein isolating the subset includes:

determining that first and second problems do not exceed a threshold difference in problem occurrence frequency;

for each of the symptoms of the first and second problems, creating symptom counts that represent the number of times the symptom exists in the correlation matrix; and

for each of the first and second problems, creating problem sums by summing the symptom counts for symptoms corresponding to the problem; and

ranking the first and second problems based which has a highest problem sum.

11 . The non-transitory, computer-readable medium of claim 9 , wherein the correlation matrix is reduced by removing rows that represent no active symptoms.

12 . The non-transitory, computer-readable medium of claim 8 , wherein identifying tenants and services includes using a network topology graph to determine tenants and services that use the impacted network resources.

13 . The non-transitory, computer-readable medium of claim 8 , wherein the impacted tenants and services are identified in an alert on the GUI.

14 . The non-transitory, computer-readable medium of claim 8 , wherein the scenario and a maximum number of synthetic failure signatures are specified by inputs on the GUI, and wherein the ranking threshold of the isolated subset is based on the maximum number.

15 . A system for impact assessment in a Telco network, comprising:

a non-transitory, computer-readable medium containing instructions; and

a processor that executes the instructions perform stages comprising:

receiving, at an impact assessment engine, a scenario that specifies a symptom for a network resource, wherein the symptom describes a state of the network resource;

constructing failure signatures in a codebook matrix, wherein the codebook matrix correlates problems at impacted network resources to symptoms at other network resources;

generating synthetic failure signatures by identifying problems in the codebook matrix that include the symptom and network resource of the scenario;

isolating a subset of the synthetic failure signatures that meet a ranking threshold, wherein the failure signatures are ranked based on at least problem occurrence frequency; and

identifying, on a graphical user interface (“GUI”), potentially impacted tenants and services for the scenario, wherein the tenants and services correspond to the impacted network resources of the subset of synthetic failure signatures.

16 . The system of claim 15 , wherein generating synthetic failure signatures includes creating a correlation matrix of problems and symptoms based on columns from the codebook matrix that include the symptom of the scenario.

17 . The system of claim 16 , wherein isolating the subset includes:

determining that first and second problems do not exceed a threshold difference in problem occurrence frequency;

for each of the symptoms of the first and second problems, creating symptom counts that represent the number of times the symptom exists in the correlation matrix; and

for each of the first and second problems, creating problem sums by summing the symptom counts for symptoms corresponding to the problem; and

ranking the first and second problems based which has a highest problem sum.

18 . The system of claim 16 , wherein the correlation matrix is reduced by removing rows that represent no active symptoms.

19 . The system of claim 15 , wherein identifying tenants and services includes using a network topology graph to determine tenants and services that use the impacted network resources.

20 . The system of claim 15 , wherein the scenario and a maximum number of synthetic failure signatures are specified by inputs on the GUI, and wherein the ranking threshold of the isolated subset is based on the maximum number.