Association rule analysis and data visualization for mobile networks

Abstract

Embodiments are provided for using association rule mining to analyze performance counters of a mobile network, including converting a plurality of performance counters of a mobile network into a plurality of key performance indicators (KPIs), quantizing each KPI into one value of a set of values associated with that KPI, creating a set of items having multiple subsets corresponding to respective KPIs, where each item of a subset corresponds to a respective value of a particular set of values associated with a particular KPI, and generating association rules based, at least in part, on the set of items. In further embodiments, the quantizing the plurality of KPIs includes quantizing a first KPI into a first value of a set of three or more values associated with the first KPI.

1 . A method comprising:
 selecting, via the one or more processors, performance counters of a network;   converting, via the one or more processors, the performance counters into key performance indicators (KPIs);   creating, via the one or more processors, a representation of the KPIs;   applying mining logic to the representation to generate rules; and   generating, via a display, a report based on the rules to enable analysis of the network.   
     
     
         2 . The method of  claim 1 , further comprising:
 quantizing each of the KPIs into one of a set of values, the quantizing including quantizing a first KPI into a first value of a set of three or more values associated with the first KPI.   
     
     
         3 . The method of  claim 2 ,
 wherein,   the representation includes a set of items,   the set of items includes a subset of three or more items corresponding to the three or more values associated with the first KPI,   one item of the three or more items indicates the first value is present, and   other items of the three or more items indicate no other values of the three or more values are present.   
     
     
         4 . The method of  claim 2 , wherein the three or more values correspond to respective threshold levels of a performance target associated with the KPI. 
     
     
         5 . The method of  claim 4 , wherein the respective threshold levels are based on respective distribution factors applied to the performance target associated with the KPI. 
     
     
         6 . The method of  claim 5 , wherein the respective distribution factors are non-linear. 
     
     
         7 . The method of  claim 1 , wherein at least one of the KPIs is a function of a subset of one or more of the performance counters. 
     
     
         8 . The method of  claim 1 , wherein each of the performance counters indicates a number of times a respective behavior has been detected in the network. 
     
     
         9 . The method of  claim 1 , further comprising:
 generating more association rules based, at least in part, on a second set of items associated with a selected proper subset of the KPIs and one or more child KPIs of the selected proper subset of the KPIs.   
     
     
         10 . The method of  claim 9 , wherein at least one of the KPIs in the selected proper subset of the KPIs is based on an aggregate of other ones of the KPIs. 
     
     
         11 . The method of  claim 10 ,
 wherein,   at least one child KPI is associated with the at least one of the KPIs, and   the at least one child KPI represents a specific type of failure in the network.   
     
     
         12 . At least one non-transitory computer readable medium comprising instructions stored therein that, when executed, cause one or more processors to:
 select performance counters of a network;   convert the performance counters into key performance indicators (KPIs);   create a representation of the KPIs;   apply mining logic to the representation to generate rules; and   generate, via a display, a report based on the rules to enable analysis of the network.   
     
     
         13 . The at least one non-transitory computer readable medium of  claim 12 , wherein applying the mining logic includes a hierarchical grouping of the KPIs. 
     
     
         14 . The at least one non-transitory computer readable medium of  claim 13 , wherein the instructions, when executed, further cause the one or more processors to isolate relevant ones of the hierarchical grouping of the KPIs. 
     
     
         15 . The at least one non-transitory computer readable medium of  claim 12 , wherein the instructions, when executed, further cause the one or more processors to quantize each of the KPIs into one of a set of values, a first KPI quantified into a first value of a set of three or more values associated with the first KPI. 
     
     
         16 . The at least one non-transitory computer readable medium of  claim 15 ,
 wherein,   the representation includes a set of items,   the set of items includes a subset of three or more items corresponding to the three or more values associated with the first KPI,   one item of the three or more items indicates the first value is present, and   other items of the three or more items indicate no other values of the three or more values are present.   
     
     
         17 . The at least one non-transitory computer readable medium of  claim 15 , wherein the three or more values correspond to respective threshold levels of a performance target associated with the KPI. 
     
     
         18 . The at least one non-transitory computer readable medium of  claim 17 , wherein the respective threshold levels are based on respective distribution factors applied to the performance target associated with the KPI. 
     
     
         19 . The at least one non-transitory computer readable medium of  claim 18 , wherein the respective distribution factors are non-linear. 
     
     
         20 . The at least one non-transitory computer readable medium of  claim 12 , wherein at least one of the KPIs is a function of a subset of one or more of the performance counters.