# US 11,115,287 B2 · System and method for predicting key performance indicator (KPI) in a telecommunication network > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,115,287 B2 - Document ID: US11115287B2 - Status: Granted - Kind: B2 - Application number: 16/235,433 - Filed: 2018-12-28 - Published: 2020-07-02 - Granted: 2021-09-07 - Earliest claimed: 2018-12-28 - Applicants: Hcl Technologies Limited - Inventors: Rahul Soundrarajan - Web page: https://patentgrep.com/patent/US11115287B2 ## CPC - H04W 24/08: Testing, {supervising or monitoring} using real traffic - H04L 41/142: using statistical or mathematical methods - H04L 41/5009: Determining service level performance parameters or violations of service level contracts, e.g. violations of agreed response time or mean time between failures [MTBF] - H04L 41/5016: {based on statistics of service availability, e.g. in percentage or over a given time} - H04L 41/5077: {wherein the managed service relates to simple transport services, i.e. providing only network infrastructure} - H04L 43/024: by adaptive sampling - H04L 43/04: Processing captured monitoring data, e.g. for logfile generation - H04L 43/06: Generation of reports - H04L 43/14: {using software, i.e. software packages (network security related monitoring H04L63/1408)} - H04W 24/02: Arrangements for optimising operational condition - H04W 24/04: Arrangements for maintaining operational condition - H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72) - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) ## Abstract The present disclosure relates to system(s) and method(s) for predicting a Key Performance Indicator (KPI) in a telecommunication network is illustrated. The system is configured to monitor a set of counters and a Key Performance Indicator corresponding to a telecommunication network. The set of counters and the Key Performance Indicator (KPI) are monitored for a predefined time interval to gather sample data. The system is configured to analyze the sample data using a data analysis technique in order to identify a subset of counters, from the set of counters, influencing the KPI and a correlation coefficient associated with each counter from the subset of counters, wherein the correlation coefficient associated with each counter is identified after normalizing the subset of counters. The system is configured to apply regression on the subset of counters and the KPI in order to build a correlation equation between the subset of counters and the KPI. ## Claims ### Claim 1 A method for predicting Key Performance Indicator (KPI) in a telecommunication network, the method comprising steps of: monitoring, by a processor, a set of counters and a Key Performance Indicator, corresponding to a telecommunication network, wherein the set of counters and the KPI are monitored for a predefined time interval to gather sample data; analyzing, by the processor, the sample data using a data analysis technique to: identify a subset of counters, from the set of counters, influencing the KPI, and identify a correlation coefficient associated with each counter from the subset of counters, wherein the correlation coefficient associated with each counter is identified after normalizing the subset of counters; and applying, by the processor regression models on the subset of counters and the KPI in order to build a correlation equation between the subset of counters and the KPI, wherein a regression model is selected based on how responsive a prediction has to be which varies depending on a KPI a user wants to model, forecasting and predicting performance of a KPI using the correlation equation. ### Claim 2 (depends on 1) The method of claim 1, wherein the set of counters correspond to a set of factors influencing the KPI. ### Claim 3 (depends on 1) The method of claim 1, wherein the KPI corresponds to a user selected performance indicator associated with the telecommunication network. ### Claim 4 (depends on 1) The method of claim 1, wherein the data analysis technique is one of: a correlation technique or covariance techniques performed after data normalization. ### Claim 5 (depends on 1) The method of claim 1, wherein the correlation coefficient is a numeric value computed based on impact of each counter from the subset of counters on the KPI. ### Claim 6 (depends on 1) The method of claim 1, wherein regression technique selected from RANdom Sample Consensus (RANSAC), Ridge and Bayes, and wherein the regression technique is applied on the subset of counters and the KPI in order to build an equation between the subset of counters and the KPI. ### Claim 7 A system for predicting Key Performance Indicator (KPI) in a telecommunication network, the system comprising: a memory; a processor coupled to the memory, wherein the processor is configured to execute programmed instructions stored in the memory for: monitoring a set of counters and a KPI, corresponding to a telecommunication network, wherein the set of counters and the KPI are monitored for a predefined time interval to gather sample data; analyzing the sample data using a data analysis technique to: identify a subset of counters, from the set of counters, influencing the KPI, and identify a correlation coefficient associated with each counter from the subset of counters, wherein the correlation coefficient associated with each counter is identified after normalizing the subset of counters; and applying regression models on the subset of counters and the KPI in order to build a correlation equation between the subset of counters and the KPI, wherein a regression model is selected based on how responsive a prediction has to be which varies depending on a KPI a user wants to model, forecasting and predicting performance of a KPI using the correlation equation. ### Claim 8 (depends on 7) The system of claim 7, wherein the set of counters correspond to a set of factors influencing the KPI. ### Claim 9 (depends on 7) The system of claim 7, wherein the KPI corresponds to a user selected performance indicator associated with the telecommunication network. ### Claim 10 (depends on 7) The system of claim 7, wherein the data analysis technique is one of: a correlation technique or covariance techniques. ### Claim 11 (depends on 7) The system of claim 7, wherein the correlation coefficient is a numeric value computed based on impact of each counter from the subset of counters on the KPI after performing data normalization. ### Claim 12 (depends on 7) The system of claim 7, wherein a regression technique selected from RANdom Sample Consensus (RANSAC), Ridge and Bayes, wherein the regression technique is applied on the subset of counters and the KPI in order to build an equation between the subset of counters and the KPI. ### Claim 13 A non-transitory computer readable medium embodying a program executable in a computing device for predicting Key Performance Indicator (KPI) in a telecommunication network, the computing device executing the program comprising: a program code for monitoring a set of counters and a Key Performance Indicator, corresponding to a telecommunication network, wherein the set of counters and the KPI are monitored for a predefined time interval to gather sample data; a program code for analyzing the sample data using a data analysis technique to: identify a subset of counters, from the set of counters, influencing the KPI, and identify a correlation coefficient associated with each counter from the subset of counters, wherein the correlation coefficient associated with each counter is identified after normalizing the subset of counters; and a program code for applying regression models on the subset of counters and the KPI in order to build a correlation equation between the subset of counters and the KPI, wherein a regression model is selected based on how responsive a prediction has to be which varies depending on a KPI a user wants to model, a program code for forecasting and predicting performance of a KPI using the correlation equation.