Abstract: A method for determining subscriber experience in a computer network including: defining a plurality of features influencing subscriber experience; initializing a weight for each of the features of the plurality of features; determining a feature value for at least one subscriber for each of the plurality of features; determining a subscriber score for the at least one subscriber based on the feature values and the weight of the feature; determining at least one subscriber with a subscriber score outside a predetermined threshold; and performing a subscriber response action for each subscriber with the subscriber score outside of the predetermined threshold.

Abstract: A system and method for determining application quality of experience. The system including: a logic module configured to collect input data associated with network traffic flow parameters and extract a feature set based on the network flow parameters; a model module configured to train a machine learning model to determine MOS based on the extracted feature set; and a traffic action module configured to monitor the MOS based on the machine learning model and the traffic flow in the network and determining application quality of experience based on the MOS. The method including: collecting input data associated with network flow parameters; extracting a feature set based on the collected data; training a model to determine MOS of network traffic based on the extract feature set; deploying the model to monitor the MOS of traffic flow in the computer network; and determining the quality of experience based on the MOS.

Abstract: A method and system for classifying a traffic flow. The method including: initializing a database with packet parameters; identifying a new flow; determining packet parameters associated with the new flow; determine whether the packet parameters match any previously stored packet parameters in the database; if the packet parameters match, determining an application classification for the traffic flow. The system including: a server profiling module configured to initialize a database; and an application module configured determine packet parameters associated with the new flow, determine whether the packet parameters match any previously stored packet parameters. A method and system for detecting a change in the classification of an application and/or content in a traffic flow. The method includes determining a change in the application behavior; detecting a change in a content category of the application, providing an updated traffic action based on the detected change.

Abstract: A method for capacity planning in a computer network, the method includes: determining traffic flow, application and network parameters; collecting the parameters for a predetermined time period; determining the features or parameters associated with various growth models; and combining the growth models to determine network capacity planning and congestion management planning for the network. A system for capacity planning in a computer network, the system including: a data collection module configured to collect data and parameters associated with the traffic flow, applications and nodes and links on the network; a forecasting module having a prediction engine configured to predict growth based on the QoE determined from the collected parameters; and a traffic action module configured to provide growth results and/or congestion management options.

Abstract: A system and method for classifying application and content in a computer network. The method including: determining an application associated with a traffic flow; determining at least one type of content category associated with the application; reviewing packet parameters to determine the content category of the traffic flow; and monitoring the traffic flow for any changes to the packet parameters that would indicate a change in the content category of the traffic flow. The system including: an application module configured to determine an application associated with a traffic flow; a signature module, a heuristic module and a machine learning module configured to review packet parameters to determine a content category associated with the traffic flow and any changes to the content category associated with the traffic flow. A system and method for determining a confidence level of a classification of an application and content category of a traffic flow.

Abstract: A method for congestion management on a network including: determining whether a cell on the network is congested; identifying at least one heavy user on the cell; determine traffic flow criteria of the at least one heavy user; and shape network traffic of the at least one heavy user based on the traffic flow criteria of the heavy user. A system for congestion management on a network including: a QoE module configured to determine whether a cell on the network is congested; an analysis module configured to identify at least one heavy user on the cell and determine traffic flow criteria of the at least one heavy user; and at least one shaper configured to shape network traffic of the at least one heavy user based on the traffic flow criteria of the heavy user.

Abstract: A method and system for root cause analysis in a computer network. The method includes: determining a degradation of QoE for at least one traffic flow of at least one user; determining a traffic pattern associated with the degradation of the QoE; determining a root cause for the degradation based on the traffic pattern; and implementing a traffic action response based on the root cause. The system includes: a QoE module configured to determine a degradation of QoE for at least one traffic flow of at least one user; a detection module configured to determine a traffic pattern associated with the degradation of the QoE; a issue determination module configured to determine a root cause for the degradation based on the traffic pattern; and a traffic action module configured to implement a traffic action response based on the root cause.

Abstract: A system and a method for traffic management on a network. The method including: determining a desired intent for a network operator's traffic; determining a set of classes for a traffic flow through a link; determining a minimum and target bandwidth for each class in the set of class based on the desired intent; measure user score and bandwidth use for each class; allocate a bandwidth per class based on the minimum and target bandwidth and measured user score; and shape the traffic flow to the allocated bandwidth.

Abstract: A system and method for creating a model for predicting and reducing subscriber churn in a computer network. The method including: for a predetermined time period: retrieving traffic flow data per subscriber for a plurality of subscribers in the computer network; determining at least one metric per subscriber from the traffic flow data; determining at least one systemic feature associated with the plurality of subscribers; and storing the at least one amalgamated metric and feature; on reaching the predetermined time period create the model by: analyzing at least one metric and at least one feature for the predetermined time period; predicting, per subscriber, whether the subscriber is going to churn within a churn period in the future based on the analysis; validating the prediction by determining whether the subscriber actually churned during the churn period; and creating the model based on the validated predictions.

Abstract: A method for managing mobile network congestion including: determining cell metrics over a predetermined time interval for each cell of a plurality of cells; determining correlations between the cell metrics for each cell; determining whether any cell of the plurality of cell are congestion based on the correlations; determining a type of congestion for any cell determined to be congested; and determining traffic actions based on the type of congestion. A system for managing mobile network congestion having: a collection module configured to determine cell metrics over a predetermined time interval for each cell of a plurality of cells; a correlation module configured to determine correlations between the cell metrics; an analysis module configured to determine whether any cell is congestion based on the correlations and a type of congestion for any cell determined to be congested; and a traffic action module configured to determine traffic actions.

Abstract: A system and method for Quality of Experience (QoE) management on a network. The method including: determining a set of service categories for an operator's traffic, wherein at least one of the service categories is video streaming; mapping a plurality of traffic flows to each of the service categories; determining a target and minimum intent for each of the service categories; measuring a score and bandwidth use for each of the service category; determining whether each of the service categories are reaching an associated minimum bandwidth intent; if the minimum bandwidth intent is not being reached for at least one service category, adjusting the minimum intent for at least one of the service categories; allocating a bandwidth per service category based on the adjusted minimum intent; and shaping the traffic flow to the allocated bandwidth; otherwise allowing the traffic flow to continue with a current bandwidth allocation.

Abstract: A method for network slice assignment including: defining an intent for at least one network slice; selecting at least one network slice instance has capability to meet the intent; monitoring the selected network slice instance to determine whether the selected network slice instance is achieving the intent; and if the intent is not being met, reprioritizing at least one network slice instance in order to prioritize the selected network slice instance; if the intent is being met, continue monitoring the selected network slice instance. A system for network slice assignment including: a selection module configured to define an intent for at least one network slice and select at least one network slice; a monitoring module configured to monitor the selected network slice instance; an analysis module configured to determine if the intent is being met; and a reprioritization module configured to reprioritize at least one network slice.

Abstract: A method for link bandwidth management in a computer network, the method including: monitoring link traffic flow for a predetermined amount of time; measuring throughput of the link traffic flow; estimating the bandwidth based on the throughput; and calibrating at least one shaper based on the estimated bandwidth. a system for link bandwidth management in a computer network, the system including: a learning module configured to monitor link traffic flow for a predetermined amount of time; an analysis module configured to measuring throughput of the link traffic flow and estimate the bandwidth based on the throughput; and a calibration module configured to calibrate at least one shaper based on the estimated bandwidth.

Abstract: A method and system for remote diagnostic of Quality of Experience (QoE) for a subscriber on a computer network. The method includes: reviewing a traffic flow associated with a subscriber to determine performance statistics correlated with the traffic flow; determining subscriber data related to the subscriber associated with the traffic flow; analyzing the subscriber data and performance statistics to determine a traffic signature associated with the traffic flow; determining whether the traffic signature matches any of the plurality of known traffic signatures; and diagnosing the QoE issue based on the match of the traffic signatures.

Abstract: A method for managing mobile network congestion including: determining cell metrics over a predetermined time interval for each cell of a plurality of cells; determining correlations between the cell metrics for each cell; determining whether any cell of the plurality of cell are congestion based on the correlations; determining a type of congestion for any cell determined to be congested; and determining traffic actions based on the type of congestion. A system for managing mobile network congestion having: a collection module configured to determine cell metrics over a predetermined time interval for each cell of a plurality of cells; a correlation module configured to determine correlations between the cell metrics; an analysis module configured to determine whether any cell is congestion based on the correlations and a type of congestion for any cell determined to be congested; and a traffic action module configured to determine traffic actions.

Abstract: A method for managing handovers on a network including: determining neighboring cells within the network; mapping the neighboring cells; analyzing handover data between the mapped cells, wherein the handover data may be retrieved from network messaging; determining for each handover whether the handover is successful or unsuccessful based on the handover data; and reporting unsuccessful handovers to an operator for the network. a system for managing handovers on a network, the system including: a relation module configured to determine neighboring cells within the network and map the neighboring cells; an analysis module configured to analyzing handover data between the mapped cells, wherein the handover data may be retrieved from network messaging and determine for each handover whether the handover is successful or unsuccessful based on the handover data; and a reporting module configured to report unsuccessful handovers to an operator for the network.

Abstract: A method for congestion management on a network including: determining whether a cell on the network is congested; identifying at least one heavy user on the cell; determine traffic flow criteria of the at least one heavy user; and shape network traffic of the at least one heavy user based on the traffic flow criteria of the heavy user. A system for congestion management on a network including: a QoE module configured to determine whether a cell on the network is congested; an analysis module configured to identify at least one heavy user on the cell and determine traffic flow criteria of the at least one heavy user; and at least one shaper configured to shape network traffic of the at least one heavy user based on the traffic flow criteria of the heavy user.

Abstract: A method and system for detecting ruleset misconfiguration in a computer network. The method including: generating a set of sample data flows; evaluating each of the set of sample data flows against a predetermined definition to generate a flow descriptor for each of the set of sample data flows; evaluating each of the flow descriptors against a ruleset; and generating a summary of how each of the flow descriptors perform with respect to the ruleset. The system including: a data flow sample retrieval module configured to generate flows; a policy engine configured to store and retrieve a ruleset; a packet processing engine configured to evaluate each of the data flows against a predetermined definition to generate a flow descriptor for each flows, evaluate each of the flow descriptors against a ruleset; and generate a summary of how each of the flow descriptors perform with respect to the ruleset.

Abstract: A system and method for creating a model for predicting and reducing subscriber churn in a computer network. The method including: for a predetermined time period: retrieving traffic flow data per subscriber for a plurality of subscribers in the computer network; determining at least one metric per subscriber from the traffic flow data; determining at least one systemic feature associated with the plurality of subscribers; and storing the at least one amalgamated metric and feature; on reaching the predetermined time period create the model by: analyzing at least one metric and at least one feature for the predetermined time period; predicting, per subscriber, whether the subscriber is going to churn within a churn period in the future based on the analysis; validating the prediction by determining whether the subscriber actually churned during the churn period; and creating the model based on the validated predictions.

Abstract: A method for congestion management on a network including: determining whether a cell on the network is congested; identifying at least one heavy user on the cell; determine traffic flow criteria of the at least one heavy user; and shape network traffic of the at least one heavy user based on the traffic flow criteria of the heavy user. A system for congestion management on a network including: a QoE module configured to determine whether a cell on the network is congested; an analysis module configured to identify at least one heavy user on the cell and determine traffic flow criteria of the at least one heavy user; and at least one shaper configured to shape network traffic of the at least one heavy user based on the traffic flow criteria of the heavy user.