Vmware, Inc.

At&t Intellectual Property I, L.p.

Uhana, Inc.

Srikanth Hariharan

Sarabjot Singh

Adnan Raja

Aditya Gudipati

Manu Sharma

Alexandros Anemogiannis

Rakesh Misra

Manu Bansal

Ernest Tsui

Helen Zeng

Guanying Ru

Rohan Agarwal

Deepak Khurana

Duyen Riggs

Benjamin C Basler

Vibhav Arun Kapnadak

Xiaojun Tang

Kanthi Nagaraj

Rajiv Ramanathan

Christopher M Riley

Bo Ji

Siddhant Deshmukh

Akash Gangil

Ben Basler

A system can include a network analysis platform that applies performance models to determine if a coverage degradation exists at a network cell, such as at a base station. The performance models are pre-trained based on network telemetry data. For a session at a cell, an expected quality of service ('QoS') metric can be compared to an actual QoS metric to determine whether the session is impacted by coverage degradation. Throughput is an example QoS metric. If the number of impacted sessions exceeds a threshold, the base station can be highlighted on a GUI. Additionally, the network analysis platform can perform root cause analysis of a victim cell.

Service aware coverage degradation detection and root cause identification

Some embodiments of the invention provide a method of reporting telemetry data in a telecommunication network. The telemetry data is collected from a set of one or more telemetry-producing (TP) network elements and is distributed to a set of one or more telemetry-consuming (TC) network elements registered to receive the telemetry data. The method receives a telemetry packet produced by a TP network element and performs a filtering operation to determine whether the telemetry packet should be reported to at least a subset of one or more TC network elements. When the filtering operations result in a determination that the telemetry packet should be reported, the method forwards the telemetry packet to the subset of TC network elements.

Collecting, processing, and distributing telemetry data

A method for automated root cause analysis in mobile radio access networks, including: determining mobile radio access network data (e.g., RAN data); detecting an anomaly for a set of user sessions and/or cells from the RAN data; and classifying the detected anomalies using a set of root cause classifiers.

Intelligent anomaly detection and root cause analysis in mobile networks

A network analysis and management system includes a processor coupled to a communications interface and a non-transitory memory. The processor is configured to read instructions from the non-transitory memory to cause the system to perform operations comprising receiving log data associated with communication between a first user device and a network using a first protocol stack including a plurality of layers. A plurality of network events are generated based on the log data. Each network event is associated with a respective log data entry of the log data and a respective layer of the plurality of layers. First network analysis information is generated by correlating first and second network events using a correlation configuration associated with a network management task. A network management message is generated using the first network analysis information, and transmitted to one of the first user device and the network for performing the network management task.

Systems and methods for network analysis and management

Examples herein describe systems and methods for Physical Uplink Control Channel (PUCCH) reallocation. Interference can be detected on a Physical Resource Block (PRB) corresponding to a time-frequency unit of a resource allocated to PUCCH by a base station. The impact the interference has on a subscriber service can be quantified. The quantified services impact can be compared to a threshold. Upon determining that the service impact exceeds the threshold, PRBs of other resources on the base station can be analyzed. The analysis can predict how reallocating the other resources to PUCCH can improve the quality of the subscriber service. One of the other resources can be selected, and instructions can be provided to reallocate the selected resource to PUCCH.

System for dynamic PUCCH reallocation

A system can include a network analysis platform that applies models to identify downlink interference at a network cell, such as at a base station. For a session at a cell, an expected performance with normalized downlink interference can be compared to an actual performance to determine whether the session is impacted. This can include normalizing channel quality index ('CQI') and negative-acknowledgement ('NACK') rate. Overshooting aggressor cells can be identified as the source of the downlink interference based on a useless overlap fraction exceeding a threshold. The impacted sessions and root causes can be displayed on a graphical user interface (&#x201c;GUI&#x201d;).

Downlink interference detection and identification of aggressor cells

A system can include an evaluation platform that applies models to improve the quality of experience of users impacted by uplink interference at a network cell, such as at a base station. For a user session at a cell, an expected performance with optimized uplink interference can be compared to an actual performance to determine whether the session is impacted. This can include iteratively increasing a hypothetical power parameter and determining uplink interference based on source and neighboring cells. When positively impacted sessions exceed a threshold, the platform can dynamically change the power parameter of the base station to reflect the hypothetical value.

Service aware closed loop uplink power control optimization

A system can include a network analysis platform that applies performance models to determine if a load imbalance exists at a cell, such as at a base station. The performance models are pre-trained based on network telemetry data. For a session at a cell, an expected load can be compared to an actual load to determine whether the session is impacted by a load imbalance. If the number of impacted sessions exceeds a threshold, the base station can be highlighted on a GUI. Additionally, the network analysis platform can perform root cause analysis of a victim cell based on session handoff analysis to determine how to decrease the imbalance impacts.

Service aware load imbalance detection and root cause identification

Systems and methods for providing information describing mobile network interference experienced by a mobile network.

Systems and methods for mobile network interference analysis

A graphical user interface ('GUI') allows for the creation of custom key performance indicators ('KPIs') for real-time analysis of network telemetry events. The GUI can include options for defining variables based on event attributes. These can correspond to events that exist in input telemetry streams at a stream processor. The GUI can allow creation of a formula based on these variables. An aggregation section specifies how the output of the formula is aggregated. This can be based on group, aggregation function, and time period. A manager process causes the stream processor to apply the custom KPI definition to real-time input streams. An output KPI stream can then be routed to a destination for analysis.

Composition of custom key performance indicators for real-time analysis of network telemetry events

Both uplink spectral efficiency and downlink spectral efficiency are improved through adjustments made to various parameters that would otherwise be treated as static type parameters. Variations in respective performance of two or more cells can be considered during the adjustment. Further, variations of respective cell performance based on time of day/week are considered and compensated for through various adjustments. Such timely adaptations are applied in order to improve the performance of each cell, during each time of day/week.

Growing community of inventors

Sunnyvale, CA, United States of America

Srikanth Hariharan