T-mobile Usa, Inc.

Khrum Kashan Jat

Gary Dousson

Marie Grace Jacinto

Spoorthy Kondapally

Otto Fonseca Escudero

Hui-Hsia Sung

Jatinder Singh Sandhu

Jessica Sacks

Ahmed Mahdaoui

Systems and methods to identify whether user traffic is generated indoors (e.g., from within a building) or outdoors for a variety of applications, including improving capacity planning, identifying new products offerings, troubleshooting/planning, competitive analysis, planning optimum locations of capacity planning solution deployment, traffic offload analysis, etc. are disclosed. The method receives and aggregates data from a variety of sources, including customer geolocation data, network data, street/building maps, indoor/outdoor classification of traffic, etc. to generate demand density maps that depict network traffic usage patterns at a building level. The method can then use the demand density maps to identify hotspots, evaluate in-building coverage, and select and rank optimum solutions and/or locations for capacity improvement solutions deployment. As a result, a telecommunications service provider is able to efficiently and economically identify targeted solutions and locations to expand capacity of cell sites and improve customer experiences.

Identification of indoor and outdoor traffic usage of customers of a telecommunications network

Systems and methods that use historical data comprising capacity gain solutions and their associated gains at various locations to train a machine learning model. The trained machine learning model, upon receiving a new location (e.g., latitude and longitude coordinates), recommends the top n (e.g., the top 3) solutions that should be deployed at the new location to improve telecommunications network performance. The machine learning model uses clustering techniques to perform the recommendations.

Identification and prioritization of optimum capacity solutions in a telecommunications network

Systems and methods to understand the roadways (roads, highways, etc.) where customers are experiencing network congestion and the time of day when customer experience is degraded are disclosed. The method receives and aggregates data from a variety of sources, including customer data (e.g., speed, experience throughputs, reported coverage, etc.), network data (site coverage&#x2014;RSRP/RSRQ, site capacity&#x2014;users and bandwidth), maps/traffic data (speed limit), etc. to measure both vehicular congestion and network congestion on roadways. Ultimately, the method can generate an enhanced map that merges vehicular traffic congestion and network traffic congestion to present feature-added routes to a user. A user can then use the enhanced map to better plan their trip to ensure maximum network coverage during their trip.

Management of telecommunications network congestion on roadways

Systems and methods to detect abnormal behavior of cell sites and/or customers are disclosed. By detecting cell site and/or customer behavior anomalies, the system enhances capacity planning by helping understand congestion, more efficiently planning event sites, suggesting installation of temporary solutions, identifying when true traffic needs are increased, and detecting abnormal customer behavior and/or demand. The system accesses historical data for a set of KPIs (e.g., 3 months of hourly data that captures traffic, users, Physical Resource Block (PRB), and throughput). The system computes, for periodic time intervals (e.g., for each hour and each day), upper and lower limits for each site and for each KPI. Using this information, the system detects anomalies for current KPI measurements. The system sends alerts when anomalies are detected for a threshold period of time (e.g., when the KPI measurement falls outside of the computed upper and/or lower bounds continuously for 2-3 hours).

Capacity planning of telecommunications network by detecting anomalies in site behavior

Systems and methods for computing a standardized composite gain metric value for each solution that has been previously deployed to fix degradation issues at cell sites or other wireless nodes is disclosed. The method selects a set of Key Performance Indicators (KPIs), each of which is highly correlated to customer experience. For example, the method selects the following KPIs: traffic, numbers of users, Physical Resource Block (PRB) utilization, Channel Quality Indicator (CQI), throughput, and so on. The method then assigns a weight to each KPI, such that the weight reflects each KPI's relative importance and ensures that the KPIs are not double counted. For each solution deployed at a cell site, the method computes values of the following composite gain metrics: weighted gain and offload index. The method then can rank the solutions based on the computed composite gain metric values so that an optimum solution can be selected.

Optimum network performance improvement solutions selection systems and methods

Systems and methods are described for monitoring performance and allocating resources to improve the performance of a wireless telecommunications network. A wireless telecommunications network may be comprised of base stations and other infrastructure equipment, which may be sourced from various suppliers. Users may generate traffic on the wireless network, and performance metrics relating to the user experience may be collected from individual base stations. The set of available metrics for a particular base station may vary according to the supplier. A machine learning model is thus trained using metrics from multiple base stations, and used to estimate values for metrics that a particular base station does not provide. The metrics are then further characterized according to the service classes of the users, and resources for improving the performance of base stations are allocated according to the reported and estimated metrics for various service classes.

Managing LTE network capacity

Systems and methods for computing a standardized composite gain metric value (e.g., weighted gain or offload index) for each solution that has been previously deployed to fix degradation issues at cell sites or other wireless nodes is disclosed. The method selects a set of Key Performance Indicators (KPIs), each of which is highly correlated to customer experience. For example, the method selects the following KPIs: traffic, number of users, Physical Resource Block (PRB) utilization, Channel Quality Indicator (CQI), throughput, and so on. The method then assigns a weight to each KPI, such that the weight reflects each KPI's relative importance and ensures that the KPIs are not double counted. For each solution deployed at a cell site, the method computes values of the following composite gain metrics: weighted gain and offload index. The method then can rank the solutions based on the computed composite gain metric values so that an optimum solution can be selected.

Systems and methods for determining network congestion (e.g., reduced or low average user throughput with telecommunications networks, such as LTE networks, are described. The systems and methods described herein facilitate the identification and/or prediction of congestion at cell sites, which may enable telecommunications networks to prevent and/or remedy current or future occurrences of congestion at cell sites within their networks.

Growing community of inventors

Sammamish, WA, United States of America

Khrum Kashan Jat