Granted Patent B2

US 12,640,993 · App. 18/592,237 · Granted May 26, 2026

Inventors: Sridhar Bethamsetty (Frisco, TX); Vikas Ranjan (Bellevue, WA); Diglio Antonio Simoni (Raleigh, NC)

Assignee: T-Mobile USA, Inc.

H04L41/16H04L43/0876

Abstract

Claims (56)

1 . A computer-implemented method for identifying correlations for adaptive noise reduction, the method comprising:

obtaining values for a first set of network performance metrics measured during a first period of time from a sensor module communicatively coupled to a first set of sensors deployed at one or more remote devices of a telecommunications network;

inputting values for the first set of network performance metrics into a machine learning model to obtain an optimal set of network performance metrics to be measured during a future period of time, wherein the machine learning model is configured to determine a next set of metrics to be measured based on detection of one or more anomalous values of a previous set of metrics, and wherein the optimal set comprises an expanded set of metrics comprising an additional metric from the first set of network performance metrics;

identifying, based on the optimal set of network performance metrics to be measured during the future period of time, a second set of sensors for usage by determining one or more additional sensors needed to measure or calculate the expanded set of metrics of the optimal set, wherein the one or more additional sensors correspond to potential fault events at the telecommunications network;

generating one or more commands configured to effectuate activation of one or more sensors of the second set of sensors, and deactivation of one or more sensors of the first set of sensors,

wherein at least one sensor of the first set of sensors is different than at least one sensor of the second set of sensors; and

transmitting, to one or more remote devices communicatively coupled to the sensor module, the one or more commands effectuating activation of the one or more sensors of the second set of sensors and deactivation of the one or more sensors of the first set of sensors.

2 . The method of claim 1 , wherein generating the one or more commands comprises:

identifying a first subset of sensors from the first set of sensors that were active during the first period of times and not part of the second set of sensors; and

generating one or more commands for deactivating the first subset of sensors.

3 . The method of claim 1 , wherein generating the one or more commands comprises:

identifying a second subset of sensors from the second set of sensors that are not part of the first set of sensors; and

generating one or more commands for activating the second subset of sensors.

4 . The method of claim 1 , wherein the method further comprises:

receiving, from one or more sensors at the one or more remote devices, values for the optimal set of network performance metrics measured over a second period of time occurring after the first period of time;

determining, based on the values for the optimal set of network performance metrics, that one or more prospective fault events are likely to occur; and

transmitting, to a remote device, a notification for performing one or more actions to prevent or mitigate the one or more prospective fault events.

5 . The method of claim 4 , wherein determining that one or more prospective fault events are likely to occur comprises inputting the values over a period of time into a second machine learning model and wherein the method further comprises training a second machine learning model for predicting occurrence of prospective fault events based on values of the network performance metrics over a period of time.

6 . The method of claim 4 , wherein determining that one or more prospective fault events are likely to occur based on values over a period of time comprises determining whether values over the period of time exceed pre-determined thresholds corresponding to one or more prospective fault events.

7 . The method of claim 4 , further comprising, responsive to determining that one or more prospective fault events are likely to occur, identifying one or more actions to be performed at a remote device or server to prevent or mitigate the one or more prospective fault events.

8 . The method of claim 7 , wherein the one or more actions comprises modifying a value of an operational parameter at a cell tower to prevent or mitigate the one or more prospective fault events and the method further comprises generating a command for modifying the value.

9 . One or more non-transitory computer-readable media containing instructions which when executed by a processor, perform a method for identifying correlations for adaptive noise reduction, the method comprising:

obtaining values for a first set of network performance metrics measured during a first period of time from a sensor module communicatively coupled to a first set of sensors deployed at one or more remote devices of a telecommunications network;

inputting values for the first set of network performance metrics into a machine learning model to obtain an optimal set of network performance metrics to be measured during a future period of time, wherein the machine learning model is configured to determine a next set of metrics to be measured based on detection of one or more anomalous values of a previous set of metrics, and wherein the optimal set comprises an expanded set of metrics comprising an additional metric from the first set of network performance metrics;

identifying, based on the optimal set of network performance metrics to be measured during the future period of time, a second set of sensors for usage by determining one or more additional sensors needed to measure or calculate the expanded set of metrics of the optimal set, wherein the one or more additional sensors correspond to potential fault events at the telecommunications network; and

generating one or more commands configured to effectuate activation of one or more sensors of the second set of sensors, and deactivation of one or more sensors of the first set of sensors,

wherein at least one sensor of the first set of sensors is different than at least one sensor of the second set of sensors.

10 . The one or more non-transitory computer-readable media of claim 9 , wherein generating the one or more commands comprises:

identifying a first subset of sensors from the first set of sensors that were active during the first period of times and not part of the second set of sensors; and

generating one or more commands for deactivating the first subset of sensors.

11 . The one or more non-transitory computer-readable media of claim 9 , wherein generating the one or more commands comprises:

identifying a second subset of sensors from the second set of sensors that are not part of the first set of sensors; and

generating one or more commands for activating the second subset of sensors.

12 . The one or more non-transitory computer-readable media of claim 10 , wherein the method further comprises:

receiving, from one or more sensors at the one or more remote devices, values for the optimal set of network performance metrics measured over a second period of time occurring after the first period of time;

determining, based on the values for the optimal set of network performance metrics, that one or more prospective fault events are likely to occur; and

transmitting, to a remote device, a notification for performing one or more actions to prevent or mitigate the one or more prospective fault events.

13 . The one or more non-transitory computer-readable media of claim 12 , wherein determining that one or more prospective fault events are likely to occur comprises inputting the values over a period of time into a second machine learning model and wherein the method further comprises training a second machine learning model for predicting occurrence of prospective fault events based on values of network performance metrics over a period of time.

14 . The one or more non-transitory computer-readable media of claim 12 , wherein determining that one or more prospective fault events are likely to occur based on values over a period of time comprises determining whether values over the period of time exceed pre-determined thresholds corresponding to one or more prospective fault events.

15 . The one or more non-transitory computer-readable media of claim 14 , further comprising, responsive to determining that one or more prospective fault events are likely to occur, identifying one or more actions to be performed at a remote device or server to prevent or mitigate the one or more prospective fault events.

16 . A system for identifying correlations for adaptive noise reduction, the system comprising:

one or more processors; and

one or more non-transitory computer-readable media storing instructions that, when executed by the one or more processors, cause operations comprising:

obtaining values for a first set of network performance metrics measured during a first period of time from a sensor module communicatively coupled to a first set of sensors deployed at one or more remote devices of a telecommunications network;

inputting values for the first set of network performance metrics into a machine learning model to obtain an optimal set of network performance metrics to be measured during a future period of time, wherein the machine learning model is configured to determine a next set of metrics to be measured based on detection of one or more anomalous values of a previous set of metrics, and wherein the optimal set comprises an expanded set of metrics comprising an additional metric from the first set of network performance metrics;

identifying, based on the optimal set of network performance metrics to be measured during the future period of time, a second set of sensors for usage by determining one or more additional sensors needed to measure or calculate the expanded set of metrics of the optimal set, wherein the one or more additional sensors correspond to potential fault events at the telecommunications network;

generating one or more commands configured to effectuate activation of one or more sensors of the second set of sensors, and deactivation of one or more sensors of the first set of sensors,

wherein at least one sensor of the first set of sensors is different than at least one sensor of the second set of sensors; and

transmitting, to one or more remote devices communicatively coupled to the sensor module, the one or more commands effectuating activation of the one or more sensors of the second set of sensors and deactivation of the one or more sensors of the first set of sensors.

17 . The system of claim 16 , wherein determining that one or more prospective fault events are likely to occur comprises inputting the values over a period of time into a second machine learning model and operations further comprise training the second machine learning model for predicting occurrence of prospective fault events based on values of the network performance metrics over a period of time.

18 . The system of claim 17 , wherein determining that one or more prospective fault events are likely to occur based on values over a period of time comprises determining whether values over the period of time exceed pre-determined thresholds corresponding to one or more prospective fault events.

19 . The system of claim 18 , wherein the one or more non-transitory computer-readable media further cause operations comprising:

responsive to determining that one or more prospective fault events are likely to occur, identifying one or more actions to be performed at a remote device or server to prevent or mitigate the one or more prospective fault events.

20 . The system of claim 18 , wherein the one or more non-transitory computer-readable media further cause operations comprising:

identifying a first subset of sensors from the first set of sensors that were active during the first period of times and not part of the second set of sensors; and

generating a command for deactivating the first subset of sensors.

Assignments (1)

Continuity (1)

References Cited (42)