Wireless communication systems for identifying faults
A method for automatically identifying a fault condition in a wireless network can include receiving, at a trained machine learning model, from multiple subsystems of the wireless network, information associated with multiple alerts triggered across the multiple subsystems, each of the multiple alerts being indicative of a corresponding potential fault condition in one of the multiple subsystems, identifying, by the machine learning model, a subset of alerts of the multiple alerts, where the subset of alerts represents a set of one or more root fault conditions associated with the multiple alerts triggered across the multiple subsystems, and identifying, by the machine learning model, one or more remediating actions configured to address the one or more root fault conditions in at least one corresponding subsystem of the multiple subsystems. The machine learning model is trained using training data that identifies correlations between alerts generated in the multiple subsystems.
1 . A method for automatically identifying a fault condition in a wireless network, the method comprising:
receiving, at a trained machine learning model from multiple subsystems of the wireless network, information associated with multiple alerts triggered across the multiple subsystems, each of the multiple alerts being indicative of a corresponding potential fault condition in one of the multiple subsystems;
receiving, from a network platform, information regarding resources of the wireless network, including a topology defining relationships, connectivity, and dependencies among network elements of the multiple subsystems;
identifying, by the machine learning model, a subset of alerts of the multiple alerts by correlating the multiple alerts with the topology to identify a root cause of a cascade of alerts across the multiple subsystems based on the information regarding resources, wherein the subset of alerts represents a set of one or more root fault conditions associated with the multiple alerts triggered across the multiple subsystems and includes fewer alerts than are included in the multiple alerts; and
identifying, by the machine learning model, one or more remediating actions configured to address the one or more root fault conditions in at least one corresponding subsystem of the multiple subsystems,
wherein the machine learning model is trained using the information regarding the resources, including the topology and physical and virtual assets of the wireless network, and training data that identifies correlations between alerts generated in the multiple subsystems according to the dependencies defined by the topology.
2 . The method of claim 1 , wherein the wireless network is configured to perform fifth-generation (5G) cloud-native network operations.
3 . The method of claim 1 , wherein the multiple subsystems include an external provider configured to provide a range of network testing, monitoring, and analytics solutions, a central component configured to perform collecting, storing, analyzing, and visualizing telemetry data, a radio access network (RAN) configured to provide wireless connectivity between user devices and the wireless network, and a cloud computing model configured to provide a platform for developing, deploying, and managing applications.
4 . The method of claim 3 , wherein each of the multiple subsystems is configured to monitor, measure, and analyze a performance of the wireless network.
5 . The method of claim 1 , further comprising generating a dashboard configured to provide real-time visibility and management of network operations of the wireless network in a single interface,
wherein the dashboard is configured to display the subset of alerts.
6 . The method of claim 1 , wherein identifying the subset of alerts comprises identifying a timeline of events associated with the subset of alerts.
7 . The method of claim 1 , wherein identifying the subset of alerts of the multiple alerts includes identifying unusual patterns of behavior in the multiple alerts to correlate the subset of alerts associated with the identified unusual patterns of behavior.
8 . The method of claim 1 , wherein identifying the subset of alerts of the multiple alerts includes combining the multiple alerts into the subset of alerts.
9 . The method of claim 1 , wherein identifying the subset of alerts of the multiple alerts includes setting a threshold value that changes over time and identifying the subset of alerts of the multiple alerts, among the multiple alerts, associated with a value greater than the threshold value.
10 . A system for automatically identifying a fault condition in a wireless network, the system comprising:
multiple subsystems configured to monitor, measure, and analyze a performance of the wireless network;
memory; and
at least one processor, coupled to the memory and using a trained machine learning model, the at least one processor configured to:
receive, at the machine learning model from the multiple subsystems of the wireless network, information associated with multiple alerts triggered across the multiple subsystems, each of the multiple alerts being indicative of a corresponding potential fault condition in one of the multiple subsystems;
receive, from a network platform, information regarding resources of the wireless network, including a topology defining relationships, connectivity, and dependencies among network elements of the multiple subsystems;
identify, by the machine learning model, a subset of alerts of the multiple alerts by correlating the multiple alerts with the topology to identify a root cause of a cascade of alerts across the multiple subsystems based on the information regarding resources, wherein the subset of alerts represents a set of one or more root fault conditions associated with the multiple alerts triggered across the multiple subsystems and includes fewer alerts than are included in the multiple alerts; and
identify, by the machine learning model, one or more remediating actions configured to address the one or more root fault conditions in at least one corresponding subsystem of the multiple subsystems,
wherein the machine learning model is trained using the information regarding the resources including the topology and physical and virtual assets of the wireless network, and training data that identifies correlations between alerts generated in the multiple subsystems according to the dependencies defined by the topology.
11 . The system of claim 10 , wherein the wireless network is configured to perform fifth-generation (5G) cloud-native network operations.
12 . The system of claim 10 , wherein the multiple subsystems include an external provider configured to provide a range of network testing, monitoring, and analytics solutions, a central component configured to perform collecting, storing, analyzing, and visualizing telemetry data, a radio access network (RAN) configured to provide wireless connectivity between user devices and the wireless network, and a cloud computing model configured to provide a platform for developing, deploying, and managing applications.
13 . The system of claim 10 , wherein the at least one processor is further configured to generate a dashboard configured to provide real-time visibility and management of network operations of the wireless network in a single interface,
wherein the dashboard is configured to display the subset of alerts.
14 . The system of claim 10 , wherein identifying the subset of alerts comprises identifying a timeline of events associated with the subset of alerts.
15 . The system of claim 10 , wherein identifying the subset of alerts of the multiple alerts includes identifying unusual patterns of behavior in the multiple alerts to correlate the subset of alerts associated with the identified unusual patterns of behavior.
16 . The system of claim 10 , wherein identifying the subset of alerts of the multiple alerts includes combining the multiple alerts into the subset of alerts.
17 . The system of claim 10 , wherein identifying the subset of alerts of the multiple alerts includes setting a threshold value that changes over time and identifying the subset of alerts of the multiple alerts, among the multiple alerts, associated with a value greater than the threshold value.
18 . A non-transitory computer-readable medium encoded with instructions that, when executed by one or more computers, cause the one or more computers to perform operations comprising:
receiving, at a trained machine learning model from multiple subsystems of a wireless network, information associated with multiple alerts triggered across the multiple subsystems, each of the multiple alerts being indicative of a corresponding potential fault condition in one of the multiple subsystems;
receiving, from a network platform, information regarding resources of the wireless network, including a topology defining relationship, connectivity, and dependencies among network elements of the multiple subsystems;
identifying, by the machine learning model, a subset of alerts of the multiple alerts by correlating the multiple alerts with the topology to identify a root cause of a cascade of alerts across the multiple subsystems based on the information regarding resources, wherein the subset of alerts represents a set of one or more root fault conditions associated with the multiple alerts triggered across the multiple subsystems and include fewer alerts than are included in the multiple alerts; and
identifying, by the machine learning model, one or more remediating actions configured to address the one or more root fault conditions in at least one corresponding subsystem of the multiple subsystems,
wherein the machine learning model is trained using the information regarding the resources including the topology and physical and virtual assets of the wireless network, and training data that identifies correlations between alerts generated in the multiple subsystems according to the dependencies defined by the topology.
19 . The non-transitory computer-readable medium of claim 18 , wherein the multiple subsystems include an external provider configured to provide a range of network testing, monitoring, and analytics solutions, a central component configured to perform collecting, storing, analyzing, and visualizing telemetry data, a radio access network (RAN) configured to provide wireless connectivity between user devices and the wireless network, and a cloud computing model configured to provide a platform for developing, deploying, and managing applications.
20 . The non-transitory computer-readable medium of claim 19 , wherein each of the multiple subsystems is configured to monitor, measure, and analyze a performance of the wireless network.