US 11,811,588 B2
Configuration management and analytics in cellular networks
Russell Douglas Ford, San Jose, CA (US); Mandar N. Kulkarni, Richardson, TX (US); Pranav Madadi, Mountain View, CA (US); Vikram Chandrasekhar, Mountain View, CA (US); Yan Xin, Princeton, NJ (US); Sangkyu Park, Seoul (KR); and Hakyung Jung, Seoul (KR)
Assigned to Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed by Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed on Mar. 4, 2021, as Appl. No. 17/192,780.
Claims priority of provisional application 63/060,614, filed on Aug. 3, 2020.
Claims priority of provisional application 63/021,183, filed on May 7, 2020.
Claims priority of provisional application 63/014,025, filed on Apr. 22, 2020.
Prior Publication US 2021/0351973 A1, Nov. 11, 2021
Int. Cl. H04L 41/0654 (2022.01); H04L 41/0631 (2022.01); H04L 41/069 (2022.01); H04L 43/067 (2022.01); H04L 41/0604 (2022.01)
CPC H04L 41/064 (2013.01) [H04L 41/069 (2013.01); H04L 41/0609 (2013.01); H04L 41/0654 (2013.01); H04L 43/067 (2013.01)] 20 Claims
OG exemplary drawing
 
1. An apparatus for identifying network anomalies, the apparatus comprising:
a communication interface configured to receive one or more of performance management (PM) data, alarm data, and configuration management (CM) data from one or more devices on a network, and
a processor operably connected to the communication interface, the processor configured to:
determine a cumulative anomaly score over a predefined time range based on a subset of historical PM samples;
determine an anomaly ratio of a first time window and a second time window, based on the cumulative anomaly score, wherein the first time window is before one or more CM parameter changes and the second time window is a time window during and after the one or more CM parameter changes;
determine one or more anomaly events coinciding with the one or more CM parameter changes based on the anomaly ratio;
collate the PM data, the alarm data, and the CM data into combined data set based on matching fields and timestamps;
generate a set of rules linking one or more CM parameter changes and the collated data to anomaly events;
control the apparatus to transmit the set of rules to a controller of the network;
generate root cause explanations for CM parameter changes that are linked to anomaly events;
identify a reference data source among two or more data sources that report key performance indicators (KPIs); and
determine whether to modify a granularity of reporting of KPIs to be a finer granularity or a more coarse granularity based on a granularity of reporting of KPIs that corresponds to the reference data source.