Systems and methods for detecting cell positioning anomalies
AssigneeNetScout Systems, Inc.
InventorsImran Hafeez, Wing F. Lo, Jonathan Zingman
Life of this patent
Estimating the term…
Abstract
A method for detecting cell positioning anomalies is disclosed. Control plane signaling data packets are collected associated with multiple cells of a communications network. Distance and azimuth values for individual communication sessions are calculated for each cell. A machine learning model is executed using various communication parameters as input to generate a classification for each cell. A list identifying which cells are experiencing anomalies is generated.
Claims23
A method comprising:
- collecting, by a processor via a probe associated with a plurality of communication channels of a communications network, a plurality of control plane signaling data packets comprising data for a plurality of communication parameters for each cell of a plurality of cells of the communications network;
- calculating, by the processor, distance values and azimuth values for individual communication sessions of each cell based on the data for the plurality of communication parameters for the cell;
- executing, by the processor using at least a portion of the data for the plurality of communication parameters for each cell, the distance values for each cell, the azimuth values for each cell, as input, a machine learning model to generate a classification for each cell, the classification indicating whether the cell is experiencing an anomaly;
- and
- generating, by the processor, a list identifying the generated classifications for the plurality of cells.
A system, comprising:
- a processor, coupled to memory, to:
- collect, by the processor via a probe associated with a plurality of communication channels of a communications network, a plurality of control plane signaling data packets comprising data for a plurality of communication parameters for each cell of a plurality of cells of the communications network;
- calculate, by the processor, distance values and azimuth values for individual communication sessions of each cell based on the data for the plurality of communication parameters for the cell;
- execute, by the processor using at least a portion of the data for the plurality of communication parameters for each cell, the distance values for each cell, or the azimuth values for each cell, as input, a machine learning model to generate a classification for each cell, the classification indicating whether the cell is experiencing an anomaly;
- and
- generate, by the processor, a list identifying the generated classifications for the plurality of cells.
A non-transitory computer readable storage medium comprising instructions stored thereon that, when executed by a processor, cause the processor to:
- collect, by the processor via a probe associated with a plurality of communication channels of a communications network, a plurality of control plane signaling data packets comprising data for a plurality of communication parameters for each cell of a plurality of cells of the communications network;
- calculate, by the processor, distance values and azimuth values for individual communication sessions for each cell based on the data for the plurality of communication parameters for the cell;
- execute, by the processor using at least a portion of the data for the plurality of communication parameters for each cell, the distance values for each cell, the azimuth values for each cell, or any combination thereof, as input, a machine learning model to generate a classification for each cell, the classification indicating whether the cell is experiencing an anomaly;
- and
- generate, by the processor, a list identifying the generated classifications for the plurality of cells.
Dependencies are inferred from the claim text.