Abstract: A computer-automated maintaining a physical configuration of an antenna operating within radio access network (RAN) of a mobile wireless network is described. A feature subset of a covering set of features for the antenna is specified. A centroid is generated for the antenna, wherein the centroid comprises a current long-term values of the feature subset obtained by processing multiple data sets for the feature subset over a relatively long time period. An antenna change detection decision is rendered, wherein the rendering an antenna change detection decision comprises first applying a current short-term values of the feature subset, which are representative of a current status of the antenna, to the centroid to render a current distance from centroid. In accordance with detecting an antenna change event during the applying, an antenna change event notification is issued that corresponds to the detected antenna change event.

Abstract: A computer-automated method is described for identifying and remediating anomalous data points for acquired performance parameter (e.g., KPI) values for components of a mobile wireless data network—such as PDSNs. The remediated data point sets is thereafter used as input to a forecasting model rendering a forecast for a mobile wireless network performance indicator/parameter. Data point sequence seasonality is exploited to improve the detection of anomalous data points. Furthermore, correcting data point sets is reiterated until changes between two iterations of the correction process are within a threshold magnitude for terminating the iterative data point sequence correction process.

Abstract: A computer-automated method is described for identifying and carrying out reconfiguration actions for a transmitter in a radio network. A computer system is configured to determine, for a first transmitter, a multitude of relative importance values for signal data points relating to the first transmitter, the signal data points being acquired by mobile wireless devices from the first transmitter. Each relative importance value is determined by: (1) calculating a relative relevance for a first signal data point for the first transmitter, acquired by a first mobile wireless device, by comparing a first value for the first signal data point to a second value for a second transmitter, (2) calculating, by a fuzzy logic engine, a quality for the first signal data point, and (3) rendering a relative importance value based upon the relative relevance and the quality for the first signal data point.

Abstract: A computer-automated method is described for identifying and remediating anomalous data points for acquired performance parameter (e.g., KPI) values for components of a mobile wireless data network—such as PDSNs. The remediated data point sets is thereafter used as input to a forecasting model rendering a forecast for a mobile wireless network performance indicator/parameter. Data point sequence seasonality is exploited to improve the detection of anomalous data points. Furthermore, correcting data point sets is reiterated until changes between two iterations of the correction process are within a threshold magnitude for terminating the iterative data point sequence correction process.

Abstract: A method of constructing a neighbor list for a plurality of sectors in a cellular communication environment sorts reference neighbor pairs in the network by number of occurrences based on data derived from one or more PSMM transmissions, analyzes pairs in the sorted list and determines for each pair whether a percentage of occurrence exceeds a first threshold and whether a measure of direct transition statistics exceeds a second threshold. If the percentage of occurrence exceeds a first threshold and the measure of direct transition statistics exceeds a second threshold, then if the reference's neighbor list and reciprocal neighbor list have fewer than a predetermined number of neighbors, the process adds neighbors to the reference's NL and reciprocal NL in order of occurrence percentage to create a final neighbor list.

Abstract: A method of constructing a neighbor list for a plurality of sectors in a cellular communication environment sorts reference neighbor pairs in the network by number of occurrences based on data derived from one or more PSMM transmissions, analyzes pairs in the sorted list and determines for each pair whether a percentage of occurrence exceeds a first threshold and whether a measure of direct transition statistics exceeds a second threshold. If the percentage of occurrence exceeds a first threshold and the measure of direct transition statistics exceeds a second threshold, then if the reference's neighbor list and reciprocal neighbor list have fewer than a predetermined number of neighbors, the process adds neighbors to the reference's NL and reciprocal NL in order of occurrence percentage to create a final neighbor list.