Real time radio coverage monitoring in self-organizing networks with user feedback

This paper describes an approach to providing more accurate estimates of current radio coverage and real-time monitoring of coverage changes over time, in the context of self-organizing networks (SON). Radio coverage probability models based on received signal strength (RSS) from base stations (BSs) in an outdoor environment are created. Clustering is used to partition the RSS space and a nonparametric probability approach is used to reliably estimate the radio coverage in each cluster, that is also used to test for discrepancies in the RSS coverage that may occur over time. It is assumed that data can be collected periodically from the physical environment. The analysis of discrepancies is based on models constructed from historical data and monitoring of current RSS from the mobile stations (MSs). The performance is evaluated using data generated from a network planning tool for a real environment.