A Scoring Method for the Verification of Con_x000C_guration Changes in Self-Organizing Networks

In today's mobile communication networks the increasing reliance on Self-Organizing Network (SON) features to perform the correct optimization tasks adds a new set of challenges. In a SON-enabled network, the impact of each function's action on the environment depends upon the actions of other functions as well. Therefore, the concept of pre-action coordination has been introduced to detect and resolve known conflicts between SON function instances. Furthermore, the idea of postaction SON verification has been proposed which is often understood as a special type of anomaly detection. It computes statistical measures on performance indicators at a relevant spatial and temporal aggregation level to assess the impact of a set of (SON-evoked) Con_x000C_guration Management (CM) changes. In this paper, we present such a veri_x000C_cation technique, which utilizes Key Performance Indicator (KPI) normalization, aggregation and statistical processing for dynamically changing areas of the network. In addition, the introduced approach rewards or punishes CM changes based on their impact on the network and generates a recommendation to accept or undo them. A Coverage and Capacity Optimization (CCO) case study based on real Performance Management (PM) and CM data from an operator's Wideband Code Division Multiple Access (WCDMA) network is presented.