Advanced mobile network monitoring and automated optimization methods

Abstract

The operation of mobile networks is a complex task with the networks serving a large amount of subscribers with both voice and data services, containing extensive sets of elements, generating extensive amounts of measurement data and being controlled by a large amount of parameters. The objective of this thesis was to ease the operation of mobile networks by introducing advanced monitoring and automated optimization methods. In the monitoring domain the thesis introduced visualization and anomaly detection methods that were applied to detect intrusions, mal-functioning network elements and cluster network elements to do parameter optimization on network-element-cluster level. A key component in the monitoring methods was the Self-Organizing Map. In the automated optimization domain several rule-based Wideband CDMA radio access parameter optimization methods were introduced. The methods tackled automated optimization in areas such as admission control, handover control and mobile base station cell size setting. The results from test usage of the monitoring methods indicated good performance and simulations indicated that the automated optimization methods enable significant improvements in mobile network performance. The presented methods constitute promising feature candidates for the mobile network management system.