Identifying the Effective Parameters for Vertical Handover in Cellular Networks Using Data Mining Techniques

Abstract

The need for seamless mobility within the heterogeneous environment of cellular networks imposed the need for finding different vertical handover (VHO) mechanisms to select the best network. The selection process is based on different factors, such as: cost, battery status of Mobile Terminal (MT), the capacity of each network link, available bandwidth (ABW), received signal strength (RSS), etc. However, the major problem here is to find the most effective parameters for VHO and their priorities for these decision mechanisms. Besides, it would be useful to know the values of these parameters for data mining (DM). For this purpose, we collected real log data server of two mobile telecom companies in Lebanon, Touch and Alfa for Global System for Mobile Communications (GSM) and Universal Mobile Telecommunications System (UMTS) networks. After preprocessing and discretizing the data, frequent patterns (FP) were extracted to summarize the log data files. The summarized data was then analyzed by using descriptive and visualization techniques in order to find the most effective parameters for handover (HO) process. Three effective parameters were obtained: the Received Signal Strength (RxLev/RSCP), the Available Bandwidth (ABW) and the Received Signal Quality (RxQual/EcNo). Results showed that they cooperatively work together to accomplish the same task. This paper provide an effective solution to identify the most valuable factors for vertical handover mechanism in telecommunication area by using frequent pattern mining.