Decision Support System for Vertical Handover in Cellular Networks


"The rapid evolution of telecommunication networks and mobile technologies imposed the need for the existence of heterogeneous environments, where signal coverage is needed throughout the different available networks. The challenge with such environment is to provide the user with the ability to navigate through the different available networks, and roam seamlessly and transparently. The navigation between different types of networks is known as vertical handover (VHO). VHO process is mainly consists of three phases: information gathering, VHO decision and VHO execution. The need for a mobile terminal to keep an acceptable Quality of Service (QoS) within the heterogeneous environments, imposed the need to extend QoS for services that are available in mobile networks. In telecommunication domain, there are four different QoS classes or traffic classes: Conversational class, Streaming class, Interactive class and Background class. The most delay sensitive applications, like voice calls, are related to Conversational realtime services which are carried in Conversational class. In literature, different vertical VHO algorithms are presented with several input parameters for various services related to different traffic classes. Most researchers focus on VHO decision phase two of VHO. Where in the first phase they suggest a number of input parameters and some of them are selected based on simulation analysis or experts opinions. In this research, our approach starts from the first phase of VHO process, the information gathering for the input parameters. Furthermore, it is very important to take into consideration that VHO process must be occurred in a minimum time to avoid service disconnection. For this purpose, we proposed a new approach in order to find the most effective parameters and their priorities by using Data Mining (DM), rather than using and processing less effective ones. Since voice call service is one of the most sensitive delay services, we collected real log data parameters for this service 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, the log data file was then summarized and the frequent patterns (FP) were extracted. In this research, two new algorithms were designed. The first, is the Data Summarization Algorithm (DaSA) to summarize the preprocessed data. The second, is the Frequent Pattern Calculation Algorithm (FPCA) to find the frequency of the simultaneous occurrence of the obtained parameters. The summarized data was then analyzed by using statistical descriptive techniques. 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 VHO process. "


Nadine Ghazi Kashmar


Dr. Ali Haidar, Dr. Mirna Attiah