The Design and Implementation of a Mobile Agent-Based Framework for Context Aware Computing

Abstract

With the progress of wireless and mobile network technology, people can access information via various kinds of handsets or facilities of Information Appliance (IA), while these facilities range from high-computed ones to low ones. Within the handsets, however, cellular phones, PDA, Tablet PC enable people to surf the internet and move at same time in the wireless network environment. Under such circumstance, people can access different type of internet information, like words, sounds, images or videos, by specific terminal device at anytime and anywhere. In such case, however, here come two problems: (1) The movement of users is limited; (2) The users must carry their terminal device with themselves. In order to solve these problems, we combine both the concepts of pervasive computing and context awareness to develop a framework possessing mobile agent paradigm and context data modeling. Aimed at the present pervasive computing in the wireless network environment, we propose a Mobile Agent Context Aware Framework– MACAF. In MACAF, we regard mobile agent system as the fundamental computing platform, and describe three kinds of context data by RDF - Component Profile, User Device Profile, and User Preference Profile. In addition, we use dynamic class loader of JAVA and XML parsing techniques so that when personal mobility and terminal mobility arise, users’ applications can move with users via two kinds of mobility technique of agent of this system - Agent Migration Approach (AMA), and State Transfer Approach (STA). This system makes applications follow users and applications be reconfigured automatically after mobility so as to accommodate various execution environments to reach the purpose of the context awareness and the pervasive computing.