An Adaptive Neuro-Fuzzy Based Vertical Handoff Decision Algorithm for Wireless Heterogeneous Networks

Currently, single wireless network technology can not satisfy all of the requirements of mobile users at anywhere and anytime. Due to such requirements as QoS provision, cost efficiency, mobility, and etc. integration of different wireless technologies is necessary and there is, in turn, an urgent demand to develop vertical handoff approaches that enable mobile terminals to seamlessly roam between wireless networks overlap with each other. In the quest for efficient handoff especially in the heterogeneous environment, various handoff decision making techniques have been proposed in the literature. In this paper, an adaptive fuzzy logic based vertical handoff decision making algorithm and an Adaptive Network Fuzzy Inference System (ANFIS) based vertical handoff decision making algorithm are developed for wireless heterogeneous networks which consist of GSM/GPRS, Wi-Fi, UMTS and WiMAX technologies. The parameters data rate, monetary cost and RSSI information are processed as inputs of the developed fuzzy based system. According to these parameters, an output value APCV which is utilized to chose the best candidate access point, is produced. Training data of ANFIS based vertical handoff decision making algorithm is obtained from the developed fuzzy based handoff algorithm and human expert. The results show that, compared to the typical fuzzy based algorithm, proposed ANFIS algorithm can provide enhanced outcomes for both user and network in terms of number of handoff, decision process time, and hardware implementation.