A capable location prediction and resource reservation scheme in wireless networks for multimedia

In this paper, NPS (neural-network prediction scheme) is proposed to provide high accurate location prediction of a MH (mobile host) in wireless networks. Currently, multimedia communications is urgently expected in wireless networks, because more and more high-speed applications emerge for wireless networks. One of the most important and complicated issues is quality of service (QoS) in third-generation (3G) wireless networks. In other words, the problem to maintain the playing continuity of multimedia streams during a handoff is hard to solve. Hence, bandwidth reservation scheme is proposed in this paper. In order to avoid too early or over reservation resulting in a waste of resources, we present a method called three-times resource-reservation scheme (TTRR) to let reserved resource become really active upon MH entering into tier-2 [C.H. Choi et al., 2000] area of a cell. NPS and TTRR can efficiently improve the accuracy of MH´s trajectory prediction, increase the success probability of resource reservation, and enhance bandwidth utilization.