期刊名称：International Journal of Computer Technology and Applications
电子版ISSN：2229-6093
出版年度：2013
卷号：4
期号：1
页码：120-125
出版社：Technopark Publications
摘要：Location prediction serves to save capacity on the air interface of mobile radio networks.Location prediction is the estimation of a mobile host’s location at a time in future. When the future location of a mobile host is known, this information can be used in a number of ways to improve the performance of the network. The hosts are free to move anywhere.The mobile hosts can move with different mobility patterns. Mobility Models are used to represent the different mobility patterns. Mobility metrics are used to differentiate the mobility models from each other. Different mobility models impact the protocols in different ways.A selection of neural networks of the feed-forward and feedback type are examined to prove their suitability for this purpose. In this paper, as first results preferable network structures, input vectors, learning parameters and the simulated prediction probabilities are presented. A comparison with conventional methods shows the advantages and disadvantages of the use of neural networks for motion prediction. The results show that the gain depends on the user profile and the amount of extraordinary movements of the subscriber
关键词：Location Prediction; Mobile hosts; neural networks; Mobility metrics; MANET
