Mobile Ad-Hoc Networks Location Prediction by Using Artificial Neural Networks: Considerations and Future Directions
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.