Node Position Forecast in MANET with PheroCast

In mobile ad hoc networks (MANET) nodes are free to move on the environment and interact with each other and with the infra-structure, enabling a multitude of applications and services. However, the same mobility that is key to MANET is also the greater limiting factor in the quality of the services provided in this environment, since the infrastructure must keep adapting to the mobility. This paper describes algorithms for predicting the future position of mobile nodes in MANET, allowing the infrastructure to proactively adapt. Our algorithms maintain the recent movement history of nodes in a compact representation, a graph, based on stigmergy of ant colonies. Predictions are generated through a limited depth first search. We have experimented this method against real world data and the results show that the prediction is accurate for short time horizons (30 seconds) in a metropolitan area (Seattle) divided in a grid of two or three-block square cells, in 77.8% of the cases. This method may be used in optimizing MANET and enabling novel applications, for example, proactive hand-off, tailored content generation, and proactive routing.