Proactive Replica Placement Using Mobility Prediction
Résumé
This work brings together data replication management and mobility modeling for mobile distributed computing scenarios. Based on a novel mobility model and on the prediction of future mobile behavior, techniques for proactive data replication and placement management are developed for mobile users. Based on this joint approach the responsiveness of a flexible replica placement algorithm is increased for the end users and the overall resource consumption is minimized. In this article we describe and evaluate our approach using GPS traces stored by taxis in the city of Vienna, Austria.