Femtocells sharing management using mobility prediction model

Abstract

Abstract-With the unexpected increase of mobile data requests which overload the traffic control infrastructure of the network, operators are faced with a serious capacity management problem. In femtocell networks, bandwidth sharing paradigm constitutes an incentive solution for femtocells owners to offer a QoS guaranteed network access to mobile users in their femtocell coverage. In this paper, we consider a techno-economic bandwidth sharing model inspired from FON system and based on a reinforcement learning algorithm. Such a model does not allow the convergence of the learning algorithm because of the small size of the femtocells, the mobile users velocity and, more importantly, the randomness of their arrivals. In order to overcome the real-time constraints faced by this bandwidth sharing model, we propose to use a mobility prediction approach based on the analysis of movements history of the mobile users. Knowing the next visited cell in advance provides more time to mobile user to negotiate with the access provider and to generate synchronized resource reservation requests that maximize the gain of the access provider.