Dynamic backhaul resource allocation in wireless networks using artificial neural networks

The increasing bandwidth demand of end-users renders the need for efficient resource management more compelling in next generation wireless networks. In the present work, a novel scheme incorporating the deployment of an intelligent agent capable of monitoring, storing, and predicting the forthcoming needs for resources of a base station (BS) is proposed. In this way, the BS can in advance commit the necessary resources for its backhaul connection, guaranteeing the end-user's quality of service. The prediction process is performed using machine learning techniques.