Towards Smart Routing: Exploiting User Context for Video Delivery in Mobile Networks

Mobile networks are undergoing active enhancement and fast evolution, so as to host the ever-growing data traffic, mainly fuelled by video services. Despite ongoing efforts to improve the last-hop transmission in Radio Access Networks (RANs), traffic scheduling and routing in core networks remain challenging. In a system swamped with video requests, the core network needs first to schedule the transmission rate for each request, then to redirect requests to respective source nodes, and finally to route so-determined peer-to-peer flows. Towards smart routing, this paper focuses on the following two problems: (1)how to manage Quality of Experience (QoE) of video streaming services, and (2) how to optimize request routing in the core network. We exploit user context and formulate a joint problem simultaneously addressing these problems. We analyze the hardness of the formulated problem and propose a fast approximate routing algorithm, which adaptively schedules transmission rate and strategically routes the scheduled video demands. Theoretical analysis and computer simulations are then carried out to study the efficiency of the proposed algorithm.