User-in-the-loop (UiL) content delivery is a recently proposed scheme for personalized content retrieval over mobile communication networks. It is a promising scheme that can better manage the overall user quality-of-experience (QoE) throughout the entire content retrieval process. The performance of the scheme, however, has only been investigated in a simplified system model that assumed synchronized user behavior, inflexible delay constraint, and identical quality-of-service (QoS) requirement among users. This paper studies the performance of UiL content delivery scheme in a generalized and realistic system model with asynchronous user behavior, flexible outage delay constraint, and customized user QoS. Heuristic algorithms and theoretical bounds are investigated for the UiL content delivery problem. The proposed system is shown to be effective in managing the user QoE in generalized practical scenarios.
展开▼
