Fractional Dynamic Caching: Minimizing the File Delivery Time under Limited Backhaul

王刘猛SPAWC17

LANGUAGE English

SOURCE  IEEE SPAWC 2017, July 3-7, Hokkaido, 2017

Published Date:2017-06

ABSTRACT

To reduce the average file delivery time under limited backhaul bandwidth, a fractional dynamic caching scheme, that coordinates the utilization of the backhaul and the cache storage, is proposed in this paper. In our scheme, only parts of the files are pre-fetched and stored in the static storage segment of small base stations (SBSs), while the remaining parts of the files will be fetched into the dynamic storage segment when requested by users.
We aim to minimize the average file delivery time by investigating the optimal pre-fetching policy, including the static caching size of each file and the size of the dynamic storage segment. We first derive the average file delivery time given the size of the dynamic storage segment, and obtain the corresponding optimal pre-fetching policy. The optimal size of the dynamic storage segment is then derived in closed-form. Numerical results show that with our scheme, the average file delivery time can be substantially reduced.