Placement of Dynamic Content Items in Mobile Edge Caching

Abstract

The emerging intelligent mobile applications such as augment/virtual reality and automatons driving require extensive context information, generating dynamic items whose content may change with time and environment. In this regard, the dynamic items should be refreshed to the newest versions timely, when cached at the network edge. The state-of-the-art content placement methods mostly target on static items, and cache the popular items with priority to maximize the local hit rate. However, popular content items may have higher dynamics and require frequent cache refresh, which consumes more transmissions and degrades the system efficiency. In this work, we revisit the content placement problem at mobile edge, where the content dynamics and popularity are jointly considered when choosing items to cache. To this end, the effective hit rate of an cached content item is derived with respect to the corresponding request rate (i.e., popularity) and version update rate (i.e., dynamics). Specifically, the effective hit rate is proved to increase with the request arrival rate in an convex manner and decrease with the version update rate. Then, the popularity- and-lifetime-aware placement (PALAP) scheme is proposed to maximize the overall effective hit rate of the local cache when providing dynamic content services. Extensive simulations are conducted on OMNeT++ platform to validate the obtained analytical results. In addition, simulation results show that the proposed scheme can double the cache hit rate compared with the conventional most-popular-first placement (MPFP) scheme, if the content requests are less concentrated. Accordingly, the average service delay can be reduced effectively, especially when the system is heavily loaded.