Learning-based optimization of cache content in a small cell base station

Abstract

Optimal cache content placement in a wireless small cell base station (sBS) with limited backhaul capacity is studied. The sBS has a large cache memory and provides content-level selective offloading by delivering high data rate contents to users in its coverage area. The goal of the sBS content controller (CC) is to store the most popular contents in the sBS cache memory such that the maximum amount of data can be fetched directly form the sBS, not relying on the limited backhaul resources during peak traffic periods. If the popularity profile is known in advance, the problem reduces to a knapsack problem. However, it is assumed in this work that, the popularity profile of the files is not known by the CC, and it can only observe the instantaneous demand for the cached content. Hence, the cache content placement is optimised based on the demand history. By refreshing the cache content at regular time intervals, the CC tries to learn the popularity profile, while exploiting the limited cache capacity in the best way possible. Three algorithms are studied for this cache content placement problem, leading to different exploitation-exploration trade-offs. We provide extensive numerical simulations in order to study the time-evolution of these algorithms, and the impact of the system parameters, such as the number of files, the number of users, the cache size, and the skewness of the popularity profile, on the performance. It is shown that the proposed algorithms quickly learn the popularity profile for a wide range of system parameters.

Fundamental limits of caching with secure delivery

“…The same holds true for the other users. The rate for the composite transmission X (A,B,C) is obtained by summing (20), (21) and (22):…”

“…The fundamental concepts presented in [7] are extended to the case of decentralized storage in [8] and non-uniform ZipF [13] user demands in [9], [14]. Some extensions of the caching problem have been investigated in the case of Device-to-Device (D2D) communications in [15]- [18], from the perspective of content distribution networks in [19] and reinforcement learning in [20]- [22].…”

Enabling context-aware HTTP with mobile edge hint

“…This meta-data includes information of each embedded object, such as object size, object URL, object type, last update time etc. It is worth mentioning that for scalability purposes this operation only targets at popular webpages that are frequently visited by local mobile users, and such popularity can be monitored by the network through specific mechanisms [21]. (2) Network measurement service.…”

Exploiting Caching and Multicast for 5G Wireless Networks

“…All the above works assume that the users' demand profiles are perfectly known and optimize caching decisions based on content demand solely, an assumption that was firstly relaxed in [29], [30]. In our recent work in [49], we proposed the caching policy design with concerns on both the user mobility statistics and the content demand.…”

“…The user demand for a set of popular files and within a certain time period is assumed to be known in advance, as in [17]- [20], [25]- [28] which is possible using learning techniques [29], [30]. Let I indicate that collection of files, with I = |I|.…”