Echo State Networks for Proactive Caching in Cloud-Based Radio Access Networks With Mobile Users

Abstract

In this paper, the problem of proactive caching is studied for cloud radio access networks (CRANs). In the studied model, the baseband units (BBUs) can predict the content request distribution and mobility pattern of each user, determine which content to cache at remote radio heads and BBUs. This problem is formulated as an optimization problem which jointly incorporates backhaul and fronthaul loads and content caching. To solve this problem, an algorithm that combines the machine learning framework of echo state networks with sublinear algorithms is proposed. Using echo state networks (ESNs), the BBUs can predict each user's content request distribution and mobility pattern while having only limited information on the network's and user's state. In order to predict each user's periodic mobility pattern with minimal complexity, the memory capacity of the corresponding ESN is derived for a periodic input. This memory capacity is shown to capture the maximum amount of user information needed for the proposed ESN model. Then, a sublinear algorithm is proposed to determine which content to cache while using limited content request distribution samples. Simulation results using real data from Youku and the Beijing University of Posts and Telecommunications show that the proposed approach yields significant gains, in terms of sum effective capacity, that reach up to 27.8% and 30.7%, respectively, compared to random caching with clustering and random caching without clustering algorithm.

Dynamic theoretic proactive caching placement game for energy saving in H‐CRAN

“…The related researches mainly focused on minimizing the file access latency (eg, Zhou et al), reducing the transmission cost of the backhaul (eg, Liao et al), or both of them (eg, Li et al), maximizing the cache hit ratio (eg, previous studies), enhancing security transmission (eg, Shi et al), size of content offload (eg, Wang et al), average caching failure probability (eg, Kang HJ and Kang CG). Others focused on energy saving (eg, previous studies). In Zhou et al, the probabilistic caching placement was advanced in clustered cellular networks, where the amount of delivered contents and the limited storage capacity of the small cells within the cluster were identified as two constraints to reduce the average latency.…”

An Economic Aspect of Device-to-Device Assisted Offloading in Cellular Networks

“…The value of content popularity can be obtained by the keywords feature extraction method [20], [21] or the machine learning method [22], [23] according to the users' download history.…”

“…Motivated by [22], the baseband units (BBUs) can predict the distribution of content request and users's mobility. This information gathering phase results in the additional computational cost for the operator, which can be approximately regarded as a fix cost.…”

Joint uplink and downlink delay‐aware resource allocation in C‐RAN

“…Due to the importance of delay QoS requirement, a considerable amount of literature has been investigated resource allocation problems to meet this essential requirement in the C‐RAN architecture . One well‐known approach for delay QoS guarantees is to impose average delay constraint .…”

“…[8][9][10] Due to the importance of delay QoS requirement, a considerable amount of literature has been investigated resource allocation problems to meet this essential requirement in the C-RAN architecture. [11][12][13] One well-known approach for delay QoS guarantees is to impose average delay constraint. 14 By exploiting the queuing theory, this restriction can be expressed in terms of the minimum transmission rate constraint.…”