English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Mobile Edge Caching (MEC) is a revolutionary technology for the SixthGeneration (6G) of wireless networks with the promise to significantly reduceusers' latency via offering storage capacities at the edge of the network. Theefficiency of the MEC network, however, critically depends on its ability todynamically predict/update the storage of caching nodes with the top-K popularcontents. Conventional statistical caching schemes are not robust to thetime-variant nature of the underlying pattern of content requests, resulting ina surge of interest in using Deep Neural Networks (DNNs) for time-seriespopularity prediction in MEC networks. However, existing DNN models within thecontext of MEC fail to simultaneously capture both temporal correlations ofhistorical request patterns and the dependencies between multiple contents.This necessitates an urgent quest to develop and design a new and innovativepopularity prediction architecture to tackle this critical challenge. The paperaddresses this gap by proposing a novel hybrid caching framework based on theattention mechanism. Referred to as the parallel Vision Transformers with CrossAttention (ViT-CAT) Fusion, the proposed architecture consists of two parallelViT networks, one for collecting temporal correlation, and the other forcapturing dependencies between different contents. Followed by a CrossAttention (CA) module as the Fusion Center (FC), the proposed ViT-CAT iscapable of learning the mutual information between temporal and spatialcorrelations, as well, resulting in improving the classification accuracy, anddecreasing the model's complexity about 8 times. Based on the simulationresults, the proposed ViT-CAT architecture outperforms its counterparts acrossthe classification accuracy, complexity, and cache-hit ratio.

ViT-CAT: Parallel Vision Transformers with Cross Attention Fusion for Popularity Prediction in MEC Networks