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

The emergence of smart Wi-Fi APs (Access Point), which are equipped with hugestorage space, opens a new research area on how to utilize these resources atthe edge network to improve users' quality of experience (QoE) (e.g., a shortstartup delay and smooth playback). One important research interest in thisarea is content prefetching, which predicts and accurately fetches contentsahead of users' requests to shift the traffic away during peak periods.However, in practice, the different video watching patterns among users, andthe varying network connection status lead to the time-varying server load,which eventually makes the content prefetching problem challenging. Tounderstand this challenge, this paper first performs a large-scale measurementstudy on users' AP connection and TV series watching patterns usingreal-traces. Then, based on the obtained insights, we formulate the contentprefetching problem as a Markov Decision Process (MDP). The objective is tostrike a balance between the increased prefetching&storage cost incurred byincorrect prediction and the reduced content download delay because ofsuccessful prediction. A learning-based approach is proposed to solve thisproblem and another three algorithms are adopted as baselines. In particular,first, we investigate the performance lower bound by using a random algorithm,and the upper bound by using an ideal offline approach. Then, we present aheuristic algorithm as another baseline. Finally, we design a reinforcementlearning algorithm that is more practical to work in the online manner. Throughextensive trace-based experiments, we demonstrate the performance gain of ourdesign. Remarkably, our learning-based algorithm achieves a better precisionand hit ratio (e.g., 80%) with about 70% (resp. 50%) cost saving compared tothe random (resp. heuristic) algorithm.

Towards Wi-Fi AP-Assisted Content Prefetching for On-Demand TV Series: A Reinforcement Learning Approach