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

Heavy data load and wide cover range have always been crucial problems foronline data processing in internet of things (IoT). Recently, mobile-edgecomputing (MEC) and unmanned aerial vehicle base stations (UAV-BSs) haveemerged as promising techniques in IoT. In this paper, we propose a three-layeronline data processing network based on MEC technique. On the bottom layer, rawdata are generated by widely distributed sensors, which reflects localinformation. Upon them, unmanned aerial vehicle base stations (UAV-BSs) aredeployed as moving MEC servers, which collect data and conduct initial steps ofdata processing. On top of them, a center cloud receives processed results andconducts further evaluation. As this is an online data processing system, theedge nodes should stabilize delay to ensure data freshness. Furthermore,limited onboard energy poses constraints to edge processing capability. Tosmartly manage network resources for saving energy and stabilizing delay, wedevelop an online determination policy based on Lyapunov Optimization. In casesof low data rate, it tends to reduce edge processor frequency for savingenergy. In the presence of high data rate, it will smartly allocate bandwidthfor edge data offloading. Meanwhile, hovering UAV-BSs bring a large andflexible service coverage, which results in the problem of effective pathplanning. In this paper, we apply deep reinforcement learning and develop anonline path planning algorithm. Taking observations of around environment asinput, a CNN network is trained to predict the reward of each action. Bysimulations, we validate its effectiveness in enhancing service coverage. Theresult will contribute to big data processing in future IoT.

Towards Big data processing in IoT: Path Planning and Resource Management of UAV Base Stations in Mobile-Edge Computing System