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

In modern networking research, infrastructure-assisted unmanned autonomousvehicles (UAVs) are actively considered for real-time learning-basedsurveillance and aerial data-delivery under unexpected 3D free mobility andcoordination. In this system model, it is essential to consider the powerlimitation in UAVs and autonomous object recognition (for abnormal behaviordetection) deep learning performance in infrastructure/towers. To overcome thepower limitation of UAVs, this paper proposes a novel aerial schedulingalgorithm between multi-UAVs and multi-towers where the towers conduct wirelesspower transfer toward UAVs. In addition, to take care of the high-performancelearning model training in towers, we also propose a data delivery scheme whichmakes UAVs deliver the training data to the towers fairly to prevent problemsdue to data imbalance (e.g., huge computation overhead caused by larger datadelivery or overfitting from less data delivery). Therefore, this paperproposes a novel workload-aware scheduling algorithm between multi-towers andmulti-UAVs for joint power-charging from towers to their associated UAVs andtraining data delivery from UAVs to their associated towers. To compute theworkload-aware optimal scheduling decisions in each unit time, our solutionapproach for the given scheduling problem is designed based on Markov decisionprocess (MDP) to deal with (i) time-varying low-complexity computation and (ii)pseudo-polynomial optimality. As shown in performance evaluation results, ourproposed algorithm ensures (i) sufficient times for resource exchanges betweentowers and UAVs, (ii) the most even and uniform data collection during theprocesses compared to the other algorithms, and (iii) the performance of alltowers convergence to optimal levels.

Workload-Aware Scheduling using Markov Decision Process for Infrastructure-Assisted Learning-Based Multi-UAV Surveillance Networks