Quantifying visual pollution from urban air mobility

K Thomas, TA Granberg - Drones, 2023 - mdpi.com
Unmanned aerial vehicles (UAVs) can bring many benefits, particularly in emergency
response and disaster management. However, they also induce negative effects, such as …

Deployment Method with Connectivity for Drone Communication Networks

H Osumi, T Kimura, K Hirata, C Premachandra… - Drones, 2023 - mdpi.com
In this paper, we consider a drone deployment problem in situations where the number of
drones to be deployed is small compared to the number of users on the ground. In this …

UrsaX: Integrating Block I/O and Message Transfer for Ultrafast Block Storage on Supercomputers

S Gai, Y Zhang, X Xie, H Chen, X Zhao… - … on Computer-Aided …, 2023 - ieeexplore.ieee.org
It is increasingly important for the next-generation exascale supercomputers to extend its
applications beyond traditional high-performance computing (HPC) scenarios, so as to …

In-network monitoring strategies for HPC cloud

M Hemmatpour, TH Larsen, N Kumar… - … Conference on Advanced …, 2024 - Springer
The optimized network architectures and interconnect technologies employed in high-
performance cloud computing environments introduce challenges when it comes to …

[HTML][HTML] Optimisation de l'allocation de la mémoire cache CPU pour les fonctions cloud et les applications haute performance

AJ Toulepi - 2024 - ut3-toulouseinp.hal.science
Les services informatiques contemporains reposent principalement sur deux paradigmes
majeurs: le cluster computing et le cloud computing. Le premier implique la répartition des …

Locality-aware batch scheduling of I/O intensive workloads

M Gonthier, L Marchal, S Thibault, E Larsson… - 2022 - inria.hal.science
Clusters make use of workload schedulers such as the Slurm Workload Manager to allocate
computing jobs onto nodes. These schedulers usually aim at a good trade-off between …

Data-Driven Locality-Aware Batch Scheduling

M Gonthier, E Larsson, L Marchal… - APDCM 2024-26th …, 2024 - inria.hal.science
Clusters employ workload schedulers such as the Slurm Workload Manager to allocate
computing jobs onto nodes. These schedulers usually aim at a good trade-off between in …