Fog computing architectures, privacy and security solutions
S Mostafavi, W Shafik - Journal of Communications Technology …, 2019 - ojs.jctecs.com
Fog computing is a promising computing paradigm that extends cloud computing to the
edge of networks where it provides services closer to users characterized by closer proximity …
edge of networks where it provides services closer to users characterized by closer proximity …
FAMG: A flow-aware and mixed granularity method for load-balancing in data center networks
Y Lu, Z Xu, X Ma - Computer Communications, 2023 - Elsevier
Abstract In current Data center Networks (DCNs), Equal-Cost Multipath (ECMP) is a default
load-balancing scheme. However, using ECMP may result in the rapid growth of Flow …
load-balancing scheme. However, using ECMP may result in the rapid growth of Flow …
DGT: A contribution-aware differential gradient transmission mechanism for distributed machine learning
Distributed machine learning is a mainstream system to learn insights for analytics and
intelligence services of many fronts (eg, health, streaming and business) from their massive …
intelligence services of many fronts (eg, health, streaming and business) from their massive …
Meeting coflow deadlines in data center networks with policy-based selective completion
Recently, the abstraction of coflow is introduced to capture the collective data transmission
patterns among modern distributed data-parallel applications. During processing, coflows …
patterns among modern distributed data-parallel applications. During processing, coflows …
New primitives for bounded degradation in network service
Certain new ascendant data center workloads can absorb some degradation in network
service, not needing fully reliable data transport and/or their fair-share of network bandwidth …
service, not needing fully reliable data transport and/or their fair-share of network bandwidth …
Tailor: Datacenter Load Balancing For Accelerating Distributed Deep Learning
Z Xu, Y Lu, J Li, X Ma, L Qian - 2021 Ninth International …, 2022 - ieeexplore.ieee.org
Accelerating Distributed Deep Learning draws increasing attention recently. Existing
solutions like gradient compression, pipelining computation/communication, flow scheduling …
solutions like gradient compression, pipelining computation/communication, flow scheduling …
Selective coflow completion for time-sensitive distributed applications with poco
Recently, the abstraction of coflow is introduced to capture the collective data transmission
patterns among modern distributed data-parallel application. During processing, coflows …
patterns among modern distributed data-parallel application. During processing, coflows …
Performance Evaluation of Networked Systems
SA Kassing - 2022 - research-collection.ethz.ch
Networked systems are tasked with processing large amounts of data and timely responding
to requests coming in at high rates. These tasks involve the collaboration and …
to requests coming in at high rates. These tasks involve the collaboration and …
[PDF][PDF] DGT: A communication-efficient differential gradient transmission protocol for distributed deep learning
In recent years, researchers have paid more attention to distributed deep learning to train
large-scale models with massive data in parallel, which is much more efficient than training …
large-scale models with massive data in parallel, which is much more efficient than training …