FLASH: Fast model adaptation in ML-centric cloud platforms
The emergence of ML in various cloud system management tasks (eg, workload autoscaling
and job scheduling) has become a core driver of ML-centric cloud platforms. However, there …
and job scheduling) has become a core driver of ML-centric cloud platforms. However, there …
Astraea: Towards Fair and Efficient Learning-based Congestion Control
Recent years have witnessed a plethora of learning-based solutions for congestion control
(CC) that demonstrate better performance over traditional TCP schemes. However, they fail …
(CC) that demonstrate better performance over traditional TCP schemes. However, they fail …
Liteflow: towards high-performance adaptive neural networks for kernel datapath
Adaptive neural networks (NN) have been used to optimize OS kernel datapath functions
because they can achieve superior performance under changing environments. However …
because they can achieve superior performance under changing environments. However …
Towards fair and efficient learning-based congestion control
Recent years have witnessed a plethora of learning-based solutions for congestion control
(CC) that demonstrate better performance over traditional TCP schemes. However, they fail …
(CC) that demonstrate better performance over traditional TCP schemes. However, they fail …
Resource Critical Flow Monitoring in Software-Defined Networks
Flow monitoring is widely applied in software-defined networks (SDNs) for monitoring
network performance. Especially, detecting heavy hitters can prevent the Distributed Denial …
network performance. Especially, detecting heavy hitters can prevent the Distributed Denial …
Dragonfly: In-Flight CCA Identification
D Carmel, I Keslassy - IEEE Transactions on Network and …, 2024 - ieeexplore.ieee.org
We introduce the Dragonfly system, which is designed to classify on the fly the congestion
control algorithm of any flow that crosses a given router, starting at any time, and quickly …
control algorithm of any flow that crosses a given router, starting at any time, and quickly …
A Data-Driven Framework for TCP to Achieve Flexible QoS Control in Mobile Data Networks
Learning-based approaches have shown their great potential to adapt themselves to various
environments (eg, PCC and Sprout). Unfortunately, they do not consistently achieve superior …
environments (eg, PCC and Sprout). Unfortunately, they do not consistently achieve superior …
[PDF][PDF] On the Promise and Challenges of Foundation Models for Learning-based Cloud Systems Management
Foundation models (FMs) are machine learning models that are trained broadly on large-
scale data and can be adapted to a set of downstream tasks via fine-tuning, few-shot …
scale data and can be adapted to a set of downstream tasks via fine-tuning, few-shot …
Towards Enabling Performance-Guaranteed Slice Management and Orchestration in 6G
Next-generation network services (eg, XR, mobile hologram, digital twin) often expect both
latency and bandwidth guarantees. In the 5G network, network slicing techniques that …
latency and bandwidth guarantees. In the 5G network, network slicing techniques that …
[HTML][HTML] DeepSHARQ: hybrid error coding using deep learning
P Gil Pereira, K Vogelgesang, M Miodek… - Journal of Reliable …, 2023 - Springer
Cyber-physical systems operate under changing environments and on resource-constrained
devices. Communication in these environments must use hybrid error coding, as pure pro-or …
devices. Communication in these environments must use hybrid error coding, as pure pro-or …