{AWARE}: Automate workload autoscaling with reinforcement learning in production cloud systems

H Qiu, W Mao, C Wang, H Franke, A Youssef… - 2023 USENIX Annual …, 2023 - usenix.org
Workload autoscaling is widely used in public and private cloud systems to maintain stable
service performance and save resources. However, it remains challenging to set the optimal …

Computers Can Learn from the Heuristic Designs and Master Internet Congestion Control

CY Yen, S Abbasloo, HJ Chao - … of the ACM SIGCOMM 2023 Conference, 2023 - dl.acm.org
In this work, for the first time, we demonstrate that computers can automatically learn from
observing the heuristic efforts of the last four decades, stand on the shoulders of the existing …

FLASH: Fast model adaptation in ML-centric cloud platforms

H Qiu, W Mao, A Patke, S Cui, C Wang… - Proceedings of …, 2024 - proceedings.mlsys.org
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 …

Spine: An efficient DRL-based congestion control with ultra-low overhead

H Tian, X Liao, C Zeng, J Zhang, K Chen - Proceedings of the 18th …, 2022 - dl.acm.org
Previous congestion control (CC) algorithms based on deep reinforcement learning (DRL)
directly adjust flow sending rate to respond to dynamic bandwidth change, resulting in high …

Prioritization-driven congestion control in networks for the internet of medical things: A cross-layer proposal

R Buenrostro-Mariscal, PC Santana-Mancilla… - Sensors, 2023 - mdpi.com
Real-life implementation of the Internet of Things (IoT) in healthcare requires sufficient
quality of service (QoS) to transmit the collected data successfully. However, unsolved …

Liteflow: towards high-performance adaptive neural networks for kernel datapath

J Zhang, C Zeng, H Zhang, S Hu, K Chen - Proceedings of the ACM …, 2022 - dl.acm.org
Adaptive neural networks (NN) have been used to optimize OS kernel datapath functions
because they can achieve superior performance under changing environments. However …

Astraea: Towards Fair and Efficient Learning-based Congestion Control

X Liao, H Tian, C Zeng, X Wan, K Chen - Proceedings of the Nineteenth …, 2024 - dl.acm.org
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 …

HINT: Supporting congestion control decisions with P4-driven in-band network telemetry

A Sacco, A Angi, F Esposito… - 2023 IEEE 24th …, 2023 - ieeexplore.ieee.org
Years of research on congestion controls have highlighted how end-to-end and in-network
protocols might perform poorly in some contexts. Recent advances in data plane network …

A machine learning-based framework for dynamic selection of congestion control algorithms

J Zhou, X Qiu, Z Li, Q Li, G Tyson… - IEEE/ACM …, 2022 - ieeexplore.ieee.org
Most congestion control algorithms (CCAs) are designed for specific network environments.
As such, there is no known algorithm that achieves uniformly good performance in all …

Habitus: Boosting Mobile Immersive Content Delivery through Full-body Pose Tracking and Multipath Networking

A Zhang, C Wang, Y Hu, A Hassan, Z Zhang… - … USENIX Symposium on …, 2024 - usenix.org
Delivering immersive content such as volumetric videos and virtual/mixed reality requires
tremendous network bandwidth. Millimeter Wave (mmWave) radios such as 802.11 ad/ay …