Satellite computing: Vision and challenges
The space industry experiences a rise in low-Earth-orbit satellite mega-constellations to
achieve universal connectivity. At the same time, cloud firms (such as Google, Microsoft, and …
achieve universal connectivity. At the same time, cloud firms (such as Google, Microsoft, and …
{AWARE}: Automate workload autoscaling with reinforcement learning in production cloud systems
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 …
service performance and save resources. However, it remains challenging to set the optimal …
{StarryNet}: empowering researchers to evaluate futuristic integrated space and terrestrial networks
Futuristic integrated space and terrestrial networks (ISTN) not only hold new opportunities
for pervasive, low-latency Internet services, but also face new challenges caused by satellite …
for pervasive, low-latency Internet services, but also face new challenges caused by satellite …
A unified congestion control framework for diverse application preferences and network conditions
With the increase of diversity in application needs and networks, existing congestion control
algorithms (CCAs) do not accommodate this complicated reality. Previous classic CCAs are …
algorithms (CCAs) do not accommodate this complicated reality. Previous classic CCAs are …
A machine learning-based framework for dynamic selection of congestion control algorithms
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 …
As such, there is no known algorithm that achieves uniformly good performance in all …
EAGLE: Heterogeneous GNN-based network performance analysis
Performance analysis is of great importance for management and optimization of space-
terrestrial integrated networks (STINs). Traditional approaches to network performance …
terrestrial integrated networks (STINs). Traditional approaches to network performance …
Learned internet congestion control for short video uploading
Short video uploading service has become increasingly important, as at least 30 million
videos are uploaded per day. However, we find that existing congestion control (CC) …
videos are uploaded per day. However, we find that existing congestion control (CC) …
A novel Congestion Control algorithm based on inverse reinforcement learning with parallel training
P Luo, Y Liu, Z Wang, J Chu, G Yang - Computer Networks, 2023 - Elsevier
With the growing impact of the Internet, computer network communication has become an
essential component for various industries. Congestion Control (CC) algorithms serve as the …
essential component for various industries. Congestion Control (CC) algorithms serve as the …
Reducing First-Frame Delay of Live Streaming by Simultaneously Initializing Window and Rate
B Wu, T Li, C Luo, X Yan, F Wang… - 2024 IEEE 44th …, 2024 - ieeexplore.ieee.org
The first-frame delay is an essential indicator for evaluating the performance of cloud CDN
vendors and affects the client-side QoE of live streaming. Instead of the traditional way of …
vendors and affects the client-side QoE of live streaming. Instead of the traditional way of …
Marten: A built-in security drl-based congestion control framework by polishing the expert
Deep reinforcement learning (DRL) has been proved to be an effective method to improve
the congestion control algorithms (CCAs). However, the lack of training data and training …
the congestion control algorithms (CCAs). However, the lack of training data and training …