Eagle: Refining Congestion Control by Learning from the Experts

Emara, Salma; Li, Baochun; Chen, Yanjiao

doi:10.1109/infocom41043.2020.9155250

Cited by 37 publications

(4 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The idea is to have two levels of controls: ine-grained control using classic TCP algorithms, e.g., BBR, to adjust the congestion window, and hence the sending rate, of a user, and coarse-grain control using DRL to calculate and enforce a new congestion windows periodically, observing environment statistics. The proposed solution therefore has more predictable performance and better convergence properties, showing how learning from an expert, e.g., BBR algorithm, can improve the performance, in terms of convergence speed, adaptation to newly seen network conditions, and average throughput [41].…”

Section: Ml-based Approachesmentioning

confidence: 93%

Machine Learning for Computer Systems and Networking: A Survey

2022

View full text Add to dashboard Cite

Machine learning has become the de-facto approach for various scientific domains such as computer vision and natural language processing. Despite recent breakthroughs, machine learning has only made its way into the fundamental challenges in computer systems and networking recently. This paper attempts to shed light on recent literature that appeals for machine learning based solutions to traditional problems in computer systems and networking. To this end, we first introduce a taxonomy based on a set of major research problem domains. Then, we present a comprehensive review per domain, where we compare the traditional approaches against the machine learning based ones. Finally, we discuss the general limitations of machine learning for computer systems and networking, including lack of training data, training overhead, real-time performance, and explainability, and reveal future research directions targeting these limitations.

show abstract

Section: Ml-based Approachesmentioning

confidence: 93%

Machine Learning for Computer Systems and Networking: A Survey

2022

View full text Add to dashboard Cite

show abstract

“…It was estimated that BBR accounts for over 40% of the total traffic on the Internet. [41][42][43][44][45][46][47][48] Remy [41] optimizes and generates congestion control algorithms offline based on pre-specified congestion control objectives, protocol assumptions, and models of both network and traffic. Performance-oriented congestion control (PCC) [42] sends packets at two different rates, slightly higher and slightly lower than the current rate.…”

Section: Survey Of Congestion Control Algorithms Share On the Internetmentioning

confidence: 99%

Congestion Control Algorithms for the Internet – A Secondary Publication

Utsumi

2024

JERA

View full text Add to dashboard Cite

In the last five years, there has been a V-shaped recovery in the number of papers on congestion controlalgorithms on the Internet. In this paper, congestion problems on the Internet are discussed, such as congestion collapse and bufferbloat from the perspective of the necessity of congestion control algorithms. The typical congestion control algorithms are introduced, and the research areas and methods of congestion control algorithms are described. Recent research trends and future prospects of congestion control algorithms are also presented.

show abstract

“…The reward metric can be observed as either the throughput or network delay that is optimised for a particular system state by the actions of the DRL agent using trained DNN [ 112 ]. Some of the CC algorithms that use DRL techniques include Aurora [ 118 ], Eagle [ 119 ] and Orca [ 120 ] ( Table 4 ).…”

Section: Machine Learning For Improving CCmentioning

confidence: 99%

A Comprehensive Overview of TCP Congestion Control in 5G Networks: Research Challenges and Future Perspectives

Lörincz

Klarin

Ožegović

2021

Sensors

View full text Add to dashboard Cite

In today’s data networks, the main protocol used to ensure reliable communications is the transmission control protocol (TCP). The TCP performance is largely determined by the used congestion control (CC) algorithm. TCP CC algorithms have evolved over the past three decades and a large number of CC algorithm variations have been developed to accommodate various network environments. The fifth-generation (5G) mobile network presents a new challenge for the implementation of the TCP CC mechanism, since networks will operate in environments with huge user device density and vast traffic flows. In contrast to the pre-5G networks that operate in the sub-6 GHz bands, the implementation of TCP CC algorithms in 5G mmWave communications will be further compromised with high variations in channel quality and susceptibility to blockages due to high penetration losses and atmospheric absorptions. These challenges will be particularly present in environments such as sensor networks and Internet of Things (IoT) applications. To alleviate these challenges, this paper provides an overview of the most popular single-flow and multy-flow TCP CC algorithms used in pre-5G networks. The related work on the previous examinations of TCP CC algorithm performance in 5G networks is further presented. A possible implementation of TCP CC algorithms is thoroughly analysed with respect to the specificities of 5G networks, such as the usage of high frequencies in the mmWave spectrum, the frequent horizontal and vertical handovers, the implementation of the 5G core network, the usage of beamforming and data buffering, the exploitation of edge computing, and the constantly transmitted always-on signals. Moreover, the capabilities of machine learning technique implementations for the improvement of TCPs CC performance have been presented last, with a discussion on future research opportunities that can contribute to the improvement of TCP CC implementation in 5G networks. This survey paper can serve as the basis for the development of novel solutions that will ensure the reliable implementation of TCP CC in different usage scenarios of 5G networks.

show abstract

Eagle: Refining Congestion Control by Learning from the Experts

Cited by 37 publications

References 6 publications

Machine Learning for Computer Systems and Networking: A Survey

Machine Learning for Computer Systems and Networking: A Survey

Congestion Control Algorithms for the Internet – A Secondary Publication

A Comprehensive Overview of TCP Congestion Control in 5G Networks: Research Challenges and Future Perspectives

Contact Info

Product

Resources

About