Data for Reinforcement Learning-based Congestion Control: A Systematic Evaluation of Fairness, Efficiency and Responsiveness
Introduction This is the dataset for the paper titled ‘Reinforcement Learning-based Congestion Control: A Systematic Evaluation of Fairness, Efficiency and Responsiveness’ that has been accepted for publication at IEEE INFOCOM 2024 . The paper’s accepted version will be available following publicati...
Main Authors: | , |
---|---|
Format: | Dataset |
Language: | unknown |
Published: |
2024
|
Subjects: | |
Online Access: | https://doi.org/10.25377/sussex.24970173.v1 https://figshare.com/articles/dataset/Data_for_Reinforcement_Learning-based_Congestion_Control_A_Systematic_Evaluation_of_Fairness_Efficiency_and_Responsiveness/24970173 |
id |
ftunivsussexfig:oai:figshare.com:article/24970173 |
---|---|
record_format |
openpolar |
spelling |
ftunivsussexfig:oai:figshare.com:article/24970173 2024-02-11T10:07:43+01:00 Data for Reinforcement Learning-based Congestion Control: A Systematic Evaluation of Fairness, Efficiency and Responsiveness Luca Giacomoni George Parisis 2024-01-22T10:28:48Z https://doi.org/10.25377/sussex.24970173.v1 https://figshare.com/articles/dataset/Data_for_Reinforcement_Learning-based_Congestion_Control_A_Systematic_Evaluation_of_Fairness_Efficiency_and_Responsiveness/24970173 unknown doi:10.25377/sussex.24970173.v1 https://figshare.com/articles/dataset/Data_for_Reinforcement_Learning-based_Congestion_Control_A_Systematic_Evaluation_of_Fairness_Efficiency_and_Responsiveness/24970173 CC BY 4.0 congestion control schemes Mininet Dataset 2024 ftunivsussexfig https://doi.org/10.25377/sussex.24970173.v1 2024-01-25T00:14:36Z Introduction This is the dataset for the paper titled ‘Reinforcement Learning-based Congestion Control: A Systematic Evaluation of Fairness, Efficiency and Responsiveness’ that has been accepted for publication at IEEE INFOCOM 2024 . The paper’s accepted version will be available following publication in May 2024 at https://sussex.figshare.com/articles/conference_contribution/Reinforcement_learningbased_congestion_control_a_systematic_evaluation_of_fairness_efficiency_and_responsiveness/24711033 . The dataset is meant to be used in conjunction with the codebase that is also made available at https://doi.org/10.25377/sussex.24978162. However, the dataset itself is of value to researchers as it contains an extensive set of metrics captured during experimentation with Reinforcement Learning-based Congestion control as discussed in the ‘Experimental Evaluation’ section of the paper. Our study is the result of a 160-hour long experimentation during which 1950 Orca, Aurora and TCP Cubic flows were measured. We have collected approximately 500GB of data encompassing diverse metrics related to network interfaces (e.g., utilisation, retransmissions, packet drops), CPU and memory parameters (such as CPU load and memory usage), as well as the data transport layer (e.g., congestion window, round trip time). Reinforcement learning (RL)-based congestion control (CC) promises efficient CC in a fast-changing networking landscape, where evolving communication technologies, applications and traffic workloads pose severe challenges to human-derived, static CC algorithms. RL-based CC is in its early days and substantial research is required to understand existing limitations, identify research challenges and, eventually, yield deployable solutions for real-world networks. In this paper we present the first reproducible and systematic study of RL-based CC with the aim to highlight strengths and uncover fundamental limitations of the state-of-the-art. We identify challenges in evaluating RL-based CC, establish a methodology for ... Dataset Orca University of Sussex: Figshare |
institution |
Open Polar |
collection |
University of Sussex: Figshare |
op_collection_id |
ftunivsussexfig |
language |
unknown |
topic |
congestion control schemes Mininet |
spellingShingle |
congestion control schemes Mininet Luca Giacomoni George Parisis Data for Reinforcement Learning-based Congestion Control: A Systematic Evaluation of Fairness, Efficiency and Responsiveness |
topic_facet |
congestion control schemes Mininet |
description |
Introduction This is the dataset for the paper titled ‘Reinforcement Learning-based Congestion Control: A Systematic Evaluation of Fairness, Efficiency and Responsiveness’ that has been accepted for publication at IEEE INFOCOM 2024 . The paper’s accepted version will be available following publication in May 2024 at https://sussex.figshare.com/articles/conference_contribution/Reinforcement_learningbased_congestion_control_a_systematic_evaluation_of_fairness_efficiency_and_responsiveness/24711033 . The dataset is meant to be used in conjunction with the codebase that is also made available at https://doi.org/10.25377/sussex.24978162. However, the dataset itself is of value to researchers as it contains an extensive set of metrics captured during experimentation with Reinforcement Learning-based Congestion control as discussed in the ‘Experimental Evaluation’ section of the paper. Our study is the result of a 160-hour long experimentation during which 1950 Orca, Aurora and TCP Cubic flows were measured. We have collected approximately 500GB of data encompassing diverse metrics related to network interfaces (e.g., utilisation, retransmissions, packet drops), CPU and memory parameters (such as CPU load and memory usage), as well as the data transport layer (e.g., congestion window, round trip time). Reinforcement learning (RL)-based congestion control (CC) promises efficient CC in a fast-changing networking landscape, where evolving communication technologies, applications and traffic workloads pose severe challenges to human-derived, static CC algorithms. RL-based CC is in its early days and substantial research is required to understand existing limitations, identify research challenges and, eventually, yield deployable solutions for real-world networks. In this paper we present the first reproducible and systematic study of RL-based CC with the aim to highlight strengths and uncover fundamental limitations of the state-of-the-art. We identify challenges in evaluating RL-based CC, establish a methodology for ... |
format |
Dataset |
author |
Luca Giacomoni George Parisis |
author_facet |
Luca Giacomoni George Parisis |
author_sort |
Luca Giacomoni |
title |
Data for Reinforcement Learning-based Congestion Control: A Systematic Evaluation of Fairness, Efficiency and Responsiveness |
title_short |
Data for Reinforcement Learning-based Congestion Control: A Systematic Evaluation of Fairness, Efficiency and Responsiveness |
title_full |
Data for Reinforcement Learning-based Congestion Control: A Systematic Evaluation of Fairness, Efficiency and Responsiveness |
title_fullStr |
Data for Reinforcement Learning-based Congestion Control: A Systematic Evaluation of Fairness, Efficiency and Responsiveness |
title_full_unstemmed |
Data for Reinforcement Learning-based Congestion Control: A Systematic Evaluation of Fairness, Efficiency and Responsiveness |
title_sort |
data for reinforcement learning-based congestion control: a systematic evaluation of fairness, efficiency and responsiveness |
publishDate |
2024 |
url |
https://doi.org/10.25377/sussex.24970173.v1 https://figshare.com/articles/dataset/Data_for_Reinforcement_Learning-based_Congestion_Control_A_Systematic_Evaluation_of_Fairness_Efficiency_and_Responsiveness/24970173 |
genre |
Orca |
genre_facet |
Orca |
op_relation |
doi:10.25377/sussex.24970173.v1 https://figshare.com/articles/dataset/Data_for_Reinforcement_Learning-based_Congestion_Control_A_Systematic_Evaluation_of_Fairness_Efficiency_and_Responsiveness/24970173 |
op_rights |
CC BY 4.0 |
op_doi |
https://doi.org/10.25377/sussex.24970173.v1 |
_version_ |
1790606398768283648 |