GFlow: GNN-Based Optimal Flow Scheduling for Multipath Transmission With Link Overlapping

IF 6.7 2区计算机科学 Q1 ENGINEERING, MULTIDISCIPLINARY

IEEE Transactions on Network Science and Engineering Pub Date : 2024-10-16 DOI:10.1109/TNSE.2024.3481413

Du Chen;Weiting Zhang;Deyun Gao;Dong Yang;Hongke Zhang

{"title":"GFlow: GNN-Based Optimal Flow Scheduling for Multipath Transmission With Link Overlapping","authors":"Du Chen;Weiting Zhang;Deyun Gao;Dong Yang;Hongke Zhang","doi":"10.1109/TNSE.2024.3481413","DOIUrl":null,"url":null,"abstract":"Multipath TCP (MPTCP) is considered as a solution capable of addressing the growing demand for bandwidth. However, the existing MPTCP mechanisms make flow scheduling based on coarse-grained end-to-end network states, which prevents MPTCP from better aggregating the bandwidth of multiple paths. Besides, link overlapping may occur between different MPTCP connections, which results in multiple subflows competing for bandwidth of the shared link. In this paper, we propose GFlow, a Graph Neural Network (GNN) based Deep Reinforcement Learning (DRL) algorithm, to make optimal flow scheduling for multipath transmission with link overlapping. Specifically, we formulate the flow scheduling problem as a problem of maximizing overall throughput by taking both bottleneck bandwidth and shared bandwidth into consideration. To support accurate network state perception, GFlow utilizes In-band Network Telemetry (INT) to collect real-time and fine-grained network states. Taking these states as input, the DRL agent with GNN integrated fully learns the relationships among links, paths (subflows), and MPTCP connections. In this way, GFlow is able to make optimal flow scheduling decisions according to the network states. We build a P4-based multipath transmission system and carry out extensive experiments to evaluate the performance of GFlow. The results show that GFlow outperforms the baseline multipath transmission mechanism in both homogeneous scenario and heterogeneous scenario, improving the average overallthroughput while reducing the average round trip time (RTT).","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"11 6","pages":"6244-6258"},"PeriodicalIF":6.7000,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Network Science and Engineering","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/10720146/","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, MULTIDISCIPLINARY","Score":null,"Total":0}

引用次数: 0

Abstract

Multipath TCP (MPTCP) is considered as a solution capable of addressing the growing demand for bandwidth. However, the existing MPTCP mechanisms make flow scheduling based on coarse-grained end-to-end network states, which prevents MPTCP from better aggregating the bandwidth of multiple paths. Besides, link overlapping may occur between different MPTCP connections, which results in multiple subflows competing for bandwidth of the shared link. In this paper, we propose GFlow, a Graph Neural Network (GNN) based Deep Reinforcement Learning (DRL) algorithm, to make optimal flow scheduling for multipath transmission with link overlapping. Specifically, we formulate the flow scheduling problem as a problem of maximizing overall throughput by taking both bottleneck bandwidth and shared bandwidth into consideration. To support accurate network state perception, GFlow utilizes In-band Network Telemetry (INT) to collect real-time and fine-grained network states. Taking these states as input, the DRL agent with GNN integrated fully learns the relationships among links, paths (subflows), and MPTCP connections. In this way, GFlow is able to make optimal flow scheduling decisions according to the network states. We build a P4-based multipath transmission system and carry out extensive experiments to evaluate the performance of GFlow. The results show that GFlow outperforms the baseline multipath transmission mechanism in both homogeneous scenario and heterogeneous scenario, improving the average overallthroughput while reducing the average round trip time (RTT).

查看原文本刊更多论文

GFlow：基于 GNN 的链路重叠多径传输优化流量调度

多路径 TCP（MPTCP）被认为是一种能够满足日益增长的带宽需求的解决方案。然而，现有的 MPTCP 机制是基于粗粒度的端到端网络状态进行流量调度的，这使得 MPTCP 无法更好地聚合多条路径的带宽。此外，不同的 MPTCP 连接之间可能会出现链路重叠，从而导致多个子流争夺共享链路的带宽。本文提出了一种基于图神经网络（GNN）的深度强化学习（DRL）算法--GFlow，为链路重叠的多径传输进行最优流量调度。具体来说，我们将流量调度问题表述为同时考虑瓶颈带宽和共享带宽的总体吞吐量最大化问题。为了支持精确的网络状态感知，GFlow 利用带内网络遥测技术（INT）收集实时和细粒度的网络状态。将这些状态作为输入，集成了 GNN 的 DRL 代理就能充分了解链路、路径（子流）和 MPTCP 连接之间的关系。这样，GFlow 就能根据网络状态做出最佳流量调度决策。我们构建了一个基于 P4 的多径传输系统，并进行了大量实验来评估 GFlow 的性能。结果表明，无论是在同构场景还是异构场景下，GFlow 的性能都优于基线多路径传输机制，在提高平均总体吞吐量的同时缩短了平均往返时间（RTT）。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

IEEE Transactions on Network Science and Engineering Engineering-Control and Systems Engineering

CiteScore

12.60

自引率

9.10%

发文量

393

期刊介绍： The proposed journal, called the IEEE Transactions on Network Science and Engineering (TNSE), is committed to timely publishing of peer-reviewed technical articles that deal with the theory and applications of network science and the interconnections among the elements in a system that form a network. In particular, the IEEE Transactions on Network Science and Engineering publishes articles on understanding, prediction, and control of structures and behaviors of networks at the fundamental level. The types of networks covered include physical or engineered networks, information networks, biological networks, semantic networks, economic networks, social networks, and ecological networks. Aimed at discovering common principles that govern network structures, network functionalities and behaviors of networks, the journal seeks articles on understanding, prediction, and control of structures and behaviors of networks. Another trans-disciplinary focus of the IEEE Transactions on Network Science and Engineering is the interactions between and co-evolution of different genres of networks.