[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123668-en":3,"doc-seo-123668-105":30,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},123668,962075006959,"Anda","https://ap-avatar.wpscdn.com/avatar/e0002397efbe92a78e?_k=1776741047341049297",8,"Research & Report","A Survey on Congestion Control and Scheduling for Multipath TCP - Machine Learning vs Classical Approaches","Multipath TCP (MPTCP) is used widely to improve communication efficiency by leveraging multiple paths to increase throughput while reducing latency in data centers, smartphones, and networks. Heavy traffic across MPTCP subflows can create congestion when subflow rates are not properly controlled, and incorrect packet scheduling can introduce additional communication delay through poor RTT selection. This survey reviews and compares non-data-driven (classical) and data-driven (machine learning) techniques, detailing simulation and real-environment implementations and summarizing strengths, weaknesses, and research directions for learning-based communications.","A Survey on Congestion Control and Scheduling for Multipath TCP: Machine Learning vs Classical  \nApproaches  \nMaisha Maliha  \nSchool of Computer Science University of Oklahoma Norman, Oklahoma, USA [Email: maisha.maliha-1@ou.edu](Email: maisha.maliha-1@ou.edu)  \nGolnaz Habibi  \nSchool of Computer Science University of Oklahoma Norman, Oklahoma, USA Email: [golnaz@ou.edu](golnaz@ou.edu)  \nMohammed Atiquzzaman  \nSchool of Computer Science University of Oklahoma Norman, Oklahoma, USA Email: [atiq@ou.edu](atiq@ou.edu)  \narXiv :2309 .09372v1 [ cs .NI] 17 Sep 2023  \nAbstract—Multipath TCP (MPTCP) has been widely used asan efficient way for communication in many applications. Data centers, smartphones, and network operators use MPTCP to balance the traffic in a network efficiently. MPTCP is an extension of TCP (Transmission Control Protocol), which provides multiple paths, leading to higher throughput and low latency. Although MPTCP has shown better performance than TCP in many applications, it has its own challenges. The network can become congested due to heavy traffic in the multiple paths (subflows) if the subflow rates are not determined correctly. Moreover, communication latency can occur if the packets are not scheduled correctly between the subflows. This paper reviews techniques to solve the above-mentioned problems based on two main approaches; non data-driven (classical) and data-driven (Machine Learning) approaches. This paper compares these two approaches and highlights their strengths and weaknesses with a view to motivating future researchers in this exciting area of machine learning for communications. This paper also provides details on the simulation of MPTCP and its implementations in real environments.  \nIndex Terms—Multipath TCP, congestion control, scheduling, deep reinforcement learning, machine learning  \nI. INTRODUCTION  \nCommunication is key in many domains, such as defense, hospitality, technology, and space. In telecommunications, packet switching is a method of grouping data in smaller packets for faster communication [1] . One of the earliest packet-switched networks started with the Advanced Research Projects Agency Network (ARPANET) [2] in the United States, which is also called the forerunner of the Internet. Today, the Internet has expanded and now consists of a set of protocols for global communications. Basically, a protocol is a set of rules that the sender and receiver must agree on to communicate with each other. The two well-known Transport layer protocols are User Datagram Protocol (UDP) [3] and Transmission Control Protocol (TCP) . UDP does not need any handshaking, which means the receiver does not send any acknowledgment to the sender when it receives a message. UDP thus leads to faster communication.  \nTCP [4] provides more consistent communication by considering handshaking between the sender and receiver. With  \nmillions of devices connected to the Internet, there is a demand for faster communication, but TCP fails to meet that need. It’s because of TCP’s congestion control algorithm, which decreases the throughput (message delivery rate) in response to the loss of packets in the network. Also, the handshaking of TCP increases the time necessary for a packet to travel, resulting in higher latency. Keeping in mind these problems, Multipath TCP (MPTCP) has been introduced by the Internet Engineering Task Force (IETF) [5] to use multiple paths effectively and efficiently between the sender and receiver.  \nTCP connections can experience packet losses or connection drops, resulting in a poor user experience [6] . MPTCP can use multiple TCP connections, known as subflows, in parallel to overcome TCP’s limitations. One of the main goals of MPTCP is to control congestion and maintain traffic flows. Another focus of MPTCP is scheduling the packets over different subflows to send packets with the smallest round-trip time (RTT)  \n[7], which is the time taken to send a data packet to the destination","cbCaiuQPNfMdAHtv","https://ap.wps.com/l/cbCaiuQPNfMdAHtv","pdf",558253,1,13,"English","en",105,"# Introduction\n## Packet switching and transport protocols (UDP, TCP)\n## Motivation for Multipath TCP (MPTCP)\n## Congestion control and packet scheduling in MPTCP\n# Classical approaches and their limits\n# Data-driven approaches and deep reinforcement learning\n# Simulation and real-environment implementation\n# Comparison and research directions","[{\"question\":\"为什么多路径 TCP（MPTCP）能提升吞吐并降低时延？\",\"answer\":\"MPTCP在发送端与接收端之间同时使用多个路径（子流）来传输数据，相比单一路径的TCP更容易获得更高吞吐与更低时延表现。\"},{\"question\":\"MPTCP中拥塞和时延问题分别由什么因素引起？\",\"answer\":\"当各子流的速率没有被正确确定且流量较大时，网络容易因多路径重叠流量而产生拥塞；当子流之间的分组调度不合理时，可能导致额外通信延迟。\"},{\"question\":\"本文如何组织对比“经典方法”和“机器学习方法”的研究内容？\",\"answer\":\"本文围绕两类主要路线回顾与对比：非数据驱动的经典方法，以及数据驱动的机器学习（尤其是深度强化学习）方法，并总结各自的优点与局限，同时提供MPTCP模拟与真实环境实现细节。\"}]","A Survey on Congestion Control and Scheduling for Multipath TCP - Machine Learning vs Classical Approaches | PDF",1785817916,33,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"a-survey-on-congestion-control-and-scheduling-for-multipath-tcp-machine-learning-vs-classical-approaches","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/a-survey-on-congestion-control-and-scheduling-for-multipath-tcp-machine-learning-vs-classical-approaches/123668/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05","2026-08-04",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"为什么多路径 TCP（MPTCP）能提升吞吐并降低时延？","Question",{"text":76,"@type":77},"MPTCP在发送端与接收端之间同时使用多个路径（子流）来传输数据，相比单一路径的TCP更容易获得更高吞吐与更低时延表现。","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"MPTCP中拥塞和时延问题分别由什么因素引起？",{"text":81,"@type":77},"当各子流的速率没有被正确确定且流量较大时，网络容易因多路径重叠流量而产生拥塞；当子流之间的分组调度不合理时，可能导致额外通信延迟。",{"name":83,"@type":74,"acceptedAnswer":84},"本文如何组织对比“经典方法”和“机器学习方法”的研究内容？",{"text":85,"@type":77},"本文围绕两类主要路线回顾与对比：非数据驱动的经典方法，以及数据驱动的机器学习（尤其是深度强化学习）方法，并总结各自的优点与局限，同时提供MPTCP模拟与真实环境实现细节。","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]