[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127412-en":3,"doc-seo-127412-105":30,"detail-sidebar-cat-0-en-105":84},{"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},127412,962085564807,"Aurelia","https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8",8,"Research & Report","Processing and classifying IP packet data on the Internet based on machine learning","Communication over the Internet is growing rapidly, while network congestion has become a serious concern for large-city, country-level, and global infrastructure. This study streamlines network-data flow by analyzing IP packet delay and classifying packets using machine learning models. Random Forest (RF) and Support Vector Machines (SVM) are applied to determine packet classes based on delay characteristics. The classification goal prioritizes low-delay packets to improve online service stability for applications such as video streaming and voice calls. The approach also supports easier packet-traffic management at routers to reduce congestion.","Processing and classifying IP packet data on the Internet based on machine learning  \nVuong Xuan Chi*, Nguyen Kim Quoc**  \nFaculty of Information Technology, Nguyen Tat Thanh University  \n*[vxchi@ntt.edu.vn](vxchi@ntt.edu.vn), **[nkquoc@ntt.edu.vn](nkquoc@ntt.edu.vn)  \nAbstract  \nNowadays, the continuous development of information technology, communication over the Internet is increasing rapidly, and network congestion has become an alarming issue. To develop communication network infrastructure in a large city, a country, or globally, streamlining and controlling network data flow to optimize communication processes and minimize network congestion is crucial and necessary. In this study, the authors analyze and process data according to the delay of Internet Protocol (IP) packets, using machine learning models with the Random Forest (RF) and the Support Vector Machines (SVM) method to classify IP packets. The primary goal of classifying packets by delay is to optimize network performance by prioritizing processing of lowdelay packets, ensuring stable and uninterrupted online services such as video streaming and voice calls. Furthermore, it is easy to manage and control packet traffic, hence minimizing network congestion at the router.  \n® 2024 Journal of Science and Technology-NTTU  \nReceived Accepted Published  \n10/03/2024 05/05/2024 20/06/2024  \nKeywords  \nIP packet classification,  \nIP network, network congestion, machine learning, random forest  \n1 Introduction  \nClassifying IP packet stream data in Internet and communication networks is highly important. Packet classification in IP networks has numerous common applications such as traffic control, bandwidth management, intrusion detection, traffic analysis, and many others. Accurate and efficient packet classification in IP networks plays a significant role in designing and operating communication network systems. In machine learning, some network classification techniques involve statistical analysis of attributes of IP data streams and use unsupervised learning mechanisms to cluster streams into groups based on similarity [1] . Additionally, algorithms and methods such as Artificial Neural Networks (ANN), Perceptron (PLA), K-Nearest Neighbor (KNN) method, Decision Tree (DT) method, Random Forest (RF) method, and Support Vector Machine (SVM)  \nmethod are applied to determine data features and can classify data into separate groups based on the attribute information of the data service [2-4] .  \nThe IP network is distributed and complex, potentially millions of packets transmitted through the network pera second. To provide fast responses to network devices within the system, latency becomes one of the critical factors. Among various types of attributes, queue delay has a more significant impact on the network than other types of delays [5] . Additionally, measuring traffic control, load balancing techniques, routing, and anomaly detection all identify causes of high-latency packets, posing challenges for network management and operation in the future [6] .  \nThe rest ofthe paper is structured as follows. Section 2 presents the research methodology. In section 2.1, the authors study the structure of IP packets. Approach DT and RF machine learning models for applying to IP packet classification in section 2.2. Next, in section 2.3,  \n[https://doi.org/10.55401/2xyvkg06](https://doi.org/10.55401/2xyvkg06)  \nanalyze and process IP packet data, monitor the proportions of incoming and outgoing data streams from source and destination addresses. In section 2.4, the paper analyzes and extracts data related to delay and in section 2.5, the authors calculate the average delay of IP packets. Subsequently, in section 3, experimenting with machine learning models, particularly SVM and RF models for classifying packets based on delay. Comparing the classification results of DT, RF, SVM, KNN models, and find that the RF model achieves the highest accuracy in the evaluation results. Fin","cbCaijyhGV1cYQqE","https://ap.wps.com/l/cbCaijyhGV1cYQqE","pdf",958297,1,11,"English","en",105,"# Abstract\n# Introduction\n## Packet classification importance\n## Machine learning approaches for IP data\n## Delay and queue delay relevance\n# Research Methods\n## IP packet structure and IP packet classification\n# Experiment and Results\n## Model comparison (DT, RF, SVM, KNN)\n# Conclusion","[{\"question\":\"How does delay-based packet classification help reduce congestion and improve services?\",\"answer\":\"By prioritizing low-delay packets, the method supports stable, uninterrupted online services such as video streaming and voice calls. It also enables easier traffic management at routers, helping minimize congestion.\"}]","Processing and classifying IP packet data on the Internet based on machine learning | PDF",1785938744,28,{"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":79,"head_meta":81,"extra_data":83,"updated_unix":28},"processing-and-classifying-ip-packet-data-on-the-internet-based-on-machine-learning","",{"@graph":36,"@context":78},[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/processing-and-classifying-ip-packet-data-on-the-internet-based-on-machine-learning/127412/",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","2026-08-22","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72],{"name":73,"@type":74,"acceptedAnswer":75},"How does delay-based packet classification help reduce congestion and improve services?","Question",{"text":76,"@type":77},"By prioritizing low-delay packets, the method supports stable, uninterrupted online services such as video streaming and voice calls. It also enables easier traffic management at routers, helping minimize congestion.","Answer","https://schema.org",{"og:url":52,"og:type":80,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":82,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":85},[86,90,94,98,103,108,113,116,121,124,128],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":87,"show_sort_weight":88,"slug":89},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":91,"show_sort_weight":92,"slug":93},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Exam",70,"exam",{"id":99,"doc_module":4,"doc_module_name":46,"category_name":100,"show_sort_weight":101,"slug":102},5,"Comic",60,"comic",{"id":104,"doc_module":4,"doc_module_name":46,"category_name":105,"show_sort_weight":106,"slug":107},6,"Technology",50,"technology",{"id":109,"doc_module":4,"doc_module_name":46,"category_name":110,"show_sort_weight":111,"slug":112},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":114,"slug":115},30,"research-report",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},9,"Religion & Spirituality",20,"religion-spirituality",{"id":119,"doc_module":4,"doc_module_name":46,"category_name":122,"show_sort_weight":119,"slug":123},"World Cup","world-cup",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":125,"slug":127},10,"Lifestyle","lifestyle",{"id":129,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":99,"slug":131},19,"General","general"]