MAСHINE LEARNING TECHNIQUE IN QOS MANAGEMENT NETWORK


Zhunussov A. Baikenov A. Zheltayev T. Serikov T. Ziyekenov T.
31 January 2023Little Lion Scientific

Journal of Theoretical and Applied Information Technology
2023#101Issue 2904 - 911 pp.

Modern telecommunication systems and data transmission networks generate large volumes of heterogeneous traffic. In such networks, traditional network management methods for monitoring and analyzing data have some problems in terms of accuracy and efficient processing of big data in real time. The purpose of the study is to show how the value of the number of PPPoE PADT session break packets sent by the router indicates the presence of packet loss along the way. The PPPoE protocol works on the client-server principle, which is mainly used in broadband networks, by encapsulating PPP frames within an Ethernet frame. Using the PPPoE protocol, operators can control the access and operation of subscriber connections, as well as manage a large number of connections at one point in the network. It is proposed to use a machine learning method that will automate the process of tracking the quality of services provided using information from PPPoE sessions in a specific VLAN at specified time intervals. The article analyzes statistics from PPPoE sessions collected in 8 directions of VLANs providing various types of services. Found and fixed problems in the direction of VLAN112, which were associated with signal distortion in the section of the radio relay link along the route. Based on the test results, the proposed method makes it possible to identify a malfunction without involving additional technological resources. To store statistics, you need to allocate memory on the server for each direction and configure PPPoE.

Maсhine learning , Monitoring , PADT , PPPoE , QoS management , VLAN

Text of the article Перейти на текст статьи

Almaty University of Power Engineering and Telecommunications Named After Gumarbek Daukeyev, Almaty, Kazakhstan
Kazakh Agrotechnical University Named After S.Seifullina, Nur-Sultan, Kazakhstan

Almaty University of Power Engineering and Telecommunications Named After Gumarbek Daukeyev
Kazakh Agrotechnical University Named After S.Seifullina

10 лет помогаем публиковать статьи Международный издатель

Книга Публикация научной статьи Волощук 2026 Book Publication of a scientific article 2026