5G/B5G Service Classification Using Supervised Learning

被引:8
|
作者
Preciado-Velasco, Jorge E. [1 ]
Gonzalez-Franco, Joan D. [2 ]
Anias-Calderon, Caridad E. [2 ]
Nieto-Hipolito, Juan I. [3 ]
Rivera-Rodriguez, Raul [4 ]
机构
[1] CICESE Res Ctr, Dept Elect & Telecommun, Carretera Ensenada Tijuana 3918, Ensenada 22860, BC, Mexico
[2] La Havana Technol Univ CUJAE, Fac Elect & Telecommun, Calle 114, Marianao 19390, La Havana, Cuba
[3] FIAD Autonomous Univ Baja California, Fac Engn Architecture & Design, Carretera Ensenada Tijuana 3917, Ensenada 22860, BC, Mexico
[4] CICESE Res Ctr, Div Telemat, Carretera Ensenada Tijuana 3918, Ensenada 22860, BC, Mexico
来源
APPLIED SCIENCES-BASEL | 2021年 / 11卷 / 11期
关键词
5G; B5G service classification; ML; predictive model; KPI; KQI; QoS; QoE; SLA;
D O I
10.3390/app11114942
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
The classification of services in 5G/B5G (Beyond 5G) networks has become important for telecommunications service providers, who face the challenge of simultaneously offering a better Quality of Service (QoS) in their networks and a better Quality of Experience (QoE) to users. Service classification allows 5G service providers to accurately select the network slices for each service, thereby improving the QoS of the network and the QoE perceived by users, and ensuring compliance with the Service Level Agreement (SLA). Some projects have developed systems for classifying these services based on the Key Performance Indicators (KPIs) that characterize the different services. However, Key Quality Indicators (KQIs) are also significant in 5G networks, although these are generally not considered. We propose a service classifier that uses a Machine Learning (ML) approach based on Supervised Learning (SL) to improve classification and to support a better distribution of resources and traffic over 5G/B5G based networks. We carry out simulations of our proposed scheme using different SL algorithms, first with KPIs alone and then incorporating KQIs and show that the latter achieves better prediction, with an accuracy of 97% and a Matthews correlation coefficient of 96.6% with a Random Forest classifier.
引用
收藏
页数:19
相关论文
共 50 条
  • [41] Service Classification of Network Traffic in 5G Core Networks using Machine Learning
    Pell, Robert
    Shojafar, Mohammad
    Kosmanos, Dimitrios
    Moschoyiannis, Sotiris
    2023 IEEE INTERNATIONAL CONFERENCE ON EDGE COMPUTING AND COMMUNICATIONS, EDGE, 2023, : 309 - 318
  • [42] 5G/B5G毫米波网络TCP传输性能分析
    陈欢
    任勇毛
    周旭
    杨望泓
    范鹏飞
    计算机系统应用, 2020, 29 (08) : 9 - 15
  • [43] Leaky-Wave Antennas for 5G/B5G Mobile Communication Systems:A Survey
    HE Yejun
    JIANG Jiachun
    ZHANG Long
    LI Wenting
    WONG Sai-Wai
    DENG Wei
    CHI Baoyong
    ZTE Communications, 2020, 18 (03) : 3 - 11
  • [44] 面向5G/B5G的智能云化网络架构探讨
    唐路
    通信电源技术, 2020, 37 (04) : 170 - 171
  • [45] Combinatorial Resource Allocation in UAV-Assisted 5G/B5G Heterogeneous Networks
    Shahzadi, Rizwana
    Ali, Mudassar
    Naeem, Muhammad
    IEEE ACCESS, 2023, 11 : 65336 - 65346
  • [46] Editorial:Special Topic on Antennas and RF Technologies for 5G/B5G Mobile Communications
    LI Ronglin
    ZHANG Yueping
    MA Jianguo
    ZTECommunications, 2020, 18 (03) : 1 - 2
  • [47] 5G/B5G Multi-Gbps Antennas for User Terminals and Their Throughput Verification
    Wong, Kin-Lu
    2020 IEEE ASIA-PACIFIC MICROWAVE CONFERENCE (APMC), 2020, : 366 - 368
  • [48] 5G and B5G NEF exposure capabilities towards an Industrial IoT use case
    Makropoulos, George
    Fragkos, Dimitrios
    Koumaras, Harilaos
    Cijan, Jaka
    Korsic, Luka
    Susnik, Rudolf
    2023 JOINT EUROPEAN CONFERENCE ON NETWORKS AND COMMUNICATIONS & 6G SUMMIT, EUCNC/6G SUMMIT, 2023, : 647 - 651
  • [49] Improving the latency for 5G/B5G based smart healthcare connectivity in rural area
    Kumar, Arun
    Gaur, Nishant
    Nanthaamornphong, Aziz
    SCIENTIFIC REPORTS, 2024, 14 (01)
  • [50] Emission-Aware Sustainable Energy Provision for 5G and B5G Mobile Networks
    Israr, Adil
    Yang, Qiang
    Israr, Ali
    IEEE TRANSACTIONS ON SUSTAINABLE COMPUTING, 2023, 8 (04): : 670 - 681