Scholarlink

In 5G wireless networks, network slicing plays a critical role by allowing operators to partition a single physical network into multiple virtual networks, each optimized for specific application requirements. This paper presents a novel integrates machine learning (ML) techniques to optimize network slicing and improve quality of service (QoS) in 5G environments. The framework combines two key algorithms: RF and NB providing a comprehensive approach to network slicing. The performance evaluation demonstrates that Random Forest achieves 95.5% accuracy, Naive Bayes reaches 94.3% accuracy. Additionally, the paper includes an extensive sensitivity analysis to assess the framework’s resilience across diverse use cases such as smart cities, autonomous vehicles, and healthcare applications. The significant potential of ML techniques to enhance the efficiency, scalability, and adaptability of 5G networks, providing crucial insights for the deployment of future wireless communication systems.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Enhancing 5G Network Slicing with Machine Learning Classification

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Apoorva Bapuram,
  • M. Akila Devi,
  • Abhishek Kumar,
  • Yakub Banoth,
  • Santosh K. Dwivedi,
  • Amarjit Kumar

摘要

In 5G wireless networks, network slicing plays a critical role by allowing operators to partition a single physical network into multiple virtual networks, each optimized for specific application requirements. This paper presents a novel integrates machine learning (ML) techniques to optimize network slicing and improve quality of service (QoS) in 5G environments. The framework combines two key algorithms: RF and NB providing a comprehensive approach to network slicing. The performance evaluation demonstrates that Random Forest achieves 95.5% accuracy, Naive Bayes reaches 94.3% accuracy. Additionally, the paper includes an extensive sensitivity analysis to assess the framework’s resilience across diverse use cases such as smart cities, autonomous vehicles, and healthcare applications. The significant potential of ML techniques to enhance the efficiency, scalability, and adaptability of 5G networks, providing crucial insights for the deployment of future wireless communication systems.