Scholarlink

<p>Modern wireless networks must efficiently allocate resources to enable network slicing for different service requirements. We used ANOVA for feature extraction, a stacking classifier (logistic regression, random forest, and SVC), and LightGBM as the meta-model. This improved the performance of our proposed ANOVA-LightGBM model with 92.76% accuracy. Our model outperforms existing methods in multiple platform tests. Comparative studies show how network slicing in next-generation wireless communication systems may improve.</p>

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

ANOVA-LightGBM Stacking Classifier for Network Slicing in Future Wireless Networks

  • 期刊论文

  • 发表日期：

    2025年9月16日

查看全文
  • Megha Jain,
  • Ravi Verma,
  • J. Amudhavel

摘要

Modern wireless networks must efficiently allocate resources to enable network slicing for different service requirements. We used ANOVA for feature extraction, a stacking classifier (logistic regression, random forest, and SVC), and LightGBM as the meta-model. This improved the performance of our proposed ANOVA-LightGBM model with 92.76% accuracy. Our model outperforms existing methods in multiple platform tests. Comparative studies show how network slicing in next-generation wireless communication systems may improve.