Scholarlink

<p>Proactive caching in cellular networks effectively reduces backhaul load and content delay. Open Radio Access Networks (O-RAN), with their multi-vendor, distributed architecture, offer additional opportunities to cache content at various components. Integrating proactive caching with O-RAN can significantly improve performance, though the process is complex due to the tight coupling between content placement and O-RAN elements. This paper proposes an Intelligent Content-Aware Proactive Caching (ICAPC) mechanism for both published and unpublished videos. In ICAPC, video features are extracted and compressed using a 3D-CNN to generate high-dimensional feature vectors. Videos with similar features are clustered into ‘video classes’ using k-means clustering. The feature vector is mapped into a G-dimensional space, where each value represents the percentage of features from each video class. A support vector machine (SVM) is then trained using these vectors and their corresponding video popularity. For unpublished videos, the trained SVM predicts popularity based on their feature representation. Videos are cached based on descending popularity–first at the RU, then DU, and finally CU. Simulation results show that the proposed method outperforms conventional approaches by achieving higher cache hit ratios and reducing both content latency and backhaul load.</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

Machine learning empowered proactive content caching in O-RAN

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月15日

查看全文
  • Ayaz Ahmad,
  • Fawad Ahmad,
  • Salman Atif,
  • Adel Aldalbahi

摘要

Proactive caching in cellular networks effectively reduces backhaul load and content delay. Open Radio Access Networks (O-RAN), with their multi-vendor, distributed architecture, offer additional opportunities to cache content at various components. Integrating proactive caching with O-RAN can significantly improve performance, though the process is complex due to the tight coupling between content placement and O-RAN elements. This paper proposes an Intelligent Content-Aware Proactive Caching (ICAPC) mechanism for both published and unpublished videos. In ICAPC, video features are extracted and compressed using a 3D-CNN to generate high-dimensional feature vectors. Videos with similar features are clustered into ‘video classes’ using k-means clustering. The feature vector is mapped into a G-dimensional space, where each value represents the percentage of features from each video class. A support vector machine (SVM) is then trained using these vectors and their corresponding video popularity. For unpublished videos, the trained SVM predicts popularity based on their feature representation. Videos are cached based on descending popularity–first at the RU, then DU, and finally CU. Simulation results show that the proposed method outperforms conventional approaches by achieving higher cache hit ratios and reducing both content latency and backhaul load.