跳到主要导航 跳到搜索 跳到主要内容

Let once-request data go: An online learning approach for ICN caching

  • Yating Yang
  • , Tian Song*
  • *此作品的通讯作者
  • Beijing Institute of Technology

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

摘要

In-network caching significantly improves the efficiency of data transmission in ICN by replicating requested data for future re-access. In this work, we shift our focus on once-request data, which cannot be re-used and would lead to under-utilization of in-network caching. We present a name feature-based online learning approach to recognizing and filtering once-request data when making caching decision. It can dynamically update its parameters through online observation on previous recognition. Evaluation results show that our learning approach can recognize once-request data with more than 80% accuracy. By filtering those data, 76% cache replacement operations are saved and cache hit ratio is increased by 151%.

源语言英语
主期刊名ICN 2019 - Proceedings of the 2019 Conference on Information-Centric Networking
出版商Association for Computing Machinery, Inc
页157-158
页数2
ISBN(电子版)9781450369701
DOI
出版状态已出版 - 24 9月 2019
活动6th ACM Conference on Information-Centric Networking, ICN 2019 - Macau, 中国
期限: 24 9月 2019 → 26 9月 2019

丛书

姓名ICN 2019 - Proceedings of the 2019 Conference on Information-Centric Networking

会议

会议6th ACM Conference on Information-Centric Networking, ICN 2019
国家/地区中国
市Macau
时期24/09/19 → 26/09/19

学术指纹

探究 'Let once-request data go: An online learning approach for ICN caching' 的科研主题。它们共同构成独一无二的学术指纹。

引用此