Robotics & Machine Learning Daily News2024,Issue(Jun.25) :42-42.

New Findings from Indian Institute of Technology Guwahati in the Area of Computa tional Intelligence Reported (Content-aware Caching At the Mobile Edge Network U sing Federated Learning)

印度Guwahati理工学院在计算智能领域的新发现报告(使用联邦学习在移动边缘网络上进行内容感知缓存)

Robotics & Machine Learning Daily News2024,Issue(Jun.25) :42-42.

New Findings from Indian Institute of Technology Guwahati in the Area of Computa tional Intelligence Reported (Content-aware Caching At the Mobile Edge Network U sing Federated Learning)

印度Guwahati理工学院在计算智能领域的新发现报告(使用联邦学习在移动边缘网络上进行内容感知缓存)

扫码查看

摘要

由一名新闻记者-机器人与机器学习的工作人员新闻编辑每日新闻-一项关于机器学习的新研究-计算机智能现在已经问世。根据NewsRx记者在印度阿萨姆邦的新闻报道,研究表明:“主要由资源匮乏的视频流会话产生的移动数据流量爆炸性增长,促使服务提供商向终端用户提供更好的服务质量。边缘计算中的内容缓存是应对视频流量指数增长的一个有希望的解决方案。”新闻记者引用了印度技术研究所Guwahati的一句话:“最流行的视频通常存储在边缘服务器的本地缓存中,以提供快速、连续的视频访问,但是各种边缘缓存策略都不能满足用户的动态请求。大多数基于学习的缓存模型通常是集中训练的。”为此,本文提出了一种基于联邦学习的强化学习缓存框架FedCache,在FedCache中,将训练分散在终端设备上,并将终端用户的训练参数聚集在中央服务器上.

Abstract

By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-A new study on Machine Learning - Comp utational Intelligence is now available. According to news reporting from Assam, India, by NewsRx journalists, research stated, "The explosive growth of mobile data traffic generated primarily from resource-hungry video streaming sessions c hallenges the service providers to deliver a better Quality of Service to the he terogeneous end-users. Content caching in Edge Computing is a promising solution to cope with this exponential rise in video traffic." The news correspondents obtained a quote from the research from the Indian Insti tute of Technology Guwahati, "The most popular videos are typically stored in th e local caches of edge servers to provide fast and continuous access to videos. However, various edge caching strategies fail to cope with the dynamic request p atterns of the users. Most learning-based caching models are generally trained i n a centralized way, which overconsumes the network resources during training an d transmission of video requests. Therefore, we propose a Federated Learning-bas ed Reinforcement Learning caching framework called FedCache in this work. In Fed Cache, the training is decentralised on the end-user devices with its local data . The trained parameters from the end users are aggregated at the central server ."

Key words

Assam/India/Asia/Computational Intell igence/Machine Learning/Indian Institute of Technology Guwahati

引用本文复制引用

出版年

2024
Robotics & Machine Learning Daily News

Robotics & Machine Learning Daily News

ISSN:
段落导航相关论文