IRES Track-I PILOT: Location-Independent Multi-Source Video Streaming

IRES Track-I PILOT：位置无关的多源视频流

• 批准号: 1940619
• 负责人: Mohsen Amini Salehi
• 金额: $ 7.5万
• 依托单位: University of Louisiana at Lafayette
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-02-01 至 2022-01-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1940619&HistoricalAwards=false
• 关键词: IRES; Track; PILOT; Location; Independent

Video streaming is the major source of Internet traffic in the U.S. and worldwide. To enable high quality and fast video streaming, independent from the viewers' geographical location, researchers propose to explore a inter-fog computing system called Latency Aware STreaming (LAST) that enables multi-source video streaming. Leveraging the locality feature exists in video stream requests, LAST will be able to partially pre-process video streams and stream the missing segments simultaneously from peer LASTs that possibly have those missing segments cached. LASTs also have the ability to locally process video streams. Therefore, for each video segment, a LAST has to determine whether to stream it from a neighboring LAST or process it locally. To reduce streaming latency further, the LAST platform proactively determines hot videos in a certain jurisdiction and preheats those videos at the fog level.This is an exploratory but potentially transformative research idea in its early stages. This project, involving the radical approach of multi-source video streaming, is considered high risk/ potentially high payoff. The project is interdisciplinary and combines cloud/fog computing and video streaming. To explore this idea, two students (possibly one graduate and oneundergraduate student) are expected to travel to visit CLOUDS Lab at Melbourne University in Australia that is directed by Dr. Rajkumar Buyya, one of the most outstanding researchers in cloud computing and he is the highest cited scientist in Cloud Computing. In a close collaboration with CLOUDS lab, the team of researchers will learn working with iFogSim, which is a platform forsimulating and testing fog computing systems developed at CLOUDS Lab. It will enable students to simulate and prototype the proposedLAST platform. During the visit, students will learn and extend iFogSim to accommodate video streaming tasks and achieve multi-sourcestreaming via inter-fog systems. This project will help undergraduate and graduate students from ULLafayette to become highly skilled and globally engaged workforce.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

视频流是美国和全球互联网流量的主要来源。为了实现高质量和快速的视频流，独立于观众的地理位置，研究人员建议探索一种名为Latency Aware Streaming（LAST）的雾间计算系统，该系统可以实现多源视频流。利用视频流请求中存在的局部性特征，LAST将能够部分地预处理视频流，并同时从可能缓存了那些缺失片段的对等LAST流式传输缺失片段。LAST还具有本地处理视频流的能力。因此，对于每个视频片段，LAST必须确定是从相邻LAST流式传输还是在本地处理。为了进一步降低流媒体延迟，LAST平台主动确定某个管辖区内的热门视频，并在雾级别对这些视频进行预热。这是一个探索性但可能具有变革性的早期研究想法。该项目涉及多源视频流的激进方法，被认为是高风险/潜在的高回报。该项目是跨学科的，结合了云/雾计算和视频流。为了探索这个想法，两名学生（可能是一名研究生和一名本科生）预计将前往访问澳大利亚墨尔本大学的CLOUDS实验室，该实验室由Rajkumar Buyya博士领导，他是云计算领域最杰出的研究人员之一，也是云计算领域被引用次数最多的科学家。在与CLOUDS实验室的密切合作中，研究人员团队将学习使用iFogSim，这是一个模拟和测试CLOUDS实验室开发的雾计算系统的平台。它将使学生模拟和原型的proposedLAST平台。 在参观期间，学生们将学习和扩展iFogSim，以适应视频流任务，并通过雾间系统实现多源数据流。该项目将帮助ULLafayette的本科生和研究生成为高技能和全球参与的劳动力。该奖项反映了NSF的法定使命，并通过使用基金会的智力价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

SAED: Edge-Based Intelligence for Privacy-Preserving Enterprise Search on the Cloud

• DOI: 10.1109/ccgrid51090.2021.00046
• 发表时间: 2021-02
• 期刊: 2021 IEEE/ACM 21st International Symposium on Cluster, Cloud and Internet Computing (CCGrid)
• 作者: Sakib Zobaed;M. Salehi;R. Buyya