SBIR Phase I: An AI-Based Collaborative Video Streaming Platform

这一小型企业创新研究（SBIR）第一阶段项目的更广泛影响是改善从消费者观看到远程教育等应用的视频流。拟议的平台减少了对数据中心和内容分发网络（CDN）的需求，从而降低了视频交付的成本。通过潜在地减少网络拥塞和提高网络对故障的弹性，所产生的解决方案可以帮助改善观众的体验。 此外，由于视频流占互联网流量的80%以上，因此该技术将有助于减少目前用于该服务的云计算基础设施的能耗和碳足迹。这个小型企业创新研究（SBIR）第一阶段项目利用并扩展了人工智能、随机系统和边缘网络方面的最新研究，解决了三个关键挑战：（1）设计一种有效管理视频流量的分散式人工智能优化算法;（2）设计一个先进的模拟环境，能够有效地模拟真实世界用户网络的行为，用于系统设计和评估;（3）系统优化，适用于各种设备。该奖项反映了NSF的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

The broader impact of this Small Business Innovation Research (SBIR) Phase I project is to improve video streaming for applications ranging from consumer viewing to remote education. The proposed platform reduces the need for data centers and Content Distribution Networks (CDNs), leading to cost reductions for video delivery. By potentially reducing network congestion and increasing network resilience to failures, the resulting solution can help improve viewers’ experience. Moreover, because video streaming represents 80+% of internet traffic, the proposed technology will contribute to a reduction in the energy consumption and carbon footprint of the cloud computing infrastructures currently used for this service. This Small Business Innovation Research (SBIR) Phase I project leverages and extend state-of-the-art research in artificial intelligence, stochastic systems and edge networks, addressing three key challenges: (1) Design of a decentralized artificial intelligence optimization algorithm that efficiently manages video traffic; (2) Design of an advanced simulation environment capable of efficiently mimicking the behavior of real-world networks of users for system design and assessment; (3) System optimization for use on a wide range of devices.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.