IMR: MT: NetFlex: A Flexible Scalable & Privacy-Preserving Network Measurement Platform to Iteratively Collect Multi-modal Multi-view Network Data from Access Networks

随着我们对基于互联网的工作、教育、医疗和娱乐服务的依赖持续增长，宽带接入的质量成为决定我们使用这些服务体验的关键因素。然而，美国的这种接入质量因地区、社区和人口群体而异，导致了数字不平等。政策制定者需要反映接入质量实际状况的高保真数据，以解决这些不平等问题。不幸的是，现有工具收集的数据质量很差，往往无法反映用户的体验。该项目旨在开发一个新的互联网测量平台NetFlex，以解决现有互联网测量工具的根本局限性。具体地说，NetFlex有助于大规模收集高质量的网络数据。政策制定者可以利用这些数据做出更好的决策，以应对数字不平等。此外，该项目计划在校园网络中部署Netflex，让学生接触到(真实的)网络测量数据，并增强他们的学习体验。该项目的新奇之处在于，它促进了从多个有利位置迭代收集“正确的”主动或被动网络测量数据，从而支持宽带接入质量评估和诊断扰乱用户体验的事件。具体地说，它提供了一个简化的用户界面，可以显示网络状态的高保真报告，并简化了对降级事件的诊断。在幕后，NetFlex采用面向服务的数据收集架构，即将不同的网络测量和数据收集任务分解为独立的服务。它还将收集的网络数据转换为整体和标准化的网络数据表示。这些设计选择使NetFlex能够在灵活性、可扩展性和保密性之间取得平衡。最后，该项目将利用两个引人注目的使用案例来展示NetFlex如何提高收集的网络测量数据的质量，以及新数据如何能够更好地评估宽带质量和诊断降级事件。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

As our dependence on internet-based services for work, education, healthcare, and entertainment continues to grow, the quality of broadband access becomes the critical factor determining our experiences with these services. However, this access quality in the US differs among regions, communities, and demographic groups, leading to digital inequities. Policymakers need high-fidelity data reflecting the actual state of access quality to address these inequities. Unfortunately, the existing tools gather poor-quality data that often fail to reflect users' experiences. This project aims to develop a new Internet measurement platform, NetFlex, that addresses the fundamental limitations of existing Internet measurement tools. Specifically, NetFlex facilitates the collection of high-quality network data at scale. Policymakers can use this data to make better decisions to counter digital inequities. Moreover, this project plans to deploy Netflex at campus networks, exposing students to (realistic) network measurement data and enhancing their learning experience.The project's novelty is that it facilitates the iterative collection of the "right" active or passive network measurement data from multiple vantage points, empowering the assessment of broadband access quality and diagnosing events that disrupt the user experience. Specifically, it offers a simplified user interface that displays high-fidelity reporting of the network's state and simplifies diagnosing degradation events. Under the hood, NetFlex embraces service-oriented architecture for data collection, i.e., it disaggregates different network measurement and data collection tasks into independent services. It also transforms the collected network data into holistic and standardized network data representations. These design choices enable NetFlex to strike a balance between flexibility, scalability, and privacy. Finally, the project will leverage two compelling use cases to showcase how NetFlex improves the quality of collected network measurement data and how the new data can better assess the broadband quality and diagnose degradation events.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.