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

University Of California-Santa Barbara, Santa Barbara CA

Investigators

Abstract

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.