AI for Connectivity Hackathon II: Building Resilient Networks 

Start

EagleNet

Barun Saha

Quality of Service (QoS) is a critical requirement in communication networks. QoS patterns can indicate potential network problems or a need for an upgrade. With millions of schools connected to the Internet, there already is an overwhelming volume of network performance data available. Moreover, as usage patterns evolve in the future, for example, from accessing data and video to running real-time, remote or virtual experiments across schools, the QoS demands would only grow stronger. Therefore, there is a need for an efficient approach to gain insights into the pool of network performance data.

QoScope takes an agentic approach to provide a natural language dashboard (NLD). Using the NLD, network administrators can express their queries in natural language, e.g., English. Based on the query, the agent uses one or more available tools to arrive at a response. For example, currently, QoScope can generate and run a SQL query when required. In addition, it can also generate bar and line diagrams to assist visualization of data. 

In particular, QoScope uses the `school_geolocation_measurements_v2/measurements.csv` dataset by Giga. This CSV file contains the network speed and latency measurements across many schools. A filtered version of these measurements (where each school has at least 120 data points) is pre-processed, resampled, and stored as an SQLite database provided with this repository (`resampled_daily_avg.sqlite`). QoScope agent queries the table in this database on the fly, if required.

The source code and live demo of QoScope are available at: https://huggingface.co/spaces/barunsaha/qoscope and https://huggingface.co/spaces/barunsaha/qoscope/tree/main (Apache 2.0 license).

An agentic, natural language dashboard for QoS monitoring

"EagleNet team on AI for Connectivity Hackathon II: Building Resilient Networks Hackathon"

Team Idea

Submission