This repository contains data and information regarding the paper:
Ali Safari Khatouni and Martino Trevisan and Danilo Giordano and Mohammad Rajiullah and Stefan Alfredsson and Anna Brunstrom and Cise Midoglu and Ozgu Alay, “An Open Dataset of Operational Mobile Networks”, submitted in the 18th ACM International Symposium on Mobility Management and Wireless Access (MobiWac 2020)
Summary
We present and provide access to the largest open international mobile network dataset collected using the MONROE platform spanning six countries, 27 mobile network operators, and 120 measurement nodes. We use them to run measurements targeting several web services from January 2018 to December 2019, collecting millions of TCP and UDP flows using these commercial mobile networks. We illustrate the data collection platforms and describe some of the main experiments. Besides a high-level overview of the dataset, we provide two practical use cases. First, we show how our data can be used as a proxy of web service performance, and, second, we study the content delivery infrastructure of Facebook.
Full dataset
Our goal is to publicize the whole MONROE measurements dataset from January 2018 to December 2019. The full dataset contains all columns exported by Tstat and metadata exporter from January 2018 to December 2019. The repository presently amounts to around 46 GB of compressed logs. The dataset is open to the community to reproduce our results or perform further analysis.
The link to download the data is:
https://mplanestore.polito.it:5001/sharing/F2amz5krF
The samples above are composed of multiple tar.gz files containing CSV files. Each tarball contains a chunk of the data. TCP (tcp.csv) and UDP (udp.csv) logs are provided in separate files. Files contain a subset of the columns exported by Tstat (find more detailed information regarding the format here. As explained in the paper, operator names are anonymized.
In addition to the Tstat features, the log contains the node ID (nodeid) to specify a specific node and additional metadata features: devicemode, rsrp, rsrq, rssi, operator (anonymized). Find more details here.
Moreover, you find:
- Roaming in {0,1}: 1 is roaming operators otherwise not.
- Mobile in {0,1}: 1 is mobile node onboard of vehicle or train otherwise stationary.
- Country: the country node is located.
- Service: the service based on this paper.