[ITU-T AI Challenge] Input/Output of project "Improving the capacity of IEEE 802.11 WLANs through Machine Learning"

This data set will be used by participants of the ITU-T AI Challenge. 

The data set contains:

• Input files: contain information such as nodes labels, nodes position, or channels used. These files have been used to simulate the behavior of random WLAN deployments under different channel bonding conditions. 
• Output files: contain the output of the simulations - throughput per STA, RSSI that each STA receives from its AP, interference map from APs' point of view, average SINR experienced by each device during packet receptions.

More details can be found on the official website of the challenge: https://www.upf.edu/web/wnrg/ai_challenge

[Update - 28 July 2020] A script (script_process_dataset.sh) has been added to process the output files. In particular, the results of each deployment are separated into different files. Besides, different files are created according to the type of label/feature (throughput, airtime, RSSI map, and interference list).

[Update - 22 September 2020] A new feature has been added to all the files in the data set. In particular, we have added the average Signal-to-Interference-plus-Noise Ration (SINR) experienced by each STA during packet receptions (including data and control packets). The SINR values in APs are marked as Inf because we focus on downlink transmissions only.

[Update - 30 September 2020] The test data set has been released, which corresponds to the simulations of a set of deployments with different characteristics. Input node files are contained in input_node_files_test.zip, while output_simulator_test.zip includes the output generated by the simulator. The label (i.e., the throughput) of the test data set will not be included in this repository until the next update (estimated date: 15 October 2020).

[Update - 19 October 2020] After participants have submitted their solutions, we provide the entire test data set, including the actual throughput obtained by each AP and STA in the test deployments.