Abstract: In one embodiment, a service receives radar data regarding usage of one or more wireless channels by a radar. The service populates a database of radar features with the received radar data. The service trains, using the database of radar features, a machine learning-based model to predict channel usages by the radar. The service causes a wireless access point to change to a different wireless channel, based on the predicted channel usages by the radar.

Abstract: In one embodiment, a system includes a processor to determine a number P of how many multi-user groups are to be formed to promote airtime fairness for N client devices in which each one client device of the N client devices will be equally represented in the to-be-formed multi-user groups and in which each of the to-be-formed groups is to be actively considered by a scheduler for transmission purposes, the N client devices being associated with N wireless connections with an access point having multi-user simultaneous communication multiple-input multiple-output technology, define P multi-user groups with each one multi-user group of the P multi-user groups having a capacity for M client devices from the N client devices, N being greater than M, and allocate the N client devices to the P multi-user groups with each one client devices of the N client devices being equally represented in the P multi-user groups.