Intelligent client steering in mesh networks

A computer-implemented method for client steering in a mesh network, the method, comprising:

• transmitting, by a first wireless access point of the mesh network, a quality of service (QOS) data packet to a client device of a plurality of client devices, the mesh network comprising a plurality of wireless access points comprising the first wireless access point;
• capturing a first received signal strength indication (RSSI) of the client device using the QoS data packet;
• determining a distance between the first wireless access point and the client device using a Wi-Fi round trip time (Wi-Fi RTT);
• determining a time and day of week;
• determining, using a machine learning model, a second wireless access point of the plurality of wireless access points for steering the client device to, based on the RSSI, the distance, and the time and day of week, wherein the machine learning model is trained to steer each client device of the plurality of client devices to a respective wireless access point of the plurality of wireless access points for increasing a throughput of the mesh network based on features extracted from client behavior of the plurality of client devices;
• connecting the second wireless access point to the client device;
• capturing a second RSSI of the client device;
• determining a difference between the first RSSI and the second RSSI;
• associating the time and day of week with the second RSSI and the distance to build a traffic pattern for the client device;
• and
• responsive to the difference exceeding a threshold difference, sending the difference to a cloud server for training the machine learning model.