Smart Handover With Predicted User Behavior Using Convolutional Neural Networks for WiGig Systems

WiGig networks and 60 GHz frequency communications have a lot of potential for commercial and personal use. The high-frequency bands can provide high transmission rates, but their high amplitude makes it so the signal cannot go through any walls or obstacles. The signal also has a strong path loss element caused by the high frequency, significantly limiting the reach of connections because the signal is too weak at moderate distances. Due to these issues, users can easily lose connection with the access point while moving and need to connect to a new device, making WiGig systems unstable as they need to rely on frequent handovers to maintain a high-quality service. However, this solution is problematic as it forces users into bad connections and downtime before they are switched to a better access point. In this work, we use machine learning to identify patterns in user behaviors and predict user actions. This prediction is used to do proactive handovers, switching users to access points with better future transmission rates and a more stable environment based on the future state of the user. Results show that not only the proposal is effective at predicting channel data, but the use of such predictions improves system performance and avoids unnecessary handovers.