Learning Wi-Fi Connection Loss Predictions for Seamless Vertical Handovers Using Multipath TCP
This addresses connectivity issues for smartphone users by enabling smoother handovers, though it is incremental as it builds on existing sensor-based prediction and MPTCP methods.
The paper tackles the problem of seamless Wi-Fi/cellular handovers on smartphones by predicting Wi-Fi connection loss 15 seconds ahead using sensor data and Multipath TCP, achieving up to 0.97 precision and 0.98 recall, and improving video streaming quality with less cellular data.
We present a novel data-driven approach to perform smooth Wi-Fi/cellular handovers on smartphones. Our approach relies on data provided by multiple smartphone sensors (e.g., Wi-Fi RSSI, acceleration, compass, step counter, air pressure) to predict Wi-Fi connection loss and uses Multipath TCP to dynamically switch between different connectivity modes. We train a random forest classifier and an artificial neural network on real-world sensor data collected by five smartphone users over a period of three months. The trained models are executed on smartphones to reliably predict Wi-Fi connection loss 15 seconds ahead of time, with a precision of up to 0.97 and a recall of up to 0.98. Furthermore, we present results for four DASH video streaming experiments that run on a Nexus 5 smartphone using available Wi-Fi/cellular networks. The neural network predictions for Wi-Fi connection loss are used to establish MPTCP subflows on the cellular link. The experiments show that our approach provides seamless wireless connectivity, improves quality of experience of DASH video streaming, and requires less cellular data compared to handover approaches without Wi-Fi connection loss predictions.