# Learning Wi-Fi Connection Loss Predictions for Seamless Vertical Handovers Using Multipath TCP

## TL;DR

This paper introduces a data-driven method using smartphone sensors and machine learning to predict Wi-Fi connection loss, enabling seamless handovers with improved streaming quality and reduced cellular data usage.

## Contribution

It presents a novel sensor-based prediction model combined with Multipath TCP for proactive Wi-Fi handovers, enhancing user experience and network efficiency.

## Key findings

- Wi-Fi connection loss can be predicted 15 seconds in advance with high accuracy.
- Using predictions improves streaming quality and reduces cellular data consumption.
- The approach is validated on real-world data and practical streaming experiments.

## Abstract

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.