Performance and Energy Efficiency of Mobile Data Offloading with Mobility Prediction and Prefetching

TL;DR

This paper evaluates how mobility prediction and prefetching techniques can improve mobile data offloading to WiFi hotspots, focusing on performance metrics like traffic offloaded, delay, and energy use.

Contribution

It provides a comprehensive empirical analysis of offloading procedures that incorporate mobility prediction and prefetching, considering various real-world factors.

Findings

Higher throughput increases offloading efficiency.

Estimation errors impact delay and energy consumption.

More hotspots improve offloading performance.

Abstract

We present a detailed evaluation of procedures that exploit mobility prediction and prefetching to enhance offloading of traffic from mobile networks to WiFi hotspots, for both delay tolerant and delay sensitive traffic. We consider empirical measurements and evaluate the percentage of offloaded traffic, data transfer delay, and energy consumption of the proposed procedures. Our results illustrate how various factors such as mobile, WiFi and hotspot backhaul throughput, data size, number of hotspots, along with time and throughput estimation errors, influence the performance and energy efficiency of mobile data offloading enhanced with mobility prediction and prefetching.