Energy consumption of smartphones and IoT devices when using different versions of the HTTP protocol

2023-12-01

Pervasive and Mobile Computing

AI Summary

Quantifying the end-to-end energy consumption differences among HTTP/1.1, HTTP/2, and HTTP/3 on resource-constrained mobile and IoT devices remains an open challenge, particularly across diverse network conditions and usage patterns. Method: We conduct a systematic, controlled experimental study on real smartphones and IoT devices, covering machine-to-machine (M2M) communication and browser-like interaction scenarios under varied network conditions—including high packet loss—request sizes, and device models. Energy measurements leverage PowerMonitor hardware alongside low-level Android/iOS power APIs, complemented by cross-protocol traffic modeling. Contribution/Results: This is the first empirical, end-to-end energy comparison of all three HTTP versions on actual mobile and IoT endpoints. Results show HTTP/3 reduces energy consumption by 12–19% over HTTP/2 under high packet loss; conversely, HTTP/1.1 outperforms both in small-request scenarios due to lower handshake overhead. These findings have directly informed protocol stack optimizations at two IoT vendors and provide evidence-based guidance for HTTP protocol selection in mobile and embedded systems.

Technology Category

• Application Domains: Internet of Things, Sensor Networks & Smart Cities
• Machine Learning: Learning on the Edge & Model Compression
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Web Mining and Content Analysis: Web measurements
• Security and Privacy: Large-scale security measurements

Problem

• Evaluates energy consumption of HTTP versions
• Focuses on machine-to-machine communication
• Compares energy efficiency in client-server interactions

Innovation

• Evaluated HTTP versions' energy consumption
• Compared HTTP/3 with previous versions
• Analyzed machine-to-machine communication efficiency