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

TL;DR

This study experimentally compares the energy cost of HTTP/1.1, HTTP/2, and HTTP/3 on energy-constrained devices (smartphones and SBCs) within edge/cloud configurations. Using real devices, LTE connectivity, power measurement, and two edge/cloud platforms (Cloudflare Workers and Google Cloud Storage), the authors analyze machine-to-machine and browsing-like traffic, applying ANCOVA to model energy versus payload size. The main finding is that HTTP/3 typically consumes more energy in machine-to-machine scenarios, driven by longer transfer times and higher CPU utilization, though HTTP/3 can be more energy-efficient in browsing-like traffic with back-to-back requests and appropriate parallelism. These results highlight that protocol choice should be tailored to workload and network conditions, with significant implications for energy budgeting in IoT and edge computing deployments.

Abstract

HTTP is frequently used by smartphones and IoT devices to access information and Web services. Nowadays, HTTP is used in three major versions, each introducing significant changes with respect to the previous one. We evaluated the energy consumption of the major versions of the HTTP protocol when used in the communication between energy-constrained devices and cloud-based or edge-based services. Experimental results show that in a machine-to-machine communication scenario, for the considered client devices - a smartphone and a Single Board Computer - and for a number of cloud/edge services and facilities, HTTP/3 frequently requires more energy than the previous versions of the protocol. The focus of our analysis is on machine-to-machine communication, but to obtain a broader view we also considered a client-server interaction pattern that is more browsing-like. In this case, HTTP/3 can be more energy efficient than the other versions.

Figures (14)

• Figure 1: The communication scheme between client and server.
• Figure 2: The setup used during the experimental phase.
• Figure 3: Communication scheme between the controlling software running on the PC connected to the power monitor and the SBC.
• Figure 4: Overview of the experiments.
• Figure 5: The energy consumption of the smartphone when interacting with the serverless edge infrastructure; payload size ($s$) is equal to 1024 kB.