Is HTTP/2 more energy efficient than HTTP/1.1 for mobile users?

Abstract

Recent technological advancements have enabled mobile devices to provide mobile users with substantial capability and accessibility. Energy is evidently one of the most critical resources for such devices; in spite of the substantial gain in popularity of mobile devices, such as smartphones, their utility is severely constrained by battery life. Mobile users are very interested in accessing the Internet while it is one of the most expensive operations in terms of energy and cost. HTTP/2 has been proposed and accepted as the new standard for supporting the World Wide Web. HTTP/2 is expected to offer better performance, such as reduced page load time. Consequently, from the mobile users point of view, question arises: Does HTTP/2 offer improved energy consumption performance achieving longer battery life? In this paper, we compare the energy consumption of HTTP/2 with its predecessor (i.e., HTTP/1.1) using a variety of real world and synthetic test scenarios. We also investigate how Transport Layer Security (TLS) impacts the energy consumption of the mobile devices. Our study suggests that Round Trip Time (RTT) is one of the biggest factors in deciding how advantageous is HTTP/2 compared to HTTP/1.1. We conclude that for networks with higher RTTs, HTTP/2 has better energy consumption performance than HTTP/1.1.

Web servers energy efficiency under HTTP/2

“…HTTP/2 optimizations have been shown to save energy for the mobile client side devices [56]. In our previous study [14], we also found client-side HTTP/2 to be more energy efficient than HTTP/1.1 with or without Transport Layer Security (TLS) applied. However, does these optimizations and reduction in PLT helps HTTP/2 speaking servers to be more energy efficient than HTTP/1.1?…”

“…Following the work done previously [14], we once again used FGallery [17], a static photo gallery generator and deployed it onto the H2O and the Jetty server. The Fgallery resources deployed consists of the home HTML page, CSS, JS, JSON and Image files.…”

“…In previous research with Green Miner [14], [5] it has been observed that a single measurement for a particular setting could give some false positive results as there could be variation in the measurements due to the factors which are not under control and are unrelated to the application under test. Therefore, it was suggested that taking an average of at least ten runs for each test will produce more accurate test results.…”

“…For example, in our tests different phases of a test included starting the Green Miner measurement service, launch the server, wait for the server to receive requests from the clients, stop the server. Chowdhury et al [14] found that a previous phase of the test may affect the energy measurements of the task we are interested in. This may happen because of the different sequence of operations in the previous phase or the different amount of time taken by the previous phase to perform its task which may leave the system components in a High power state.…”

“…The web initially meant to serve a collection of hyperlinked textual information, has since transformed to serve multimedia content and provide access to services like emails, social networks, business applications, search engines over the Internet. Loading content rich and complex web pages have become more resource intensive [14]. It highlighted the inefficiencies of HTTP/1.1 protocol which has been serving the web for more than 15 years.…”