[Paper Review] Web Performance with Android's Battery-Saver Mode

Utkarsh Goel, Stephen Ludin+1 more|arXiv (Cornell University)|Mar 13, 2020

Green IT and Sustainability10 references4 citations

TL;DR

This study investigates how Android's battery-saver mode—by throttling CPU clock speeds—impacts mobile web performance using a large-scale real-user monitoring dataset. It finds that older Huawei and Sony smartphones experience significant degradation in page load time, time to interactive, and frame rate under battery-saver mode, while newer flagship devices show no such impact, urging developers to optimize for low-power, throttled devices.

ABSTRACT

A Web browser utilizes a device's CPU to parse HTML, build a Document Object Model, a Cascading Style Sheets Object Model, and render trees, and parse, compile, and execute computationally-heavy JavaScript. A powerful CPU is required to perform these tasks as quickly as possible and provide the user with a great experience. However, increased CPU performance comes with increased power consumption and reduced battery life on mobile devices. As an option to extend battery life, Android offers a battery-saver mode that when activated, turns off the power-hungry and faster processor cores and turns on the battery-conserving and slower processor cores on the device. The transition from using faster processor cores to using slower processor cores throttles the CPU clock speed on the device, and therefore impacts the webpage load process. We utilize a large-scale data-set collected by a real user monitoring system of a major content delivery network to investigate the impact of Android's battery-saver mode on various mobile Web performance metrics. Our analysis suggests that users of select smartphones of Huawei and Sony experience a sudden or gradual degradation in Web performance when battery-saver mode is active. Battery-saver mode on newer flagship smartphones, however, does not impact the mobile Web performance. Finally, we encourage for new website design goals that treat slow (and throttled-CPU) devices kindly in favor of improving end-user experience and suggest that Web performance measurements should be aware of user device battery charge levels to correctly associate Web performance.

Motivation & Objective

• To investigate the impact of Android's battery-saver mode on mobile web performance metrics such as page load time and time to interactive.
• To identify whether CPU throttling under battery-saver mode leads to perceptible user experience degradation on specific smartphone models.
• To highlight the need for new website design practices that account for low-power, throttled devices to maintain responsiveness.
• To advocate for performance measurements that consider device battery levels to avoid misattributing performance issues to web optimization.

Proposed method

• Collected a large-scale dataset of 10 million real-user web performance measurements from Akamai mPulse across 300 smartphone models and 81 cellular ISPs in 39 countries (July 2017–March 2018).
• Used real-user monitoring (RUM) to measure key performance metrics: page load time (PLT), time to first paint (TTFP), time to interactive (TTI), total LongTask time, and frame rate (FPS).
• Analyzed performance distributions across different battery charge levels, particularly focusing on thresholds where battery-saver mode activates (e.g., 5%, 10%, 15%, 20%, 30%, 50%).
• Employed boxplot visualizations to compare performance metric distributions across battery levels, identifying sudden performance drops at specific thresholds.
• Focused analysis on devices like Huawei P8 Lite and Sony Xperia models showing notable performance degradation under battery-saver mode.
• Utilized the mPulse Continuity plugin to collect frame rate data during page loading to assess visual responsiveness.

Experimental results

Research questions

• RQ1 Does enabling Android's battery-saver mode lead to measurable degradation in mobile web performance metrics such as page load time and time to interactive?
• RQ2 Are certain smartphone models more affected by CPU throttling under battery-saver mode than others?
• RQ3 Does the impact of battery-saver mode vary depending on network conditions, particularly in faster mobile networks?
• RQ4 At what battery charge level threshold does performance degradation begin to manifest on affected devices?
• RQ5 To what extent does reduced frame rate under battery-saver mode contribute to perceived unresponsiveness in web applications?

Key findings

• On Huawei P8 Lite (2015), page load time (PLT) and time to interactive (TTI) metrics showed a sudden increase as battery charge dropped below 10%.
• Frame rate (FPS) on the Huawei P8 Lite declined significantly when battery charge fell below 10%, indicating reduced visual responsiveness.
• Devices such as Huawei P8 Lite and Sony Xperia models exhibited a clear performance degradation under battery-saver mode, particularly in PLT, TTI, and LongTask time.
• The performance impact of battery-saver mode was more pronounced on faster mobile network conditions, suggesting that network speed can amplify CPU-related bottlenecks.
• Newer flagship smartphones (e.g., newer Samsung Galaxy and Huawei models) showed no measurable performance degradation under battery-saver mode, indicating improved power management or CPU architecture.
• The study reveals a disconnect between current web performance measurement practices and real-world device behavior under low-battery conditions, urging inclusion of battery level in performance analysis.