CSR: Small: Extending Smartphone Battery Life via Prescriptive Energy Profiling

智能手机在全球拥有超过20亿用户，在谷歌和苹果的数字市场上各有超过200万个应用程序(APP)，智能手机将人类社会带入了移动时代。尽管智能手机对社会产生了深远的影响，但智能手机的电池续航时间严重限制了用户体验。延长智能手机电池寿命的明显想法是改进电池技术，然而，电池技术在过去15年里停滞不前，电池容量通常被视为接近物理学的极限。相反，该项目致力于通过减少智能手机上运行的各种软件的能量消耗来显著延长智能手机的电池寿命。该项目旨在解决智能手机电池消耗的主要因素，即应用程序在前台运行时的能量消耗，目标是将其减少2倍。拟议的研究包括将开发第一套规范性能量分析技术的主要推动力，这些技术将把能量分析从“被动”应用程序开发步骤转变为“主动”过程：(A)它将开发第一个自动发现参数配置和框架/库方法调用之间的因果关系的能力，这是基于框架的移动编程中的一个独特而困难的程序分析问题；(B)它将开发第一个自动识别节能执行类似任务的能力，这是一个通常难以解决的问题，但对于移动应用程序来说，通过比较在庞大的移动应用程序市场中广泛可用的类似应用程序是可以实现的。智能手机是发达国家和发展中国家弱势群体接入互联网的重要推动因素，因此是克服“数字鸿沟”的重要工具，从而加强了该项目的重要性。从技术上讲，这项工作将通过增加通用事件驱动计算机程序的编译器能力，在开发节能移动应用程序的领域之外产生深远的影响。将维持一个项目储存库，以提供查阅代码、显示所开发技术的有效性的原始实验数据以及处理结果和技术出版物的途径。该储存库将在项目的三年期间和之后的两年内维持，以促进其他人在这一重要领域的研究活动。

With over 2 billion users worldwide and over 2 million applications (apps) each in Google and Apple's digital marketplaces, smartphones have advanced human society into the mobile era. Despite the far-reaching societal impact of smartphones, the user experience has been severely limited by smartphone battery life. The obvious idea of extending smartphone battery life is to improve the battery technology, which, however, has stagnated in the past 15 years, and battery capacity is generally viewed as nearing the limits of physics. Instead, this project pursues a course of research to significantly extend smartphone battery life by reducing the energy drain of various software running on the smartphone.This project aims to tackle a major smartphone battery drain contributor, app energy drain when running in the foreground, with the goal of reducing it by 2x. The proposed research includes major thrusts that will develop the first set of prescriptive energy profiling techniques that will transform energy profiling from a "passive" app development step into a "proactive" process: (a) It will develop the first capability to automatically uncover the causal relationship between parameter configurations and framework/library method invocations, a unique and hard program analysis problem in framework-based mobile programming; (b) It will develop the first capability to automatically identify an energy-efficient implementation of similar tasks, a generally intractable problem but attainable for mobile apps by comparing similar apps that are widely available in the huge mobile app marketplace.The importance of this project is heightened by smartphones being an important enabler of Internet access for disadvantaged people in both developed and developing countries, and hence being an important tool in overcoming the "digital divide". Technically, this work will have a far-reaching impact outside of the area of developing energy efficient mobile apps by increasing compiler capabilities for general event-driven computer programs. A project repository will be maintained to provide access to code, raw experimental data showcasing the effectiveness of the developed techniques, and processed results and technical publications. The repository will be maintained during the three-year project period and the two years afterwards, to foster research activities by others in this important area.