CNS Core: Small: Lease-based, Utilitarian Mobile System Design to Enable Energy-Efficient Apps

CNS 核心：小型：基于租赁的实用移动系统设计，支持节能应用

• 批准号: 1910133
• 负责人: Yinzhi Cao
• 金额: $ 50万
• 依托单位: Johns Hopkins University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-10-01 至 2023-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1910133&HistoricalAwards=false
• 关键词: CNS; Core; Small; Lease; based

Mobile devices are a pervasive computing platform with a rich set of programming interfaces for third-party developers to write software applications. However, mobile application programming is challenging. Software developers need to consider user interactions, changes in the conditions in which the mobile application is running, and carefully monitor resources on the mobile device. As a result, many mobile applications have software errors (bugs) that waste energy and cause the battery to be discharged quickly. The goal of this project is to provide a comprehensive solution to reduce energy waste caused by software bugs and enable application developers to create energy-efficient apps.Specifically, the project studies how real-world applications with energy bugs behave by collecting their runtime information and characterizing the energy misbehavior. This project then explores a utilitarian mobile operating system design with a new abstraction lease, to manage mobile resources efficiently even when applications have energy bugs. To facilitate application developers to leverage the new operating system design, this project further designs new interfaces for developers to define custom utility, a library to perform online optimization on utility and energy efficiency at application runtime, and an energy profiler to optimize low-utility code.Mobile applications today provide services integral to our daily life. Building energy-aware applications is ever more important. This project can effectively improve our understanding of application runtime behavior, significantly reduce the impact of potential energy bugs, and help application developers more easily build energy-efficient applications. This project will also promote teaching, outreach, and training by exposing students to the real-world challenges and design principles in building energy-aware applications.The project outcomes include paper publications, technical reports, presentations, course material, datasets, and software. The outcomes will be made available for download at https://www.cs.jhu.edu/~huang and be maintained for at least five years beyond the completion of the project. The source code of the new mobile operating system design will also be released and available on GitHub.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

移动设备是一个普遍存在的计算平台，其编程接口集为第三方开发人员编写软件应用程序。但是，移动应用程序编程具有挑战性。软件开发人员需要考虑用户交互，移动应用程序正在运行的条件的变化，并仔细监视移动设备上的资源。 结果，许多移动应用程序具有浪费能源并导致电池快速放电的软件错误（错误）。该项目的目的是提供一个全面的解决方案，以减少由软件错误引起的能源浪费，并使应用程序开发人员能够创建节能应用程序。特别是，该项目研究了通过收集其运行时信息并表征能源不当行为的现实世界应用程序如何行事。 然后，该项目将探索具有新的抽象租赁的功利主义移动操作系统设计，即使应用程序具有能源错误，也可以有效地管理移动资源。为了促进应用程序开发人员利用新的​​操作系统设计，该项目进一步设计了新的界面，以供开发人员定义自定义实用程序，库在应用程序运行时对实用程序和能源效率进行在线优化的库以及一个能源辅助仪来优化低实用代码。今天为我们的日常生活提供了服务的整体服务。建立能源感知的应用程序越来越重要。该项目可以有效地提高我们对应用程序运行时行为的理解，大大减少势能错误的影响，并帮助应用程序开发人员更容易地构建节能应用程序。该项目还将通过使学生面临建立能源感知应用程序的现实挑战和设计原则来促进教学，推广和培训。项目成果包括纸质出版物，技术报告，演示文稿，课程材料，数据集和软件。结果将在https://www.cs.jhu.edu/~huang上下载，并在项目完成之后维护至少五年。新移动操作系统设计的源代码还将发布并在GitHub上发布。该奖项反映了NSF的法定任务，并使用基金会的知识分子优点和更广泛的影响评估标准，被认为值得通过评估来获得支持。

项目成果

Automated Reasoning and Detection of Specious Configuration in Large Systems with Symbolic Execution

• 发表时间: 2020-10
• 期刊: ArXiv
• 作者: Yigong Hu;Gongqi Huang;Peng Huang

Operating System Support for Safe and Efficient Auxiliary Execution

操作系统支持安全高效的辅助执行

• 发表时间: 2022
• 期刊: 16th USENIX Symposium on Operating Systems Design and Implementation
• 作者: Jing, Yuzhuo;Huang, Peng
• 通讯作者: Huang, Peng

Argus: Debugging Performance Issues in Modern Desktop Applications with Annotated Causal Tracing

Argus：使用带注释的因果跟踪调试现代桌面应用程序中的性能问题

• 发表时间: 2021
• 期刊: The 2021 USENIX Annual Technical Conference
• 作者: Weng, Lingmei;Huang, Peng;Nieh, Jason;Yang, Junfeng
• 通讯作者: Yang, Junfeng