A Computing Profiling Procedure for Mobile Developers to Estimate Energy Cost

Proceedings of the 18th ACM International Conference on Modeling, Analysis and Simulation of Wireless and Mobile Systems Pub Date : 2015-11-02 DOI:10.1145/2811587.2811627

M. Altamimi, S. Naik

{"title":"A Computing Profiling Procedure for Mobile Developers to Estimate Energy Cost","authors":"M. Altamimi, S. Naik","doi":"10.1145/2811587.2811627","DOIUrl":null,"url":null,"abstract":"Mobile devices are constrained by the limited capacities of their small batteries. However, profiling the energy consumed in the task execution is crucial to help the developers to build energy efficient applications. Therefore, the major challenge in the profiling approach is to accurately estimating the energy consumed for an application by the hardware components, such as CPU, memory, storage unit, and network interfaces. In this work, we develop and validate hardware and software profiling models and procedures. We profile smartphone CPU, where we consider multi-core CPUs and the impact of Dynamic Voltage and Frequency Scaling mechanism on the power consumption. In addition, we profile smartphone storage unit by taking into account the writing and reading rate to the unit. Moreover, we experimentally validated these profiles on two diverse smartphones with different versions of operating systems. The experimental results reveal that our profiles are able to estimate the application energy accurately.","PeriodicalId":371317,"journal":{"name":"Proceedings of the 18th ACM International Conference on Modeling, Analysis and Simulation of Wireless and Mobile Systems","volume":"86 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2015-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"8","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 18th ACM International Conference on Modeling, Analysis and Simulation of Wireless and Mobile Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/2811587.2811627","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 8

Abstract

Mobile devices are constrained by the limited capacities of their small batteries. However, profiling the energy consumed in the task execution is crucial to help the developers to build energy efficient applications. Therefore, the major challenge in the profiling approach is to accurately estimating the energy consumed for an application by the hardware components, such as CPU, memory, storage unit, and network interfaces. In this work, we develop and validate hardware and software profiling models and procedures. We profile smartphone CPU, where we consider multi-core CPUs and the impact of Dynamic Voltage and Frequency Scaling mechanism on the power consumption. In addition, we profile smartphone storage unit by taking into account the writing and reading rate to the unit. Moreover, we experimentally validated these profiles on two diverse smartphones with different versions of operating systems. The experimental results reveal that our profiles are able to estimate the application energy accurately.

查看原文本刊更多论文

一种用于移动开发者估算能源成本的计算分析程序

移动设备受到小型电池容量有限的限制。然而，分析任务执行中消耗的能量对于帮助开发人员构建节能的应用程序是至关重要的。因此，分析方法中的主要挑战是准确地估计硬件组件(如CPU、内存、存储单元和网络接口)对应用程序消耗的能量。在这项工作中，我们开发和验证硬件和软件分析模型和过程。我们分析了智能手机CPU，其中我们考虑了多核CPU和动态电压和频率缩放机制对功耗的影响。此外，我们通过考虑对该单元的写入和读取速率来分析智能手机存储单元。此外，我们还在两款不同版本操作系统的智能手机上进行了实验验证。实验结果表明，我们的轮廓能准确地估计出应用能量。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Proceedings of the 18th ACM International Conference on Modeling, Analysis and Simulation of Wireless and Mobile Systems

自引率

0.00%

发文量