ISSN 1000-1239 CN 11-1777/TP

计算机研究与发展 ›› 2018, Vol. 55 ›› Issue (3): 563-571.doi: 10.7544/issn1000-1239.2018.20170716

所属专题: 2018边缘计算专题

• 网络技术 • 上一篇    下一篇

移动边缘计算中基于内容动态刷新的能耗优化

郭延超1,高岭1,2,王海1,郑杰1,任杰1   

  1. 1(西北大学信息科学与技术学院 西安 710127); 2(西安工程大学计算机科学学院 西安 710048) (guoyanchao@stumail.nwu.edu.cn)
  • 出版日期: 2018-03-01
  • 基金资助: 
    国家自然科学基金项目(61572401,61672426);陕西省工业攻关项目(2014K05-42)

Power Optimization Based on Dynamic Content Refresh in Mobile Edge Computing

Guo Yanchao1, Gao Ling1,2, Wang Hai1, Zheng Jie1, Ren Jie1   

  1. 1(School of Infomation and Technology, Northwest University, Xi’an 710127); 2(College of Computer Science, Xi’an Polytechnic University, Xi’an 710048)
  • Online: 2018-03-01

摘要: 随着移动互联网的飞速发展与相关技术的不断提升,社交类应用已成为现下主流应用之一.同时,手机应用的功能也越来越丰富,其能耗需求以及信息处理能力也越来越大.针对移动社交平台忽略网络状态、频繁刷新内容(文字、图片、视频等)造成的高能耗以及运算能力问题,提出一种边缘计算模式下基于Markov决策过程(Markov decision process, MDP)的能耗优化模型.该模型考虑不同环境的网络状态,根据手机当前电量以及用户刷新频率,通过本地移动边缘计算层完成数据处理,在Markov决策过程生成的决策表中选择最优策略,动态选择最佳的网络接入以及刷新下载最佳的图片格式.该模型不仅减少刷新时间,而且能够降低移动平台的能耗.实验结果表明:相比于使用单一网络的图片刷新模式,在保证不减少用户刷新次数的前提下,该能耗优化模型降低能耗约12.1%.

关键词: 社交APP, Markov决策过程, 能耗优化, 刷新模式, 边缘计算

Abstract: Nowadays, with the rapid development of mobile Internet and related technologies, social applications have become one of the mainstream applications. At the same time, the functions of mobile applications are also getting richer and richer, and their energy consumption requirements and information processing capabilities are also growing. In view of the problem of high energy consumption and computing power caused by mobile social platforms ignoring network status and frequently refreshing content (words, pictures, videos, etc.), a consumption optimization model based on Markov decision process (MDP) in edge computing is proposed. The model considers the network status in different environments and performs data processing through the local edge computing layer (simulating the local edge computing mode and completing data processing) according to the current power of the mobile phone and the user refresh rate. It selects optimal strategy from the decision tables generated by the Markov decision process, and dynamically selects the best network access and refreshes the best download picture format. The model not only reduces refresh time, but also reduces the power consumption of the mobile platform. The experimental results show that compared with the picture refresh mode using a single network, the energy consumption optimization model proposed in this paper reduces the energy consumption by about 12.1% without reducing the number of user refresh cycles.

Key words: social APP, Markov decision process, energy consumption optimization, refresh mode, edge computing

中图分类号: