Dandelion

A Unified Code Offloading System for Wearable Computing

Morteza Golkarifard, Ji Yang, Zhanpeng Huang, Ali Movaghar, Pan Hui

Forskningsoutput: TidskriftsbidragArtikelVetenskapligPeer review

Sammanfattning

Execution speed seriously bothers application developers and users for wearable devices such as Google Glass. Intensive applications like 3D games suffer from significant delays when CPU is busy. Energy is another concern when the devices are in low battery level, but users need them for urgency use. To ease such pains, one approach is to expand the computational power by cloud offloading. This paradigm works well when the available Internet access has enough bandwidth. Another way is to leverage nearby devices for computation-offloading, which is known as device-to-device (D2D) offloading. In this paper, we present Dandelion, a unified code offloading system for wearable computing. Such applications can leverage both the nearby devices and cloud for performance acceleration and energy efficiency. Dandelion is a novel generic code offloading system for wearable computing with a reference implementation on Google Glass. Dandelion includes a programmer-friendly framework based on Java annotation, a lightweight offloading service, and a runtime task scheduler to make offloading decisions. We design some wearable applications and several parallel execution benchmark methods for Dandelion performance evaluation. Extensive experiments on a testbed of Google Glass and Android phones demonstrate that Dandelion generally achieves over 5X execution speedup for local execution and can quickly recover from errors caused by network disruption.
Originalspråkengelska
TidskriftIEEE Transactions on Mobile Computing
Volym18
Utgåva3
Sidor (från-till)546-559
Antal sidor14
ISSN1536-1233
DOI
StatusPublicerad - 1 mar 2019
MoE-publikationstypA1 Tidskriftsartikel-refererad

Vetenskapsgrenar

  • 113 Data- och informationsvetenskap

Citera det här

Golkarifard, Morteza ; Yang, Ji ; Huang, Zhanpeng ; Movaghar, Ali ; Hui, Pan. / Dandelion : A Unified Code Offloading System for Wearable Computing. I: IEEE Transactions on Mobile Computing. 2019 ; Vol. 18, Nr. 3. s. 546-559.
@article{af93779423794c3b8c7907aa5fdbc35a,
title = "Dandelion: A Unified Code Offloading System for Wearable Computing",
abstract = "Execution speed seriously bothers application developers and users for wearable devices such as Google Glass. Intensive applications like 3D games suffer from significant delays when CPU is busy. Energy is another concern when the devices are in low battery level, but users need them for urgency use. To ease such pains, one approach is to expand the computational power by cloud offloading. This paradigm works well when the available Internet access has enough bandwidth. Another way is to leverage nearby devices for computation-offloading, which is known as device-to-device (D2D) offloading. In this paper, we present Dandelion, a unified code offloading system for wearable computing. Such applications can leverage both the nearby devices and cloud for performance acceleration and energy efficiency. Dandelion is a novel generic code offloading system for wearable computing with a reference implementation on Google Glass. Dandelion includes a programmer-friendly framework based on Java annotation, a lightweight offloading service, and a runtime task scheduler to make offloading decisions. We design some wearable applications and several parallel execution benchmark methods for Dandelion performance evaluation. Extensive experiments on a testbed of Google Glass and Android phones demonstrate that Dandelion generally achieves over 5X execution speedup for local execution and can quickly recover from errors caused by network disruption.",
keywords = "Computation offloading, wearable computing, Google Glass, D2D, 113 Computer and information sciences",
author = "Morteza Golkarifard and Ji Yang and Zhanpeng Huang and Ali Movaghar and Pan Hui",
year = "2019",
month = "3",
day = "1",
doi = "10.1109/TMC.2018.2841836",
language = "English",
volume = "18",
pages = "546--559",
journal = "IEEE Transactions on Mobile Computing",
issn = "1536-1233",
publisher = "IEEE Computer Society",
number = "3",

}

Dandelion : A Unified Code Offloading System for Wearable Computing. / Golkarifard, Morteza; Yang, Ji; Huang, Zhanpeng; Movaghar, Ali; Hui, Pan.

I: IEEE Transactions on Mobile Computing, Vol. 18, Nr. 3, 01.03.2019, s. 546-559.

Forskningsoutput: TidskriftsbidragArtikelVetenskapligPeer review

TY - JOUR

T1 - Dandelion

T2 - A Unified Code Offloading System for Wearable Computing

AU - Golkarifard, Morteza

AU - Yang, Ji

AU - Huang, Zhanpeng

AU - Movaghar, Ali

AU - Hui, Pan

PY - 2019/3/1

Y1 - 2019/3/1

N2 - Execution speed seriously bothers application developers and users for wearable devices such as Google Glass. Intensive applications like 3D games suffer from significant delays when CPU is busy. Energy is another concern when the devices are in low battery level, but users need them for urgency use. To ease such pains, one approach is to expand the computational power by cloud offloading. This paradigm works well when the available Internet access has enough bandwidth. Another way is to leverage nearby devices for computation-offloading, which is known as device-to-device (D2D) offloading. In this paper, we present Dandelion, a unified code offloading system for wearable computing. Such applications can leverage both the nearby devices and cloud for performance acceleration and energy efficiency. Dandelion is a novel generic code offloading system for wearable computing with a reference implementation on Google Glass. Dandelion includes a programmer-friendly framework based on Java annotation, a lightweight offloading service, and a runtime task scheduler to make offloading decisions. We design some wearable applications and several parallel execution benchmark methods for Dandelion performance evaluation. Extensive experiments on a testbed of Google Glass and Android phones demonstrate that Dandelion generally achieves over 5X execution speedup for local execution and can quickly recover from errors caused by network disruption.

AB - Execution speed seriously bothers application developers and users for wearable devices such as Google Glass. Intensive applications like 3D games suffer from significant delays when CPU is busy. Energy is another concern when the devices are in low battery level, but users need them for urgency use. To ease such pains, one approach is to expand the computational power by cloud offloading. This paradigm works well when the available Internet access has enough bandwidth. Another way is to leverage nearby devices for computation-offloading, which is known as device-to-device (D2D) offloading. In this paper, we present Dandelion, a unified code offloading system for wearable computing. Such applications can leverage both the nearby devices and cloud for performance acceleration and energy efficiency. Dandelion is a novel generic code offloading system for wearable computing with a reference implementation on Google Glass. Dandelion includes a programmer-friendly framework based on Java annotation, a lightweight offloading service, and a runtime task scheduler to make offloading decisions. We design some wearable applications and several parallel execution benchmark methods for Dandelion performance evaluation. Extensive experiments on a testbed of Google Glass and Android phones demonstrate that Dandelion generally achieves over 5X execution speedup for local execution and can quickly recover from errors caused by network disruption.

KW - Computation offloading

KW - wearable computing

KW - Google Glass

KW - D2D

KW - 113 Computer and information sciences

U2 - 10.1109/TMC.2018.2841836

DO - 10.1109/TMC.2018.2841836

M3 - Article

VL - 18

SP - 546

EP - 559

JO - IEEE Transactions on Mobile Computing

JF - IEEE Transactions on Mobile Computing

SN - 1536-1233

IS - 3

ER -