Deep reinforcement learning based computation offloading for not only stack architecture

Xiangyun Zheng; Lu Ge; Jie Zeng; Bei Liu; Xin Su

doi:10.1109/GCWkshps45667.2019.9024617

Deep reinforcement learning based computation offloading for not only stack architecture

Xiangyun Zheng
, Lu Ge
, Jie Zeng^*
, Bei Liu
, Xin Su

^*Corresponding author for this work

University of Electronic Science and Technology of China
Tsinghua University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Citation (Scopus)

Abstract

New technologies emerge with regard to computation offloading, allocating parts of applications to powerful servers to meet demands for the massive traffic of mobile devices. In this paper, we study an offloading framework enabled by Not Only Stack (NO Stack). NO Stack, a promising architecture adopts the virtualization technology, guarantees the implementation of machine learning. A deep reinforcement algorithm triggers energy-efficient strategies with handover control when a mobile device moves among cells. Offloading decisions are formulated by an agent with the feedback from the complex environment. Simulation results demonstrate that our proposed offloading system based on NO Stack reduces the energy consumption and cuts down handover rates for mobile devices, compared with the conventional system when executing a service workflow.

Original language	English
Title of host publication	2019 IEEE Globecom Workshops, GC Wkshps 2019 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728109602
DOIs	https://doi.org/10.1109/GCWkshps45667.2019.9024617
Publication status	Published - Dec 2019
Externally published	Yes
Event	2019 IEEE Globecom Workshops, GC Wkshps 2019 - Waikoloa, United States Duration: 9 Dec 2019 → 13 Dec 2019

Publication series

Name	2019 IEEE Globecom Workshops, GC Wkshps 2019 - Proceedings

Conference

Conference	2019 IEEE Globecom Workshops, GC Wkshps 2019
Country/Territory	United States
City	Waikoloa
Period	9/12/19 → 13/12/19

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

Computation offloading
Deep reinforcement learning
Energy-efficiency
Handover
Not Only Stack

Access to Document

10.1109/GCWkshps45667.2019.9024617

Cite this

Zheng, X., Ge, L., Zeng, J., Liu, B., & Su, X. (2019). Deep reinforcement learning based computation offloading for not only stack architecture. In 2019 IEEE Globecom Workshops, GC Wkshps 2019 - Proceedings Article 9024617 (2019 IEEE Globecom Workshops, GC Wkshps 2019 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/GCWkshps45667.2019.9024617

@inproceedings{d8b61351cf4848f9a6062c1e0b3595e3,

title = "Deep reinforcement learning based computation offloading for not only stack architecture",

abstract = "New technologies emerge with regard to computation offloading, allocating parts of applications to powerful servers to meet demands for the massive traffic of mobile devices. In this paper, we study an offloading framework enabled by Not Only Stack (NO Stack). NO Stack, a promising architecture adopts the virtualization technology, guarantees the implementation of machine learning. A deep reinforcement algorithm triggers energy-efficient strategies with handover control when a mobile device moves among cells. Offloading decisions are formulated by an agent with the feedback from the complex environment. Simulation results demonstrate that our proposed offloading system based on NO Stack reduces the energy consumption and cuts down handover rates for mobile devices, compared with the conventional system when executing a service workflow.",

keywords = "Computation offloading, Deep reinforcement learning, Energy-efficiency, Handover, Not Only Stack",

author = "Xiangyun Zheng and Lu Ge and Jie Zeng and Bei Liu and Xin Su",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 2019 IEEE Globecom Workshops, GC Wkshps 2019 ; Conference date: 09-12-2019 Through 13-12-2019",

year = "2019",

month = dec,

doi = "10.1109/GCWkshps45667.2019.9024617",

language = "English",

series = "2019 IEEE Globecom Workshops, GC Wkshps 2019 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2019 IEEE Globecom Workshops, GC Wkshps 2019 - Proceedings",

address = "United States",

}

Zheng, X, Ge, L, Zeng, J, Liu, B & Su, X 2019, Deep reinforcement learning based computation offloading for not only stack architecture. in 2019 IEEE Globecom Workshops, GC Wkshps 2019 - Proceedings., 9024617, 2019 IEEE Globecom Workshops, GC Wkshps 2019 - Proceedings, Institute of Electrical and Electronics Engineers Inc., 2019 IEEE Globecom Workshops, GC Wkshps 2019, Waikoloa, United States, 9/12/19. https://doi.org/10.1109/GCWkshps45667.2019.9024617

Deep reinforcement learning based computation offloading for not only stack architecture. / Zheng, Xiangyun; Ge, Lu; Zeng, Jie et al.
2019 IEEE Globecom Workshops, GC Wkshps 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. 9024617 (2019 IEEE Globecom Workshops, GC Wkshps 2019 - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Deep reinforcement learning based computation offloading for not only stack architecture

AU - Zheng, Xiangyun

AU - Ge, Lu

AU - Zeng, Jie

AU - Liu, Bei

AU - Su, Xin

PY - 2019/12

Y1 - 2019/12

N2 - New technologies emerge with regard to computation offloading, allocating parts of applications to powerful servers to meet demands for the massive traffic of mobile devices. In this paper, we study an offloading framework enabled by Not Only Stack (NO Stack). NO Stack, a promising architecture adopts the virtualization technology, guarantees the implementation of machine learning. A deep reinforcement algorithm triggers energy-efficient strategies with handover control when a mobile device moves among cells. Offloading decisions are formulated by an agent with the feedback from the complex environment. Simulation results demonstrate that our proposed offloading system based on NO Stack reduces the energy consumption and cuts down handover rates for mobile devices, compared with the conventional system when executing a service workflow.

AB - New technologies emerge with regard to computation offloading, allocating parts of applications to powerful servers to meet demands for the massive traffic of mobile devices. In this paper, we study an offloading framework enabled by Not Only Stack (NO Stack). NO Stack, a promising architecture adopts the virtualization technology, guarantees the implementation of machine learning. A deep reinforcement algorithm triggers energy-efficient strategies with handover control when a mobile device moves among cells. Offloading decisions are formulated by an agent with the feedback from the complex environment. Simulation results demonstrate that our proposed offloading system based on NO Stack reduces the energy consumption and cuts down handover rates for mobile devices, compared with the conventional system when executing a service workflow.

KW - Computation offloading

KW - Deep reinforcement learning

KW - Energy-efficiency

KW - Handover

KW - Not Only Stack

UR - https://www.scopus.com/pages/publications/85082307209

U2 - 10.1109/GCWkshps45667.2019.9024617

DO - 10.1109/GCWkshps45667.2019.9024617

M3 - Conference contribution

AN - SCOPUS:85082307209

T3 - 2019 IEEE Globecom Workshops, GC Wkshps 2019 - Proceedings

BT - 2019 IEEE Globecom Workshops, GC Wkshps 2019 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2019 IEEE Globecom Workshops, GC Wkshps 2019

Y2 - 9 December 2019 through 13 December 2019

ER -

Deep reinforcement learning based computation offloading for not only stack architecture

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this