Deep reinforcement learning based task offloading in SDN-enabled industrial internet of things

Jiadai Wang; Yurui Cao; Jiajia Liu; Yanning Zhang

doi:10.1007/978-3-030-22971-9_37

Deep reinforcement learning based task offloading in SDN-enabled industrial internet of things

Jiadai Wang, Yurui Cao, Jiajia Liu, Yanning Zhang

Xidian University

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

3 Scopus citations

Abstract

Recent advances in communication and sensor network technologies make Industrial Internet of Things (IIoT) a major driving force for future industry. Various devices in wide industry fields generate diverse computation tasks with their distinct service requirements. Note that the distribution of such tasks has essential intrinsic patterns and varies according to factors like region, season and time. Different from previous efforts to develop algorithms in specific scenarios for reducing task execution latency without considering the task generation patterns of IIoT, we propose a DRL-based Task Offloading algorithm (DRLTO) to learn such generation patterns and maximize the task completion rate. A SDN-enabled multi-layer heterogeneous computing framework is also introduced to efficiently assign tasks according to the obtained knowledges towards their features. Extensive experiments validate that our algorithm can not only significantly improve the average task completion rate, but also achieve near-optimal results in lots of IIoT scenarios.

Original language	English
Title of host publication	Artificial Intelligence for Communications and Networks - 1st EAI International Conference, AICON 2019, Proceedings
Editors	Shuai Han, Liang Ye, Weixiao Meng
Publisher	Springer Verlag
Pages	425-437
Number of pages	13
ISBN (Print)	9783030229702
DOIs	https://doi.org/10.1007/978-3-030-22971-9_37
State	Published - 2019
Event	1st EAI International Conference on Artificial Intelligence for Communications and Networks, AICON 2019 - Harbin, China Duration: 25 May 2019 → 26 May 2019

Publication series

Name	Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST
Volume	287
ISSN (Print)	1867-8211

Conference

Conference	1st EAI International Conference on Artificial Intelligence for Communications and Networks, AICON 2019
Country/Territory	China
City	Harbin
Period	25/05/19 → 26/05/19

Keywords

Deep Reinforcement Learning
IIoT
Task offloading

Access to Document

10.1007/978-3-030-22971-9_37

Cite this

Wang, J., Cao, Y., Liu, J., & Zhang, Y. (2019). Deep reinforcement learning based task offloading in SDN-enabled industrial internet of things. In S. Han, L. Ye, & W. Meng (Eds.), Artificial Intelligence for Communications and Networks - 1st EAI International Conference, AICON 2019, Proceedings (pp. 425-437). (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST; Vol. 287). Springer Verlag. https://doi.org/10.1007/978-3-030-22971-9_37

Wang, Jiadai ; Cao, Yurui ; Liu, Jiajia et al. / Deep reinforcement learning based task offloading in SDN-enabled industrial internet of things. Artificial Intelligence for Communications and Networks - 1st EAI International Conference, AICON 2019, Proceedings. editor / Shuai Han ; Liang Ye ; Weixiao Meng. Springer Verlag, 2019. pp. 425-437 (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST).

@inproceedings{fd728bf15308460f88d45e5b8eefe63f,

title = "Deep reinforcement learning based task offloading in SDN-enabled industrial internet of things",

abstract = "Recent advances in communication and sensor network technologies make Industrial Internet of Things (IIoT) a major driving force for future industry. Various devices in wide industry fields generate diverse computation tasks with their distinct service requirements. Note that the distribution of such tasks has essential intrinsic patterns and varies according to factors like region, season and time. Different from previous efforts to develop algorithms in specific scenarios for reducing task execution latency without considering the task generation patterns of IIoT, we propose a DRL-based Task Offloading algorithm (DRLTO) to learn such generation patterns and maximize the task completion rate. A SDN-enabled multi-layer heterogeneous computing framework is also introduced to efficiently assign tasks according to the obtained knowledges towards their features. Extensive experiments validate that our algorithm can not only significantly improve the average task completion rate, but also achieve near-optimal results in lots of IIoT scenarios.",

keywords = "Deep Reinforcement Learning, IIoT, Task offloading",

author = "Jiadai Wang and Yurui Cao and Jiajia Liu and Yanning Zhang",

note = "Publisher Copyright: {\textcopyright} ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2019 Published by Springer Nature Switzerland AG 2019. All Rights Reserved.; 1st EAI International Conference on Artificial Intelligence for Communications and Networks, AICON 2019 ; Conference date: 25-05-2019 Through 26-05-2019",

year = "2019",

doi = "10.1007/978-3-030-22971-9_37",

language = "英语",

isbn = "9783030229702",

series = "Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST",

publisher = "Springer Verlag",

pages = "425--437",

editor = "Shuai Han and Liang Ye and Weixiao Meng",

booktitle = "Artificial Intelligence for Communications and Networks - 1st EAI International Conference, AICON 2019, Proceedings",

}

Wang, J, Cao, Y, Liu, J & Zhang, Y 2019, Deep reinforcement learning based task offloading in SDN-enabled industrial internet of things. in S Han, L Ye & W Meng (eds), Artificial Intelligence for Communications and Networks - 1st EAI International Conference, AICON 2019, Proceedings. Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST, vol. 287, Springer Verlag, pp. 425-437, 1st EAI International Conference on Artificial Intelligence for Communications and Networks, AICON 2019, Harbin, China, 25/05/19. https://doi.org/10.1007/978-3-030-22971-9_37

Deep reinforcement learning based task offloading in SDN-enabled industrial internet of things. / Wang, Jiadai; Cao, Yurui; Liu, Jiajia et al.
Artificial Intelligence for Communications and Networks - 1st EAI International Conference, AICON 2019, Proceedings. ed. / Shuai Han; Liang Ye; Weixiao Meng. Springer Verlag, 2019. p. 425-437 (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST; Vol. 287).

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

TY - GEN

T1 - Deep reinforcement learning based task offloading in SDN-enabled industrial internet of things

AU - Wang, Jiadai

AU - Cao, Yurui

AU - Liu, Jiajia

AU - Zhang, Yanning

PY - 2019

Y1 - 2019

N2 - Recent advances in communication and sensor network technologies make Industrial Internet of Things (IIoT) a major driving force for future industry. Various devices in wide industry fields generate diverse computation tasks with their distinct service requirements. Note that the distribution of such tasks has essential intrinsic patterns and varies according to factors like region, season and time. Different from previous efforts to develop algorithms in specific scenarios for reducing task execution latency without considering the task generation patterns of IIoT, we propose a DRL-based Task Offloading algorithm (DRLTO) to learn such generation patterns and maximize the task completion rate. A SDN-enabled multi-layer heterogeneous computing framework is also introduced to efficiently assign tasks according to the obtained knowledges towards their features. Extensive experiments validate that our algorithm can not only significantly improve the average task completion rate, but also achieve near-optimal results in lots of IIoT scenarios.

AB - Recent advances in communication and sensor network technologies make Industrial Internet of Things (IIoT) a major driving force for future industry. Various devices in wide industry fields generate diverse computation tasks with their distinct service requirements. Note that the distribution of such tasks has essential intrinsic patterns and varies according to factors like region, season and time. Different from previous efforts to develop algorithms in specific scenarios for reducing task execution latency without considering the task generation patterns of IIoT, we propose a DRL-based Task Offloading algorithm (DRLTO) to learn such generation patterns and maximize the task completion rate. A SDN-enabled multi-layer heterogeneous computing framework is also introduced to efficiently assign tasks according to the obtained knowledges towards their features. Extensive experiments validate that our algorithm can not only significantly improve the average task completion rate, but also achieve near-optimal results in lots of IIoT scenarios.

KW - Deep Reinforcement Learning

KW - IIoT

KW - Task offloading

UR - http://www.scopus.com/inward/record.url?scp=85069209755&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-22971-9_37

DO - 10.1007/978-3-030-22971-9_37

M3 - 会议稿件

AN - SCOPUS:85069209755

SN - 9783030229702

T3 - Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST

SP - 425

EP - 437

BT - Artificial Intelligence for Communications and Networks - 1st EAI International Conference, AICON 2019, Proceedings

A2 - Han, Shuai

A2 - Ye, Liang

A2 - Meng, Weixiao

PB - Springer Verlag

T2 - 1st EAI International Conference on Artificial Intelligence for Communications and Networks, AICON 2019

Y2 - 25 May 2019 through 26 May 2019

ER -

Wang J, Cao Y, Liu J , Zhang Y. Deep reinforcement learning based task offloading in SDN-enabled industrial internet of things. In Han S, Ye L, Meng W, editors, Artificial Intelligence for Communications and Networks - 1st EAI International Conference, AICON 2019, Proceedings. Springer Verlag. 2019. p. 425-437. (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST). doi: 10.1007/978-3-030-22971-9_37

Deep reinforcement learning based task offloading in SDN-enabled industrial internet of things

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this