DeepSlicing: Deep Reinforcement Learning Assisted Resource Allocation for Network Slicing

Qiang Liu; Tao Han; Ning Zhang; Ye Wang

doi:10.1109/GLOBECOM42002.2020.9322106

DeepSlicing: Deep Reinforcement Learning Assisted Resource Allocation for Network Slicing

Qiang Liu, Tao Han, Ning Zhang, Ye Wang

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

19 Scopus citations

Abstract

Network slicing enables multiple virtual networks run on the same physical infrastructure to support various use cases in 5G and beyond. These use cases, however, have very diverse network resource demands, e.g., communication and computation, and various performance metrics such as latency and throughput. To effectively allocate network resources to slices, we propose DeepSlicing that integrates the alternating direction method of multipliers (ADMM) and deep reinforcement learning (DRL). DeepSlicing decomposes the network slicing problem into a master problem and several slave problems. The master problem is solved based on convex optimization and the slave problem is handled by DRL method which learns the optimal resource allocation policy. The performance of the proposed algorithm is validated through network simulations.

Original language	English (US)
Title of host publication	2020 IEEE Global Communications Conference, GLOBECOM 2020 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728182988
DOIs	https://doi.org/10.1109/GLOBECOM42002.2020.9322106
State	Published - Dec 2020
Externally published	Yes
Event	2020 IEEE Global Communications Conference, GLOBECOM 2020 - Virtual, Taipei, Taiwan, Province of China Duration: Dec 7 2020 → Dec 11 2020

Publication series

Name	2020 IEEE Global Communications Conference, GLOBECOM 2020 - Proceedings

Conference

Conference	2020 IEEE Global Communications Conference, GLOBECOM 2020
Country/Territory	Taiwan, Province of China
City	Virtual, Taipei
Period	12/7/20 → 12/11/20

All Science Journal Classification (ASJC) codes

Media Technology
Modeling and Simulation
Instrumentation
Artificial Intelligence
Computer Networks and Communications
Hardware and Architecture
Software
Safety, Risk, Reliability and Quality

Access to Document

10.1109/GLOBECOM42002.2020.9322106

Cite this

Liu, Q., Han, T., Zhang, N., & Wang, Y. (2020). DeepSlicing: Deep Reinforcement Learning Assisted Resource Allocation for Network Slicing. In 2020 IEEE Global Communications Conference, GLOBECOM 2020 - Proceedings Article 9322106 (2020 IEEE Global Communications Conference, GLOBECOM 2020 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/GLOBECOM42002.2020.9322106

@inproceedings{ea0beb9d63a84fbebb44aa28581dac9c,

title = "DeepSlicing: Deep Reinforcement Learning Assisted Resource Allocation for Network Slicing",

abstract = "Network slicing enables multiple virtual networks run on the same physical infrastructure to support various use cases in 5G and beyond. These use cases, however, have very diverse network resource demands, e.g., communication and computation, and various performance metrics such as latency and throughput. To effectively allocate network resources to slices, we propose DeepSlicing that integrates the alternating direction method of multipliers (ADMM) and deep reinforcement learning (DRL). DeepSlicing decomposes the network slicing problem into a master problem and several slave problems. The master problem is solved based on convex optimization and the slave problem is handled by DRL method which learns the optimal resource allocation policy. The performance of the proposed algorithm is validated through network simulations.",

author = "Qiang Liu and Tao Han and Ning Zhang and Ye Wang",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 2020 IEEE Global Communications Conference, GLOBECOM 2020 ; Conference date: 07-12-2020 Through 11-12-2020",

year = "2020",

month = dec,

doi = "10.1109/GLOBECOM42002.2020.9322106",

language = "English (US)",

series = "2020 IEEE Global Communications Conference, GLOBECOM 2020 - Proceedings",

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

booktitle = "2020 IEEE Global Communications Conference, GLOBECOM 2020 - Proceedings",

address = "United States",

}

Liu, Q, Han, T, Zhang, N & Wang, Y 2020, DeepSlicing: Deep Reinforcement Learning Assisted Resource Allocation for Network Slicing. in 2020 IEEE Global Communications Conference, GLOBECOM 2020 - Proceedings., 9322106, 2020 IEEE Global Communications Conference, GLOBECOM 2020 - Proceedings, Institute of Electrical and Electronics Engineers Inc., 2020 IEEE Global Communications Conference, GLOBECOM 2020, Virtual, Taipei, Taiwan, Province of China, 12/7/20. https://doi.org/10.1109/GLOBECOM42002.2020.9322106

DeepSlicing: Deep Reinforcement Learning Assisted Resource Allocation for Network Slicing. / Liu, Qiang; Han, Tao; Zhang, Ning et al.
2020 IEEE Global Communications Conference, GLOBECOM 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2020. 9322106 (2020 IEEE Global Communications Conference, GLOBECOM 2020 - Proceedings).

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

TY - GEN

T1 - DeepSlicing

T2 - 2020 IEEE Global Communications Conference, GLOBECOM 2020

AU - Liu, Qiang

AU - Han, Tao

AU - Zhang, Ning

AU - Wang, Ye

PY - 2020/12

Y1 - 2020/12

N2 - Network slicing enables multiple virtual networks run on the same physical infrastructure to support various use cases in 5G and beyond. These use cases, however, have very diverse network resource demands, e.g., communication and computation, and various performance metrics such as latency and throughput. To effectively allocate network resources to slices, we propose DeepSlicing that integrates the alternating direction method of multipliers (ADMM) and deep reinforcement learning (DRL). DeepSlicing decomposes the network slicing problem into a master problem and several slave problems. The master problem is solved based on convex optimization and the slave problem is handled by DRL method which learns the optimal resource allocation policy. The performance of the proposed algorithm is validated through network simulations.

AB - Network slicing enables multiple virtual networks run on the same physical infrastructure to support various use cases in 5G and beyond. These use cases, however, have very diverse network resource demands, e.g., communication and computation, and various performance metrics such as latency and throughput. To effectively allocate network resources to slices, we propose DeepSlicing that integrates the alternating direction method of multipliers (ADMM) and deep reinforcement learning (DRL). DeepSlicing decomposes the network slicing problem into a master problem and several slave problems. The master problem is solved based on convex optimization and the slave problem is handled by DRL method which learns the optimal resource allocation policy. The performance of the proposed algorithm is validated through network simulations.

UR - http://www.scopus.com/inward/record.url?scp=85100420798&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85100420798&partnerID=8YFLogxK

U2 - 10.1109/GLOBECOM42002.2020.9322106

DO - 10.1109/GLOBECOM42002.2020.9322106

M3 - Conference contribution

AN - SCOPUS:85100420798

T3 - 2020 IEEE Global Communications Conference, GLOBECOM 2020 - Proceedings

BT - 2020 IEEE Global Communications Conference, GLOBECOM 2020 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 7 December 2020 through 11 December 2020

ER -

Liu Q, Han T, Zhang N, Wang Y. DeepSlicing: Deep Reinforcement Learning Assisted Resource Allocation for Network Slicing. In 2020 IEEE Global Communications Conference, GLOBECOM 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2020. 9322106. (2020 IEEE Global Communications Conference, GLOBECOM 2020 - Proceedings). doi: 10.1109/GLOBECOM42002.2020.9322106

DeepSlicing: Deep Reinforcement Learning Assisted Resource Allocation for Network Slicing

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this