Constraint-Aware Deep Reinforcement Learning for End-to-End Resource Orchestration in Mobile Networks

Qiang Liu, Nakjung Choi, Tao Han

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Scopus citations

Abstract

Network slicing is a promising technology that allows mobile network operators to efficiently serve various emerging use cases in 5G. It is challenging to optimize the utilization of network infrastructures while guaranteeing the performance of network slices according to service level agreements (SLAs). To solve this problem, we propose SafeSlicing that introduces a new constraint-aware deep reinforcement learning (CaDRL) algorithm to learn the optimal resource orchestration policy within two steps, i.e., offline training in a simulated environment and online learning with the real network system. On optimizing the resource orchestration, we incorporate the constraints on the statistical performance of slices in the reward function using Lagrangian multipliers, and solve the Lagrangian relaxed problem via a policy network. To satisfy the constraints on the system capacity, we design a constraint network to map the latent actions generated from the policy network to the orchestration actions such that the total resources allocated to network slices do not exceed the system capacity. We prototype SafeSlicing on an end-to-end testbed developed by using OpenAirInterface LTE, OpenDayLight-based SDN, and CUDA GPU computing platform. The experimental results show that SafeSlicing reduces more than 20% resource usage while meeting SLAs of network slices as compared with other solutions.

Original languageEnglish (US)
Title of host publication2021 IEEE 29th International Conference on Network Protocols, ICNP 2021
PublisherIEEE Computer Society
ISBN (Electronic)9781665441315
DOIs
StatePublished - 2021
Event29th IEEE International Conference on Network Protocols, ICNP 2021 - Virtual, Online, United States
Duration: Nov 1 2021Nov 5 2021

Publication series

NameProceedings - International Conference on Network Protocols, ICNP
Volume2021-November
ISSN (Print)1092-1648

Conference

Conference29th IEEE International Conference on Network Protocols, ICNP 2021
Country/TerritoryUnited States
CityVirtual, Online
Period11/1/2111/5/21

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Software

Keywords

  • Constraint-Awareness
  • Deep Reinforcement Learning
  • End-to-End Slicing
  • Resource Orchestration

Fingerprint

Dive into the research topics of 'Constraint-Aware Deep Reinforcement Learning for End-to-End Resource Orchestration in Mobile Networks'. Together they form a unique fingerprint.

Cite this