GAN-based deep distributional reinforcement learning for resource management in network slicing

Yuxiu Hua, Rongpeng Li, Zhifeng Zhao, Honggang Zhang, Xianfu Chen

    Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

    5 Citations (Scopus)

    Abstract

    Network slicing is a key technology in 5G communications system, which aims to dynamically and efficiently allocate resources for diversified services with distinct requirements over a common underlying physical infrastructure. Therein, demand-aware allocation is of significant importance to network slicing. In this paper, we consider a scenario that contains several slices in one base station on sharing the same bandwidth. Deep reinforcement learning (DRL) is leveraged to solve this problem by regarding the varying demands and the allocated bandwidth as the environment emph{state} and emph{action}, respectively. In order to obtain better quality of experience (QoE) satisfaction ratio and spectrum efficiency (SE), we propose generative adversarial network (GAN) based deep distributional Q network (GAN- DDQN) to learn the distribution of state-action values. Furthermore, we estimate the distributions by approximating a full quantile function, which can make the training error more controllable. In order to protect the stability of GAN-DDQN's training process from the widely-spanning utility values, we also put forward a reward-clipping mechanism. Finally, we verify the performance of the proposed GAN-DDQN algorithm through extensive simulations.

    Original languageEnglish
    Title of host publication2019 IEEE Global Communications Conference, GLOBECOM 2019 - Proceedings
    PublisherIEEE Institute of Electrical and Electronic Engineers
    ISBN (Electronic)978-1-72810-962-6
    DOIs
    Publication statusPublished - Dec 2019
    MoE publication typeA4 Article in a conference publication
    Event2019 IEEE Global Communications Conference, GLOBECOM 2019 - Waikoloa, United States
    Duration: 9 Dec 201913 Dec 2019

    Publication series

    Series2019 IEEE Global Communications Conference, GLOBECOM 2019 - Proceedings

    Conference

    Conference2019 IEEE Global Communications Conference, GLOBECOM 2019
    Country/TerritoryUnited States
    CityWaikoloa
    Period9/12/1913/12/19

    Keywords

    • 5G
    • Deep reinforcement learning
    • Distributional reinforcement learning
    • Generative adversarial network
    • Network slicing

    Fingerprint

    Dive into the research topics of 'GAN-based deep distributional reinforcement learning for resource management in network slicing'. Together they form a unique fingerprint.

    Cite this