Poster Abstract: Deep Reinforcement Learning-based Resource Allocation in Vehicular Fog Computing

Seung Seob Lee; Sukyoung Lee

doi:10.1109/INFCOMW.2019.8845095

Poster Abstract: Deep Reinforcement Learning-based Resource Allocation in Vehicular Fog Computing

Seung Seob Lee, Sukyoung Lee

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

2 Citations (Scopus)

Abstract

In vehicular fog computing (VFC), it is challenging to design efficient resource allocation (RA) to satisfy the latency requirements of emerging vehicular applications due to the limited network resources and dynamically changing resource availability. In this paper, we formulate the problem of VFC resource allocation (VFC-RA) and utilize reinforcement learning (RL) to predict the availability of VFC resources and service demands. We also propose a training method to decompose the high dimensional continuous action space into a three-dimensional grid so that the efficiency of training deep neural networks (DNNs) can be improved.

Original language	English
Title of host publication	INFOCOM 2019 - IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1029-1030
Number of pages	2
ISBN (Electronic)	9781728118789
DOIs	https://doi.org/10.1109/INFCOMW.2019.8845095
Publication status	Published - 2019 Apr
Event	2019 INFOCOM IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2019 - Paris, France Duration: 2019 Apr 29 → 2019 May 2

Publication series

Name	INFOCOM 2019 - IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2019

Conference

Conference	2019 INFOCOM IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2019
Country/Territory	France
City	Paris
Period	19/4/29 → 19/5/2

All Science Journal Classification (ASJC) codes

Hardware and Architecture
Signal Processing
Information Systems and Management
Safety, Risk, Reliability and Quality
Computer Networks and Communications

Access to Document

10.1109/INFCOMW.2019.8845095

Cite this

Lee, S. S., & Lee, S. (2019). Poster Abstract: Deep Reinforcement Learning-based Resource Allocation in Vehicular Fog Computing. In INFOCOM 2019 - IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2019 (pp. 1029-1030). Article 8845095 (INFOCOM 2019 - IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/INFCOMW.2019.8845095

Lee, Seung Seob ; Lee, Sukyoung. / Poster Abstract : Deep Reinforcement Learning-based Resource Allocation in Vehicular Fog Computing. INFOCOM 2019 - IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2019. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 1029-1030 (INFOCOM 2019 - IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2019).

@inproceedings{2c8ef844dba44936b77adb566ac05945,

title = "Poster Abstract: Deep Reinforcement Learning-based Resource Allocation in Vehicular Fog Computing",

abstract = "In vehicular fog computing (VFC), it is challenging to design efficient resource allocation (RA) to satisfy the latency requirements of emerging vehicular applications due to the limited network resources and dynamically changing resource availability. In this paper, we formulate the problem of VFC resource allocation (VFC-RA) and utilize reinforcement learning (RL) to predict the availability of VFC resources and service demands. We also propose a training method to decompose the high dimensional continuous action space into a three-dimensional grid so that the efficiency of training deep neural networks (DNNs) can be improved.",

author = "Lee, {Seung Seob} and Sukyoung Lee",

year = "2019",

month = apr,

doi = "10.1109/INFCOMW.2019.8845095",

language = "English",

series = "INFOCOM 2019 - IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2019",

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

pages = "1029--1030",

booktitle = "INFOCOM 2019 - IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2019",

address = "United States",

note = "2019 INFOCOM IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2019 ; Conference date: 29-04-2019 Through 02-05-2019",

}

Lee, SS & Lee, S 2019, Poster Abstract: Deep Reinforcement Learning-based Resource Allocation in Vehicular Fog Computing. in INFOCOM 2019 - IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2019., 8845095, INFOCOM 2019 - IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2019, Institute of Electrical and Electronics Engineers Inc., pp. 1029-1030, 2019 INFOCOM IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2019, Paris, France, 19/4/29. https://doi.org/10.1109/INFCOMW.2019.8845095

Poster Abstract: Deep Reinforcement Learning-based Resource Allocation in Vehicular Fog Computing. / Lee, Seung Seob; Lee, Sukyoung.
INFOCOM 2019 - IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 1029-1030 8845095 (INFOCOM 2019 - IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2019).

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

TY - GEN

T1 - Poster Abstract

T2 - 2019 INFOCOM IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2019

AU - Lee, Seung Seob

AU - Lee, Sukyoung

PY - 2019/4

Y1 - 2019/4

N2 - In vehicular fog computing (VFC), it is challenging to design efficient resource allocation (RA) to satisfy the latency requirements of emerging vehicular applications due to the limited network resources and dynamically changing resource availability. In this paper, we formulate the problem of VFC resource allocation (VFC-RA) and utilize reinforcement learning (RL) to predict the availability of VFC resources and service demands. We also propose a training method to decompose the high dimensional continuous action space into a three-dimensional grid so that the efficiency of training deep neural networks (DNNs) can be improved.

AB - In vehicular fog computing (VFC), it is challenging to design efficient resource allocation (RA) to satisfy the latency requirements of emerging vehicular applications due to the limited network resources and dynamically changing resource availability. In this paper, we formulate the problem of VFC resource allocation (VFC-RA) and utilize reinforcement learning (RL) to predict the availability of VFC resources and service demands. We also propose a training method to decompose the high dimensional continuous action space into a three-dimensional grid so that the efficiency of training deep neural networks (DNNs) can be improved.

UR - http://www.scopus.com/inward/record.url?scp=85073187974&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073187974&partnerID=8YFLogxK

U2 - 10.1109/INFCOMW.2019.8845095

DO - 10.1109/INFCOMW.2019.8845095

M3 - Conference contribution

T3 - INFOCOM 2019 - IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2019

SP - 1029

EP - 1030

BT - INFOCOM 2019 - IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2019

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 29 April 2019 through 2 May 2019

ER -

Lee SS, Lee S. Poster Abstract: Deep Reinforcement Learning-based Resource Allocation in Vehicular Fog Computing. In INFOCOM 2019 - IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 1029-1030. 8845095. (INFOCOM 2019 - IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2019). doi: 10.1109/INFCOMW.2019.8845095

Poster Abstract: Deep Reinforcement Learning-based Resource Allocation in Vehicular Fog Computing

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this