Routing for crowd management in smart cities: A deep reinforcement learning perspective

Lei Zhao; Jiadai Wang; Jiajia Liu; Nei Kato

doi:10.1109/MCOM.2019.1800603

Routing for crowd management in smart cities: A deep reinforcement learning perspective

Lei Zhao, Jiadai Wang, Jiajia Liu, Nei Kato

Research output: Contribution to journal › Review article › peer-review

112 Scopus citations

Abstract

The concept of smart city has been flourishing based on the prosperous development of various advanced technologies: Mobile edge computing (MEC), ultra-dense networking, and software defined networking. However, it becomes increasingly complicated to design routing strategies to meet the stringent and ever changing network requirements due to the dynamic distribution of the crowd in different sectors of smart cities. To alleviate the network congestion and balance the network load for supporting smart city services with dramatic disparities, we design a deep-reinforcement-learning-based smart routing algorithm to make the distributed computing and communication infrastructure thoroughly viable while simultaneously satisfying the latency constraints of service requests from the crowd. Besides the proposed algorithm, extensive numerical results are also presented to validate its efficacy.

Original language	English
Article number	8703471
Pages (from-to)	88-93
Number of pages	6
Journal	IEEE Communications Magazine
Volume	57
Issue number	4
DOIs	https://doi.org/10.1109/MCOM.2019.1800603
State	Published - Apr 2019
Externally published	Yes

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/MCOM.2019.1800603

Cite this

@article{18823e9158b54530a55a401e6520aca2,

title = "Routing for crowd management in smart cities: A deep reinforcement learning perspective",

abstract = "The concept of smart city has been flourishing based on the prosperous development of various advanced technologies: Mobile edge computing (MEC), ultra-dense networking, and software defined networking. However, it becomes increasingly complicated to design routing strategies to meet the stringent and ever changing network requirements due to the dynamic distribution of the crowd in different sectors of smart cities. To alleviate the network congestion and balance the network load for supporting smart city services with dramatic disparities, we design a deep-reinforcement-learning-based smart routing algorithm to make the distributed computing and communication infrastructure thoroughly viable while simultaneously satisfying the latency constraints of service requests from the crowd. Besides the proposed algorithm, extensive numerical results are also presented to validate its efficacy.",

author = "Lei Zhao and Jiadai Wang and Jiajia Liu and Nei Kato",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.",

year = "2019",

month = apr,

doi = "10.1109/MCOM.2019.1800603",

language = "英语",

volume = "57",

pages = "88--93",

journal = "IEEE Communications Magazine",

issn = "0163-6804",

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

number = "4",

}

TY - JOUR

T1 - Routing for crowd management in smart cities

T2 - A deep reinforcement learning perspective

AU - Zhao, Lei

AU - Wang, Jiadai

AU - Liu, Jiajia

AU - Kato, Nei

PY - 2019/4

Y1 - 2019/4

N2 - The concept of smart city has been flourishing based on the prosperous development of various advanced technologies: Mobile edge computing (MEC), ultra-dense networking, and software defined networking. However, it becomes increasingly complicated to design routing strategies to meet the stringent and ever changing network requirements due to the dynamic distribution of the crowd in different sectors of smart cities. To alleviate the network congestion and balance the network load for supporting smart city services with dramatic disparities, we design a deep-reinforcement-learning-based smart routing algorithm to make the distributed computing and communication infrastructure thoroughly viable while simultaneously satisfying the latency constraints of service requests from the crowd. Besides the proposed algorithm, extensive numerical results are also presented to validate its efficacy.

AB - The concept of smart city has been flourishing based on the prosperous development of various advanced technologies: Mobile edge computing (MEC), ultra-dense networking, and software defined networking. However, it becomes increasingly complicated to design routing strategies to meet the stringent and ever changing network requirements due to the dynamic distribution of the crowd in different sectors of smart cities. To alleviate the network congestion and balance the network load for supporting smart city services with dramatic disparities, we design a deep-reinforcement-learning-based smart routing algorithm to make the distributed computing and communication infrastructure thoroughly viable while simultaneously satisfying the latency constraints of service requests from the crowd. Besides the proposed algorithm, extensive numerical results are also presented to validate its efficacy.

UR - http://www.scopus.com/inward/record.url?scp=85065435968&partnerID=8YFLogxK

U2 - 10.1109/MCOM.2019.1800603

DO - 10.1109/MCOM.2019.1800603

M3 - 文献综述

AN - SCOPUS:85065435968

SN - 0163-6804

VL - 57

SP - 88

EP - 93

JO - IEEE Communications Magazine

JF - IEEE Communications Magazine

IS - 4

M1 - 8703471

ER -

Routing for crowd management in smart cities: A deep reinforcement learning perspective

Abstract

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this