Multiagent Actor-Critic Network-Based Incentive Mechanism for Mobile Crowdsensing in Industrial Systems

Bo Gu; Xinxin Yang; Ziqi Lin; Weiwei Hu; Mamoun Alazab; Rupak Kharel

doi:10.1109/TII.2020.3024611

Multiagent Actor-Critic Network-Based Incentive Mechanism for Mobile Crowdsensing in Industrial Systems

Bo Gu, Xinxin Yang, Ziqi Lin, Weiwei Hu, Mamoun Alazab, Rupak Kharel

Research output: Contribution to journal › Article › peer-review

44 Citations (Scopus)

Abstract

Mobile crowdsensing (MCS) is an appealing sensing paradigm that leverages the sensing capabilities of smart devices and the inherent mobility of device owners to accomplish sensing tasks with the aim of constructing powerful industrial systems. Incentivizing mobile users (MUs) to participate in sensing activities and contribute high-quality data is of paramount importance to the success of MCS services. In this article, we formulate the competitive interactions between a sensing platform (SP) and MUs as a multistage Stackelberg game with the SP as the leader player and the MUs as the followers. Given the unit prices announced by MUs, the SP calculates the quantity of sensing time to purchase from each MU by solving a convex optimization problem. Then, each follower observes the trading records and iteratively adjusts their pricing strategy in a trial-and-error manner based on a multiagent deep reinforcement learning algorithm. Simulation results demonstrate the efficiency of the proposed method.

Original language	English
Article number	9201550
Pages (from-to)	6182-6191
Number of pages	10
Journal	IEEE Transactions on Industrial Informatics
Volume	17
Issue number	9
DOIs	https://doi.org/10.1109/TII.2020.3024611
Publication status	Published - Sept 2021

Bibliographical note

Funding Information:
Manuscript received April 29, 2020; revised July 4, 2020, August 15, 2020, and August 28, 2020; accepted September 5, 2020. Date of publication September 21, 2020; date of current version June 16, 2021. This work was supported by the National Key Research and Development Program of China under Grant 2019YFB1704702. Paper no. TII-20-2140. (Corresponding author: Bo Gu.) Bo Gu, Xinxin Yang, Ziqi Lin, and Weiwei Hu are with the School of Intelligent Systems Engineering, Sun Yat-sen University, Guangzhou 510275, China (e-mail: [email protected]; [email protected]; [email protected]; Huww1998@ 163.com).

Publisher Copyright:
© 2005-2012 IEEE.

Copyright:
Copyright 2021 Elsevier B.V., All rights reserved.

Access to Document

10.1109/TII.2020.3024611

Cite this

@article{e02b037cfa274bb7a62f0ce35dfffd9e,

title = "Multiagent Actor-Critic Network-Based Incentive Mechanism for Mobile Crowdsensing in Industrial Systems",

abstract = "Mobile crowdsensing (MCS) is an appealing sensing paradigm that leverages the sensing capabilities of smart devices and the inherent mobility of device owners to accomplish sensing tasks with the aim of constructing powerful industrial systems. Incentivizing mobile users (MUs) to participate in sensing activities and contribute high-quality data is of paramount importance to the success of MCS services. In this article, we formulate the competitive interactions between a sensing platform (SP) and MUs as a multistage Stackelberg game with the SP as the leader player and the MUs as the followers. Given the unit prices announced by MUs, the SP calculates the quantity of sensing time to purchase from each MU by solving a convex optimization problem. Then, each follower observes the trading records and iteratively adjusts their pricing strategy in a trial-and-error manner based on a multiagent deep reinforcement learning algorithm. Simulation results demonstrate the efficiency of the proposed method. ",

keywords = "Cognitive sensor networks, deep reinforcement learning (DRL), incentive mechanism, mobile crowd sensing (MCS), multiagent deep deterministic policy gradient (MADDPG), Stackelberg game",

author = "Bo Gu and Xinxin Yang and Ziqi Lin and Weiwei Hu and Mamoun Alazab and Rupak Kharel",

note = "Funding Information: Manuscript received April 29, 2020; revised July 4, 2020, August 15, 2020, and August 28, 2020; accepted September 5, 2020. Date of publication September 21, 2020; date of current version June 16, 2021. This work was supported by the National Key Research and Development Program of China under Grant 2019YFB1704702. Paper no. TII-20-2140. (Corresponding author: Bo Gu.) Bo Gu, Xinxin Yang, Ziqi Lin, and Weiwei Hu are with the School of Intelligent Systems Engineering, Sun Yat-sen University, Guangzhou 510275, China (e-mail: [email protected]; [email protected]; [email protected]; Huww1998@ 163.com). Publisher Copyright: {\textcopyright} 2005-2012 IEEE. Copyright: Copyright 2021 Elsevier B.V., All rights reserved.",

year = "2021",

month = sep,

doi = "10.1109/TII.2020.3024611",

language = "English",

volume = "17",

pages = "6182--6191",

journal = "IEEE Transactions on Industrial Informatics",

issn = "1551-3203",

publisher = "IEEE Computer Society",

number = "9",

}

TY - JOUR

T1 - Multiagent Actor-Critic Network-Based Incentive Mechanism for Mobile Crowdsensing in Industrial Systems

AU - Gu, Bo

AU - Yang, Xinxin

AU - Lin, Ziqi

AU - Hu, Weiwei

AU - Alazab, Mamoun

AU - Kharel, Rupak

N1 - Funding Information: Manuscript received April 29, 2020; revised July 4, 2020, August 15, 2020, and August 28, 2020; accepted September 5, 2020. Date of publication September 21, 2020; date of current version June 16, 2021. This work was supported by the National Key Research and Development Program of China under Grant 2019YFB1704702. Paper no. TII-20-2140. (Corresponding author: Bo Gu.) Bo Gu, Xinxin Yang, Ziqi Lin, and Weiwei Hu are with the School of Intelligent Systems Engineering, Sun Yat-sen University, Guangzhou 510275, China (e-mail: [email protected]; [email protected]; [email protected]; Huww1998@ 163.com). Publisher Copyright: © 2005-2012 IEEE. Copyright: Copyright 2021 Elsevier B.V., All rights reserved.

PY - 2021/9

Y1 - 2021/9

N2 - Mobile crowdsensing (MCS) is an appealing sensing paradigm that leverages the sensing capabilities of smart devices and the inherent mobility of device owners to accomplish sensing tasks with the aim of constructing powerful industrial systems. Incentivizing mobile users (MUs) to participate in sensing activities and contribute high-quality data is of paramount importance to the success of MCS services. In this article, we formulate the competitive interactions between a sensing platform (SP) and MUs as a multistage Stackelberg game with the SP as the leader player and the MUs as the followers. Given the unit prices announced by MUs, the SP calculates the quantity of sensing time to purchase from each MU by solving a convex optimization problem. Then, each follower observes the trading records and iteratively adjusts their pricing strategy in a trial-and-error manner based on a multiagent deep reinforcement learning algorithm. Simulation results demonstrate the efficiency of the proposed method.

AB - Mobile crowdsensing (MCS) is an appealing sensing paradigm that leverages the sensing capabilities of smart devices and the inherent mobility of device owners to accomplish sensing tasks with the aim of constructing powerful industrial systems. Incentivizing mobile users (MUs) to participate in sensing activities and contribute high-quality data is of paramount importance to the success of MCS services. In this article, we formulate the competitive interactions between a sensing platform (SP) and MUs as a multistage Stackelberg game with the SP as the leader player and the MUs as the followers. Given the unit prices announced by MUs, the SP calculates the quantity of sensing time to purchase from each MU by solving a convex optimization problem. Then, each follower observes the trading records and iteratively adjusts their pricing strategy in a trial-and-error manner based on a multiagent deep reinforcement learning algorithm. Simulation results demonstrate the efficiency of the proposed method.

KW - Cognitive sensor networks

KW - deep reinforcement learning (DRL)

KW - incentive mechanism

KW - mobile crowd sensing (MCS)

KW - multiagent deep deterministic policy gradient (MADDPG)

KW - Stackelberg game

UR - http://www.scopus.com/inward/record.url?scp=85112325791&partnerID=8YFLogxK

U2 - 10.1109/TII.2020.3024611

DO - 10.1109/TII.2020.3024611

M3 - Article

AN - SCOPUS:85112325791

SN - 1551-3203

VL - 17

SP - 6182

EP - 6191

JO - IEEE Transactions on Industrial Informatics

JF - IEEE Transactions on Industrial Informatics

IS - 9

M1 - 9201550

ER -

Multiagent Actor-Critic Network-Based Incentive Mechanism for Mobile Crowdsensing in Industrial Systems

Abstract

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this