Distributed Reinforcement Learning Algorithm for Multi-Wave Fire Fighting Scheduling Problem

Xiaoyu Chen; Junjie Fu; Jialing Zhou; Yuheng Li

doi:10.1016/j.ifacol.2022.05.043

Distributed Reinforcement Learning Algorithm for Multi-Wave Fire Fighting Scheduling Problem

Xiaoyu Chen, Junjie Fu, Jialing Zhou, Yuheng Li

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

5 Citations (Scopus)

Abstract

This paper studies the distribution of FFEs (fire fighting equipments) carried by UAVs (unmanned aerial vehicles) from FFUs (fire fighting units) under the background of multi-wave forest fire. The objective is to allocate the FFEs of each FFU to minimize the sum of the probabilities of each fire site's unsuccessful extinguishment. In order to solve the multi-wave equipment distribution problem of the FFUs, a distributed reinforcement learning algorithm is designed in this paper. In the algorithm, agents cooperate to find the optimal distribution of FFEs based on information exchange, and a local Q-function is established for each agent to find the optimal FFE distribution combination. Simulation results demonstrate the effectiveness of the algorithm.

Original language	English
Pages (from-to)	245-250
Number of pages	6
Journal	IFAC-PapersOnLine
Volume	55
Issue number	3
DOIs	https://doi.org/10.1016/j.ifacol.2022.05.043
Publication status	Published - 2022
Externally published	Yes
Event	16th IFAC Symposium on Large Scale Complex Systems: Theory and Applications LSS 2022 - Xi'an, China Duration: 22 Apr 2022 → 24 Apr 2022

Keywords

FFE
Multi-agent systems
UAV
distributed reinforcement learning
fire fighting

Access to Document

10.1016/j.ifacol.2022.05.043

Cite this

@article{f01720dafd3d4e56a3176e0f4cd55a6f,

title = "Distributed Reinforcement Learning Algorithm for Multi-Wave Fire Fighting Scheduling Problem",

abstract = "This paper studies the distribution of FFEs (fire fighting equipments) carried by UAVs (unmanned aerial vehicles) from FFUs (fire fighting units) under the background of multi-wave forest fire. The objective is to allocate the FFEs of each FFU to minimize the sum of the probabilities of each fire site's unsuccessful extinguishment. In order to solve the multi-wave equipment distribution problem of the FFUs, a distributed reinforcement learning algorithm is designed in this paper. In the algorithm, agents cooperate to find the optimal distribution of FFEs based on information exchange, and a local Q-function is established for each agent to find the optimal FFE distribution combination. Simulation results demonstrate the effectiveness of the algorithm.",

keywords = "FFE, Multi-agent systems, UAV, distributed reinforcement learning, fire fighting",

author = "Xiaoyu Chen and Junjie Fu and Jialing Zhou and Yuheng Li",

note = "Publisher Copyright: {\textcopyright} 2022 Elsevier B.V.. All rights reserved.; 16th IFAC Symposium on Large Scale Complex Systems: Theory and Applications LSS 2022 ; Conference date: 22-04-2022 Through 24-04-2022",

year = "2022",

doi = "10.1016/j.ifacol.2022.05.043",

language = "English",

volume = "55",

pages = "245--250",

journal = "IFAC-PapersOnLine",

issn = "2405-8963",

publisher = "Elsevier B.V.",

number = "3",

}

TY - JOUR

T1 - Distributed Reinforcement Learning Algorithm for Multi-Wave Fire Fighting Scheduling Problem

AU - Chen, Xiaoyu

AU - Fu, Junjie

AU - Zhou, Jialing

AU - Li, Yuheng

PY - 2022

Y1 - 2022

N2 - This paper studies the distribution of FFEs (fire fighting equipments) carried by UAVs (unmanned aerial vehicles) from FFUs (fire fighting units) under the background of multi-wave forest fire. The objective is to allocate the FFEs of each FFU to minimize the sum of the probabilities of each fire site's unsuccessful extinguishment. In order to solve the multi-wave equipment distribution problem of the FFUs, a distributed reinforcement learning algorithm is designed in this paper. In the algorithm, agents cooperate to find the optimal distribution of FFEs based on information exchange, and a local Q-function is established for each agent to find the optimal FFE distribution combination. Simulation results demonstrate the effectiveness of the algorithm.

AB - This paper studies the distribution of FFEs (fire fighting equipments) carried by UAVs (unmanned aerial vehicles) from FFUs (fire fighting units) under the background of multi-wave forest fire. The objective is to allocate the FFEs of each FFU to minimize the sum of the probabilities of each fire site's unsuccessful extinguishment. In order to solve the multi-wave equipment distribution problem of the FFUs, a distributed reinforcement learning algorithm is designed in this paper. In the algorithm, agents cooperate to find the optimal distribution of FFEs based on information exchange, and a local Q-function is established for each agent to find the optimal FFE distribution combination. Simulation results demonstrate the effectiveness of the algorithm.

KW - FFE

KW - Multi-agent systems

KW - UAV

KW - distributed reinforcement learning

KW - fire fighting

UR - http://www.scopus.com/inward/record.url?scp=85134528149&partnerID=8YFLogxK

U2 - 10.1016/j.ifacol.2022.05.043

DO - 10.1016/j.ifacol.2022.05.043

M3 - Conference article

AN - SCOPUS:85134528149

SN - 2405-8963

VL - 55

SP - 245

EP - 250

JO - IFAC-PapersOnLine

JF - IFAC-PapersOnLine

IS - 3

T2 - 16th IFAC Symposium on Large Scale Complex Systems: Theory and Applications LSS 2022

Y2 - 22 April 2022 through 24 April 2022

ER -

Distributed Reinforcement Learning Algorithm for Multi-Wave Fire Fighting Scheduling Problem

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this