AI-Enabled Offloading Decision-Making and Resource Allocation Optimization Under Emergency Scenarios

Mengqian Cheng; Xiaoqin Song; Lei Lei

doi:10.1109/GCWkshps58843.2023.10464428

AI-Enabled Offloading Decision-Making and Resource Allocation Optimization Under Emergency Scenarios

Mengqian Cheng, Xiaoqin Song, Lei Lei^*

^*Corresponding author for this work

Nanjing University of Aeronautics and Astronautics

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

1 Citation (Scopus)

Abstract

In this paper, we present an AI-enabled approach for multi-server computation offloading in aerial computing networks, with a focus on addressing the challenges of computation-intensive services in emergency scenarios for 6G. Our method utilizes unmanned aerial vehicles as computing platforms to serve emergency vehicle users. We firstly construct the network architecture and define the optimization objective, which aims to minimize the total system delay while satisfying several constraints. To solve this problem, we introduce an improved dueling double deep Q network algorithm that incorporates dueling networks and prioritized experience replay. Numerical simulation results demonstrate the effectiveness of our approach, compared to the traditional DDQN algorithm, the proposed algorithm can reduce the total system delay by about 25%.

Original language	English
Title of host publication	2023 IEEE Globecom Workshops, GC Wkshps 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1734-1739
Number of pages	6
ISBN (Electronic)	9798350370218
DOIs	https://doi.org/10.1109/GCWkshps58843.2023.10464428
Publication status	Published - 2023
Externally published	Yes
Event	2023 IEEE Globecom Workshops, GC Wkshps 2023 - Kuala Lumpur, Malaysia Duration: 4 Dec 2023 → 8 Dec 2023

Publication series

Name	2023 IEEE Globecom Workshops, GC Wkshps 2023

Conference

Conference	2023 IEEE Globecom Workshops, GC Wkshps 2023
Country/Territory	Malaysia
City	Kuala Lumpur
Period	4/12/23 → 8/12/23

Keywords

AI model
aerial computing networks
dueling double deep Q-network
multi-access edge computing

Access to Document

10.1109/GCWkshps58843.2023.10464428

Cite this

@inproceedings{d52a27456bf64cb4aaeed28276b94596,

title = "AI-Enabled Offloading Decision-Making and Resource Allocation Optimization Under Emergency Scenarios",

abstract = "In this paper, we present an AI-enabled approach for multi-server computation offloading in aerial computing networks, with a focus on addressing the challenges of computation-intensive services in emergency scenarios for 6G. Our method utilizes unmanned aerial vehicles as computing platforms to serve emergency vehicle users. We firstly construct the network architecture and define the optimization objective, which aims to minimize the total system delay while satisfying several constraints. To solve this problem, we introduce an improved dueling double deep Q network algorithm that incorporates dueling networks and prioritized experience replay. Numerical simulation results demonstrate the effectiveness of our approach, compared to the traditional DDQN algorithm, the proposed algorithm can reduce the total system delay by about 25\%.",

keywords = "AI model, aerial computing networks, dueling double deep Q-network, multi-access edge computing",

author = "Mengqian Cheng and Xiaoqin Song and Lei Lei",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE Globecom Workshops, GC Wkshps 2023 ; Conference date: 04-12-2023 Through 08-12-2023",

year = "2023",

doi = "10.1109/GCWkshps58843.2023.10464428",

language = "English",

series = "2023 IEEE Globecom Workshops, GC Wkshps 2023",

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

pages = "1734--1739",

booktitle = "2023 IEEE Globecom Workshops, GC Wkshps 2023",

address = "United States",

}

Cheng, M, Song, X & Lei, L 2023, AI-Enabled Offloading Decision-Making and Resource Allocation Optimization Under Emergency Scenarios. in 2023 IEEE Globecom Workshops, GC Wkshps 2023. 2023 IEEE Globecom Workshops, GC Wkshps 2023, Institute of Electrical and Electronics Engineers Inc., pp. 1734-1739, 2023 IEEE Globecom Workshops, GC Wkshps 2023, Kuala Lumpur, Malaysia, 4/12/23. https://doi.org/10.1109/GCWkshps58843.2023.10464428

AI-Enabled Offloading Decision-Making and Resource Allocation Optimization Under Emergency Scenarios. / Cheng, Mengqian; Song, Xiaoqin; Lei, Lei.
2023 IEEE Globecom Workshops, GC Wkshps 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 1734-1739 (2023 IEEE Globecom Workshops, GC Wkshps 2023).

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

TY - GEN

T1 - AI-Enabled Offloading Decision-Making and Resource Allocation Optimization Under Emergency Scenarios

AU - Cheng, Mengqian

AU - Song, Xiaoqin

AU - Lei, Lei

PY - 2023

Y1 - 2023

N2 - In this paper, we present an AI-enabled approach for multi-server computation offloading in aerial computing networks, with a focus on addressing the challenges of computation-intensive services in emergency scenarios for 6G. Our method utilizes unmanned aerial vehicles as computing platforms to serve emergency vehicle users. We firstly construct the network architecture and define the optimization objective, which aims to minimize the total system delay while satisfying several constraints. To solve this problem, we introduce an improved dueling double deep Q network algorithm that incorporates dueling networks and prioritized experience replay. Numerical simulation results demonstrate the effectiveness of our approach, compared to the traditional DDQN algorithm, the proposed algorithm can reduce the total system delay by about 25%.

AB - In this paper, we present an AI-enabled approach for multi-server computation offloading in aerial computing networks, with a focus on addressing the challenges of computation-intensive services in emergency scenarios for 6G. Our method utilizes unmanned aerial vehicles as computing platforms to serve emergency vehicle users. We firstly construct the network architecture and define the optimization objective, which aims to minimize the total system delay while satisfying several constraints. To solve this problem, we introduce an improved dueling double deep Q network algorithm that incorporates dueling networks and prioritized experience replay. Numerical simulation results demonstrate the effectiveness of our approach, compared to the traditional DDQN algorithm, the proposed algorithm can reduce the total system delay by about 25%.

KW - AI model

KW - aerial computing networks

KW - dueling double deep Q-network

KW - multi-access edge computing

UR - https://www.scopus.com/pages/publications/85190297463

U2 - 10.1109/GCWkshps58843.2023.10464428

DO - 10.1109/GCWkshps58843.2023.10464428

M3 - Conference contribution

AN - SCOPUS:85190297463

T3 - 2023 IEEE Globecom Workshops, GC Wkshps 2023

SP - 1734

EP - 1739

BT - 2023 IEEE Globecom Workshops, GC Wkshps 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2023 IEEE Globecom Workshops, GC Wkshps 2023

Y2 - 4 December 2023 through 8 December 2023

ER -

AI-Enabled Offloading Decision-Making and Resource Allocation Optimization Under Emergency Scenarios

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this