Home > Research > Publications & Outputs > A DQN-Based Edge Offloading Method for Smart Ci...

Associated organisational unit

Links

Text available via DOI:

View graph of relations

A DQN-Based Edge Offloading Method for Smart City Pollution Control

Research output: Contribution to Journal/MagazineJournal articlepeer-review

E-pub ahead of print

Standard

A DQN-Based Edge Offloading Method for Smart City Pollution Control. / Xu, Jiajie; Xiang, Haolong; Zang, Shaobo et al.
In: Tsinghua Science and Technology, Vol. 30, No. 5, 31.10.2025, p. 2227-2242.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Xu, J, Xiang, H, Zang, S, Bilal, M, Khan, M & Cui, G 2025, 'A DQN-Based Edge Offloading Method for Smart City Pollution Control', Tsinghua Science and Technology, vol. 30, no. 5, pp. 2227-2242. https://doi.org/10.26599/tst.2024.9010105

APA

Xu, J., Xiang, H., Zang, S., Bilal, M., Khan, M., & Cui, G. (2025). A DQN-Based Edge Offloading Method for Smart City Pollution Control. Tsinghua Science and Technology, 30(5), 2227-2242. Advance online publication. https://doi.org/10.26599/tst.2024.9010105

Vancouver

Xu J, Xiang H, Zang S, Bilal M, Khan M, Cui G. A DQN-Based Edge Offloading Method for Smart City Pollution Control. Tsinghua Science and Technology. 2025 Oct 31;30(5):2227-2242. Epub 2025 Apr 29. doi: 10.26599/tst.2024.9010105

Author

Xu, Jiajie ; Xiang, Haolong ; Zang, Shaobo et al. / A DQN-Based Edge Offloading Method for Smart City Pollution Control. In: Tsinghua Science and Technology. 2025 ; Vol. 30, No. 5. pp. 2227-2242.

Bibtex

@article{18222f223f154aab92ae8f502e97f77a,
title = "A DQN-Based Edge Offloading Method for Smart City Pollution Control",
abstract = "Smart city pollution control is fundamental to urban sustainability, which relies extensively on physical infrastructure such as sensors and cameras for real-time monitoring. Generally, monitoring data needs to be transmitted to centralized servers for pollution control service determination. In order to achieve highly efficient service quality, edge computing is involved in the smart city pollution control system (SCPCS) as it provides computational capabilities near the monitoring devices and low-latency pollution control services. However, considering the diversity of service requests, determination of offloading destination is a crucial challenge for SCPCS. In this paper, A Deep Q-Network (DQN)-based edge offloading method, called N-DEO, is proposed. Initially, N-DEO employs neural hierarchical interpolation for time series forecasting (N-HITS) to forecast pollution control service requests. Afterwards, an epsilon-greedy policy is designed to select actions. Finally, the optimal service offloading strategy is determined by the DQN algorithm. Experimental results demonstrate that N-DEO achieves the higher performance on service latency and system load compared with the current state-of-the-art methods.",
author = "Jiajie Xu and Haolong Xiang and Shaobo Zang and Muhammad Bilal and Maqbool Khan and Guangming Cui",
year = "2025",
month = apr,
day = "29",
doi = "10.26599/tst.2024.9010105",
language = "English",
volume = "30",
pages = "2227--2242",
journal = "Tsinghua Science and Technology",
issn = "1007-0214",
publisher = "Tsinghua University",
number = "5",

}

RIS

TY - JOUR

T1 - A DQN-Based Edge Offloading Method for Smart City Pollution Control

AU - Xu, Jiajie

AU - Xiang, Haolong

AU - Zang, Shaobo

AU - Bilal, Muhammad

AU - Khan, Maqbool

AU - Cui, Guangming

PY - 2025/4/29

Y1 - 2025/4/29

N2 - Smart city pollution control is fundamental to urban sustainability, which relies extensively on physical infrastructure such as sensors and cameras for real-time monitoring. Generally, monitoring data needs to be transmitted to centralized servers for pollution control service determination. In order to achieve highly efficient service quality, edge computing is involved in the smart city pollution control system (SCPCS) as it provides computational capabilities near the monitoring devices and low-latency pollution control services. However, considering the diversity of service requests, determination of offloading destination is a crucial challenge for SCPCS. In this paper, A Deep Q-Network (DQN)-based edge offloading method, called N-DEO, is proposed. Initially, N-DEO employs neural hierarchical interpolation for time series forecasting (N-HITS) to forecast pollution control service requests. Afterwards, an epsilon-greedy policy is designed to select actions. Finally, the optimal service offloading strategy is determined by the DQN algorithm. Experimental results demonstrate that N-DEO achieves the higher performance on service latency and system load compared with the current state-of-the-art methods.

AB - Smart city pollution control is fundamental to urban sustainability, which relies extensively on physical infrastructure such as sensors and cameras for real-time monitoring. Generally, monitoring data needs to be transmitted to centralized servers for pollution control service determination. In order to achieve highly efficient service quality, edge computing is involved in the smart city pollution control system (SCPCS) as it provides computational capabilities near the monitoring devices and low-latency pollution control services. However, considering the diversity of service requests, determination of offloading destination is a crucial challenge for SCPCS. In this paper, A Deep Q-Network (DQN)-based edge offloading method, called N-DEO, is proposed. Initially, N-DEO employs neural hierarchical interpolation for time series forecasting (N-HITS) to forecast pollution control service requests. Afterwards, an epsilon-greedy policy is designed to select actions. Finally, the optimal service offloading strategy is determined by the DQN algorithm. Experimental results demonstrate that N-DEO achieves the higher performance on service latency and system load compared with the current state-of-the-art methods.

U2 - 10.26599/tst.2024.9010105

DO - 10.26599/tst.2024.9010105

M3 - Journal article

VL - 30

SP - 2227

EP - 2242

JO - Tsinghua Science and Technology

JF - Tsinghua Science and Technology

SN - 1007-0214

IS - 5

ER -