Dual-Time-Scale Cloud–Edge–End Collaborative Task Offloading for Multi-AGV Intelligent Warehousing in Industrial Internet of Things
Sensors · 21.06.2026 · 26 (12) · 3936
DOI: 10.3390/s26123936 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 21.06.2026. Verfasst von Junjie Xue und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Advanced Manufacturing, Fuzhou University, Quanzhou 362251, China. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Fujian Province, NSF of Fujian Province.
Abstract (Originalsprache)
In embodied-intelligence Industrial Internet of Things (IIoT), multi-AGV intelligent warehousing requires continuous processing of latency-sensitive tasks, such as environmental perception, inventory monitoring, and anomaly detection. Due to limited onboard computing capability and energy capacity, purely local execution can hardly satisfy real-time requirements, whereas fully cloud-based processing may incur excessive transmission delay and backhaul overhead. To address this issue, this paper investigates the joint optimization of AGV service-point migration and task offloading under a cloud-edge-end collaborative architecture. Considering the impact of service-point selection on wireless access, MEC resources, movement delay, and energy consumption, as well as the effect of offloading decisions on transmission, computation, and AGV-side energy cost, a dual-time-scale optimization model is formulated to minimize the long-term accumulated system delay while satisfying task latency and AGV energy constraints. To solve the resulting mixed discrete problem, a DPSO-MAPPO algorithm is proposed, where DPSO searches service-point plans satisfying movement and conflict constraints at the slow time scale, and MAPPO learns coordinated multi-AGV offloading policies at the fast time scale. The delay and energy feedback further enables coordination between the two types of decisions. Simulation results show that the proposed algorithm converges stably, reduces system delay by 13.55% compared with benchmark algorithms, and improves total energy consumption and energy-violation control.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Advanced Manufacturing, Fuzhou University, Quanzhou 362251, China.
- China Mobile Research Institute, Beijing 100053, China.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Fujian Province
- NSF of Fujian Province
Zitieren
APA
Xue, J., Huang, Y., Guo, Y., Lin, Z., & Tian, B. (2026). Dual-Time-Scale Cloud–Edge–End Collaborative Task Offloading for Multi-AGV Intelligent Warehousing in Industrial Internet of Things. Sensors, 26(12), 3936. https://doi.org/10.3390/s26123936
Vancouver
Xue J, Huang Y, Guo Y, Lin Z, Tian B. Dual-Time-Scale Cloud–Edge–End Collaborative Task Offloading for Multi-AGV Intelligent Warehousing in Industrial Internet of Things. Sensors. 2026;26(12):3936. doi:10.3390/s26123936
BibTeX
@article{Xue2026,
author = {Xue, Junjie and Huang, Yuyi and Guo, Yuheng and Lin, Zhijian and Tian, Bingxin},
title = {Dual-Time-Scale Cloud–Edge–End Collaborative Task Offloading for Multi-AGV Intelligent Warehousing in Industrial Internet of Things},
journal = {Sensors},
year = {2026},
volume = {26},
number = {12},
pages = {3936},
doi = {10.3390/s26123936}
}
EUVIMED