Fine-grained Task Scheduling Based on Priority for Heterogeneous Mobile Edge Computing DOI
Bin Xu, Dan Liu,

Jinming Chai

et al.

2021 China Automation Congress (CAC), Journal Year: 2022, Volume and Issue: unknown, P. 4889 - 4894

Published: Nov. 25, 2022

With the advance of novel applications, it is harder to deal with computation-intensive tasks due resource-constrained devices. Task offloading in Mobile Edge Computing (MEC) can effectively this problem. Most existing studies view task as a whole and do not consider partition task, which may result increasing delay processing. First, we construct model fine-grained scheduling problem for heterogeneous MEC Directed Acyclic Graph (DAG). Second, optimize average delay, propose priority-based heuristic algorithm handle dependencies subtasks achieve reasonable schemes between servers. Moreover, design an idle time slot insertion strategy realize full utilization resources. Finally, topology DAGs generated simulation based on practical applications. Experimental indicates that proposed HFGO-CI could efficiently goal system reduction basis decisions.

Language: Английский

Task offloading in cloud-edge collaboration-based cyber physical machine tool DOI

Chuting Wang,

Ruifeng Guo, Haoyu Yu

et al.

Robotics and Computer-Integrated Manufacturing, Journal Year: 2022, Volume and Issue: 79, P. 102439 - 102439

Published: Aug. 23, 2022

Language: Английский

Citations

22
A Bibliometric Analysis of Edge Computing for Internet of Things DOI Creative Commons
Yiou Wang, Fuquan Zhang, Junfeng Wang

et al.

Security and Communication Networks, Journal Year: 2021, Volume and Issue: 2021, P. 1 - 10

Published: April 9, 2021

In recent years, with the emergence of many Internet Things applications such as smart homes, city, and connected vehicles, amount network edge data increases rapidly. Now, computing for has attracted research interest researchers. Then, a thorough analysis current body knowledge in is conducive to comprehensive understanding status future trends this field. paper, bibliometric was performed using Web Science (WoS) Core Collection dataset. The relevant literature studies published field were quantitatively analyzed based on method combined VOSviewer software, development history, hotspots, directions studied. results show that number rise over time, especially after 2017, growth rate accelerating. China USA take lead position published. Zhang most productive author, Satyanarayanan influential author. IEEE Access Journal are main journals Beijing University Posts Telecommunications studies. Research hotspots mainly include specific problem resource management, architecture research, application fusion some other fields artificial intelligence 5G.

Language: Английский

Citations

11
Multi-Resource Computing Offload Strategy for Energy Consumption Optimization in Mobile Edge Computing DOI Open Access
Zhe Wei, Xuebin Yu, Lei Zou

et al.

Processes, Journal Year: 2022, Volume and Issue: 10(9), P. 1762 - 1762

Published: Sept. 2, 2022

The energy consumption optimization of edge devices in the mobile computing environment is mainly based on computational offload strategy. Most current common strategies only consider a single resource and do not comprehensively different kinds resources environments, which cannot fully reduce under condition ensuring response time constraints. To solve this problem, multi-resource unloading model proposed environment, new fitness calculation method for evaluating designed. Combined with workflow management system, offloading particle swarm task scheduling algorithm proposed. can terminals considering constraint. Experiments show that, compared existing four algorithms, corresponding to strategy has stable convergence optimal fitness. Under constraint user time, scheme better than other strategies.

Language: Английский

Citations

6
ECViST: Mine Intelligent Monitoring Based on Edge Computing and Vision Swin Transformer-YOLOv5 DOI Creative Commons
Fan Zhang, Jiawei Tian, Jianhao Wang

et al.

Energies, Journal Year: 2022, Volume and Issue: 15(23), P. 9015 - 9015

Published: Nov. 29, 2022

Mine video surveillance has a key role in ensuring the production safety of intelligent mining. However, existing mine monitoring technology mainly processes data cloud, which problems, such as network congestion, large memory consumption, and untimely response to regional emergencies. In this paper, we address these limitations by utilizing edge-cloud collaborative optimization framework. First, obtained coarse model using architecture updated realize continuous improvement detection model. Second, further proposed target based on Vision Swin Transformer-YOLOv5(ViST-YOLOv5) algorithm improved for edge device deployment. The experimental results showed that object ViST-YOLOv5, with size only 27.057 MB, average accuracy is 25% compared state-of-the-art model, makes it suitable edge-end deployment mining workface. For actual video, can achieve better performance robustness typical application scenarios, weak lighting occlusion, verifies feasibility designed architecture.

Language: Английский

Citations

5
Research on optimized scheduling of cloud-edge collaboration resources for industrial internet platform in home appliance industry DOI
Xiaoping Lü, Zhenfa Yang, Quan Z. Sheng

et al.

Published: July 5, 2024

Language: Английский

Citations

0
A Decomposition-Based Approach for Multitask Scheduling With Execution Uncertainty in Industrial Internet of Things DOI
Yong Wang, Bingtao Hu, Yixiong Feng

et al.

IEEE Internet of Things Journal, Journal Year: 2023, Volume and Issue: 10(12), P. 10222 - 10235

Published: Jan. 17, 2023

Industrial Internet of Things (IIoT) is changing the way in which factories operate with help various industrial applications. However, execution uncertainty computing tasks has always been ignored IIoT In this article, we define a novel conditional task graph to describe and present generation algorithm obtain all scenario graphs corresponding occurrence probabilities. Then, new IIoT-oriented multitask scheduling model under built. This simplified by reformulating nonlinear constraints subsequently decomposed into several small-scale models using Lagrange multipliers, from decomposition-based derived solve progressively acquire well-optimized solution initial model. Furthermore, patching constructed improve obtained solution. Finally, many test cases are generated, four selected algorithms taken for comparison evaluate performance our algorithms. The results demonstrate that remarkably outperform others. Besides, solutions proposed can completely satisfy deadline different scenarios.

Language: Английский

Citations

1
Fine-grained Task Scheduling Based on Priority for Heterogeneous Mobile Edge Computing DOI
Bin Xu, Dan Liu,

Jinming Chai

et al.

2021 China Automation Congress (CAC), Journal Year: 2022, Volume and Issue: unknown, P. 4889 - 4894

Published: Nov. 25, 2022

With the advance of novel applications, it is harder to deal with computation-intensive tasks due resource-constrained devices. Task offloading in Mobile Edge Computing (MEC) can effectively this problem. Most existing studies view task as a whole and do not consider partition task, which may result increasing delay processing. First, we construct model fine-grained scheduling problem for heterogeneous MEC Directed Acyclic Graph (DAG). Second, optimize average delay, propose priority-based heuristic algorithm handle dependencies subtasks achieve reasonable schemes between servers. Moreover, design an idle time slot insertion strategy realize full utilization resources. Finally, topology DAGs generated simulation based on practical applications. Experimental indicates that proposed HFGO-CI could efficiently goal system reduction basis decisions.

Language: Английский

Citations

2