Optimizing Mobile Cloud Computing: A Comparative Analysis and Innovative Cost-Efficient Partitioning Model DOI
Mushtaq Ali, Dost Muhammad, Osamah Ibrahim Khalaf

et al.

SN Computer Science, Journal Year: 2024, Volume and Issue: 6(1)

Published: Dec. 26, 2024

Language: Английский

Attention-augmented multi-agent collaboration for Smart Industrial Internet of Things task offloading DOI

Yihang Wang,

Shengchao Su, Yiwang Wang

et al.

Internet of Things, Journal Year: 2025, Volume and Issue: unknown, P. 101572 - 101572

Published: March 1, 2025

Language: Английский

Citations

1
A novel task offloading model for IoT: enhancing resource utilization with actor-critic-based reinforcement learning DOI

G. Saranya,

K Kumaran,

M. Vivekanandan

et al.

Earth Science Informatics, Journal Year: 2025, Volume and Issue: 18(3)

Published: Feb. 17, 2025

Language: Английский

Citations

0
MADDPG-Based Offloading Strategy for Timing-Dependent Tasks in Edge Computing DOI Creative Commons
Yuchen Wang,

Zishan Huang,

Zhongcheng Wei

et al.

Future Internet, Journal Year: 2024, Volume and Issue: 16(6), P. 181 - 181

Published: May 21, 2024

With the increasing popularity of Internet Things (IoT), proliferation computation-intensive and timing-dependent applications has brought serious load pressure on terrestrial networks. In order to solve problem computing resource conflict long response delay caused by concurrent application service from multiple users, this paper proposes an improved edge timing-dependent, task-offloading scheme based Multi-Agent Deep Deterministic Policy Gradient (MADDPG) that aims shorten offloading improve utilization rate means prediction collaboration among agents utilization. First, coordinate global resource, gated recurrent unit is utilized, which predicts next requirements tasks according historical information. Second, predicted information, decisions current state are used as inputs, training process reinforcement learning algorithm propose a MADDPG. The simulation results show reduces latency 6.7% improves 30.6% compared with suboptimal benchmark algorithm, it nearly 500 rounds during process, effectively timeliness strategy.

Language: Английский

Citations

2
Multi-resource interleaving for task scheduling in cloud-edge system by deep reinforcement learning DOI
Xinglong Pei, Penghao Sun, Yuxiang Hu

et al.

Future Generation Computer Systems, Journal Year: 2024, Volume and Issue: 160, P. 522 - 536

Published: June 19, 2024

Language: Английский

Citations

1
Edge network softwarization and intelligence: Challenges and opportunities DOI
Sebastian Troìa, Marco Savi, Christian Grasso

et al.

Computer Networks, Journal Year: 2024, Volume and Issue: unknown, P. 110910 - 110910

Published: Nov. 1, 2024

Language: Английский

Citations

0
Optimizing Mobile Cloud Computing: A Comparative Analysis and Innovative Cost-Efficient Partitioning Model DOI
Mushtaq Ali, Dost Muhammad, Osamah Ibrahim Khalaf

et al.

SN Computer Science, Journal Year: 2024, Volume and Issue: 6(1)

Published: Dec. 26, 2024

Language: Английский

Citations

0