COPSA: a computation offloading strategy based on PPO algorithm and self-attention mechanism in MEC-empowered smart factories DOI Creative Commons
Yining Chen, Kai Peng, Chengfang Ling

и другие.

Journal of Cloud Computing Advances Systems and Applications, Год журнала: 2024, Номер 13(1)

Опубликована: Ноя. 5, 2024

With the dawn of Industry 5.0 upon us, smart factory emerges as a pivotal element, playing crucial role in realm intelligent manufacturing. Meanwhile, mobile edge computing is proposed to alleviate computational burden presented by substantial workloads factories. Nonetheless, it very challenging effectively incorporate resources improve efficiency resource deployment Accordingly, we devise novel approach based on Proximal Policy Optimization algorithm with Self-Attention Mechanism implement allocation MEC-Empowered Smart Factories. More specifically, self-attention mechanism incorporated enable dynamic focus state information, accelerates convergence and facilitates global control. A great number experiments conducted both simulated real datasets have verified superiority our compared state-of-the-art baselines.

Язык: Английский

Comprehensive systematic review of information fusion methods in smart cities and urban environments DOI Creative Commons
Mohammed A. Fadhel, Ali M. Duhaim, Ahmed Saihood

и другие.

Information Fusion, Год журнала: 2024, Номер 107, С. 102317 - 102317

Опубликована: Фев. 21, 2024

Smart cities result from integrating advanced technologies and intelligent sensors into modern urban infrastructure. The Internet of Things (IoT) data integration are pivotal in creating interconnected spaces. In this literature review, we explore the different methods information fusion used smart cities, along with their advantages challenges. However, there notable challenges managing diverse sources, handling large volumes, meeting near-real-time demands various city applications. review aims to examine applications detail, incorporating quality evaluation techniques identifying critical issues while outlining promising research directions. order accomplish our goal, conducted a comprehensive search applied selective criteria. We identified 59 recent studies addressing machine learning (ML) deep (DL) These were obtained databases such as ScienceDirect (SD), Scopus, Web Science (WoS), IEEE Xplore. main objective study is provide more detailed insights by supplementing existing research. word cloud visualisation learning/deep papers shows landscape, covering both technical aspects artificial intelligence practical settings. Apart exploration, also delves ethical privacy implications arising cities. Moreover, it thoroughly examines that must be addressed realise revolution's potential fully.

Язык: Английский

Процитировано

77

B2RAM: Design and practical implementation of a secured information management framework for dynamic resource allocation using a novel 2-Tier blockchain model DOI
Tamal Chakraborty,

A Ashish,

Prasanta Kumar Das

и другие.

Simulation Modelling Practice and Theory, Год журнала: 2025, Номер unknown, С. 103096 - 103096

Опубликована: Март 1, 2025

Язык: Английский

Процитировано

0

Energy‐efficient resource allocation over wireless communication systems through deep reinforcement learning DOI Open Access
Kirti Shukla, Archana Kollu, Poonam Panwar

и другие.

International Journal of Communication Systems, Год журнала: 2023, Номер 38(1)

Опубликована: Авг. 21, 2023

Summary As the popularity of Internet Things (IoT) increases, so do energy requirements IoT terminal equipment. To address shortage problem equipment and ensure continuous stable operation in light renewable an uncertain environment, a rational efficient allocation strategy is required. This paper proposes deep reinforcement learning that uses DQN algorithm to directly interact with unknown environment. The best method independent environmental knowledge, pretraining proposed maximise initialization state strategy. Experiments comparison simulation are conducted under various channel data circumstances. Results indicate outperforms current multiple conditions has high capacity for adaptation changing conditions.

Язык: Английский

Процитировано

1

Empowering Principals for Lifelong Learning: Self-directed Approaches in Digitalized Information Systems DOI Open Access
Yuan Zhou, Piyapong Sumettikoon

Journal of Information Systems Engineering & Management, Год журнала: 2024, Номер 9(4), С. 27098 - 27098

Опубликована: Сен. 29, 2024

The study delves into the dynamic interplay between digitalized information systems, competencies, self-directed learning, and lifelong learning in context of contemporary educational landscape. With integration Artificial Intelligence (AI) evolving competencies becoming integral to education, understanding their combined impact on individuals' attitudes toward is paramount. Past research has explored these elements individually, but a comprehensive examination interconnected relationships remains scarce. primary purpose investigate how AI integration, collectively influence attitudes. aims uncover intricate dynamics by exploring systems mediating role overall implications for behaviors. Utilizing quantitative approach, focuses teachers China, distributing 500 questionnaires receiving 340 responses. design incorporates cross-sectional survey methodology, employing structured questionnaire gather data Preliminary findings reveal significant correlations observes highlighting its importance shaping relationship inclination learning. This contributes theoretical complex education. Its originality lies integrating framework.

Язык: Английский

Процитировано

0

Multi-UAVs task allocation method based on MPSO-SA-DQN DOI Creative Commons
Pengfei Peng, Gong Xue,

Zheng Yalian

и другие.

Measurement and Control, Год журнала: 2024, Номер unknown

Опубликована: Окт. 13, 2024

Multi-UAVs play an important role in the battlefield. Although many methods are proposed to solve Multi-UAV task allocation, there still existing problems of complex time constraints and uncertain solution space. The reason is that multi-UAVs usually face changing environmental factors. Aiming at solving such problem, this paper proposes a multi-UAV assignment method based on Deep Q-based evolutionary reinforcement learning algorithms (MPSO-SA-DQN). Specifically, builds multi-agent training framework deep mechanism SA-DQN. Its aim improve global exploration optimization capabilities multi-agents. At same time, multi-dimensional particle swarm algorithm introduced optimize state Based priority mapping, MPSO-SA-DQN proposed. As result, multi-agents can execution real environment interaction. Besides, it also has ability reach optimal maximum reward. According characteristics assignment, designs space autoencoder strategy feature. A tasks allocation iterative proposed, so as continuously scheme. simulation results show effectively problem uncertainty allocation. achieves faster convergence good prospect promotion field UAV cooperative planning.

Язык: Английский

Процитировано

0

COPSA: a computation offloading strategy based on PPO algorithm and self-attention mechanism in MEC-empowered smart factories DOI Creative Commons
Yining Chen, Kai Peng, Chengfang Ling

и другие.

Journal of Cloud Computing Advances Systems and Applications, Год журнала: 2024, Номер 13(1)

Опубликована: Ноя. 5, 2024

With the dawn of Industry 5.0 upon us, smart factory emerges as a pivotal element, playing crucial role in realm intelligent manufacturing. Meanwhile, mobile edge computing is proposed to alleviate computational burden presented by substantial workloads factories. Nonetheless, it very challenging effectively incorporate resources improve efficiency resource deployment Accordingly, we devise novel approach based on Proximal Policy Optimization algorithm with Self-Attention Mechanism implement allocation MEC-Empowered Smart Factories. More specifically, self-attention mechanism incorporated enable dynamic focus state information, accelerates convergence and facilitates global control. A great number experiments conducted both simulated real datasets have verified superiority our compared state-of-the-art baselines.

Язык: Английский

Процитировано

0