Digital Twin: Enabling Technologies, Challenges and Open Research

IEEE Access, Год журнала: 2020, Номер 8, С. 108952 - 108971

Опубликована: Янв. 1, 2020

Digital Twin technology is an emerging concept that has become the centre of attention for industry and, in more recent years, academia. The advancements 4.0 concepts have facilitated its growth, particularly manufacturing industry. defined extensively but best described as effortless integration data between a physical and virtual machine either direction. challenges, applications, enabling technologies Artificial Intelligence, Internet Things (IoT) Twins are presented. A review publications relating to performed, producing categorical papers. categorised them by research areas: manufacturing, healthcare smart cities, discussing range papers reflect these areas current state research. paper provides assessment technologies, challenges open Twins.

Язык: Английский

---

Machine Learning Meets Computation and Communication Control in Evolving Edge and Cloud: Challenges and Future Perspective

IEEE Communications Surveys & Tutorials, Год журнала: 2019, Номер 22(1), С. 38 - 67

Опубликована: Сен. 24, 2019

Mobile Edge Computing (MEC) is considered an essential future service for the implementation of 5G networks and Internet Things, as it best method delivering computation communication resources to mobile devices. It based on connection users servers located edge network, which especially relevant real-time applications that demand minimal latency. In order guarantee a resource-efficient MEC (which, example, could mean improved Quality Service or lower costs providers), important consider certain aspects model, such where offload tasks generated by devices, how many allocate each user (specially in wired wireless device-server communication) handle inter-server communication. However, scenarios with varied users, applications, these problems are characterized parameters exceedingly high levels dimensionality, resulting too much data be processed complicating task finding efficient configurations. This will particularly troublesome when Things roll out, their massive amounts To address this concern, solution utilize Machine Learning (ML) algorithms, enable computer draw conclusions make predictions existing without human supervision, leading quick near-optimal solutions even dimensionality. Indeed, parameters, ML algorithms often only feasible alternative. paper, comprehensive survey use systems provided, offering insight into current progress research area. Furthermore, helpful guidance supplied pointing out challenges can solved solutions, what trending frontier they used MEC. These pieces information should prove fundamental encouraging combines

Язык: Английский

---

Distributed intelligence on the Edge-to-Cloud Continuum: A systematic literature review

Journal of Parallel and Distributed Computing, Год журнала: 2022, Номер 166, С. 71 - 94

Опубликована: Апрель 20, 2022

Язык: Английский

---

Fog data analytics: A taxonomy and process model

Journal of Network and Computer Applications, Год журнала: 2018, Номер 128, С. 90 - 104

Опубликована: Дек. 28, 2018

Язык: Английский

---

Industrial Agents as a Key Enabler for Realizing Industrial Cyber-Physical Systems: Multiagent Systems Entering Industry 4.0

IEEE Industrial Electronics Magazine, Год журнала: 2020, Номер 14(3), С. 18 - 32

Опубликована: Сен. 1, 2020

Industrial agents (IAs) [1] are multiagent-based systems (MASs) [2] that, for many years, have been advocated as a promising and realistic solution an emerging set of industrial challenges. In the past, MASs fell into scope enterprise agility [3]-[8], now, more than ever, pertain to digital transformation sustainability spheres. MAS technology is being applied several applications in cyber-physical system (CPS) context, namely, smart production, electric grids, logistics, health care [9]. To understand future potential IAs, one must first sufficiently concise view past present efforts, i.e., their early current directions. Such necessary because, over last decades, concept IA has proven be bit moving target, adjusting needs, visions, technologies each era.

Язык: Английский

---

Resource provisioning for IoT services in the fog computing environment: An autonomic approach

Computer Communications, Год журнала: 2020, Номер 161, С. 109 - 131

Опубликована: Июль 23, 2020

Язык: Английский

---

MAFC: Multi-Agent Fog Computing Model for Healthcare Critical Tasks Management

Sensors, Год журнала: 2020, Номер 20(7), С. 1853 - 1853

Опубликована: Март 27, 2020

In healthcare applications, numerous sensors and devices produce massive amounts of data which are the focus critical tasks. Their management at edge network can be done by Fog computing implementation. However, Nodes suffer from lake resources That could limit time needed for final outcome/analytics. perform just a small number A difficult decision concerns tasks will locally Nodes. Each node should select such carefully based on current contextual information, example, tasks’ priority, resource load, availability. We suggest in this paper Multi-Agent Computing model management. The main role multi-agent system is mapping between three tables to optimize scheduling assigning with their load network, first step decide whether task processed locally; otherwise, second involves sophisticated selection most suitable neighbor Node allocate it. If no capable processing throughout it then sent Cloud facing highest latency. test proposed scheme thoroughly, demonstrating its applicability optimality using iFogSim simulator UTeM clinic data.

Язык: Английский

---

Highly efficient federated learning with strong privacy preservation in cloud computing

Computers & Security, Год журнала: 2020, Номер 96, С. 101889 - 101889

Опубликована: Май 28, 2020

Язык: Английский

---

Edge Cloud Server Deployment With Transmission Power Control Through Machine Learning for 6G Internet of Things

IEEE Transactions on Emerging Topics in Computing, Год журнала: 2019, Номер 9(4), С. 2099 - 2108

Опубликована: Дек. 31, 2019

Cloud computing is an important technology for bringing a big pool of elastic resources to client devices. Their main drawback has long been the distance between users and servers, but this remedied by Edge Computing, where cloud servers are located in network edge. Computing regarded as essential future networks consequently, there plenty research on how optimize its operation. However, vast majority them ignore decision edge should be deployed, despite severely can affect performance system. Furthermore, must also deal with massive amounts clients such ones characteristic Internet Things 6G Networks. This demands solutions that scalable. Given these two points, we propose Machine Learning-based server deployment policy environments. Our solution proven approach optimality while being feasible. prove our proposal leads lower latency higher resource efficiency than conventional solutions.

Язык: Английский

---

Application placement in Fog computing with AI approach: Taxonomy and a state of the art survey

Journal of Network and Computer Applications, Год журнала: 2021, Номер 185, С. 103078 - 103078

Опубликована: Апрель 19, 2021

Язык: Английский

---