C2PS: A Digital Twin Architecture Reference Model for the Cloud-Based Cyber-Physical Systems

Alam, Kazi Masudul; Saddik, Abdulmotaleb El

doi:10.1109/access.2017.2657006

Cited by 561 publications

(247 citation statements)

References 35 publications

Supporting

Mentioning

214

Contrasting

Unclassified

Order By: Relevance

“…In particular, we aggregate the model first (8), then we run one gradient descent round using the received gradients (13), and finally, a number of SGD rounds (14) using local mini-batches. As 4 Sending multiple gradients (corresponding to mini-batches) is an alternative option, not considered here for bandwidth limitations. Algorithm 2 CFA with gradients exchange…”

Section: B Consensus Based Federated Averaging With Gradients Exchanmentioning

confidence: 99%

“…The combination of powerful AI tools, e.g. Deep Neural Networks (DNN), with massive usage of Internet of Things (IoT), is expected to provide advanced services [2] in several domains such as Industry 4.0 [3], Cyber-Physical Systems (CPS) [4] and smart mobility [5]. Considering this envisioned landscape, it is of paramount importance to integrate emerging deep learning breakthroughs within future generation wireless networks, characterized by arbitrary distributed connectivity c 2019 IEEE.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Federated Learning With Cooperating Devices: A Consensus Approach for Massive IoT Networks

Savazzi¹,

Nicoli²,

Rampa³

2020

IEEE Internet Things J.

316

164

View full text Add to dashboard Cite

Federated learning (FL) is emerging as a new paradigm to train machine learning models in distributed systems. Rather than sharing, and disclosing, the training dataset with the server, the model parameters (e.g., neural networks weights and biases) are optimized collectively by large populations of interconnected devices, acting as local learners. FL can be applied to power-constrained IoT devices with slow and sporadic connections. In addition, it does not need data to be exported to third parties, preserving privacy. Despite these benefits, a main limit of existing approaches is the centralized optimization which relies on a server for aggregation and fusion of local parameters; this has the drawback of a single point of failure and scaling issues for increasing network size. The paper proposes a fully distributed (or server-less) learning approach: the proposed FL algorithms leverage the cooperation of devices that perform data operations inside the network by iterating local computations and mutual interactions via consensus-based methods. The approach lays the groundwork for integration of FL within 5G and beyond networks characterized by decentralized connectivity and computing, with intelligence distributed over the end-devices. The proposed methodology is verified by experimental datasets collected inside an industrial IoT environment.

show abstract

Section: B Consensus Based Federated Averaging With Gradients Exchanmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Federated Learning With Cooperating Devices: A Consensus Approach for Massive IoT Networks

Savazzi¹,

Nicoli²,

Rampa³

2020

IEEE Internet Things J.

316

164

View full text Add to dashboard Cite

show abstract

“…The physical systems include actuators and sensors collecting data and transmitting them over a network. The virtual counterparts of the physical systems map the physical parts, monitor them, and use their data to control the actuators of the physical component [3], creating a closed-loop circuit. In this increasingly complex work environment, Digital Twins (DT) are often discussed.…”

Section: Introductionmentioning

confidence: 99%

“…In this increasingly complex work environment, Digital Twins (DT) are often discussed. They also implement the mentioned closed-loop approach [3], but focus on the simulation of different scenarios.…”

Section: Introductionmentioning

confidence: 99%

The Digital Twin – Birth of an Integrated System in the Digital Age

Wache

Dinter

2020

Proceedings of the Annual Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

Today we live in a time where new technologies are developing rapidly. Digitalization and automation are finding their way into various industrial sectors, especially in the area of Industry 4.0. As in previous digitalization efforts in the manufacturing sector, it can be observed that the discourse is strongly concentrated on technological themes, neglecting the overall integration of technologies into the organization. In this paper, we conduct a literature review on the concept of a digital twin, i.e. a simulation-oriented closed loop system consisting of physical and digital components. We map the identified themes to the elements of a socio-technical system to show which issues in the discourse are underrepresented from a managerial point of view in order to provide indications for a more holistic discourse.

show abstract

“…Their architecture, however, assumes the existence of an MES where the twin does not directly interact with the physical system and an online use-case of the twin is missing. A cloud-based digital twin architecture reference model is introduced in [6]. On the high-level, the model of cyber things are composed as a set of finite state machines.…”

Section: Introductionmentioning

confidence: 99%

TiLA: Twin-in-the-Loop Architecture for Cyber-Physical Production Systems

Park

Easwaran

Andalam³

2019

2019 IEEE 37th International Conference on Computer Design (ICCD)

View full text Add to dashboard Cite

Digital twin is a virtual replica of a real-world object that lives simultaneously with its physical counterpart. Since its first introduction in 2003 by Grieves, digital twin has gained momentum in a wide range of applications such as industrial manufacturing, automotive and artificial intelligence. However, many digital-twin-related approaches, found in industries as well as literature, mainly focus on modelling individual physical things with high-fidelity methods with limited scalability. In this paper, we introduce a digital-twin architecture called TiLA (Twin-in-the-Loop Architecture). TiLA employs heterogeneous models and online data to create a digital twin, which follows a Globally Asynchronous Locally Synchronous (GALS) model of computation. It facilitates the creation of a scalable digital twin with different levels of modelling abstraction as well as giving GALS formalism for execution strategy. Furthermore, TiLA provides facilities to develop applications around the twin as well as an interface to synchronise the twin with the physical system through an industrial communication protocol. A digital twin for a manufacturing line has been developed as a case study using TiLA. It demonstrates the use of digital twin models together with online data for monitoring and analysing failures in the physical system.

show abstract

C2PS: A Digital Twin Architecture Reference Model for the Cloud-Based Cyber-Physical Systems

Cited by 561 publications

References 35 publications

Federated Learning With Cooperating Devices: A Consensus Approach for Massive IoT Networks

Federated Learning With Cooperating Devices: A Consensus Approach for Massive IoT Networks

The Digital Twin – Birth of an Integrated System in the Digital Age

TiLA: Twin-in-the-Loop Architecture for Cyber-Physical Production Systems

Contact Info

Product

Resources

About