Figure - uploaded by Nikos Panopoulos
Content may be subject to copyright.
![Comparison of 3G/4G and 5G latency times and data speeds [25,26]](profile/Nikos-Panopoulos/publication/359102091/figure/tbl1/AS:1131684804202505@1646826091880/Comparison-of-3G-4G-and-5G-latency-times-and-data-speeds-25-26.png)
Source publication
![Comparison of 3G/4G and 5G latency times and data speeds [25,26]](profile/Nikos-Panopoulos/publication/359102091/figure/tbl1/AS:1131684804202505@1646826091880/Comparison-of-3G-4G-and-5G-latency-times-and-data-speeds-25-26_Q320.jpg)
During the last decades numerous innovations and inventions have been presented under the framework of Industry 4.0. The ultimate goal of the latest industrial revolution is the digitalization of modern manufacturing systems. Therefore, several techniques and technologies have been investigated by the academia and the industrial practitioners, such...
Context in source publication
Context 1
... deployment of 5G has raised expectations that it will open new opportunities for manufacturing business models, given the expected increase in data requirements ranging from mission-critical to massive machine connectivity. As shown in Table 1, 5G promises faster download speeds, lower latency, and increased capacity. ...Citations
... This could be achieved by storing the content related to the game in MEC servers closest to the stadium. Similarly, a factory may collect data from sensors, vehicles, wearable devices and drones used in the factory and process these locally helping it to operate more efficiently [24,35,42]. While the servers used in mobile edge computing may reside closer to network elements to reduce latency, they are essentially providing a cloud or hosting service. ...
As we transition into the era of B5G/6G networks, the promise of seamless, high-speed connectivity brings unprecedented opportunities and challenges. Among the most critical concerns is the preservation of location privacy, given the enhanced precision and pervasive connectivity of these advanced networks. This paper systematically reviews the state of knowledge on location privacy in B5G/6G networks, highlighting the architectural advancements and infrastructural complexities that contribute to increased privacy risks. The urgency of studying these technologies is underscored by the rapid adoption of B5G/6G and the growing sophistication of location tracking methods. We evaluate current and emerging privacy-preserving mechanisms, exploring the implications of sophisticated tracking methods and the challenges posed by the complex network infrastructures. Our findings reveal the effectiveness of various mitigation strategies and emphasize the important role of physical layer security. Additionally, we propose innovative approaches, including decentralized authentication systems and the potential of satellite communications, to enhance location privacy. By addressing these challenges, this paper provides a comprehensive perspective on preserving user privacy in the rapidly evolving landscape of modern communication networks.
... Similarly, Mourtzis et al. (2022) developed a framework for integrating predictive maintenance and edge computing. To leverage the advantages of the edge, Raspberry Pi nodes are installed close to the sensors. ...
Industrial internet of things (IIoT) has ushered us into a world where most machine parts are now embedded with sensors that collect data. This huge data reservoir has enhanced data-driven diagnostics and prognoses of machine health. With technologies like cloud or centralized computing, the data could be sent to powerful remote data centers for machine health analysis using artificial intelligence (AI) tools. However, centralized computing has its own challenges, such as privacy issues, long latency, and low availability. To overcome these problems, edge computing technology was embraced. Thus, instead of moving all the data to the remote server, the data can now transition on the edge layer where certain computations are done. Thus, access to the central server is infrequent. Although placing AI on edge devices aids in fast inference, it poses new research problems, as highlighted in this paper. Moreover, the paper discusses studies that use edge computing to develop artificial intelligence-based diagnostic and prognostic techniques for industrial machines. It highlights the locations of data preprocessing, model training, and deployment. After analysis of several works, trends of the field are outlined, and finally, future research directions are elaborated
... Research in this direction explores the integration of contextual information into predictive analytics models to enhance the adaptability and personalization of adaptive streaming. [24], [2], [18], [21], [16] The integration of edge computing in the context of predictive analytics for adaptive streaming is an emerging research direction. Edge computing involves processing data closer to the source, reducing latency and enabling faster decision-making. ...
As the demand for high-quality video streaming continues to surge, the adaptability of streaming systems to dynamic and unpredictable network conditions becomes paramount. This review paper delves into the realm of adaptive video streaming, focusing on the integration of AI-driven predictive analytics to anticipate and optimize network conditions. The paper provides an extensive overview of existing adaptive streaming algorithms, highlighting the challenges posed by fluctuating network conditions. It explores the role of predictive analytics in mitigating these challenges, emphasizing the use of machine learning models and AI technologies. Through case studies and discussions on real-world implementations, the paper showcases how predictive analytics enhances the decision-making process in adaptive streaming systems, leading to improved bitrate adaptation and content delivery. Challenges and limitations associated with predictive analytics are scrutinized, paving the way for a comprehensive understanding of its implications. The integration of predictive analytics into adaptive streaming systems is examined, emphasizing its potential to revolutionize the quality of service. Finally, the paper outlines future trends and research directions, offering insights into the evolving landscape of adaptive video streaming. This review consolidates knowledge and provides a valuable resource for researchers, practitioners, and industry professionals involved in the intersection of video streaming, predictive analytics, and artificial intelligence.
... Finally, the Metaverse is expected to open new directions towards collaboration, since its essence is the creation of a digital parallel of the physical world. By extension, the integration of Metaverse in Industry will facilitate engineers to bridge the gap between their partners, create opportunities for expanding their manufacturing network, and most importantly include the customers in the design phase of new products [66][67][68]. ...
... Müller has identified four different levels of integrating products and physical resources with services and elementary service skill (see [71] and Fig. 11), starting from low dependency on the first level up to a stringent cross-linked dependency of the highest level. Fig. 11 Degrees of product-service integration according to [66] As the degree of product-service integration increases, the value proposition gradually moves toward outcome-based PSS, where the product service is sold instead of the product (pay-per-use). By means of sensors in products and networking, digitization enables the continuous and precise determination of system conditions in the field, which can provide insights into the product life cycle and enable optimized operation of the product in conjunction with other services [72]. ...
Modelling and Simulation (M&S) are critical capabilities for Cloud Computing. M&S products and services are valuable resources that have to be easily accessible and available on demand in a cost-effective way to users; they provide the required level of agility so that capabilities can be integrated quickly and easily. To address new design and manufacturing challenges in Industry 4.0, digital-driven technologies use simulation tools, Computer Aided Design (CAD), Product Lifecycle Management (PLM) systems and Extended Reality (XR) services to support digital design and information flow throughout a product lifecycle. Thus, XR creates new business value by improving the customer journey, optimizing employee performance, and developing new content and services. The vision of Modelling and Simulation as a Service (MSaaS) aims to make products, data, and processes easily accessible and available on-demand to all users to improve operational effectiveness. The scope of this essay is to provide a comprehensive vision of MSaaS for products, data, and processes in combination with XR services to improve operational effectiveness under the framework of Industry 4.0.
... Mourtzis et al. [19] have devised an edge computing platform to calculate the remaining life of industrial machines. Microcontroller units (MCU) send the data to the edge nodes and then classify the data using machine learning. ...
... We deployed InfluxDB 18 as time-series database in the data lake. Fluentd also connects Kafka and the data lake with the plugin influxdb-pluginfluent 19 . Furthermore, our prototype uses Docker containers and Kubernetes, an open-source container orchestration; Kafka, InfluxDB, and Fluentd are deployed in our cloud cluster. ...
Leveraging previously untapped data sources offers significant potential for value creation in the manufacturing sector. However, asset-heavy shop floors, extended machine replacement cycles, and equipment diversity necessitate considerable investments for achieving smart manufacturing, which can be particularly challenging for small businesses. Retrofitting presents a viable solution, enabling the integration of low-cost sensors and microcontrollers with older machines to collect and transmit data. In this paper, we introduce a concept and a prototype for retrofitting industrial environments using lightweight web technologies at the edge. Our approach employs WebAssembly as a novel bytecode standard, facilitating a consistent development environment from the cloud to the edge by operating on both browsers and bare-metal hardware. By attaining near-native performance and modularity reminiscent of container-based service architectures, we demonstrate the feasibility of our approach. Our prototype was evaluated with an actual industrial robot within a showcase factory, including measurements of data exchange with a cutting-edge data lake system. We further extended the prototype to incorporate a peer-to-peer network that facilitates message routing and WebAssembly software updates. Our technology establishes a foundational framework for the transition towards Industry 4.0. By integrating considerations of sustainability and human factors, it further extends this groundwork to facilitate progression into Industry 5.0.
... Modern technologies, such as intelligent decision-making engines and augmented reality systems, have been developed to support predictive and prescriptive maintenance operations [15]. Along with this, internet connectivity has substantially improved industrial processes in terms of speed, latency, volume transmission, data security, and efficiency by combining assurance with multiple frameworks, as the operator can view the workflow in real-time and take action on the optimization routine as it helps administrators to deal with their network system proficiently with high intricacy, assists in edge computing, assists in conveying robotized experiences during functioning cycles, as well as provides insights to operators and administrators in foreseeing future challenges [16]. The main advantages of advanced internet connectivity are latency and reliability, service deployment and energy efficiency, speed, and volume transmission [17]. ...
In the current production scenario, asset management and performance are necessities. Predictive and prescriptive maintenance permits various industries to analyze historical data in real-time for the purpose of optimization of industrial operations such as production, manufacturing, supplantation, etc., to increase productivity and cumulative outcome. The data-driven Industry 4.0 paradigm provides various competitive advantages affecting productivity, quality, and key performance indicators (KPIs). It considers three essential indicators of availability, quality, and performance. Overall equipment efficiency (OEE) has become the target KPI for most manufacturing companies.
This article presents the unique condition monitoring-based predictive maintenance framework incorporated into the modern world to create a machine learning-based predictive maintenance approach for automotive industries. We also provide insights into the various methods utilized for data acquisition for a condition-based predictive maintenance framework. The proposed framework has been validated by collecting the raw data from the water pump machine through sensors to preprocess and analyze the performance indicators. The equipment's remaining useful lifetime (RUL) was calculated based on the data points acquired in real-time by calculating the adjacent variation. The developed dashboard has allowed the visible monitoring of all possible anomalies and the remaining useful life of equipment while the machine runs in real-time.</p
... The recent advances in information and communication technologies (ICT) such as 5G networks have also facilitated the ultra-fast transmission of high-resolution data streams back to the stakeholders [4]. Besides 5G networks other cutting-edge digital technologies such as Big Data Analytics (BDA), and Artificial Intelligence (AI) attributed to the emergence of the big data streams, are increasingly becoming popular the last years, especially during Industry 4.0 [5,6]. ...
... For example, [3] recently constructed a comprehensive model of the U.S. power grid, based on the open-source smart grid profiles collected across the Internet, to investigate carbon emissions by 2030. State-ofthe-art machine learning models, including deep learning, reinforcement learning and generative networks, are also intensively explored to forecast load and renewable profiles [4], address grid disturbances [5] and defend against false injection attacks [6]. One key feature inherent in the big data analytics of smart grids is the natural separation of data by different dataholding parties. ...
During the last decades numerous innovations and inventions have been presented under the framework of Industry 4.0. The ultimate goal of the latest industrial revolution is the digitalization of modern manufacturing systems. Therefore, several techniques and technologies have been investigated by the academia and the industrial practitioners, such as Edge Computing. The above-mentioned paradigm adheres to the distributed computing paradigm, which is an analogous to the trend of decentralization of manufacturing systems. However, there are still several challenges to be addressed in the integration of such decentralized computing systems in real-life industries. Therefore, in this paper, the design and preliminary development of an Edge-computing platform is proposed, in order to distribute the computational load to the nodes and by extension to enable the utilization of machine learning techniques for the calculation of Remaining Useful Life (RUL) of critical machine tool components. Moreover, the proposed framework promotes the utilization of 5G cellular networks, in order to take advantage of the ultra-low latency and increased bandwidth offered by this technology.KeywordsSmart gridSociety 5.0Artificial intelligenceEdge computingFederated learning
... The contribution of the integration of edge computing technology in this case study was a reduction in data traffic and an improvement in the reliability of the communication between the edge layer and the cloud layer. An edge computing framework based on the utilization of microcomputers has been presented [47]. The contribution of this work is focused on the offloading of the cloud layer, thus enabling the minimization of simulation times and, by extension, the response time of the Digital Twin paradigm. ...
... The ultimate goal in the current case study is to increase the overall throughput of the system. Therefore, and according to [47,68,69], the "Larger is better" SNR is selected, as indicated in Equation (1): ...
In the era of digital transformation, industry is facing multiple challenges due to the need for implementation of the Industry 4.0 standards, as well as the volatility of customer demands. The latter has created the need for the design and operation of more complex manufacturing systems and networks. A case study derived from Process Industries (PIs) is adopted in this research work in order to design a framework for flexible design of production lines, automation of quality control points, and improvement of the performance of the manufacturing system. Therefore, a Digital Shadow of a production line is developed to collect, analyze and identify potential issues (bottlenecks). An edge computing system for reliable and low-latency communications is also implemented. The digital model is validated using statistical Design Of Experiments (DOE) and ANalysis Of VAriance (ANOVA). For the assessment of what-if scenarios, the Digital Shadow model will be used in order to evaluate and find the desired solution. Ultimately, the goal of this research work is to improve the design and performance of the industry’s production section, as well as to increase the production rate and the product mix.
... The work presented by [38] shows the benefits and capabilities of remote data acquisition and edge computing. Using the 5G cellular network, an edge computing platform, machine learning, and other specific techniques and protocols, this work presents a system capable of improving the equipment's predictive maintenance based on remote data acquisition from multiple sensors and devices. ...
The vehicle testing–validation phase is a crucial and demanding task in the automotive development process for vehicle manufacturers. It ensures the correct operation, safety, and efficiency of the vehicle. To meet this demand, some commercial solutions are available on the market, but they are usually expensive, have few connectivity options, and are PC-dependent. This paper presents an IoT-based intelligent low-cost system for vehicle data acquisition during on-road tests as an alternative solution. The system integrates low-cost acquisition hardware with an IoT server, collecting and transmitting data in near real-time, while artificial intelligence (AI) algorithms process the information and report errors and/or failures to the manufacturing engineers. The proposed solution was compared with other commercial systems in terms of features, performance, and cost. The results indicate that the proposed system delivers similar performance in terms of the data acquisition rate, but at a lower cost (up to 13 times cheaper) and with more advanced features, such as near real-time intelligent data processing and reduced time to find and correct errors or failures in the vehicle.
... For time-varying error control, Liu et al. [13] proposed a method of the time-varying error prediction and compensation for the movement axis of the CNC machine tool based on DT, to improve the accuracy stability of the hole pitch. For predictive maintenance, Qiao et al. [14] combined DT with a bi-directional gate recurrent unit for machining tool condition prediction; Luo et al. [21] proposed a hybrid predictive maintenance method of CNC machine tool driven by DT, which could fuse milling multi-domain model reflecting the actual operating conditions; Wei et al. [22] proposed a consistency retention method for CNC machine tool DT model, which could realize the update of DT model with the performance attenuation of the machine tool; Mourtzis, Angelopoulos, and Panopoulos [23] designed a edge-computing platform that promoted the utilization of 5G cellular networks for improving equipment predictive maintenance. ...
... Edge computing is an emerging computing infrastructure that bridges the gap between cloud and things by distributing edge nodes and providing storage resources close to end-users or devices, thus processing time-sensitive data near the data generation source at the network edge [24]. Edge computing brings several advantages for DT-based industrial intelligence, such as reduced latency, increased bandwidth, and improved data security [23,25]. MEC is a typical edge computing architecture that is characterized by ultra-low latency and high bandwidth as well as real-time access to radio network information that can be leveraged by applications, while providing a strong data security mechanism. ...
... AMP could be performed by an intelligent monitoring, simulation, prediction, optimization, and control strategy enabled by the edge-cloud collaborative DTMT swarm and its knowledge sharing mechanism, which could maximize the product quality and throughput, while reducing cost. In addition, the DTMT swarm could enhance MRO through the following three aspects: (1) The DTMT swarm could achieve the real-time machine tool condition monitoring based on the DT data; (2) Fault data/knowledge accumulated by one machine tool could be shared by another similar machine tool in the swarm, thus learning a more accurate and reliable fault diagnosis model for that machine tool; (3) The DTMT swarm could also be integrated with the augmented reality technology and predictive maintenance strategy [23] to achieve the intelligent maintenance decision-making and control. In the following sections, we mainly discuss technologies and implementation tools of the proposed framework for AMP. ...
Developing intelligent machine tools has been front and center for manufacturing enterprises to take a step towards intelligent manufacturing in Industry 4.0, which has attracted increasing attention from both academics and industry. Nevertheless, most current approaches focus on the construction of a single digital twin machine tool with limited intelligence due to the lack of data and knowledge accumulated by that machine tool for decision-making support. Consequently, this paper integrates digital twin with multi-access edge computing (MEC) and proposes a novel framework for the construction of a knowledge-sharing intelligent machine tool swarm that supports the secure knowledge sharing across the authorized machine tools in the swarm with ultra-low latency performance. Then, three key enabling methodologies of the framework are introduced from the perspective of digital twin machine tool swarm construction, knowledge-based cloud brain learning, and MEC-enhanced system deployment. Finally, a prototype system is implemented, where its application examples and evaluation experiments demonstrate the feasibility and effectiveness of the proposed approach.
