sensors-logo

Journal Browser

Journal Browser

Performance, Simulation and Modelling of Sensors Networks in the Context of IoT, Edge Computing, and AI

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Sensor Networks".

Deadline for manuscript submissions: closed (30 June 2023) | Viewed by 28032

Special Issue Editors

Department of Software and Information Technology Engineering, École de technologie supérieure, Montreal, QC H3C 1K3, Canada
Interests: IoT; sensor networks; virtualization; resource allocation; optimization algorithms; network management and orchestration; wireless communications
Special Issues, Collections and Topics in MDPI journals
Department of Informatics, Ionian University, 49100 Corfu, Greece
Interests: cognitive radio networks; cross-layer design; delay-tolerant networks; malware propagation modeling; network science and complex networks; queuing theory; resource allocation; topology control
Special Issues, Collections and Topics in MDPI journals
Department of Electrical and Computer Engineering, National Technical University of Athens, 15780 Athens, Greece
Interests: software-defined networks; cognitive radio networks; IoT; big data; social network analysis; recommender systems
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

The Internet of Things (IoT) is gaining considerable momentum. Even though the term was captured the previous decade and actual implementations of IoT did not start for some years later, we are already currently living in the fourth industrial revolution. The core component of this revolution are sensor networks and the data they generate. As the cost of sensors and actuators is decreasing and data analysis can render the applications more intelligent, the IoT thrives.

However, as often happens with every new technology (much more with every new revolution), there are a number of challenges to be resolved. Sensor nodes are characterized as low-power and constrained nodes that cannot cope with the increasing requirements of emerging applications. Recent trends of repositioning computational resources closer to the user have generated the notion of edge computing, yet Edge resources are much scarcer than traditional cloud resources and need finer scheduling and allocation techniques. Furthermore, IoT access networks can be very dynamic and unreliable, creating an unstable communication that needs to be predicted to ensure a smooth end-to-end communication environment. Artificial Intelligence can be deemed a viable solution if combined with sensor networks and can facilitate the scheduling of a spectrum, or classify sensor/IoT applications according to their traffic characteristics. Finally, one other obvious challenge is scalability. With the evolution of the IoT and the advent of 5G and massive machine-type communications, highly dense networks are expected to be created, stressing even more the available infrastructure.

To this end, this Special Issue is soliciting conceptual, theoretical, and experimental contributions to a set of currently unresolved challenges in the area of sensor networks, IoT, Edge Computing, and AI. The topics of interest include but are not limited to:

  • Resource allocation and scheduling in sensor networks;
  • Optimization algorithms for virtual sensor networks;
  • Network routing in sensor networks;
  • Resource allocation for an IoT/edge interplay;
  • Management and orchestration of sensors networks through edge;
  • Scalability issues in sensor networks/the IoT;
  • Security issues in sensor networks;
  • Data analytics, traffic analysis, and classification in the IoT and sensor networks;
  • AI for QoS management in sensor networks;
  • Energy sustained development in the IoT/edge;
  • Performance analysis and modeling in the context of AI, sensor networks, and edge;
  • Sensor network monitoring;
  • Applications of sensor networks and performance evaluation in agriculture and/or aquaculture;
  • 5G architectures and trials in agriculture and/or aquaculture;
  • Sensing and performance evaluation for autonomous and remote driving;
  • Resource orchestration at the network edge;
  • Virtual network embedding at the network edge;
  • Testbeds and experimental facilities reports;
  • Business and techno-economics opportunities.

Dr. Aris Leivadeas
Dr. Vasileios Karyotis
Dr. Dimitrios Dechouniotis
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Published Papers (10 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Jump to: Review

34 pages, 24941 KiB  
Article
WiCHORD+: A Scalable, Sustainable, and P2P Chord-Based Ecosystem for Smart Agriculture Applications
by Christos-Panagiotis Balatsouras, Aristeidis Karras, Christos Karras, Ioannis Karydis and Spyros Sioutas
Sensors 2023, 23(23), 9486; https://0-doi-org.brum.beds.ac.uk/10.3390/s23239486 - 28 Nov 2023
Viewed by 1347
Abstract
In the evolving landscape of Industry 4.0, the convergence of peer-to-peer (P2P) systems, LoRa-enabled wireless sensor networks (WSNs), and distributed hash tables (DHTs) represents a major advancement that enhances sustainability in the modern agriculture framework and its applications. In this study, we propose [...] Read more.
In the evolving landscape of Industry 4.0, the convergence of peer-to-peer (P2P) systems, LoRa-enabled wireless sensor networks (WSNs), and distributed hash tables (DHTs) represents a major advancement that enhances sustainability in the modern agriculture framework and its applications. In this study, we propose a P2P Chord-based ecosystem for sustainable and smart agriculture applications, inspired by the inner workings of the Chord protocol. The node-centric approach of WiCHORD+ is a standout feature, streamlining operations in WSNs and leading to more energy-efficient and straightforward system interactions. Instead of traditional key-centric methods, WiCHORD+ is a node-centric protocol that is compatible with the inherent characteristics of WSNs. This unique design integrates seamlessly with distributed hash tables (DHTs), providing an efficient mechanism to locate nodes and ensure robust data retrieval while reducing energy consumption. Additionally, by utilizing the MAC address of each node in data routing, WiCHORD+ offers a more direct and efficient data lookup mechanism, essential for the timely and energy-efficient operation of WSNs. While the increasing dependence of smart agriculture on cloud computing environments for data storage and machine learning techniques for real-time prediction and analytics continues, frameworks like the proposed WiCHORD+ appear promising for future IoT applications due to their compatibility with modern devices and peripherals. Ultimately, the proposed approach aims to effectively incorporate LoRa, WSNs, DHTs, cloud computing, and machine learning, by providing practical solutions to the ongoing challenges in the current smart agriculture landscape and IoT applications. Full article
Show Figures

Figure 1

18 pages, 1778 KiB  
Article
Case Studies with the Contiki-NG Simulator to Design Strategies for Sensors’ Communication Optimization in an IoT-Fog Ecosystem
by Antonio Marcos Almeida Ferreira, Leonildo José de Melo de Azevedo, Júlio Cezar Estrella and Alexandre Cláudio Botazzo Delbem
Sensors 2023, 23(4), 2300; https://0-doi-org.brum.beds.ac.uk/10.3390/s23042300 - 18 Feb 2023
Cited by 3 | Viewed by 1648
Abstract
With the development of mobile communications and the Internet of Things (IoT), IoT devices have increased, allowing their application in numerous areas of Industry 4.0. Applications on IoT devices are time sensitive and require a low response time, making reducing latency in IoT [...] Read more.
With the development of mobile communications and the Internet of Things (IoT), IoT devices have increased, allowing their application in numerous areas of Industry 4.0. Applications on IoT devices are time sensitive and require a low response time, making reducing latency in IoT networks an essential task. However, it needs to be emphasized that data production and consumption are interdependent, so when designing the implementation of a fog network, it is crucial to consider criteria other than latency. Defining the strategy to deploy these nodes based on different criteria and sub-criteria is a challenging optimization problem, as the amount of possibilities is immense. This work aims to simulate a hybrid network of sensors related to public transport in the city of São Carlos - SP using Contiki-NG to select the most suitable place to deploy an IoT sensor network. Performance tests were carried out on five analyzed scenarios, and we collected the transmitted data based on criteria corresponding to devices, applications, and network communication on which we applied Multiple Attribute Decision Making (MADM) algorithms to generate a multicriteria decision ranking. The results show that based on the TOPSIS and VIKOR decision-making algorithms, scenario four is the most viable among those analyzed. This approach makes it feasible to optimally select the best option among different possibilities. Full article
Show Figures

Figure 1

19 pages, 2651 KiB  
Article
Performance Analysis of Turbo Codes, LDPC Codes, and Polar Codes over an AWGN Channel in the Presence of Inter Symbol Interference
by Adriana-Maria Cuc, Florin Lucian Morgoș and Cristian Grava
Sensors 2023, 23(4), 1942; https://0-doi-org.brum.beds.ac.uk/10.3390/s23041942 - 09 Feb 2023
Cited by 2 | Viewed by 2352
Abstract
This paper discusses the results of simulations relating to the performances of turbo codes, low density parity check (LDPC) codes, and polar codes over an additive white Gaussian noise (AWGN) channel in the presence of inter symbol interference, denoting the disturbances that altered [...] Read more.
This paper discusses the results of simulations relating to the performances of turbo codes, low density parity check (LDPC) codes, and polar codes over an additive white Gaussian noise (AWGN) channel in the presence of inter symbol interference, denoting the disturbances that altered the original signal. To eliminate the negative effects of inter symbol interference (ISI), an equalizer was used at the level of the receiver. Practically, two types of equalizers were used: zero forcing (ZF) and minimum mean square error (MMSE), considering the case of perfect channel estimation and the case of estimation using the least square algorithm. The performance measure used was the modification of the bit error rate compared to a given signal to noise ratio; in this sense, the MMSE equalizer offered a higher performance than the ZF equalizer. The aspect of channel equalization considered here is not novel, but there have been very few works that dealt with equalization in the context of the use of turbo codes, especially LDPC codes and polar codes for channel coding. In this respect, this research can be considered a contribution to the field of digital communications. Full article
Show Figures

Figure 1

25 pages, 2586 KiB  
Article
Enabling Artificial Intelligent Virtual Sensors in an IoT Environment
by Georgios Stavropoulos, John Violos, Stylianos Tsanakas and Aris Leivadeas
Sensors 2023, 23(3), 1328; https://0-doi-org.brum.beds.ac.uk/10.3390/s23031328 - 24 Jan 2023
Cited by 5 | Viewed by 2616
Abstract
The demands for a large number of sensors increase as the proliferation of Internet of Things (IoT) and smart cities applications are continuing at a rapid pace. This also increases the cost of the infrastructure and the installation and maintenance overhead and creates [...] Read more.
The demands for a large number of sensors increase as the proliferation of Internet of Things (IoT) and smart cities applications are continuing at a rapid pace. This also increases the cost of the infrastructure and the installation and maintenance overhead and creates significant performance degradation in the end-to-end communication, monitoring, and orchestration of the various connected devices. In order to solve the problem of increasing sensor demands, this paper suggests replacing physical sensors with machine learning (ML) models. These software-based artificial intelligence models are called virtual sensors. Extensive research and simulation comparisons between fourteen ML models provide a solid ground decision when it comes to the selection of the most accurate model to replace physical sensors, such as temperature and humidity sensors. In this problem at hand, the virtual and physical sensors are designed to be scattered in a smart home, while being connected and run on the same IoT platform. Thus, this paper also introduces a custom lightweight IoT platform that runs on a Raspberry Pi equipped with physical temperature and humidity sensors, which may also execute the virtual sensors. The evaluation results of the devised virtual sensors in a smart home scenario are promising and corroborate the applicability of the proposed methodology. Full article
Show Figures

Figure 1

14 pages, 544 KiB  
Article
IoT Clusters for Enhancing Multimedia Applications
by Jorge Coelho and Luís Nogueira
Sensors 2022, 22(23), 9077; https://0-doi-org.brum.beds.ac.uk/10.3390/s22239077 - 23 Nov 2022
Viewed by 992
Abstract
In this paper, we present a framework for exploring the spare capacity of IoT devices for clustered execution of multimedia applications. Applications of this type are usually framed with specific quality parameters that enable a desirable level of service. This means that the [...] Read more.
In this paper, we present a framework for exploring the spare capacity of IoT devices for clustered execution of multimedia applications. Applications of this type are usually framed with specific quality parameters that enable a desirable level of service. This means that the IoT cluster must guarantee strict quality ranges of service to work as expected. The framework is totally customizable, and QoS dimensions can be easily added or removed given their relevance in the application scenario. The achieved results clearly demonstrate the utility of using the spare capacity of IoT devices, otherwise unused, to cooperatively execute servies within the desired quality of service levels. Full article
Show Figures

Figure 1

23 pages, 575 KiB  
Article
A Probability-Based Models Ranking Approach: An Alternative Method of Machine-Learning Model Performance Assessment
by Stanisław Gajda and Marcin Chlebus
Sensors 2022, 22(17), 6361; https://0-doi-org.brum.beds.ac.uk/10.3390/s22176361 - 24 Aug 2022
Cited by 2 | Viewed by 1667
Abstract
Performance measures are crucial in selecting the best machine learning model for a given problem. Estimating classical model performance measures by subsampling methods like bagging or cross-validation has several weaknesses. The most important ones are the inability to test the significance of the [...] Read more.
Performance measures are crucial in selecting the best machine learning model for a given problem. Estimating classical model performance measures by subsampling methods like bagging or cross-validation has several weaknesses. The most important ones are the inability to test the significance of the difference, and the lack of interpretability. Recently proposed Elo-based Predictive Power (EPP)—a meta-measure of machine learning model performance, is an attempt to address these weaknesses. However, the EPP is based on wrong assumptions, so its estimates may not be correct. This paper introduces the Probability-based Ranking Model Approach (PMRA), which is a modified EPP approach with a correction that makes its estimates more reliable. PMRA is based on the calculation of the probability that one model achieves a better result than another one, using the Mixed Effects Logistic Regression model. The empirical analysis was carried out on a real mortgage credits dataset. The analysis included a comparison of how the PMRA and state-of-the-art k-fold cross-validation ranked the 49 machine learning models, an example application of a novel method in hyperparameters tuning problem, and a comparison of PMRA and EPP indications. PMRA gives the opportunity to compare a newly developed algorithm to state-of-the-art algorithms based on statistical criteria. It is the solution to select the best hyperparameters configuration and to formulate criteria for the continuation of the hyperparameters space search. Full article
Show Figures

Figure 1

28 pages, 1843 KiB  
Article
Performance Evaluation Analysis of Spark Streaming Backpressure for Data-Intensive Pipelines
by Kassiano J. Matteussi, Julio C. S. dos Anjos, Valderi R. Q. Leithardt and Claudio F. R. Geyer
Sensors 2022, 22(13), 4756; https://0-doi-org.brum.beds.ac.uk/10.3390/s22134756 - 23 Jun 2022
Cited by 4 | Viewed by 1811
Abstract
A significant rise in the adoption of streaming applications has changed the decision-making processes in the last decade. This movement has led to the emergence of several Big Data technologies for in-memory processing, such as the systems Apache Storm, Spark, Heron, Samza, Flink, [...] Read more.
A significant rise in the adoption of streaming applications has changed the decision-making processes in the last decade. This movement has led to the emergence of several Big Data technologies for in-memory processing, such as the systems Apache Storm, Spark, Heron, Samza, Flink, and others. Spark Streaming, a widespread open-source implementation, processes data-intensive applications that often require large amounts of memory. However, Spark Unified Memory Manager cannot properly manage sudden or intensive data surges and their related in-memory caching needs, resulting in performance and throughput degradation, high latency, a large number of garbage collection operations, out-of-memory issues, and data loss. This work presents a comprehensive performance evaluation of Spark Streaming backpressure to investigate the hypothesis that it could support data-intensive pipelines under specific pressure requirements. The results reveal that backpressure is suitable only for small and medium pipelines for stateless and stateful applications. Furthermore, it points out the Spark Streaming limitations that lead to in-memory-based issues for data-intensive pipelines and stateful applications. In addition, the work indicates potential solutions. Full article
Show Figures

Figure 1

29 pages, 2842 KiB  
Article
ENERDGE: Distributed Energy-Aware Resource Allocation at the Edge
by Marios Avgeris, Dimitrios Spatharakis, Dimitrios Dechouniotis, Aris Leivadeas, Vasileios Karyotis and Symeon Papavassiliou
Sensors 2022, 22(2), 660; https://0-doi-org.brum.beds.ac.uk/10.3390/s22020660 - 15 Jan 2022
Cited by 16 | Viewed by 2340
Abstract
Mobile applications are progressively becoming more sophisticated and complex, increasing their computational requirements. Traditional offloading approaches that use exclusively the Cloud infrastructure are now deemed unsuitable due to the inherent associated delay. Edge Computing can address most of the Cloud limitations at the [...] Read more.
Mobile applications are progressively becoming more sophisticated and complex, increasing their computational requirements. Traditional offloading approaches that use exclusively the Cloud infrastructure are now deemed unsuitable due to the inherent associated delay. Edge Computing can address most of the Cloud limitations at the cost of limited available resources. This bottleneck necessitates an efficient allocation of offloaded tasks from the mobile devices to the Edge. In this paper, we consider a task offloading setting with applications of different characteristics and requirements, and propose an optimal resource allocation framework leveraging the amalgamation of the edge resources. To balance the trade-off between retaining low total energy consumption, respecting end-to-end delay requirements and load balancing at the Edge, we additionally introduce a Markov Random Field based mechanism for the distribution of the excess workload. The proposed approach investigates a realistic scenario, including different categories of mobile applications, edge devices with different computational capabilities, and dynamic wireless conditions modeled by the dynamic behavior and mobility of the users. The framework is complemented with a prediction mechanism that facilitates the orchestration of the physical resources. The efficiency of the proposed scheme is evaluated via modeling and simulation and is shown to outperform a well-known task offloading solution, as well as a more recent one. Full article
Show Figures

Figure 1

22 pages, 2867 KiB  
Article
Design Space Exploration of a Multi-Model AI-Based Indoor Localization System
by Konstantinos Kotrotsios, Anastasios Fanariotis, Helen-Catherine Leligou and Theofanis Orphanoudakis
Sensors 2022, 22(2), 570; https://0-doi-org.brum.beds.ac.uk/10.3390/s22020570 - 12 Jan 2022
Cited by 6 | Viewed by 1977
Abstract
In this paper, we present the results of a performance evaluation and optimization process of an indoor positioning system (IPS) designed to operate on portable as well as miniaturized embedded systems. The proposed method uses the Received Signal Strength Indicator (RSSI) values from [...] Read more.
In this paper, we present the results of a performance evaluation and optimization process of an indoor positioning system (IPS) designed to operate on portable as well as miniaturized embedded systems. The proposed method uses the Received Signal Strength Indicator (RSSI) values from multiple Bluetooth Low-Energy (BLE) beacons scattered around interior spaces. The beacon signals were received from the user devices and processed through an RSSI filter and a group of machine learning (ML) models, in an arrangement of one model per detected node. Finally, a multilateration problem was solved using as an input the inferred distances from the advertising nodes and returning the final position approximation. In this work, we first presented the evaluation of different ML models for inferring the distance between the devices and the installed beacons by applying different optimization algorithms. Then, we presented model reduction methods to implement the optimized algorithm on the embedded system by appropriately adapting it to its constraint resources and compared the results, demonstrating the efficiency of the proposed method. Full article
Show Figures

Figure 1

Review

Jump to: Research

25 pages, 1370 KiB  
Review
Performance Measurement System and Quality Management in Data-Driven Industry 4.0: A Review
by Parkash Tambare, Chandrashekhar Meshram, Cheng-Chi Lee, Rakesh Jagdish Ramteke and Agbotiname Lucky Imoize
Sensors 2022, 22(1), 224; https://0-doi-org.brum.beds.ac.uk/10.3390/s22010224 - 29 Dec 2021
Cited by 39 | Viewed by 9781
Abstract
The birth of mass production started in the early 1900s. The manufacturing industries were transformed from mechanization to digitalization with the help of Information and Communication Technology (ICT). Now, the advancement of ICT and the Internet of Things has enabled smart manufacturing or [...] Read more.
The birth of mass production started in the early 1900s. The manufacturing industries were transformed from mechanization to digitalization with the help of Information and Communication Technology (ICT). Now, the advancement of ICT and the Internet of Things has enabled smart manufacturing or Industry 4.0. Industry 4.0 refers to the various technologies that are transforming the way we work in manufacturing industries such as Internet of Things, cloud, big data, AI, robotics, blockchain, autonomous vehicles, enterprise software, etc. Additionally, the Industry 4.0 concept refers to new production patterns involving new technologies, manufacturing factors, and workforce organization. It changes the production process and creates a highly efficient production system that reduces production costs and improves product quality. The concept of Industry 4.0 is relatively new; there is high uncertainty, lack of knowledge and limited publication about the performance measurement and quality management with respect to Industry 4.0. Conversely, manufacturing companies are still struggling to understand the variety of Industry 4.0 technologies. Industrial standards are used to measure performance and manage the quality of the product and services. In order to fill this gap, our study focuses on how the manufacturing industries use different industrial standards to measure performance and manage the quality of the product and services. This paper reviews the current methods, industrial standards, key performance indicators (KPIs) used for performance measurement systems in data-driven Industry 4.0, and the case studies to understand how smart manufacturing companies are taking advantage of Industry 4.0. Furthermore, this article discusses the digitalization of quality called Quality 4.0, research challenges and opportunities in data-driven Industry 4.0 are discussed. Full article
Show Figures

Figure 1

Back to TopTop