Pub Date : 2024-05-01DOI: 10.1109/IOTM.001.2300059
A. Abdellatif, K. Shaban, Ahmed Massoud
The future of electric grids is undergoing a remarkable transformation driven by the increasing adoption of emerging technologies, notably Artificial Intelligence (AI) and Blockchain. These innovative technologies are revolutionizing smart grid management by introducing novel approaches that enhance efficiency, reliability, and sustainability, all while securing information across distributed grid components. AI empowers predictive analytics and real-time optimization, while Blockchain ensures secure and transparent transactions, laying the foundation for a more resilient and adaptive electrical grid system. This article introduces a novel Secure, Distributed, and Collaborative Learning (SDCL) framework for the smart grid. The SDCL framework leverages advances in distributed learning and blockchain technologies to provide scalability, secure data exchange, and rapid response capabilities. The proposed architecture not only enables secure data and model exchange among different microgrids but also facilitates the integration of multiple microgrids and distributed network operators. This integration enables the correlation of unforeseen events and enhances the management and control of emerging failures. Our resilient, blockchain-based architecture optimizes information sharing and security levels within the blockchain, accommodating diverse requirements for smart grid services. Finally, we highlight the advantages of the proposed SDCL framework and outline future research directions that warrant further investigation.
{"title":"SDCL: A Framework for Secure, Distributed, and Collaborative Learning in Smart Grids","authors":"A. Abdellatif, K. Shaban, Ahmed Massoud","doi":"10.1109/IOTM.001.2300059","DOIUrl":"https://doi.org/10.1109/IOTM.001.2300059","url":null,"abstract":"The future of electric grids is undergoing a remarkable transformation driven by the increasing adoption of emerging technologies, notably Artificial Intelligence (AI) and Blockchain. These innovative technologies are revolutionizing smart grid management by introducing novel approaches that enhance efficiency, reliability, and sustainability, all while securing information across distributed grid components. AI empowers predictive analytics and real-time optimization, while Blockchain ensures secure and transparent transactions, laying the foundation for a more resilient and adaptive electrical grid system. This article introduces a novel Secure, Distributed, and Collaborative Learning (SDCL) framework for the smart grid. The SDCL framework leverages advances in distributed learning and blockchain technologies to provide scalability, secure data exchange, and rapid response capabilities. The proposed architecture not only enables secure data and model exchange among different microgrids but also facilitates the integration of multiple microgrids and distributed network operators. This integration enables the correlation of unforeseen events and enhances the management and control of emerging failures. Our resilient, blockchain-based architecture optimizes information sharing and security levels within the blockchain, accommodating diverse requirements for smart grid services. Finally, we highlight the advantages of the proposed SDCL framework and outline future research directions that warrant further investigation.","PeriodicalId":235472,"journal":{"name":"IEEE Internet of Things Magazine","volume":"4 26","pages":"84-90"},"PeriodicalIF":0.0,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141041949","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-01DOI: 10.1109/IOTM.001.2300262
Nour El-Houda Sayah Ben Aissa, C. A. Kerrache, Ahmed Korichi, Abderrahmane Lakas, Abdelkader Nasreddine Belkacem
Electroencephalogram (EEG) based brain computer interfaces (BCIs) have particularly benefited from deep learning models thanks to their remarkable performance for classification purposes. Despite their success, these models have shown to be vulnerable to adversarial attacks, which are attacks that manipulate EEG signals to cause misclassification. Adversarial training, where models are trained on both normal and adversarial examples, has been proposed to address this issue. However, overfitting on adversarial examples can lead to reduced performance. To overcome this challenge, we present a new approach of adversarial training based on a generative adversarial network (GAN). In particular, we first generate real adversarial examples using fast gradient sign method, Then, Our GAN generates new adversarial EEG signals using real adversarial examples as a validation set. By incorporating both real and generated adversarial examples during training, we enhance the EEG model performance. Finally, we evaluate our approach on BCI competition 2a dataset showing that it achieves a statistically significant performance improvement and enhances the robustness to adversarial attacks.
{"title":"Enhancing EEG Signal Classifier Robustness Against Adversarial Attacks Using a Generative Adversarial Network Approach","authors":"Nour El-Houda Sayah Ben Aissa, C. A. Kerrache, Ahmed Korichi, Abderrahmane Lakas, Abdelkader Nasreddine Belkacem","doi":"10.1109/IOTM.001.2300262","DOIUrl":"https://doi.org/10.1109/IOTM.001.2300262","url":null,"abstract":"Electroencephalogram (EEG) based brain computer interfaces (BCIs) have particularly benefited from deep learning models thanks to their remarkable performance for classification purposes. Despite their success, these models have shown to be vulnerable to adversarial attacks, which are attacks that manipulate EEG signals to cause misclassification. Adversarial training, where models are trained on both normal and adversarial examples, has been proposed to address this issue. However, overfitting on adversarial examples can lead to reduced performance. To overcome this challenge, we present a new approach of adversarial training based on a generative adversarial network (GAN). In particular, we first generate real adversarial examples using fast gradient sign method, Then, Our GAN generates new adversarial EEG signals using real adversarial examples as a validation set. By incorporating both real and generated adversarial examples during training, we enhance the EEG model performance. Finally, we evaluate our approach on BCI competition 2a dataset showing that it achieves a statistically significant performance improvement and enhances the robustness to adversarial attacks.","PeriodicalId":235472,"journal":{"name":"IEEE Internet of Things Magazine","volume":"20 23","pages":"44-49"},"PeriodicalIF":0.0,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141048765","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-01DOI: 10.1109/miot.2024.10517514
{"title":"IEEE App","authors":"","doi":"10.1109/miot.2024.10517514","DOIUrl":"https://doi.org/10.1109/miot.2024.10517514","url":null,"abstract":"","PeriodicalId":235472,"journal":{"name":"IEEE Internet of Things Magazine","volume":"2 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141029464","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-01DOI: 10.1109/miot.2024.10397566
{"title":"Cover 3","authors":"","doi":"10.1109/miot.2024.10397566","DOIUrl":"https://doi.org/10.1109/miot.2024.10397566","url":null,"abstract":"","PeriodicalId":235472,"journal":{"name":"IEEE Internet of Things Magazine","volume":"29 25","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139456549","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-01DOI: 10.1109/IOTM.001.2300111
Min Wu, K. Guo, Xingwang Li, Ali Nauman, Kang An, Ji Wang
Satellite networks have been emerged as a critical part of the next-generation wireless networks. However, the high transmission latency, highly dynamic channel conditions and energy resource constraints of Internet of Things (IoT) devices pose a challenge to performance improvements. To tackle above issues, technologies such as integrated satellite-unmanned aerial vehicle-terrestrial networks (IS-UAV-TNs), deep reinforcement learning (DRL), reconfigurable intelligent surface (RIS) are highly anticipated in 6G IoT. In this article, we consider the application of RIS to IS-UAV-TNs to reshape wireless channels by controlling the phase shift of the scattering elements. The dynamic configuration of the RIS reflection unit poses a high-dimensional problem, making beamforming optimization challenging. We focus on discussing the optimization method of integrating DRL in RIS-assisted IS-UAV-TNs, which offers flexibility in scenarios where precise channel state information (CSI) is unknown. To illustrate the advantage of the DRL framework in RIS-assisted IS-UAV-TNs, we design a representative communication scenario, where the results are provided according to the considered scenario. Finally, potential future research directions and challenges are presented.
{"title":"Optimization Design in RIS-Assisted Integrated Satellite-UAV-Served 6G IoT: A Deep Reinforcement Learning Approach","authors":"Min Wu, K. Guo, Xingwang Li, Ali Nauman, Kang An, Ji Wang","doi":"10.1109/IOTM.001.2300111","DOIUrl":"https://doi.org/10.1109/IOTM.001.2300111","url":null,"abstract":"Satellite networks have been emerged as a critical part of the next-generation wireless networks. However, the high transmission latency, highly dynamic channel conditions and energy resource constraints of Internet of Things (IoT) devices pose a challenge to performance improvements. To tackle above issues, technologies such as integrated satellite-unmanned aerial vehicle-terrestrial networks (IS-UAV-TNs), deep reinforcement learning (DRL), reconfigurable intelligent surface (RIS) are highly anticipated in 6G IoT. In this article, we consider the application of RIS to IS-UAV-TNs to reshape wireless channels by controlling the phase shift of the scattering elements. The dynamic configuration of the RIS reflection unit poses a high-dimensional problem, making beamforming optimization challenging. We focus on discussing the optimization method of integrating DRL in RIS-assisted IS-UAV-TNs, which offers flexibility in scenarios where precise channel state information (CSI) is unknown. To illustrate the advantage of the DRL framework in RIS-assisted IS-UAV-TNs, we design a representative communication scenario, where the results are provided according to the considered scenario. Finally, potential future research directions and challenges are presented.","PeriodicalId":235472,"journal":{"name":"IEEE Internet of Things Magazine","volume":"4 1","pages":"12-18"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139457794","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-01DOI: 10.1109/IOTM.001.2300028
Ihsan Ali, Hasniuj Zahan, Spyridon Mastorakis
In recent years, Wireless Sensor Networks (WSNs) have been used in many important areas, including weather forecasting, security, environmental monitoring, health care, and industry. However, the constraints of WSNs are in terms of energy, processing, connectivity, computation, and data integrity. The efficient administration of the enormous volumes of data generated by WSNs is a key concern in this study area. As a result, robust and scalable high-performance computing and storage infrastructures are} absolutely necessary for the processing and storing of WSN data in real-time. Combining WSNs and cloud computing to create sensor clouds can address this issue. In this article, we investigate, highlight, and report {data collection techniques, aiming to highlight the significance of sensor clouds. In this context, a comprehensive overview of WSNs and sensor cloud platforms are also provided. This article covers their definitions, architectures, and applications by categorizing and classifying data collection methods in WSNs and sensor clouds. Key research challenges for future work and use cases in this research domain are also discussed.
{"title":"Sensor Clouds: Recent Advancements, Use Cases and Open Challenges","authors":"Ihsan Ali, Hasniuj Zahan, Spyridon Mastorakis","doi":"10.1109/IOTM.001.2300028","DOIUrl":"https://doi.org/10.1109/IOTM.001.2300028","url":null,"abstract":"In recent years, Wireless Sensor Networks (WSNs) have been used in many important areas, including weather forecasting, security, environmental monitoring, health care, and industry. However, the constraints of WSNs are in terms of energy, processing, connectivity, computation, and data integrity. The efficient administration of the enormous volumes of data generated by WSNs is a key concern in this study area. As a result, robust and scalable high-performance computing and storage infrastructures are} absolutely necessary for the processing and storing of WSN data in real-time. Combining WSNs and cloud computing to create sensor clouds can address this issue. In this article, we investigate, highlight, and report {data collection techniques, aiming to highlight the significance of sensor clouds. In this context, a comprehensive overview of WSNs and sensor cloud platforms are also provided. This article covers their definitions, architectures, and applications by categorizing and classifying data collection methods in WSNs and sensor clouds. Key research challenges for future work and use cases in this research domain are also discussed.","PeriodicalId":235472,"journal":{"name":"IEEE Internet of Things Magazine","volume":"112 9","pages":"98-103"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139454181","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-01DOI: 10.1109/IOTM.001.2300112
Pau Ferrer-Cid, J.A. Paredes-Ahumada, Xhensilda Allka, Manel Guerrero-Zapata, J. Barceló-Ordinas, J. García-Vidal
In this article, we present our research vision of a framework for obtaining quality data in air quality monitoring networks using low-cost sensors (LCSs). The use of LCS networks is gaining increasing acceptance in many IoT air quality applications. However, data quality and reliability issues are a major barrier to widespread adoption, which means that the pre-processing tasks that are critical to achieving the required levels of data quality are crucial aspects of LCS network designs. The proposed framework takes advantage of a layered architecture, which has also proven useful in other fields, and from which we show the challenges and state-of-the-art techniques for obtaining quality data. In addition, we show its usefulness in application cases, including a real case with data measured by a LCS deployment measuring O3 in the area of Barcelona, Spain.
{"title":"A Data-Driven Framework for Air Quality Sensor Networks","authors":"Pau Ferrer-Cid, J.A. Paredes-Ahumada, Xhensilda Allka, Manel Guerrero-Zapata, J. Barceló-Ordinas, J. García-Vidal","doi":"10.1109/IOTM.001.2300112","DOIUrl":"https://doi.org/10.1109/IOTM.001.2300112","url":null,"abstract":"In this article, we present our research vision of a framework for obtaining quality data in air quality monitoring networks using low-cost sensors (LCSs). The use of LCS networks is gaining increasing acceptance in many IoT air quality applications. However, data quality and reliability issues are a major barrier to widespread adoption, which means that the pre-processing tasks that are critical to achieving the required levels of data quality are crucial aspects of LCS network designs. The proposed framework takes advantage of a layered architecture, which has also proven useful in other fields, and from which we show the challenges and state-of-the-art techniques for obtaining quality data. In addition, we show its usefulness in application cases, including a real case with data measured by a LCS deployment measuring O3 in the area of Barcelona, Spain.","PeriodicalId":235472,"journal":{"name":"IEEE Internet of Things Magazine","volume":"22 10","pages":"128-134"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139455818","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-01DOI: 10.1109/IOTM.001.2300092
Jiancong Zhang, Shining Li
Blockchain-empowered federated learning is a promising learning framework, which mitigates several potential security threats in learning. However, in the Internet of Vehicles, the asynchronous network puts higher requirements on blockchains. Specifically, due to the asynchronous transaction updates, traditional consensus mechanisms require nodes to frequently coordinate to reach a consensus on the global order of transactions. This strong consistency brings excessive computing time and low efficiency to federated learning. Existing solutions completely relax the consistency of transactions, which, however, reduces the persistence and traceability. Therefore, we propose a lightweight permissioned blockchain with partial consensus, which reduce the coordination among nodes to reduce the system overhead. First, we run the consensus of transactions for global models and relax the strong consistency for local models, which are stored in parallel in real-time without coordination among nodes. Accordingly, we provide relative persistence to ensure the traceability of local models. Then, due to the orderless transactions, we use smart contracts, instead of time stamps, to control the staleness weight of local models in aggregation to reduce the vulnerability. Experimental results show that our scheme effectively improves the performance of blockchain-empowered systems and overcomes the challenges of asynchrony to the security of vehicular networks.
{"title":"Blockchain-Empowered Vehicular Intelligence: A Perspective of Asynchronous Federated Learning","authors":"Jiancong Zhang, Shining Li","doi":"10.1109/IOTM.001.2300092","DOIUrl":"https://doi.org/10.1109/IOTM.001.2300092","url":null,"abstract":"Blockchain-empowered federated learning is a promising learning framework, which mitigates several potential security threats in learning. However, in the Internet of Vehicles, the asynchronous network puts higher requirements on blockchains. Specifically, due to the asynchronous transaction updates, traditional consensus mechanisms require nodes to frequently coordinate to reach a consensus on the global order of transactions. This strong consistency brings excessive computing time and low efficiency to federated learning. Existing solutions completely relax the consistency of transactions, which, however, reduces the persistence and traceability. Therefore, we propose a lightweight permissioned blockchain with partial consensus, which reduce the coordination among nodes to reduce the system overhead. First, we run the consensus of transactions for global models and relax the strong consistency for local models, which are stored in parallel in real-time without coordination among nodes. Accordingly, we provide relative persistence to ensure the traceability of local models. Then, due to the orderless transactions, we use smart contracts, instead of time stamps, to control the staleness weight of local models in aggregation to reduce the vulnerability. Experimental results show that our scheme effectively improves the performance of blockchain-empowered systems and overcomes the challenges of asynchrony to the security of vehicular networks.","PeriodicalId":235472,"journal":{"name":"IEEE Internet of Things Magazine","volume":"4 3","pages":"74-80"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139458391","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-01DOI: 10.1109/IOTM.001.2300048
Aviral Shrivastava, M. Khayatian, Bob Iannucci
Time has become an essential aspect of many computing systems where temporal correctness is as important as functional correctness. Autonomous vehicles, Industry 4.0, and smart grids are a few examples of time-sensitive systems. As time-sensitive applications become large, complex, and distributed, traditional methods fall short of achieving the desired orchestration among components. In this vision article, we first propose a standard to maintain an accurate notion of time among all components of the system, i.e., sensors, computing platforms, and actuators. Then, we propose explicit-time state estimation and closed-loop control algorithms that can tolerate large delays while achieving reasonable performance, and an integrated fail-safe mechanism that achieves a high level of robustness when timing failures happen.
{"title":"Design Methodology for Robust, Distributed Time-Sensitive Applications","authors":"Aviral Shrivastava, M. Khayatian, Bob Iannucci","doi":"10.1109/IOTM.001.2300048","DOIUrl":"https://doi.org/10.1109/IOTM.001.2300048","url":null,"abstract":"Time has become an essential aspect of many computing systems where temporal correctness is as important as functional correctness. Autonomous vehicles, Industry 4.0, and smart grids are a few examples of time-sensitive systems. As time-sensitive applications become large, complex, and distributed, traditional methods fall short of achieving the desired orchestration among components. In this vision article, we first propose a standard to maintain an accurate notion of time among all components of the system, i.e., sensors, computing platforms, and actuators. Then, we propose explicit-time state estimation and closed-loop control algorithms that can tolerate large delays while achieving reasonable performance, and an integrated fail-safe mechanism that achieves a high level of robustness when timing failures happen.","PeriodicalId":235472,"journal":{"name":"IEEE Internet of Things Magazine","volume":"52 12","pages":"104-110"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139454775","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-01DOI: 10.1109/miot.2024.10397592
{"title":"IEEE Foundation","authors":"","doi":"10.1109/miot.2024.10397592","DOIUrl":"https://doi.org/10.1109/miot.2024.10397592","url":null,"abstract":"","PeriodicalId":235472,"journal":{"name":"IEEE Internet of Things Magazine","volume":"8 7","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139457207","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：