The very new evolution towards 6G networks necessitates a paradigm shift towards unified 3D network architectures, encompassing space, air, and ground segments. This paper outlines the conceptualization, challenges, and prospects of such a transformative architecture. We outline the foundational principles, drawn from standardization endeavors and cutting-edge research initiatives, to articulate the envisioned architecture poised to redefine network capabilities. Driven by the need to enhance capacity, increase data rates, support diverse mobility models, and facilitate heterogeneous connectivity, the conceptual framework of a unified 3D network is presented. The focus is on seamlessly integrating diverse network segments and fostering holistic network orchestration. In examining the technical challenges inherent to the realization of a unified 3D network, we outline our strategies to address mobility management, handover optimization, interference mitigation, and the integration of distributed physical layer concepts. Proposals encompass federated learning mechanisms, advanced beamforming techniques, and energy-efficient computational offloading strategies, aimed at enhancing network performance and resilience. Moreover, we outline compelling utilization scenarios and highlighted promising avenues for future research.
{"title":"Unified 3D Networks: Architecture, Challenges, Recent Results, and Future Opportunities","authors":"Mohamed Rihan;Dirk Wübben;Abhipshito Bhattacharya;Marina Petrova;Xiaopeng Yuan;Anke Schmeink;Amina Fellan;Shreya Tayade;Mervat Zarour;Daniel Lindenschmitt;Hans Schotten;Armin Dekorsy","doi":"10.1109/OJVT.2024.3508026","DOIUrl":"https://doi.org/10.1109/OJVT.2024.3508026","url":null,"abstract":"The very new evolution towards 6G networks necessitates a paradigm shift towards unified 3D network architectures, encompassing space, air, and ground segments. This paper outlines the conceptualization, challenges, and prospects of such a transformative architecture. We outline the foundational principles, drawn from standardization endeavors and cutting-edge research initiatives, to articulate the envisioned architecture poised to redefine network capabilities. Driven by the need to enhance capacity, increase data rates, support diverse mobility models, and facilitate heterogeneous connectivity, the conceptual framework of a unified 3D network is presented. The focus is on seamlessly integrating diverse network segments and fostering holistic network orchestration. In examining the technical challenges inherent to the realization of a unified 3D network, we outline our strategies to address mobility management, handover optimization, interference mitigation, and the integration of distributed physical layer concepts. Proposals encompass federated learning mechanisms, advanced beamforming techniques, and energy-efficient computational offloading strategies, aimed at enhancing network performance and resilience. Moreover, we outline compelling utilization scenarios and highlighted promising avenues for future research.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"6 ","pages":"170-201"},"PeriodicalIF":5.3,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10770553","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142858978","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-27DOI: 10.1109/OJVT.2024.3507288
Vitou That;Kimchheang Chhea;Jung-Ryun Lee
With the increasing computational demands of Internet of Things (IoT) applications, air-ground integrated networks (AGIN), leveraging the capabilities of Unmanned Aerial Vehicles (UAVs) and High-Altitude Platform (HAP), provides an essential solution to these challenges. In this paper, we propose a framework that facilitates local computing at IoT devices and offers the flexibility to offload tasks to aerial platforms when necessary. Specifically, we formulate a multi-objective optimization model aiming at simultaneously minimizing energy consumption and reducing task latency by adjusting control variables such as transmit power, offloading decisions, and UAV placement in a distributed network of IoT devices. Our proposed framework employs Deep Deterministic Policy Gradient (DDPG) techniques to dynamically optimize network operations, allowing for efficient real-time adjustments to network conditions and task demands. The performance of the proposed algorithm is compared to traditional algorithms, including the Whale Optimization Algorithm (WOA), Gradient Search with Barrier, and Bayesian Optimization (BO). Simulation results show that this approach significantly minimizes energy consumption and latency, outperforming conventional optimization methods. Additionally, scalability tests confirm that our framework can efficiently integrate an increasing number of IoT devices and UAVs.
{"title":"Optimizing Energy Consumption and Latency in IoT Through Edge Computing in Air–Ground Integrated Network With Deep Reinforcement Learning","authors":"Vitou That;Kimchheang Chhea;Jung-Ryun Lee","doi":"10.1109/OJVT.2024.3507288","DOIUrl":"https://doi.org/10.1109/OJVT.2024.3507288","url":null,"abstract":"With the increasing computational demands of Internet of Things (IoT) applications, air-ground integrated networks (AGIN), leveraging the capabilities of Unmanned Aerial Vehicles (UAVs) and High-Altitude Platform (HAP), provides an essential solution to these challenges. In this paper, we propose a framework that facilitates local computing at IoT devices and offers the flexibility to offload tasks to aerial platforms when necessary. Specifically, we formulate a multi-objective optimization model aiming at simultaneously minimizing energy consumption and reducing task latency by adjusting control variables such as transmit power, offloading decisions, and UAV placement in a distributed network of IoT devices. Our proposed framework employs Deep Deterministic Policy Gradient (DDPG) techniques to dynamically optimize network operations, allowing for efficient real-time adjustments to network conditions and task demands. The performance of the proposed algorithm is compared to traditional algorithms, including the Whale Optimization Algorithm (WOA), Gradient Search with Barrier, and Bayesian Optimization (BO). Simulation results show that this approach significantly minimizes energy consumption and latency, outperforming conventional optimization methods. Additionally, scalability tests confirm that our framework can efficiently integrate an increasing number of IoT devices and UAVs.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"6 ","pages":"412-425"},"PeriodicalIF":5.3,"publicationDate":"2024-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10768987","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106228","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Smart charging for Electric Vehicles (EVs) is gaining traction as a key solution to alleviate grid congestion, delay the need for costly network upgrades, and capitalize on off-peak electricity rates. Governments are now enforcing the inclusion of smart charging capabilities in EV charging stations to facilitate this transition. While much of the current research focuses on managing voltage profiles, there is a growing need to examine harmonic emissions in greater detail. This study presents comprehensive data on harmonic distortion during the smart charging of eight popular EV models. We conducted an experimental analysis, measuring harmonic levels with charging current increments of 1A, ranging from the minimum to the maximum for each vehicle. The analysis compared harmonic emissions from both single and multiple EV charging scenarios against the thresholds for total harmonic distortion (THD) and individual harmonic limits outlined in power quality standards (e.g. IEC). Monte Carlo simulations were employed to further understand the behavior in multi-vehicle scenarios. The results reveal that harmonic distortion increases as the charging current decreases across both single and multiple vehicle charging instances. In case studies where several vehicles charge simultaneously, the findings show that as more EVs charge together, harmonic cancellation effects become more pronounced, leading to a gradual reduction in overall harmonic distortion. However, under worst-case conditions, the aggregate current THD can rise as high as 25%, with half of the tested vehicles surpassing the individual harmonic limits.
{"title":"Harmonics Measurement, Analysis, and Impact Assessment of Electric Vehicle Smart Charging","authors":"Murat Senol;I. Safak Bayram;Lewis Hunter;Kristian Sevdari;Connor McGarry;David Campos Gaona;Oliver Gehrke;Stuart Galloway","doi":"10.1109/OJVT.2024.3505778","DOIUrl":"https://doi.org/10.1109/OJVT.2024.3505778","url":null,"abstract":"Smart charging for Electric Vehicles (EVs) is gaining traction as a key solution to alleviate grid congestion, delay the need for costly network upgrades, and capitalize on off-peak electricity rates. Governments are now enforcing the inclusion of smart charging capabilities in EV charging stations to facilitate this transition. While much of the current research focuses on managing voltage profiles, there is a growing need to examine harmonic emissions in greater detail. This study presents comprehensive data on harmonic distortion during the smart charging of eight popular EV models. We conducted an experimental analysis, measuring harmonic levels with charging current increments of 1A, ranging from the minimum to the maximum for each vehicle. The analysis compared harmonic emissions from both single and multiple EV charging scenarios against the thresholds for total harmonic distortion (THD) and individual harmonic limits outlined in power quality standards (e.g. IEC). Monte Carlo simulations were employed to further understand the behavior in multi-vehicle scenarios. The results reveal that harmonic distortion increases as the charging current decreases across both single and multiple vehicle charging instances. In case studies where several vehicles charge simultaneously, the findings show that as more EVs charge together, harmonic cancellation effects become more pronounced, leading to a gradual reduction in overall harmonic distortion. However, under worst-case conditions, the aggregate current THD can rise as high as 25%, with half of the tested vehicles surpassing the individual harmonic limits.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"6 ","pages":"109-127"},"PeriodicalIF":5.3,"publicationDate":"2024-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10766666","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142875114","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-25DOI: 10.1109/OJVT.2024.3506277
Yantao Wang;Jiashuai Li;Yujie Yuan;Chun Sing Lai
The progression of low-carbon aviation policies and the maturation of electric vertical take-off and landing (eVTOL) technology have engendered considerable prospects for the advancement of short-haul intercity and intra-city transportation systems. To harness the potential of eVTOL travel in ameliorating transportation carbon emissions and alleviating ground transportation congestion, the judicious selection of optimal eVTOL stop sites emerges as a pivotal consideration. This study delineates a framework for the delineation of intra-city and short-distance inter-city eVTOL site selection predicated on comprehensive analysis of ground transportation system interconnections. The initial phase of the framework entails the identification of potential optimal take-off and landing sites through a multi-faceted assessment of factors encompassing vehicular and passenger traffic flows, regional economic dynamics, travel behavioral patterns, and prevailing eVTOL flight regulations across heterogeneous ground transportation networks. Employing an enhanced iteration of the K -means algorithm, this phase undertakes the clustering of optimal takeoff and landing locations, thereby discerning their spatial distribution to effectively alleviate ground traffic congestion while aligning with eVTOL vertical port requirements and airspace regulatory mandates. The second phase involves the establishment of a demand gravity model to validate the optimal take-off and landing coordinate sites of eVTOL and further assess a service index indicative of traffic flow optimization. The case shows that six optimal eVTOL take-off and landing locations have been discerned by our model within the Beijing-Tianjin-Xiong'an (Hebei) region. These locations are anticipated to yield a cumulative service index of 75,465 instances, thereby efficaciously mitigating travel pressure on ground transportation infrastructure.
{"title":"Optimizing Urban Air Mobility: A Ground-Connected Approach to Select Optimal eVTOL Takeoff and Landing Sites for Short-Distance Intercity Travel","authors":"Yantao Wang;Jiashuai Li;Yujie Yuan;Chun Sing Lai","doi":"10.1109/OJVT.2024.3506277","DOIUrl":"https://doi.org/10.1109/OJVT.2024.3506277","url":null,"abstract":"The progression of low-carbon aviation policies and the maturation of electric vertical take-off and landing (eVTOL) technology have engendered considerable prospects for the advancement of short-haul intercity and intra-city transportation systems. To harness the potential of eVTOL travel in ameliorating transportation carbon emissions and alleviating ground transportation congestion, the judicious selection of optimal eVTOL stop sites emerges as a pivotal consideration. This study delineates a framework for the delineation of intra-city and short-distance inter-city eVTOL site selection predicated on comprehensive analysis of ground transportation system interconnections. The initial phase of the framework entails the identification of potential optimal take-off and landing sites through a multi-faceted assessment of factors encompassing vehicular and passenger traffic flows, regional economic dynamics, travel behavioral patterns, and prevailing eVTOL flight regulations across heterogeneous ground transportation networks. Employing an enhanced iteration of the \u0000<italic>K</i>\u0000-means algorithm, this phase undertakes the clustering of optimal takeoff and landing locations, thereby discerning their spatial distribution to effectively alleviate ground traffic congestion while aligning with eVTOL vertical port requirements and airspace regulatory mandates. The second phase involves the establishment of a demand gravity model to validate the optimal take-off and landing coordinate sites of eVTOL and further assess a service index indicative of traffic flow optimization. The case shows that six optimal eVTOL take-off and landing locations have been discerned by our model within the Beijing-Tianjin-Xiong'an (Hebei) region. These locations are anticipated to yield a cumulative service index of 75,465 instances, thereby efficaciously mitigating travel pressure on ground transportation infrastructure.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"6 ","pages":"216-239"},"PeriodicalIF":5.3,"publicationDate":"2024-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10767205","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142890165","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-21DOI: 10.1109/OJVT.2024.3504481
Hyo Jong Chung;Byungkon Kang;Yoon Seok Yang
Driver motion recognition is a key factor in ensuring the safety of driving systems. This paper presents a novel system for learning and predicting driver motions, along with an event-based (720 × 720) dataset, N-DriverMotion, newly collected to train a neuromorphic vision system. The system includes an event-based camera that generates a driver motion dataset representing spike inputs and efficient spiking neural networks (SNNs) that are effective in training and predicting the driver's gestures. The event dataset consists of 13 driver motion categories classified by direction (front, side), illumination (bright, moderate, dark), and participant. A novel optimized four-layer convolutional spiking neural network (CSNN) was trained directly without any time-consuming preprocessing. This enables efficient adaptation to energy- and resource-constrained on-device SNNs for real-time inference on high-resolution event-based streams. Compared to recent gesture recognition systems adopting neural networks for vision processing, the proposed neuromorphic vision system achieves competitive accuracy of 94.04% in a 13-class classification task, and 97.24% in an unexpected abnormal driver motion classification task with the CSNN architecture. Additionally, when deployed to Intel Loihi 2 neuromorphic chips, the energy-delay product (EDP) of the model achieved 20,721 times more efficient than that of a non-edge GPU, and 541 times more efficient than edge-purpose GPU. Our proposed CSNN and the dataset can be used to develop safer and more efficient driver-monitoring systems for autonomous vehicles or edge devices requiring an efficient neural network architecture.
{"title":"N-DriverMotion: Driver Motion Learning and Prediction Using an Event-Based Camera and Directly Trained Spiking Neural Networks on Loihi 2","authors":"Hyo Jong Chung;Byungkon Kang;Yoon Seok Yang","doi":"10.1109/OJVT.2024.3504481","DOIUrl":"https://doi.org/10.1109/OJVT.2024.3504481","url":null,"abstract":"Driver motion recognition is a key factor in ensuring the safety of driving systems. This paper presents a novel system for learning and predicting driver motions, along with an event-based (720 × 720) dataset, N-DriverMotion, newly collected to train a neuromorphic vision system. The system includes an event-based camera that generates a driver motion dataset representing spike inputs and efficient spiking neural networks (SNNs) that are effective in training and predicting the driver's gestures. The event dataset consists of 13 driver motion categories classified by direction (front, side), illumination (bright, moderate, dark), and participant. A novel optimized four-layer convolutional spiking neural network (CSNN) was trained directly without any time-consuming preprocessing. This enables efficient adaptation to energy- and resource-constrained on-device SNNs for real-time inference on high-resolution event-based streams. Compared to recent gesture recognition systems adopting neural networks for vision processing, the proposed neuromorphic vision system achieves competitive accuracy of 94.04% in a 13-class classification task, and 97.24% in an unexpected abnormal driver motion classification task with the CSNN architecture. Additionally, when deployed to Intel Loihi 2 neuromorphic chips, the energy-delay product (EDP) of the model achieved 20,721 times more efficient than that of a non-edge GPU, and 541 times more efficient than edge-purpose GPU. Our proposed CSNN and the dataset can be used to develop safer and more efficient driver-monitoring systems for autonomous vehicles or edge devices requiring an efficient neural network architecture.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"6 ","pages":"68-80"},"PeriodicalIF":5.3,"publicationDate":"2024-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10763457","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142810415","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper investigates resource management in device-to-device (D2D) networks coexisting with cellular user equipment (CUEs). We introduce a novel model for joint scheduling and resource management in D2D networks, taking into account environmental constraints. To preserve information freshness, measured by minimizing the average age of information (AoI), and to effectively utilize energy harvesting (EH) technology to satisfy the network's energy needs, we formulate an online optimization problem. This formulation considers factors such as the quality of service (QoS) for both CUEs and D2Ds, available power, information freshness, and environmental sensing requirements. Due to the mixed-integer nonlinear nature and online characteristics of the problem, we propose a deep reinforcement learning (DRL) approach to solve it effectively. Numerical results show that the proposed joint scheduling and resource management strategy, utilizing the soft actor-critic (SAC) algorithm, reduces the average AoI by 20% compared to other baseline methods.
{"title":"Enhancing Information Freshness and Energy Efficiency in D2D Networks Through DRL-Based Scheduling and Resource Management","authors":"Parisa Parhizgar;Mehdi Mahdavi;Mohammad Reza Ahmadzadeh;Melike Erol-Kantarci","doi":"10.1109/OJVT.2024.3502803","DOIUrl":"https://doi.org/10.1109/OJVT.2024.3502803","url":null,"abstract":"This paper investigates resource management in device-to-device (D2D) networks coexisting with cellular user equipment (CUEs). We introduce a novel model for joint scheduling and resource management in D2D networks, taking into account environmental constraints. To preserve information freshness, measured by minimizing the average age of information (AoI), and to effectively utilize energy harvesting (EH) technology to satisfy the network's energy needs, we formulate an online optimization problem. This formulation considers factors such as the quality of service (QoS) for both CUEs and D2Ds, available power, information freshness, and environmental sensing requirements. Due to the mixed-integer nonlinear nature and online characteristics of the problem, we propose a deep reinforcement learning (DRL) approach to solve it effectively. Numerical results show that the proposed joint scheduling and resource management strategy, utilizing the soft actor-critic (SAC) algorithm, reduces the average AoI by 20% compared to other baseline methods.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"6 ","pages":"52-67"},"PeriodicalIF":5.3,"publicationDate":"2024-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10758763","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142798029","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-20DOI: 10.1109/OJVT.2024.3502921
Raik Orbay;Evelina Wikner
Research into novel approaches like Machine Learning (ML) promotes a new set of opportunities for sustainable development of applications through automation. However, there are certain ML tasks which are prone to spurious classification, mainly due to the bias in legacy data. One well-known and highly actual misclassification case concerns gender. As the vast dataset for engineering rules, standards and experiments are based on men, a bias towards women is the subject of research. Accordingly, any bias should be contained before the algorithms are deployed to the service of the sustainable society. There is a substantial amount of data on ML gender-bias in the literature. In these, the majority of the investigated cases are for ML branches like image or sound processing and text recognition. However, utilizing ML for driving style investigations is not an extensively researched area. In this work, a novel application for gender-based classification with bias-attenuation using anonymized driving data will be presented. Using data devoid of biometric and geographic information, the proposed pipeline distinguishes manifested binary genders with 80% accuracy for the drivers in the holdout data set. In addition, a method for sustainable algorithm selection and its extension to embedded applications, is proposed. An investigation into the environmental burden of seven different types of ML algorithms was conducted and the popular neural network algorithm had the highest environmental burden.
{"title":"Sustainable Selection of Machine Learning Algorithm for Gender-Bias Attenuated Prediction","authors":"Raik Orbay;Evelina Wikner","doi":"10.1109/OJVT.2024.3502921","DOIUrl":"https://doi.org/10.1109/OJVT.2024.3502921","url":null,"abstract":"Research into novel approaches like Machine Learning (ML) promotes a new set of opportunities for sustainable development of applications through automation. However, there are certain ML tasks which are prone to spurious classification, mainly due to the bias in legacy data. One well-known and highly actual misclassification case concerns gender. As the vast dataset for engineering rules, standards and experiments are based on men, a bias towards women is the subject of research. Accordingly, any bias should be contained before the algorithms are deployed to the service of the sustainable society. There is a substantial amount of data on ML gender-bias in the literature. In these, the majority of the investigated cases are for ML branches like image or sound processing and text recognition. However, utilizing ML for driving style investigations is not an extensively researched area. In this work, a novel application for gender-based classification with bias-attenuation using anonymized driving data will be presented. Using data devoid of biometric and geographic information, the proposed pipeline distinguishes manifested binary genders with 80% accuracy for the drivers in the holdout data set. In addition, a method for sustainable algorithm selection and its extension to embedded applications, is proposed. An investigation into the environmental burden of seven different types of ML algorithms was conducted and the popular neural network algorithm had the highest environmental burden.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"6 ","pages":"348-358"},"PeriodicalIF":5.3,"publicationDate":"2024-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10759097","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993440","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Intelligent reflecting surface (IRS) is a promising enabler for achieving communication quality of service (QoS) and enhancing sensing QoS in Integrated Sensing and Communication (ISAC) systems. It has been regarded as one of the most attractive solutions for facilitating vehicle applications in internet of vehicles (IoV) by utilizing ISAC technologies. In this paper, the trajectory of target vehicle goes through no obstacle blocking stage and obstacle blocking stage successively in ISAC systems. And the performance trad-off is pursued in the sensing QoS and the communication QoS of the target vehicle. The achievable rate and posterior Cramer-Rao lower bounds (PCRLBs) are defined to reflect communication QoS and sensing QoS, respectively. In this process, the trade-off strategy on QoS for communication and IRS assisted sensing is explored in IoV. Hence, an optimization problem is designed to ensure communication capability of the target while ensuring its sensing ability. The joint semidefinite relaxation (SDR) and alternating optimization (AO) method is proposed to obtain the optimal solution on resource allocation (RA) and IRS phase shift. Simulation results verify the effectiveness of the proposed method in terms of performance trade-off between communication QoS and sensing QoS.
{"title":"Resource Allocation for Intelligent Reflecting Surface Enabled Target Tracking in Integrated Sensing and Communication Systems","authors":"Guilu Wu;Haoyu Liu;Junkang You;Xiangshuo Zhao;Han chen","doi":"10.1109/OJVT.2024.3502153","DOIUrl":"https://doi.org/10.1109/OJVT.2024.3502153","url":null,"abstract":"Intelligent reflecting surface (IRS) is a promising enabler for achieving communication quality of service (QoS) and enhancing sensing QoS in Integrated Sensing and Communication (ISAC) systems. It has been regarded as one of the most attractive solutions for facilitating vehicle applications in internet of vehicles (IoV) by utilizing ISAC technologies. In this paper, the trajectory of target vehicle goes through no obstacle blocking stage and obstacle blocking stage successively in ISAC systems. And the performance trad-off is pursued in the sensing QoS and the communication QoS of the target vehicle. The achievable rate and posterior Cramer-Rao lower bounds (PCRLBs) are defined to reflect communication QoS and sensing QoS, respectively. In this process, the trade-off strategy on QoS for communication and IRS assisted sensing is explored in IoV. Hence, an optimization problem is designed to ensure communication capability of the target while ensuring its sensing ability. The joint semidefinite relaxation (SDR) and alternating optimization (AO) method is proposed to obtain the optimal solution on resource allocation (RA) and IRS phase shift. Simulation results verify the effectiveness of the proposed method in terms of performance trade-off between communication QoS and sensing QoS.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"6 ","pages":"1-12"},"PeriodicalIF":5.3,"publicationDate":"2024-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10758430","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142761401","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-19DOI: 10.1109/OJVT.2024.3502296
Mahdi Shahbazi Khojasteh;Armin Salimi-Badr
Autonomous navigation is a formidable challenge for autonomous aerial vehicles operating in dense or dynamic environments. This paper proposes a path-planning approach based on deep reinforcement learning for a quadrotor equipped with only a monocular camera. The proposed method employs a two-stage structure comprising a depth estimation and a decision-making module. The former module uses a convolutional encoder-decoder network to learn image depth from visual cues self-supervised, with the output serving as input for the latter module. The latter module uses dueling double deep recurrent Q-learning to make decisions in high-dimensional and partially observable state spaces. To reduce meaningless explorations, we introduce the Insight Memory Pool alongside the regular memory pool to provide a rapid boost in learning by emphasizing early sampling from it and relying on the agent's experiences later. Once the agent has gained enough knowledge from the insightful data, we transition to a targeted exploration phase by employing the Boltzmann behavior policy, which relies on the refined Q-value estimates. To validate our approach, we tested the model in three diverse environments simulated with AirSim: a dynamic city street, a downtown, and a pillar world, each with different weather conditions. Experimental results show that our method significantly improves success rates and demonstrates strong generalization across various starting points and environmental transformations.
{"title":"Autonomous Quadrotor Path Planning Through Deep Reinforcement Learning With Monocular Depth Estimation","authors":"Mahdi Shahbazi Khojasteh;Armin Salimi-Badr","doi":"10.1109/OJVT.2024.3502296","DOIUrl":"https://doi.org/10.1109/OJVT.2024.3502296","url":null,"abstract":"Autonomous navigation is a formidable challenge for autonomous aerial vehicles operating in dense or dynamic environments. This paper proposes a path-planning approach based on deep reinforcement learning for a quadrotor equipped with only a monocular camera. The proposed method employs a two-stage structure comprising a depth estimation and a decision-making module. The former module uses a convolutional encoder-decoder network to learn image depth from visual cues self-supervised, with the output serving as input for the latter module. The latter module uses dueling double deep recurrent Q-learning to make decisions in high-dimensional and partially observable state spaces. To reduce meaningless explorations, we introduce the Insight Memory Pool alongside the regular memory pool to provide a rapid boost in learning by emphasizing early sampling from it and relying on the agent's experiences later. Once the agent has gained enough knowledge from the insightful data, we transition to a targeted exploration phase by employing the Boltzmann behavior policy, which relies on the refined Q-value estimates. To validate our approach, we tested the model in three diverse environments simulated with AirSim: a dynamic city street, a downtown, and a pillar world, each with different weather conditions. Experimental results show that our method significantly improves success rates and demonstrates strong generalization across various starting points and environmental transformations.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"6 ","pages":"34-51"},"PeriodicalIF":5.3,"publicationDate":"2024-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10758436","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142777744","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-12DOI: 10.1109/OJVT.2024.3496583
Osama Elgarhy;Yannick Le Moullec;Luca Reggiani;Muhammad Moazam Azeem;Tarik Taleb;Muhammad Mahtab Alam
In this paper, the goal is to reduce the time needed for the placement and migration of services of Connected Automated Vehicles (CAVs) using precise hybrid positioning method. First, to place a service in a Multi-access Edge Computing (MEC) node, there should be sufficient resources in the served MEC node; otherwise, the service would be placed on the neighboring MEC node or even on the core node, resulting in higher delays. We start by modeling our problem with the aid of traffic theory to analytically obtain the necessary number of resources for achieving the desired delay. Second, to reduce the migration process delay, the migration should begin before the vehicle reaches the MEC node. Thus, an AI lane-based scheme is proposed to predict candidate nodes for migration based on precise positioning. Precise positioning data is acquired from a Real-Time Kinematic Global Navigation Satellite System (RTK- GNSS) measurement campaign. The obtained imbalanced raw data is treated and used in the prediction scheme, and the resulting prediction accuracy achieves 99.3%. Finally, we formulate a service placement and migration delay optimization problem and propose an algorithm to solve it. The algorithm shows a latency reduction of approximately 50% compared to the core placement and up to 29% compared to the benchmark prediction algorithm. Moreover, the simulation results for the proposed service placement and migration algorithm show that in case the MEC resource calculations are not used, the delay is 2.2 times greater than when they are used.
{"title":"Towards Optimal Placement and Runtime Migration of Time-Sensitive Services of Connected and Automated Vehicles","authors":"Osama Elgarhy;Yannick Le Moullec;Luca Reggiani;Muhammad Moazam Azeem;Tarik Taleb;Muhammad Mahtab Alam","doi":"10.1109/OJVT.2024.3496583","DOIUrl":"https://doi.org/10.1109/OJVT.2024.3496583","url":null,"abstract":"In this paper, the goal is to reduce the time needed for the placement and migration of services of Connected Automated Vehicles (CAVs) using precise hybrid positioning method. First, to place a service in a Multi-access Edge Computing (MEC) node, there should be sufficient resources in the served MEC node; otherwise, the service would be placed on the neighboring MEC node or even on the core node, resulting in higher delays. We start by modeling our problem with the aid of traffic theory to analytically obtain the necessary number of resources for achieving the desired delay. Second, to reduce the migration process delay, the migration should begin before the vehicle reaches the MEC node. Thus, an AI lane-based scheme is proposed to predict candidate nodes for migration based on precise positioning. Precise positioning data is acquired from a Real-Time Kinematic Global Navigation Satellite System (RTK- GNSS) measurement campaign. The obtained imbalanced raw data is treated and used in the prediction scheme, and the resulting prediction accuracy achieves 99.3%. Finally, we formulate a service placement and migration delay optimization problem and propose an algorithm to solve it. The algorithm shows a latency reduction of approximately 50% compared to the core placement and up to 29% compared to the benchmark prediction algorithm. Moreover, the simulation results for the proposed service placement and migration algorithm show that in case the MEC resource calculations are not used, the delay is 2.2 times greater than when they are used.","PeriodicalId":34270,"journal":{"name":"IEEE Open Journal of Vehicular Technology","volume":"6 ","pages":"13-33"},"PeriodicalIF":5.3,"publicationDate":"2024-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10750435","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142777801","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","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：