Deborsi Basu, Abhishek Jain, Uttam Ghosh, R. Datta
The advancement of wireless communication networks has been highly influenced by the development of UAV networks. The real-time realization and quick installation of UAV networks make it extremely suitable for emergency services. Due to limited energy and processing memory, vSDN-enabled UAV networks are brought into the picture where the central SDN controller is used to manage the Data Plane UAV activities. The placement of the controller is a critical issue due to random mobility and distant coverage. In this work, we have proposed a controller implantation technique for low latency communication and service delivery. A two-tier hierarchical data plane (D-plane) segmentation has been introduced to place the UAV entities at D-plane. Our algorithmic approach shows that the centralization of SDN controller causes comparatively low latency with respect to other potential regions. We have relaxed the traffic overheads considering minimal data exchange between D-plane and C-plane. The latency trade-off significantly helps to identify the most suitable positions to deploy the Controller units. This work also contributes towards the CPP-UAV (Controller Placement Problem in UAV-networks).
{"title":"QoS-aware dynamic controller implantation over vSDN-enabled UAV networks for real-time service delivery","authors":"Deborsi Basu, Abhishek Jain, Uttam Ghosh, R. Datta","doi":"10.1145/3477090.3481055","DOIUrl":"https://doi.org/10.1145/3477090.3481055","url":null,"abstract":"The advancement of wireless communication networks has been highly influenced by the development of UAV networks. The real-time realization and quick installation of UAV networks make it extremely suitable for emergency services. Due to limited energy and processing memory, vSDN-enabled UAV networks are brought into the picture where the central SDN controller is used to manage the Data Plane UAV activities. The placement of the controller is a critical issue due to random mobility and distant coverage. In this work, we have proposed a controller implantation technique for low latency communication and service delivery. A two-tier hierarchical data plane (D-plane) segmentation has been introduced to place the UAV entities at D-plane. Our algorithmic approach shows that the centralization of SDN controller causes comparatively low latency with respect to other potential regions. We have relaxed the traffic overheads considering minimal data exchange between D-plane and C-plane. The latency trade-off significantly helps to identify the most suitable positions to deploy the Controller units. This work also contributes towards the CPP-UAV (Controller Placement Problem in UAV-networks).","PeriodicalId":261033,"journal":{"name":"Proceedings of the 4th ACM MobiCom Workshop on Drone Assisted Wireless Communications for 5G and Beyond","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129323027","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}
{"title":"Proceedings of the 4th ACM MobiCom Workshop on Drone Assisted Wireless Communications for 5G and Beyond","authors":"","doi":"10.1145/3477090","DOIUrl":"https://doi.org/10.1145/3477090","url":null,"abstract":"","PeriodicalId":261033,"journal":{"name":"Proceedings of the 4th ACM MobiCom Workshop on Drone Assisted Wireless Communications for 5G and Beyond","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125656367","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}
R. DhineshKumar, Suresh Chavhan, Deepak Gupta, Ashish Khanna, J. Rodrigues
The objective of the study is to investigate the efficient packet transfer among vehicles in the smart city. With the evolution of Intelligent Transportation Systems (ITS), Vehicle to Vehicle (V2V) communication is becoming more prominent for safety and non-safety related applications. The V2V communication facilitates vehicles to interconnect with each other to support numerous applications that will be highly helpful for drivers and passenger's welfare. However, due to the extreme dynamic nature of transportation, the Vehicular Ad hoc Network (VANET) faces many challenges for transferring information among vehicles. Therefore, efficient clustering and dynamic routing are becoming a supreme area of improvement to increase the Packet Delivery Ratio (PDR) and reduce the End-to-End delay for data transfer. In order to overcome the major obstacle, in this paper, we propose an intelligent self-learning approach-based hybrid clustering by integrating Adaptive Network-based Fuzzy Inference System (ANFIS) and dynamic Dijkstra routing for packet transfer between vehicles. Also, experiments were carried out to support the data transfer with the help of drones to provide higher coverage in high dynamic vehicle mobility scenarios. The proposed algorithm is modeled, trained, and tested for performance evaluations metrics such as Packet Delivery Ratio (PDR), End to End delay, CH selection delay.
本研究的目的是研究智慧城市中车辆之间的有效数据包传输。随着智能交通系统(ITS)的发展，车对车(V2V)通信在安全和非安全相关应用中变得越来越重要。V2V通信使车辆能够相互连接，以支持众多应用程序，这将对驾驶员和乘客的福利有很大帮助。然而，由于交通运输的极端动态性，车辆自组织网络(Vehicular Ad hoc Network, VANET)在车辆之间的信息传递面临着许多挑战。因此，高效的集群和动态路由成为提高PDR (Packet Delivery Ratio)和减少端到端数据传输延迟的一个重要改进领域。为了克服这一主要障碍，本文提出了一种基于智能自学习方法的混合聚类方法，该方法将基于自适应网络的模糊推理系统(ANFIS)和动态Dijkstra路由相结合，用于车辆之间的分组传输。通过实验支持无人机的数据传输，在高动态车辆移动场景下提供更高的覆盖。提出的算法建模，训练，并测试了性能评估指标，如包投递率(PDR)，端到端延迟，CH选择延迟。
{"title":"An intelligent self-learning drone assistance approach towards V2V communication in smart city","authors":"R. DhineshKumar, Suresh Chavhan, Deepak Gupta, Ashish Khanna, J. Rodrigues","doi":"10.1145/3477090.3481050","DOIUrl":"https://doi.org/10.1145/3477090.3481050","url":null,"abstract":"The objective of the study is to investigate the efficient packet transfer among vehicles in the smart city. With the evolution of Intelligent Transportation Systems (ITS), Vehicle to Vehicle (V2V) communication is becoming more prominent for safety and non-safety related applications. The V2V communication facilitates vehicles to interconnect with each other to support numerous applications that will be highly helpful for drivers and passenger's welfare. However, due to the extreme dynamic nature of transportation, the Vehicular Ad hoc Network (VANET) faces many challenges for transferring information among vehicles. Therefore, efficient clustering and dynamic routing are becoming a supreme area of improvement to increase the Packet Delivery Ratio (PDR) and reduce the End-to-End delay for data transfer. In order to overcome the major obstacle, in this paper, we propose an intelligent self-learning approach-based hybrid clustering by integrating Adaptive Network-based Fuzzy Inference System (ANFIS) and dynamic Dijkstra routing for packet transfer between vehicles. Also, experiments were carried out to support the data transfer with the help of drones to provide higher coverage in high dynamic vehicle mobility scenarios. The proposed algorithm is modeled, trained, and tested for performance evaluations metrics such as Packet Delivery Ratio (PDR), End to End delay, CH selection delay.","PeriodicalId":261033,"journal":{"name":"Proceedings of the 4th ACM MobiCom Workshop on Drone Assisted Wireless Communications for 5G and Beyond","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134531095","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}
Recent advances in deep learning make it possible to implement neural network architecture fitted to the task. In this paper we present new deep neural network model developed for drone assisted systems, in which image from drone camera is processed for smart crowd counting operation. Our proposed architecture works to estimate the crowd in the image by using derivative of ResNet conception model. We have used RMSprop algorithm to train it. Research results from our experiments show 98% of Accuracy, Precision and Recall which is very high efficiency in such systems. Proposed model is easy to configure and has high potential for further development.
{"title":"Deep learning based crowd counting model for drone assisted systems","authors":"M. Woźniak, J. Siłka, Michal Wieczorek","doi":"10.1145/3477090.3481054","DOIUrl":"https://doi.org/10.1145/3477090.3481054","url":null,"abstract":"Recent advances in deep learning make it possible to implement neural network architecture fitted to the task. In this paper we present new deep neural network model developed for drone assisted systems, in which image from drone camera is processed for smart crowd counting operation. Our proposed architecture works to estimate the crowd in the image by using derivative of ResNet conception model. We have used RMSprop algorithm to train it. Research results from our experiments show 98% of Accuracy, Precision and Recall which is very high efficiency in such systems. Proposed model is easy to configure and has high potential for further development.","PeriodicalId":261033,"journal":{"name":"Proceedings of the 4th ACM MobiCom Workshop on Drone Assisted Wireless Communications for 5G and Beyond","volume":"206 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117296983","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}
B. Liu, Keping Yu, Chaosheng Feng, Kim-Kwang Raymond Choo
While 5G facilitates high-speed Internet access and makes over-the-horizon control a reality for unmanned aerial vehicles (UAVs), there are also potential security and privacy considerations, for example, authentication among drones. The centralized authentication approaches not only suffer from a single point of failure, but they are also incapable of cross-domain authentication, which complicates the cooperation of drones from different domains. To address these challenges, we propose a blockchain-based solution to achieve cross-domain authentication for 5G-enabled UAVs. Our approach employs multiple signatures based on threshold sharing to build an identity federation for collaborative domains. Reliable communication between cross-domain devices is achieved by utilizing smart contract for authentication. Our performance evaluations show the effectiveness and efficiency of the proposed scheme.
{"title":"Cross-domain authentication for 5G-enabled UAVs: a blockchain approach","authors":"B. Liu, Keping Yu, Chaosheng Feng, Kim-Kwang Raymond Choo","doi":"10.1145/3477090.3481053","DOIUrl":"https://doi.org/10.1145/3477090.3481053","url":null,"abstract":"While 5G facilitates high-speed Internet access and makes over-the-horizon control a reality for unmanned aerial vehicles (UAVs), there are also potential security and privacy considerations, for example, authentication among drones. The centralized authentication approaches not only suffer from a single point of failure, but they are also incapable of cross-domain authentication, which complicates the cooperation of drones from different domains. To address these challenges, we propose a blockchain-based solution to achieve cross-domain authentication for 5G-enabled UAVs. Our approach employs multiple signatures based on threshold sharing to build an identity federation for collaborative domains. Reliable communication between cross-domain devices is achieved by utilizing smart contract for authentication. Our performance evaluations show the effectiveness and efficiency of the proposed scheme.","PeriodicalId":261033,"journal":{"name":"Proceedings of the 4th ACM MobiCom Workshop on Drone Assisted Wireless Communications for 5G and Beyond","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126729889","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}
D. Zhai, Qiqi Shi, Ruonan Zhang, Haotong Cao, Bin Li, Dawei Wang
Unmanned aerial vehicle (UAV) has great potential in the future wireless networks. In this paper, we investigate the system optimization algorithms for the heterogeneous aerial networks. Specifically, we propose a cooperative heterogeneous aerial network, where several low-altitude aerial base stations (LABSs) with high frequency are dynamically deployed to enhance the coverage of a high-altitude aerial base station (HABS) with low frequency. For this network, we formulate a joint position optimization, channel allocation, and power allocation problem with the objective to maximize the total data rate of all users under the constraint of the minimum rate requirement of each user. To tackle this hard problem, we first adopt the particle-and-fish swarm algorithm to optimize the positions of the LABSs. Then, the channel-and-power allocation algorithms are designed based on the matching theory and the Lagrangian dual decomposition technique. Simulation results indicate that our proposed algorithms can greatly improve the network performance.
{"title":"Position optimization and resource allocation for cooperative heterogeneous aerial networks","authors":"D. Zhai, Qiqi Shi, Ruonan Zhang, Haotong Cao, Bin Li, Dawei Wang","doi":"10.1145/3477090.3481049","DOIUrl":"https://doi.org/10.1145/3477090.3481049","url":null,"abstract":"Unmanned aerial vehicle (UAV) has great potential in the future wireless networks. In this paper, we investigate the system optimization algorithms for the heterogeneous aerial networks. Specifically, we propose a cooperative heterogeneous aerial network, where several low-altitude aerial base stations (LABSs) with high frequency are dynamically deployed to enhance the coverage of a high-altitude aerial base station (HABS) with low frequency. For this network, we formulate a joint position optimization, channel allocation, and power allocation problem with the objective to maximize the total data rate of all users under the constraint of the minimum rate requirement of each user. To tackle this hard problem, we first adopt the particle-and-fish swarm algorithm to optimize the positions of the LABSs. Then, the channel-and-power allocation algorithms are designed based on the matching theory and the Lagrangian dual decomposition technique. Simulation results indicate that our proposed algorithms can greatly improve the network performance.","PeriodicalId":261033,"journal":{"name":"Proceedings of the 4th ACM MobiCom Workshop on Drone Assisted Wireless Communications for 5G and Beyond","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128765330","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}
UAVs mounted with millimeter wave base stations will enable last-mile high bandwidth access, as well as help in rapidly deploying point to point aerial backhaul links. Because such transmitters use directional beamforming to increase capacity, UAV deployments require careful selection of the beamwidth. Even under regular hovering conditions, UAVs display minor relative rotations and displacements caused by GPS inaccuracies and environmental factors like wind. To ensure narrow beams are perfectly aligned in such practical conditions, we propose a beamforming framework that (i) fuses out-of-band information obtained from cameras and (ii) leverages antenna beam-patterns characterized online during flight. These inputs provide the UAV pair forming the link with an improved estimate of relative orientation, and furthermore, guide controlled and coordinated movements to ensure the mmWave beams remain aligned. We implement this joint robotics-communication framework within the robot operating system and evaluate the performance for emulated DJI M100 UAVs. Our results reveal 33% improvement in physical bitrate and 60.4% reduction in latency when compared to RF-only beam sweeping methods.
{"title":"Camera-enabled joint robotic-communication paradigm for UAVs mounted with mmWave radios","authors":"Saray Sanchez, Rishabh Shukla, K. Chowdhury","doi":"10.1145/3477090.3481052","DOIUrl":"https://doi.org/10.1145/3477090.3481052","url":null,"abstract":"UAVs mounted with millimeter wave base stations will enable last-mile high bandwidth access, as well as help in rapidly deploying point to point aerial backhaul links. Because such transmitters use directional beamforming to increase capacity, UAV deployments require careful selection of the beamwidth. Even under regular hovering conditions, UAVs display minor relative rotations and displacements caused by GPS inaccuracies and environmental factors like wind. To ensure narrow beams are perfectly aligned in such practical conditions, we propose a beamforming framework that (i) fuses out-of-band information obtained from cameras and (ii) leverages antenna beam-patterns characterized online during flight. These inputs provide the UAV pair forming the link with an improved estimate of relative orientation, and furthermore, guide controlled and coordinated movements to ensure the mmWave beams remain aligned. We implement this joint robotics-communication framework within the robot operating system and evaluate the performance for emulated DJI M100 UAVs. Our results reveal 33% improvement in physical bitrate and 60.4% reduction in latency when compared to RF-only beam sweeping methods.","PeriodicalId":261033,"journal":{"name":"Proceedings of the 4th ACM MobiCom Workshop on Drone Assisted Wireless Communications for 5G and Beyond","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125201998","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}
P. Chhikara, Rajkumar Tekchandani, Neeraj Kumar, S. Tanwar
The utilization of drones has recently revolutionized remote sensing with their high spatial resolution and flexibility in capturing images. In the proposed work, we employ a swarm of drones that communicate in a wireless network. Each drone captures the image frames, and each frame is further used to locate and differentiate different objects in an image frame. The semantic segmentation of the captured images is done using deep learning algorithms. To identify the most suitable, cost-efficient, and accurate segmentation method, various state-of-the-art models, are appraised and compared based on different evaluation metrics. Resnet50 model with U-net segmentation model performs the best out of all used models by providing 91.51% pixel accuracy. Also, to give real-time predictions, we have used federated learning with the drone network. Each drone trains a local model using its accumulated data and then transfers the locally trained model to the central server that aggregates the received models, generates a global federated learning model, and transmits it in the swarm network.
{"title":"Federated learning-based aerial image segmentation for collision-free movement and landing","authors":"P. Chhikara, Rajkumar Tekchandani, Neeraj Kumar, S. Tanwar","doi":"10.1145/3477090.3481051","DOIUrl":"https://doi.org/10.1145/3477090.3481051","url":null,"abstract":"The utilization of drones has recently revolutionized remote sensing with their high spatial resolution and flexibility in capturing images. In the proposed work, we employ a swarm of drones that communicate in a wireless network. Each drone captures the image frames, and each frame is further used to locate and differentiate different objects in an image frame. The semantic segmentation of the captured images is done using deep learning algorithms. To identify the most suitable, cost-efficient, and accurate segmentation method, various state-of-the-art models, are appraised and compared based on different evaluation metrics. Resnet50 model with U-net segmentation model performs the best out of all used models by providing 91.51% pixel accuracy. Also, to give real-time predictions, we have used federated learning with the drone network. Each drone trains a local model using its accumulated data and then transfers the locally trained model to the central server that aggregates the received models, generates a global federated learning model, and transmits it in the swarm network.","PeriodicalId":261033,"journal":{"name":"Proceedings of the 4th ACM MobiCom Workshop on Drone Assisted Wireless Communications for 5G and Beyond","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122325346","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：