Pub Date : 2021-01-13DOI: 10.1109/ICOIN50884.2021.9333975
Hyunjun Mun, Seonggwan Seo, J. Yun
There are several DNN-driven autonomous cars being developed in the world. However, despite their splendid progress, DNNs frequently demonstrate incorrect behaviors which can lead to fatal damages. For example, an adversarial example generated by adding a small perturbation to an image causes a misclassification of the DNN. Numerous techniques have been studied so far in order to research those adversarial examples and the results are remarkable. However, the results are not good on the huge and complex ImageNet dataset. In this paper, we propose the recycling of adversarial attacks, which shows a high success rate of the ImageNet attack. Our method is highly successful and relatively fast by recycling adversarial examples which failed once. We also compare our method with the state-of-the-art techniques and prove that our method is more effective to generate adversarial examples of the ImageNet dataset through experiments.
{"title":"Recycling of Adversarial Attacks on the DNN of Autonomous Cars","authors":"Hyunjun Mun, Seonggwan Seo, J. Yun","doi":"10.1109/ICOIN50884.2021.9333975","DOIUrl":"https://doi.org/10.1109/ICOIN50884.2021.9333975","url":null,"abstract":"There are several DNN-driven autonomous cars being developed in the world. However, despite their splendid progress, DNNs frequently demonstrate incorrect behaviors which can lead to fatal damages. For example, an adversarial example generated by adding a small perturbation to an image causes a misclassification of the DNN. Numerous techniques have been studied so far in order to research those adversarial examples and the results are remarkable. However, the results are not good on the huge and complex ImageNet dataset. In this paper, we propose the recycling of adversarial attacks, which shows a high success rate of the ImageNet attack. Our method is highly successful and relatively fast by recycling adversarial examples which failed once. We also compare our method with the state-of-the-art techniques and prove that our method is more effective to generate adversarial examples of the ImageNet dataset through experiments.","PeriodicalId":6741,"journal":{"name":"2021 International Conference on Information Networking (ICOIN)","volume":"35 1","pages":"814-817"},"PeriodicalIF":0.0,"publicationDate":"2021-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73166923","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 : 2021-01-13DOI: 10.1109/ICOIN50884.2021.9333918
Seongju Kang, Chaeeun Jeong, K. Chung
A deep neural network (DNN) has become a key technique in many intelligent application domains. Since the DNN model has dozens of layers and millions of levels of parameters, the machine has to execute computation-intensive workloads. Therefore, it is difficult to perform DNN inference in resource-constrained devices such as mobile devices. In this paper, we propose a context-aware model selection for on-device DNN inference. The proposed model selection chooses a DNN model corresponding to a spatiotemporal domain based on the context information of the device. Since a context-aware model detects related objects by spatiotemporal domain, it has a low dimension of parameters. In resource-constrained environments, the proposed context-aware model enables high-accuracy inference at low latency. To evaluate the performance of the proposed model selection, we conduct comparison experiments with the existing object detection model. Through experiments, we confirm that the context-aware model performs better than the existing trained models when on-device object detection is performed. Finally, we discuss the limits of the proposed model selection.
{"title":"Context-aware Model Selection for On-Device Object Detection","authors":"Seongju Kang, Chaeeun Jeong, K. Chung","doi":"10.1109/ICOIN50884.2021.9333918","DOIUrl":"https://doi.org/10.1109/ICOIN50884.2021.9333918","url":null,"abstract":"A deep neural network (DNN) has become a key technique in many intelligent application domains. Since the DNN model has dozens of layers and millions of levels of parameters, the machine has to execute computation-intensive workloads. Therefore, it is difficult to perform DNN inference in resource-constrained devices such as mobile devices. In this paper, we propose a context-aware model selection for on-device DNN inference. The proposed model selection chooses a DNN model corresponding to a spatiotemporal domain based on the context information of the device. Since a context-aware model detects related objects by spatiotemporal domain, it has a low dimension of parameters. In resource-constrained environments, the proposed context-aware model enables high-accuracy inference at low latency. To evaluate the performance of the proposed model selection, we conduct comparison experiments with the existing object detection model. Through experiments, we confirm that the context-aware model performs better than the existing trained models when on-device object detection is performed. Finally, we discuss the limits of the proposed model selection.","PeriodicalId":6741,"journal":{"name":"2021 International Conference on Information Networking (ICOIN)","volume":"45 1","pages":"662-666"},"PeriodicalIF":0.0,"publicationDate":"2021-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74145586","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 : 2021-01-13DOI: 10.1109/ICOIN50884.2021.9333899
Joonpyo Hong, Y. Cho, S. K. Kim, J. Na, Jeongho Kwak
According to Cisco’s recent white paper, the usage of mobile data is exponentially increasing by 2022, namely 330% enhancement compared to 2017. Therefore, improvement of network capacity can be placed on the top priority in the future 5G/6G network systems. To tackle this issue, in this paper, we develop a small cell interference management technology with controls of transmission power of base stations (BSs) and user scheduling under edge SON (Self-Organizing Networks) architecture. In order to resolve the severe interference problem as the cell size decreases, this paper proposes an idea to share power in time and space, and develop the joint transmission power and user scheduling algorithm in each time slot aiming to maximize sum utilities of all users leveraging the Lyapunov optimization framework. Finally, we verify and compare the performance of the proposed algorithm and comparing algorithms in the multicell and multi-user scenario.
{"title":"Spatio-Temporal Degree of Freedom: Interference Management in 5G Edge SON Networks","authors":"Joonpyo Hong, Y. Cho, S. K. Kim, J. Na, Jeongho Kwak","doi":"10.1109/ICOIN50884.2021.9333899","DOIUrl":"https://doi.org/10.1109/ICOIN50884.2021.9333899","url":null,"abstract":"According to Cisco’s recent white paper, the usage of mobile data is exponentially increasing by 2022, namely 330% enhancement compared to 2017. Therefore, improvement of network capacity can be placed on the top priority in the future 5G/6G network systems. To tackle this issue, in this paper, we develop a small cell interference management technology with controls of transmission power of base stations (BSs) and user scheduling under edge SON (Self-Organizing Networks) architecture. In order to resolve the severe interference problem as the cell size decreases, this paper proposes an idea to share power in time and space, and develop the joint transmission power and user scheduling algorithm in each time slot aiming to maximize sum utilities of all users leveraging the Lyapunov optimization framework. Finally, we verify and compare the performance of the proposed algorithm and comparing algorithms in the multicell and multi-user scenario.","PeriodicalId":6741,"journal":{"name":"2021 International Conference on Information Networking (ICOIN)","volume":"45 1","pages":"491-494"},"PeriodicalIF":0.0,"publicationDate":"2021-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73868113","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 : 2021-01-13DOI: 10.1109/ICOIN50884.2021.9333964
Jong-Beom Jeong, Soonbin Lee, I. Kim, Eun‐Seok Ryu
Because 360-degree video streaming has become significantly popular in the field of virtual reality, the viewport-adaptive tiled streaming technology for 360-degree video is emerging. This paper presents a viewport tile extractor (VTE) that is implemented on high-efficiency video coding (HEVC). The VTE extracts multiple tiles that represent the viewport of a user and merges them into one bitstream. The proposed system transmits the bitstream of high-quality tiles and the low-quality video bitstream of entire area to reduce both latency and bandwidth. The proposed method shows more than 16.98% of bjontegaard delta rate saving in terms of the luma peak signal-to-noise ratio, compared with the HEVC-compliant streaming method. Additionally, compared with the existing tiled streaming method, it achieves 66.16% and 69.79% saving of decoding memory and time consumption, respectively.
{"title":"Implementing Viewport Tile Extractor for Viewport-Adaptive 360-Degree Video Tiled Streaming","authors":"Jong-Beom Jeong, Soonbin Lee, I. Kim, Eun‐Seok Ryu","doi":"10.1109/ICOIN50884.2021.9333964","DOIUrl":"https://doi.org/10.1109/ICOIN50884.2021.9333964","url":null,"abstract":"Because 360-degree video streaming has become significantly popular in the field of virtual reality, the viewport-adaptive tiled streaming technology for 360-degree video is emerging. This paper presents a viewport tile extractor (VTE) that is implemented on high-efficiency video coding (HEVC). The VTE extracts multiple tiles that represent the viewport of a user and merges them into one bitstream. The proposed system transmits the bitstream of high-quality tiles and the low-quality video bitstream of entire area to reduce both latency and bandwidth. The proposed method shows more than 16.98% of bjontegaard delta rate saving in terms of the luma peak signal-to-noise ratio, compared with the HEVC-compliant streaming method. Additionally, compared with the existing tiled streaming method, it achieves 66.16% and 69.79% saving of decoding memory and time consumption, respectively.","PeriodicalId":6741,"journal":{"name":"2021 International Conference on Information Networking (ICOIN)","volume":"13 5 1","pages":"8-12"},"PeriodicalIF":0.0,"publicationDate":"2021-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85385556","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 : 2021-01-13DOI: 10.1109/ICOIN50884.2021.9333929
M. Pourkiani, Masoud Abedi
For efficient utilization of Internet bandwidth and reducing the response time for delay-sensitive applications, we propose Machine Learning Based Task Distribution (MLTD) technique, which uses the Artificial Neural Networks for smart task distribution between the fog and cloud servers. In this paper, we evaluate the efficiency of MLTD in different conditions to detect the parameters that can impact its performance. Also, we compare the performance of MLTD with other similar methods in terms of Internet bandwidth utilization, response time, and resource utilization. The achieved results show that the performance of MLTD can be better or worse than the other methods, and the training procedure of the neural networks plays an important role in increasing the efficiency of MLTD.
{"title":"Using Machine Learning for Task Distribution in Fog-Cloud Scenarios: A Deep Performance Analysis","authors":"M. Pourkiani, Masoud Abedi","doi":"10.1109/ICOIN50884.2021.9333929","DOIUrl":"https://doi.org/10.1109/ICOIN50884.2021.9333929","url":null,"abstract":"For efficient utilization of Internet bandwidth and reducing the response time for delay-sensitive applications, we propose Machine Learning Based Task Distribution (MLTD) technique, which uses the Artificial Neural Networks for smart task distribution between the fog and cloud servers. In this paper, we evaluate the efficiency of MLTD in different conditions to detect the parameters that can impact its performance. Also, we compare the performance of MLTD with other similar methods in terms of Internet bandwidth utilization, response time, and resource utilization. The achieved results show that the performance of MLTD can be better or worse than the other methods, and the training procedure of the neural networks plays an important role in increasing the efficiency of MLTD.","PeriodicalId":6741,"journal":{"name":"2021 International Conference on Information Networking (ICOIN)","volume":"16 1","pages":"445-450"},"PeriodicalIF":0.0,"publicationDate":"2021-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77084689","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 : 2021-01-13DOI: 10.1109/icoin50884.2021.9333945
{"title":"ICOIN 2021 Conference Room Map","authors":"","doi":"10.1109/icoin50884.2021.9333945","DOIUrl":"https://doi.org/10.1109/icoin50884.2021.9333945","url":null,"abstract":"","PeriodicalId":6741,"journal":{"name":"2021 International Conference on Information Networking (ICOIN)","volume":"24 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78513999","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 : 2021-01-13DOI: 10.1109/ICOIN50884.2021.9333980
Changyoung An, Hyeong Min Kwon, H. Ryu
In this paper, a new lowest-in first-service system is proposed for the efficient MPT (Microwave Power Transfer) to multiple receivers. Basically, the power transmitter of the conventional MPT system for the multiple receivers provides the wireless power to a receiver in the power request sequence order, which can be consider as the first-in first-service method. From the aspect of overall power management and control of wireless power transfer system, this has critically serious problem to the receivers with very low battery power level because of the too long waiting or delay time to them. This drawback can be overcome by the proposed system. Using the power receiver identification (ID) and battery state information (BSI), the proposed system transmits the wireless power to the receiver of the lowest battery power. In this paper, to evaluate the performance of the proposed system, the total workload of the receivers is evaluated by applying each of the proposed system and the conventional system. Through the simulation results, it is confirmed that the proposed MPT system can provide a power efficient environment in which each receiver can perform work more effectively than the conventional MPT system in various receiver conditions.
{"title":"Lowest-In First-Service System for the Efficient MPT (Microwave Power Transfer) to Multiple Receivers","authors":"Changyoung An, Hyeong Min Kwon, H. Ryu","doi":"10.1109/ICOIN50884.2021.9333980","DOIUrl":"https://doi.org/10.1109/ICOIN50884.2021.9333980","url":null,"abstract":"In this paper, a new lowest-in first-service system is proposed for the efficient MPT (Microwave Power Transfer) to multiple receivers. Basically, the power transmitter of the conventional MPT system for the multiple receivers provides the wireless power to a receiver in the power request sequence order, which can be consider as the first-in first-service method. From the aspect of overall power management and control of wireless power transfer system, this has critically serious problem to the receivers with very low battery power level because of the too long waiting or delay time to them. This drawback can be overcome by the proposed system. Using the power receiver identification (ID) and battery state information (BSI), the proposed system transmits the wireless power to the receiver of the lowest battery power. In this paper, to evaluate the performance of the proposed system, the total workload of the receivers is evaluated by applying each of the proposed system and the conventional system. Through the simulation results, it is confirmed that the proposed MPT system can provide a power efficient environment in which each receiver can perform work more effectively than the conventional MPT system in various receiver conditions.","PeriodicalId":6741,"journal":{"name":"2021 International Conference on Information Networking (ICOIN)","volume":"28 1","pages":"594-596"},"PeriodicalIF":0.0,"publicationDate":"2021-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80311258","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 : 2021-01-13DOI: 10.1109/ICOIN50884.2021.9333953
Seoyoung Yu, Yun Jae Jeong, J. W. Lee
In this paper, we propose a decentralized resource allocation scheme based on deep reinforcement learning designed for device-to-device communications underlay cellular networks. The proposed scheme allocates appropriate channel resource and transmit power to each D2D pairs iteratively to maximize the overall effective throughput by utilizing observation consisting of location information of mobile devices and resource allocation of the other devices.
{"title":"Resource Allocation Scheme Based on Deep Reinforcement Learning for Device-to-Device Communications","authors":"Seoyoung Yu, Yun Jae Jeong, J. W. Lee","doi":"10.1109/ICOIN50884.2021.9333953","DOIUrl":"https://doi.org/10.1109/ICOIN50884.2021.9333953","url":null,"abstract":"In this paper, we propose a decentralized resource allocation scheme based on deep reinforcement learning designed for device-to-device communications underlay cellular networks. The proposed scheme allocates appropriate channel resource and transmit power to each D2D pairs iteratively to maximize the overall effective throughput by utilizing observation consisting of location information of mobile devices and resource allocation of the other devices.","PeriodicalId":6741,"journal":{"name":"2021 International Conference on Information Networking (ICOIN)","volume":"22 1","pages":"712-714"},"PeriodicalIF":0.0,"publicationDate":"2021-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86364485","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 : 2021-01-13DOI: 10.1109/ICOIN50884.2021.9333872
Rodrigo Moreira, Larissa Ferreira Rodrigues, P. F. Rosa, R. Aguiar, Flávio de Oliveira Silva
With the variety of applications and the different user requirements, it is necessary to offer tailored resources efficiently not only in access but also in the core of the network. Inspired by the definition and standardization of mobile networks, especially 5G that focused on business verticals, the term network slicing has received numerous state-of-the-art efforts to materialize an approach that meets dynamism, programmability, and flexibility requirements. Leveraged by SDN and NFV technologies, network slicing is inspiring by resource sharing similar to virtual machine management, allowing standard network hardware to accommodate a wide variety of logical networks with specific requirements and data and control planes. However, state-of-the-art approaches do not address resource slicing at the core of the network in detail and appropriately. Therefore, we built NASOR to provide network slicing over the Internet data plane spanning across multiple domains through a segment routing and a distributed-based approach. Our approach excels those found in state-of-the-art by delivering an open policy interface that allows third-party applications to manage network slices dynamically. In this sense, this paper exploits this interface through a mechanism of convolutional neural networks that classifies network traffic, instructing the path-setting agent to be aware of application which predominantly runs on the network improving dynamism in the network slices deployment. Experiments showcase the convolutional neural network applicability and suitability as an enabling technology to enhance and instruct NASOR to establish network slices over multiple domains.
{"title":"Enhancing dynamism in management and network slice establishment through deep learning","authors":"Rodrigo Moreira, Larissa Ferreira Rodrigues, P. F. Rosa, R. Aguiar, Flávio de Oliveira Silva","doi":"10.1109/ICOIN50884.2021.9333872","DOIUrl":"https://doi.org/10.1109/ICOIN50884.2021.9333872","url":null,"abstract":"With the variety of applications and the different user requirements, it is necessary to offer tailored resources efficiently not only in access but also in the core of the network. Inspired by the definition and standardization of mobile networks, especially 5G that focused on business verticals, the term network slicing has received numerous state-of-the-art efforts to materialize an approach that meets dynamism, programmability, and flexibility requirements. Leveraged by SDN and NFV technologies, network slicing is inspiring by resource sharing similar to virtual machine management, allowing standard network hardware to accommodate a wide variety of logical networks with specific requirements and data and control planes. However, state-of-the-art approaches do not address resource slicing at the core of the network in detail and appropriately. Therefore, we built NASOR to provide network slicing over the Internet data plane spanning across multiple domains through a segment routing and a distributed-based approach. Our approach excels those found in state-of-the-art by delivering an open policy interface that allows third-party applications to manage network slices dynamically. In this sense, this paper exploits this interface through a mechanism of convolutional neural networks that classifies network traffic, instructing the path-setting agent to be aware of application which predominantly runs on the network improving dynamism in the network slices deployment. Experiments showcase the convolutional neural network applicability and suitability as an enabling technology to enhance and instruct NASOR to establish network slices over multiple domains.","PeriodicalId":6741,"journal":{"name":"2021 International Conference on Information Networking (ICOIN)","volume":"7 1","pages":"321-326"},"PeriodicalIF":0.0,"publicationDate":"2021-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84389790","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 : 2021-01-13DOI: 10.1109/ICOIN50884.2021.9333983
Aunas Manzoor, Nguyen Dang Tri, C. Hong
Owing to the flexibility, automation and quick deployment features of unmanned aerial vehicles (UAVs), they can be used to deliver the data to the ground vehicles (GVs) efficiently in vehicular area networks (VENETs). However, the heterogeneity, high mobility and network dynamics of VANETs pose significant challenges for such communication. In this paper, we propose a trajectory design scheme for efficient UAV2-GV communication in vehicular area networks (VANETs). Specifically, given the high traffic routes of a dense city, the UAV trajectory is optimized to serve the maximum number of GVs. The trajectory design problem is formulated under the constraints of limited UAV power and association capacities. Moreover, a simplified trajectory design scheme is proposed by exploiting the known traffic road lengths. After the deployment of the UAV according to the designed trajectory, optimal vehicle association and power allocation is performed. Simulation results reveal that the proposed UAV-assisted VANETs can deliver better rates as compared to the traditional terrestrial base-station (TBS)-based networks.
{"title":"UAV Trajectory Design for UAV-2-GV Communication in VANETs","authors":"Aunas Manzoor, Nguyen Dang Tri, C. Hong","doi":"10.1109/ICOIN50884.2021.9333983","DOIUrl":"https://doi.org/10.1109/ICOIN50884.2021.9333983","url":null,"abstract":"Owing to the flexibility, automation and quick deployment features of unmanned aerial vehicles (UAVs), they can be used to deliver the data to the ground vehicles (GVs) efficiently in vehicular area networks (VENETs). However, the heterogeneity, high mobility and network dynamics of VANETs pose significant challenges for such communication. In this paper, we propose a trajectory design scheme for efficient UAV2-GV communication in vehicular area networks (VANETs). Specifically, given the high traffic routes of a dense city, the UAV trajectory is optimized to serve the maximum number of GVs. The trajectory design problem is formulated under the constraints of limited UAV power and association capacities. Moreover, a simplified trajectory design scheme is proposed by exploiting the known traffic road lengths. After the deployment of the UAV according to the designed trajectory, optimal vehicle association and power allocation is performed. Simulation results reveal that the proposed UAV-assisted VANETs can deliver better rates as compared to the traditional terrestrial base-station (TBS)-based networks.","PeriodicalId":6741,"journal":{"name":"2021 International Conference on Information Networking (ICOIN)","volume":"54 1","pages":"219-224"},"PeriodicalIF":0.0,"publicationDate":"2021-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85822606","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：