Deep neural network-based image classification models are vulnerable to adversarial examples, which are meticulously crafted to mislead the model by adding perturbations to clean images. Although adversarial training demonstrates outstanding performance in enhancing models robustness against adversarial examples, it often incurs the expense of accuracy. To address this problem, this article proposes a strategy to achieve a better tradeoff between accuracy and robustness, which mainly consists of symbol perturbations and examples mixing. First, we employ a symbol processing approach for randomly generated initial perturbations, which makes model identify the correct parameter attack direction faster during the training process. Second, we put forward a methodology that utilizes a mixture of different examples to generate more distinct adversarial features. Further, we utilize scaling conditions for tensor feature modulation, enabling the model to achieve both improved accuracy and robustness after learning more diverse adversarial features. Finally, we conduct extensive experiments to show the feasibility and effectiveness of the proposed methods.
{"title":"Toward a Better Tradeoff Between Accuracy and Robustness for Image Classification via Adversarial Feature Diversity","authors":"Wei Xue;Yonghao Wang;Yuchi Wang;Yue Wang;Mingyang Du;Xiao Zheng","doi":"10.1109/JMASS.2024.3462548","DOIUrl":"https://doi.org/10.1109/JMASS.2024.3462548","url":null,"abstract":"Deep neural network-based image classification models are vulnerable to adversarial examples, which are meticulously crafted to mislead the model by adding perturbations to clean images. Although adversarial training demonstrates outstanding performance in enhancing models robustness against adversarial examples, it often incurs the expense of accuracy. To address this problem, this article proposes a strategy to achieve a better tradeoff between accuracy and robustness, which mainly consists of symbol perturbations and examples mixing. First, we employ a symbol processing approach for randomly generated initial perturbations, which makes model identify the correct parameter attack direction faster during the training process. Second, we put forward a methodology that utilizes a mixture of different examples to generate more distinct adversarial features. Further, we utilize scaling conditions for tensor feature modulation, enabling the model to achieve both improved accuracy and robustness after learning more diverse adversarial features. Finally, we conduct extensive experiments to show the feasibility and effectiveness of the proposed methods.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"5 4","pages":"254-264"},"PeriodicalIF":0.0,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142679371","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 : 2024-08-29DOI: 10.1109/JMASS.2024.3451477
Li Zhao;Chuan Qin;Qiuni Li;Chongchong Han;Jialong Jian;Yuanfei Liu
An improved dynamic surface control (IDSC) method is proposed for a class of strict-feedback nonlinear systems with internal uncertainties and external disturbances. First, compared with the typical first-order sliding-mode differentiator, this article presents an improved method to obtain the first-order differential approximation of the virtual control signals, which tackles the obstacle of “explosion of complexity.” Second, to eliminate the effect of filtering errors that exist in traditional dynamic surface control method, in this article, the tracking errors are directly constructed using the virtual control signal. Third, composite disturbances were estimated and compensated by designing a novel disturbance observer, which eliminates the limitations that the disturbance terms must be differentiable or even slow tensors. Finally, to illustrate that the proposed method has a great ability to suppress fast time-varying and nondifferentiable disturbances, the simulation results of a numerical example and a practical example of a modern advanced fighter jet system were presented.
{"title":"Improved Dynamic Surface Control for Uncertain Nonlinear Systems With Application to Fighter Jet System","authors":"Li Zhao;Chuan Qin;Qiuni Li;Chongchong Han;Jialong Jian;Yuanfei Liu","doi":"10.1109/JMASS.2024.3451477","DOIUrl":"https://doi.org/10.1109/JMASS.2024.3451477","url":null,"abstract":"An improved dynamic surface control (IDSC) method is proposed for a class of strict-feedback nonlinear systems with internal uncertainties and external disturbances. First, compared with the typical first-order sliding-mode differentiator, this article presents an improved method to obtain the first-order differential approximation of the virtual control signals, which tackles the obstacle of “explosion of complexity.” Second, to eliminate the effect of filtering errors that exist in traditional dynamic surface control method, in this article, the tracking errors are directly constructed using the virtual control signal. Third, composite disturbances were estimated and compensated by designing a novel disturbance observer, which eliminates the limitations that the disturbance terms must be differentiable or even slow tensors. Finally, to illustrate that the proposed method has a great ability to suppress fast time-varying and nondifferentiable disturbances, the simulation results of a numerical example and a practical example of a modern advanced fighter jet system were presented.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"5 4","pages":"246-253"},"PeriodicalIF":0.0,"publicationDate":"2024-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142679334","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 : 2024-08-28DOI: 10.1109/JMASS.2024.3451011
B. Sainath;Sai Kartik Tadinada
Rapid advancements in the Internet of Things (IoT), uncrewed aerial vehicles (UAVs), and energy harvesting (EH) technologies can be leveraged to design and develop green and reliable cooperative Cube satellite communication (CSC) systems and networks. In this work, we propose a novel cooperative CSC system model comprising green UAVs as intelligent relays equipped with IoT sensors, intelligent processing and EH modules, and transceivers. Using a novel and intelligent probabilistic transmission policy (PTP) that we propose, CubeSats can conserve energy by deactivating transmissions in unfavorable weather conditions based on control signals from the smart UAV via a telemetry link. We extend this model to include multiple CubeSats and analyze it by deriving and evaluating network energy efficiency and its lower bound. Our numerical plots show that the proposed PTP significantly outperforms the continuous transmission policy (CTP). At a specific transmission probability of 0.125, PTP is 40 times more energy efficient than CTP. We extend the work and develop a novel and insightful performance analysis for energy efficiency outage (EEO) probability. Specifically, we derive closed-form approximate expressions for EEO probability and present numerical results. Furthermore, we analyze the performance of clustered CSC networks (CSCNs) and present numerical results to assess EEO probability, providing valuable insights for future large-scale green CSCN design and deployment.
{"title":"Environment-Aware Green UAV-Assisted, CubeSat Communication Network Energy Efficiency, and Outage Probability Analysis","authors":"B. Sainath;Sai Kartik Tadinada","doi":"10.1109/JMASS.2024.3451011","DOIUrl":"https://doi.org/10.1109/JMASS.2024.3451011","url":null,"abstract":"Rapid advancements in the Internet of Things (IoT), uncrewed aerial vehicles (UAVs), and energy harvesting (EH) technologies can be leveraged to design and develop green and reliable cooperative Cube satellite communication (CSC) systems and networks. In this work, we propose a novel cooperative CSC system model comprising green UAVs as intelligent relays equipped with IoT sensors, intelligent processing and EH modules, and transceivers. Using a novel and intelligent probabilistic transmission policy (PTP) that we propose, CubeSats can conserve energy by deactivating transmissions in unfavorable weather conditions based on control signals from the smart UAV via a telemetry link. We extend this model to include multiple CubeSats and analyze it by deriving and evaluating network energy efficiency and its lower bound. Our numerical plots show that the proposed PTP significantly outperforms the continuous transmission policy (CTP). At a specific transmission probability of 0.125, PTP is 40 times more energy efficient than CTP. We extend the work and develop a novel and insightful performance analysis for energy efficiency outage (EEO) probability. Specifically, we derive closed-form approximate expressions for EEO probability and present numerical results. Furthermore, we analyze the performance of clustered CSC networks (CSCNs) and present numerical results to assess EEO probability, providing valuable insights for future large-scale green CSCN design and deployment.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"6 2","pages":"125-132"},"PeriodicalIF":0.0,"publicationDate":"2024-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144178877","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 : 2024-08-23DOI: 10.1109/JMASS.2024.3449071
Elisa Robert;Mathieu Barthelemy;Thierry Sequies
The satellites for auroral tomography in space (SATIS) project is a mission concept that proposes to perform auroral tomography from space using imagers placed on a constellation of satellites. Auroral tomography is particularly interesting for reconstructing the flux of particles precipitating into the atmosphere. The advantage of space observations is that they avoid cloud cover problems, allowing larger set of data and with a dedicated ground-based infrastructure ensure quasi-continuous monitoring. However, the main difficulty of this mission is to synchronize orbits and attitudes of the satellites in order to observe the same volume of emission at the same time and from different perspectives. The attitude and determination control system will thus have to be very precise and stable. The data volume is also an issue especially in a monitoring point of view. Furthermore, atmospheric drag will have to be correctly considered to limit orbit disturbances and keep satellites synchronized. We present here the preliminary study of this project and the initial requirements identified to be able to perform this mission concept.
{"title":"The Satellites for Auroral Tomography in Space (SATIS) Project: Tomographic Reconstruction of the Auroral Emissions From Space","authors":"Elisa Robert;Mathieu Barthelemy;Thierry Sequies","doi":"10.1109/JMASS.2024.3449071","DOIUrl":"https://doi.org/10.1109/JMASS.2024.3449071","url":null,"abstract":"The satellites for auroral tomography in space (SATIS) project is a mission concept that proposes to perform auroral tomography from space using imagers placed on a constellation of satellites. Auroral tomography is particularly interesting for reconstructing the flux of particles precipitating into the atmosphere. The advantage of space observations is that they avoid cloud cover problems, allowing larger set of data and with a dedicated ground-based infrastructure ensure quasi-continuous monitoring. However, the main difficulty of this mission is to synchronize orbits and attitudes of the satellites in order to observe the same volume of emission at the same time and from different perspectives. The attitude and determination control system will thus have to be very precise and stable. The data volume is also an issue especially in a monitoring point of view. Furthermore, atmospheric drag will have to be correctly considered to limit orbit disturbances and keep satellites synchronized. We present here the preliminary study of this project and the initial requirements identified to be able to perform this mission concept.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"5 4","pages":"237-245"},"PeriodicalIF":0.0,"publicationDate":"2024-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142679377","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 : 2024-08-23DOI: 10.1109/JMASS.2024.3448433
Heng Zhang;Zhemin Sun;Chaoqun Yang;Xianghui Cao
Mobile edge computing (MEC) revolutionizes data processing by shifting it from the network core to the edge, significantly reducing latency and ensuring Quality of Service. Integrating the agile and flexible unmanned- aerial-vehicle (UAV) technology with MEC offers new opportunities and challenges in decision making for dynamic and complex environments due to the UAVs’ mobility and Line of Sight advantages. Motivated by the potential of UAV-assisted MEC systems with caching mechanisms, this study addresses the optimization problem under uncertain conditions and user demand. To tackle the complex nonconvex sequential decision problem, a deep reinforcement learning framework named delay hybrid action actor-critic is proposed, possessing the capability to handle scenarios requiring both continuous and discrete actions. Comprehensive simulations are conducted to validate the capability of the proposed framework, demonstrating its superiority over traditional methods.
{"title":"Latency Optimization in UAV-Assisted Mobile Edge Computing Empowered by Caching Mechanisms","authors":"Heng Zhang;Zhemin Sun;Chaoqun Yang;Xianghui Cao","doi":"10.1109/JMASS.2024.3448433","DOIUrl":"https://doi.org/10.1109/JMASS.2024.3448433","url":null,"abstract":"Mobile edge computing (MEC) revolutionizes data processing by shifting it from the network core to the edge, significantly reducing latency and ensuring Quality of Service. Integrating the agile and flexible unmanned- aerial-vehicle (UAV) technology with MEC offers new opportunities and challenges in decision making for dynamic and complex environments due to the UAVs’ mobility and Line of Sight advantages. Motivated by the potential of UAV-assisted MEC systems with caching mechanisms, this study addresses the optimization problem under uncertain conditions and user demand. To tackle the complex nonconvex sequential decision problem, a deep reinforcement learning framework named delay hybrid action actor-critic is proposed, possessing the capability to handle scenarios requiring both continuous and discrete actions. Comprehensive simulations are conducted to validate the capability of the proposed framework, demonstrating its superiority over traditional methods.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"5 4","pages":"228-236"},"PeriodicalIF":0.0,"publicationDate":"2024-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142679335","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 : 2024-08-22DOI: 10.1109/JMASS.2024.3440776
{"title":"The Journal of Miniaturized Air and Space Systems","authors":"","doi":"10.1109/JMASS.2024.3440776","DOIUrl":"https://doi.org/10.1109/JMASS.2024.3440776","url":null,"abstract":"","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"5 3","pages":"C2-C2"},"PeriodicalIF":0.0,"publicationDate":"2024-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10643755","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142041461","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 : 2024-08-21DOI: 10.1109/JMASS.2024.3447457
Gazali Bashir;Amit K. Singh;Ankit Dubey
This article introduces a compact wideband beam-switching digital metasurface reflector (MSR) array antenna featuring extreme offset illumination for satellite communications in the Ka band. The MSR comprises phase-modulating subwave length unit cell elements. The unit cell consists of a cross dipole loaded with curved stubs. The arrangement of the stubs across the dipole modulates the phase characteristics of the incident electric field. An MSR composed of $15times 15$ metabits is designed, fabricated, and validated. The metasurface reflectarray is excited by three antipodal Vivaldi antennas with an extreme offset configuration, which effectively mitigates the blockage due to the feeding source. The measured results show highly directive, stable beam-switching characteristics over a broad spectrum ranging from 26 to 32 GHz. A beam steering range of −35° to +35° is obtained along the azimuthal plane, with a maximum measured peak gain of 19.1 dBi at 28.5 GHz and maximum beam-switching loss of 1.5 dBi. A maximum measured aperture efficiency of 35% is obtained, and a 3-dB gain bandwidth of 20.7%.
{"title":"Beam-Switching Digital Metasurface Reflectarray Antenna With Extreme Offset Illumination for Satellite Communications","authors":"Gazali Bashir;Amit K. Singh;Ankit Dubey","doi":"10.1109/JMASS.2024.3447457","DOIUrl":"https://doi.org/10.1109/JMASS.2024.3447457","url":null,"abstract":"This article introduces a compact wideband beam-switching digital metasurface reflector (MSR) array antenna featuring extreme offset illumination for satellite communications in the Ka band. The MSR comprises phase-modulating subwave length unit cell elements. The unit cell consists of a cross dipole loaded with curved stubs. The arrangement of the stubs across the dipole modulates the phase characteristics of the incident electric field. An MSR composed of \u0000<inline-formula> <tex-math>$15times 15$ </tex-math></inline-formula>\u0000 metabits is designed, fabricated, and validated. The metasurface reflectarray is excited by three antipodal Vivaldi antennas with an extreme offset configuration, which effectively mitigates the blockage due to the feeding source. The measured results show highly directive, stable beam-switching characteristics over a broad spectrum ranging from 26 to 32 GHz. A beam steering range of −35° to +35° is obtained along the azimuthal plane, with a maximum measured peak gain of 19.1 dBi at 28.5 GHz and maximum beam-switching loss of 1.5 dBi. A maximum measured aperture efficiency of 35% is obtained, and a 3-dB gain bandwidth of 20.7%.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"5 4","pages":"221-227"},"PeriodicalIF":0.0,"publicationDate":"2024-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142679337","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 : 2024-08-16DOI: 10.1109/JMASS.2024.3445257
Jiawang Li;Yitong Shi;Lei Xiang
This article presents a novel wide stopband suppression millimeter wave (mmWave) filtering antenna (filtenna). A three-order resonance substrate integrated waveguide (SIW) topology structure, including a driven patch and a radiation patch, is applied to enhance the bandwidth. In contrast to traditional stacked patch antennas, this design modifies the driven and radiation patches in different shapes. The full mode SIW (FMSIW) cavity is adopted due to its high-quality (high-Q) factor, which effectively improves the antenna’s selectivity. Besides, the generation of main upper band radiation nulls is attributed to the designed FMSIW cavity. Four parasitic vertical dumbbell structures are added to increase the stopband bandwidth. A pair of U-shape slots are etched on the driven patch to generate a lower band radiation null. A polycyclic structure rather than a single radiation patch can generate another lower band radiation null. To reduce the effect of the antenna element on the ground area and increase the isolation between elements, a via array is added around it, which also slightly enhances the sideband suppression of the antenna in the upper sideband. For verification, a filtenna working for the N258 band (24.25–27.5 GHz) is designed, fabricated, and measured. The measured results show that a measured −10-dB impedance bandwidth covering from 24.25 to 29.06 GHz is successfully implemented. The average realized gain can reach 5 dBi, and the lower and upper band suppression can reach more than 30 and 19.1 dB, respectively. Furthermore, the upper stopband achieves wide suppression from 30 to 50 GHz. Overall, this filtenna is a competitive candidate for 5G mmWave applications.
{"title":"Compact Wide Upper Stopband Suppression Filtering Antenna for Aerospace Applications","authors":"Jiawang Li;Yitong Shi;Lei Xiang","doi":"10.1109/JMASS.2024.3445257","DOIUrl":"https://doi.org/10.1109/JMASS.2024.3445257","url":null,"abstract":"This article presents a novel wide stopband suppression millimeter wave (mmWave) filtering antenna (filtenna). A three-order resonance substrate integrated waveguide (SIW) topology structure, including a driven patch and a radiation patch, is applied to enhance the bandwidth. In contrast to traditional stacked patch antennas, this design modifies the driven and radiation patches in different shapes. The full mode SIW (FMSIW) cavity is adopted due to its high-quality (high-Q) factor, which effectively improves the antenna’s selectivity. Besides, the generation of main upper band radiation nulls is attributed to the designed FMSIW cavity. Four parasitic vertical dumbbell structures are added to increase the stopband bandwidth. A pair of U-shape slots are etched on the driven patch to generate a lower band radiation null. A polycyclic structure rather than a single radiation patch can generate another lower band radiation null. To reduce the effect of the antenna element on the ground area and increase the isolation between elements, a via array is added around it, which also slightly enhances the sideband suppression of the antenna in the upper sideband. For verification, a filtenna working for the N258 band (24.25–27.5 GHz) is designed, fabricated, and measured. The measured results show that a measured −10-dB impedance bandwidth covering from 24.25 to 29.06 GHz is successfully implemented. The average realized gain can reach 5 dBi, and the lower and upper band suppression can reach more than 30 and 19.1 dB, respectively. Furthermore, the upper stopband achieves wide suppression from 30 to 50 GHz. Overall, this filtenna is a competitive candidate for 5G mmWave applications.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"5 4","pages":"211-220"},"PeriodicalIF":0.0,"publicationDate":"2024-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142679258","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 : 2024-08-01DOI: 10.1109/JMASS.2024.3436642
Danyang Wang;Ji Wang;Jinxiu Wang;Jin Liu
Uncrewed aerial vehicles (UAVs) have been widely used in various fields in recent years due to their affordability, mobility flexibility, and convenience. However, faced with the emergence of a large number of UAVs, the shortage of spectrum resources has become a key bottleneck that restricts the quality of service and communication efficiency of UAV networks. The cognitive radio (CR) technology can help to solve this spectrum shortage problem through spectrum-sharing technology. In order to make full use of the available spectrum resources, this article proposes a spectrum-sharing scheme based on multiagent deep reinforcement learning (DRL) in a scenario where the UAV network and terrestrial network coexist. The spectrum used by the UAVs in this scenario consists of two parts: 1) the dedicated spectrum of the UAV network and 2) the shared spectrum of the terrestrial network. The goal of our work in this article is to maximize the total throughput of the UAV network, with the maximum allowable transmission power of the UAV and the mutual interference between the UAV network and the terrestrial network as constraints. The optimization function is a mixed-integer nonconvex programming problem, DRL algorithms are an effective way to solve this problem. Therefore, we propose a multiagent DRL approach that jointly optimizes UAV signal-to-noise ratio control, power control, and access control (USPA) to effectively address this issue. Finally, by comparing with traditional algorithms, simulation results show that using the USPA algorithm can improve the effectiveness of data transmission in UAV networks.
{"title":"Spectrum Sharing in Cognitive UAV Networks Based on Multiagent Reinforcement Learning","authors":"Danyang Wang;Ji Wang;Jinxiu Wang;Jin Liu","doi":"10.1109/JMASS.2024.3436642","DOIUrl":"https://doi.org/10.1109/JMASS.2024.3436642","url":null,"abstract":"Uncrewed aerial vehicles (UAVs) have been widely used in various fields in recent years due to their affordability, mobility flexibility, and convenience. However, faced with the emergence of a large number of UAVs, the shortage of spectrum resources has become a key bottleneck that restricts the quality of service and communication efficiency of UAV networks. The cognitive radio (CR) technology can help to solve this spectrum shortage problem through spectrum-sharing technology. In order to make full use of the available spectrum resources, this article proposes a spectrum-sharing scheme based on multiagent deep reinforcement learning (DRL) in a scenario where the UAV network and terrestrial network coexist. The spectrum used by the UAVs in this scenario consists of two parts: 1) the dedicated spectrum of the UAV network and 2) the shared spectrum of the terrestrial network. The goal of our work in this article is to maximize the total throughput of the UAV network, with the maximum allowable transmission power of the UAV and the mutual interference between the UAV network and the terrestrial network as constraints. The optimization function is a mixed-integer nonconvex programming problem, DRL algorithms are an effective way to solve this problem. Therefore, we propose a multiagent DRL approach that jointly optimizes UAV signal-to-noise ratio control, power control, and access control (USPA) to effectively address this issue. Finally, by comparing with traditional algorithms, simulation results show that using the USPA algorithm can improve the effectiveness of data transmission in UAV networks.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"6 2","pages":"82-91"},"PeriodicalIF":0.0,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144179142","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 : 2024-07-17DOI: 10.1109/JMASS.2024.3429514
Yulong Sun;Guoshen Ding;Yandong Zhao;Renchi Zhang;Wenjun Wang
Due to the increasingly widespread application of unmanned aerial vehicle (UAV), the study of flight conflict resolution can effectively avoid the collision of different UAVs. First, describe flight conflict resolution as an optimization problem. Second, the improved fruit fly optimization algorithm (IFOA) is proposed. The smell concentration judgment is equal to the coordinate instead of the reciprocal of the distance in order to make the variable accessible to be negative and occur with equal probability in the defined domain. Next, introduce the limited number of searches of the Artificial Bee Colony Algorithm to avoid falling into the local optimum. Meanwhile, generate a direction and distance of the fruit fly individual through roulette. Finally, the effectiveness of the algorithm is demonstrated by computational experiments on 18 benchmark functions and the simulation of the flight conflict resolution of two and four UAVs. The results show that compared with the standard fruit fly optimization algorithm, the IFOA has superior global convergence ability and effectively reduces the delay distance, which has important potential in flight conflict resolution.
{"title":"Flight Conflict Resolution Simulation Study Based on the Improved Fruit Fly Optimization Algorithm","authors":"Yulong Sun;Guoshen Ding;Yandong Zhao;Renchi Zhang;Wenjun Wang","doi":"10.1109/JMASS.2024.3429514","DOIUrl":"https://doi.org/10.1109/JMASS.2024.3429514","url":null,"abstract":"Due to the increasingly widespread application of unmanned aerial vehicle (UAV), the study of flight conflict resolution can effectively avoid the collision of different UAVs. First, describe flight conflict resolution as an optimization problem. Second, the improved fruit fly optimization algorithm (IFOA) is proposed. The smell concentration judgment is equal to the coordinate instead of the reciprocal of the distance in order to make the variable accessible to be negative and occur with equal probability in the defined domain. Next, introduce the limited number of searches of the Artificial Bee Colony Algorithm to avoid falling into the local optimum. Meanwhile, generate a direction and distance of the fruit fly individual through roulette. Finally, the effectiveness of the algorithm is demonstrated by computational experiments on 18 benchmark functions and the simulation of the flight conflict resolution of two and four UAVs. The results show that compared with the standard fruit fly optimization algorithm, the IFOA has superior global convergence ability and effectively reduces the delay distance, which has important potential in flight conflict resolution.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"5 3","pages":"200-209"},"PeriodicalIF":0.0,"publicationDate":"2024-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142041376","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：