Pub Date : 2025-12-23DOI: 10.1109/LCOMM.2025.3647715
Yanwei Shao;Yuan Zeng;Yi Gong
In wireless communication systems, the modulated radio signals are commonly susceptible to sensor-level changes and defects during transmission, resulting in data distribution shifts in the received signals. Deep learning-based automatic modulation recognition (AMR) has made significant strides but still struggles with performance on out-of-distribution (OOD) samples due to domain shifts in practical communication systems. Test-time adaptation (TTA) methods adapt models using test samples at inference time, emerging as a promising solution to this challenge. In this letter, we propose a novel self-supervised TTA strategy to adapt mask autoencoders to better recognize modulation modes in OOD scenarios. The key idea is to optimize the main modulation recognition task and the modulated signal spectrogram reconstruction task during training toward effective feature extraction, and design an entropy control mechanism to adapt the model toward better modulation recognition of the test signals. With extensive experiments, we show that the proposed method effectively improves the performance of TTA for AMR in various distribution shift scenarios.
{"title":"Test-Time Adaptation for Robust Modulation Recognition Under Unknown Channel Distortions","authors":"Yanwei Shao;Yuan Zeng;Yi Gong","doi":"10.1109/LCOMM.2025.3647715","DOIUrl":"https://doi.org/10.1109/LCOMM.2025.3647715","url":null,"abstract":"In wireless communication systems, the modulated radio signals are commonly susceptible to sensor-level changes and defects during transmission, resulting in data distribution shifts in the received signals. Deep learning-based automatic modulation recognition (AMR) has made significant strides but still struggles with performance on out-of-distribution (OOD) samples due to domain shifts in practical communication systems. Test-time adaptation (TTA) methods adapt models using test samples at inference time, emerging as a promising solution to this challenge. In this letter, we propose a novel self-supervised TTA strategy to adapt mask autoencoders to better recognize modulation modes in OOD scenarios. The key idea is to optimize the main modulation recognition task and the modulated signal spectrogram reconstruction task during training toward effective feature extraction, and design an entropy control mechanism to adapt the model toward better modulation recognition of the test signals. With extensive experiments, we show that the proposed method effectively improves the performance of TTA for AMR in various distribution shift scenarios.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"30 ","pages":"657-661"},"PeriodicalIF":4.4,"publicationDate":"2025-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145886673","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This letter proposes a method to enhance satellite communication security based on high-dimensional spatiotemporal chaos. It separates information into two parts and processes both parts simultaneously using a single 2D spatiotemporal chaotic signal matrix. One part is mapped to the spatial-domain index value as Chaos Shift Keying (CSK), and another part is spread spectrum (SS) using a sequence generated by the spatiotemporal chaotic time-domain array determined by the index value. At the receiver, the spatiotemporal chaotic matrix is reconstructed to demodulate the spatial index and then despread the chaotic sequence. CSK and SS using one spatiotemporal chaos can simplify the transmitting and receiving process. And the theoretical analysis and simulation results show that the method proposed in this letter can improve the security performance while reducing the bit error rate.
{"title":"Spatiotemporal Chaotic Spread Dimension Shift Keying for Enhanced Symbol Security","authors":"Yinxia Zhu;Jian Zhang;Hongpeng Zhu;Bangning Zhang;Daoxing Guo;Jian Cheng","doi":"10.1109/LCOMM.2025.3647553","DOIUrl":"https://doi.org/10.1109/LCOMM.2025.3647553","url":null,"abstract":"This letter proposes a method to enhance satellite communication security based on high-dimensional spatiotemporal chaos. It separates information into two parts and processes both parts simultaneously using a single 2D spatiotemporal chaotic signal matrix. One part is mapped to the spatial-domain index value as Chaos Shift Keying (CSK), and another part is spread spectrum (SS) using a sequence generated by the spatiotemporal chaotic time-domain array determined by the index value. At the receiver, the spatiotemporal chaotic matrix is reconstructed to demodulate the spatial index and then despread the chaotic sequence. CSK and SS using one spatiotemporal chaos can simplify the transmitting and receiving process. And the theoretical analysis and simulation results show that the method proposed in this letter can improve the security performance while reducing the bit error rate.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"30 ","pages":"752-756"},"PeriodicalIF":4.4,"publicationDate":"2025-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145929382","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-22DOI: 10.1109/LCOMM.2025.3647351
Haoran Gao;Yinuo Du;Yi Li;Hanying Zhao;Yuan Shen
Network ranging plays a role in achieving high-accuracy clock synchronization and localization in large-scale networks. However, compared to point-to-point ranging, it is more vulnerable to timestamp anomalies, since a single corrupted timestamp can influence multiple range estimates. In contrast to conventional distance-based approaches, this paper proposes a collaborative timestamp-based anomaly detection method that enhances security by sequentially identifying malicious nodes and spoofed timestamps. Furthermore, a timestamp-based maximum likelihood (ML) localization method with alternating optimization is proposed for robust localization and clock synchronization. Simulation and experimental results demonstrate that our method significantly enhances the robustness of network ranging.
{"title":"Detecting Timestamp Anomalies in Network Ranging","authors":"Haoran Gao;Yinuo Du;Yi Li;Hanying Zhao;Yuan Shen","doi":"10.1109/LCOMM.2025.3647351","DOIUrl":"https://doi.org/10.1109/LCOMM.2025.3647351","url":null,"abstract":"Network ranging plays a role in achieving high-accuracy clock synchronization and localization in large-scale networks. However, compared to point-to-point ranging, it is more vulnerable to timestamp anomalies, since a single corrupted timestamp can influence multiple range estimates. In contrast to conventional distance-based approaches, this paper proposes a collaborative timestamp-based anomaly detection method that enhances security by sequentially identifying malicious nodes and spoofed timestamps. Furthermore, a timestamp-based maximum likelihood (ML) localization method with alternating optimization is proposed for robust localization and clock synchronization. Simulation and experimental results demonstrate that our method significantly enhances the robustness of network ranging.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"30 ","pages":"667-671"},"PeriodicalIF":4.4,"publicationDate":"2025-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145886533","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-22DOI: 10.1109/LCOMM.2025.3646724
Qianfan Wang;Jifan Liang;Lvzhou Li;Linqi Song;Xiao Ma
Belief propagation (BP) combined with ordered statistics decoding (OSD) can achieve near-optimal logical error rates for surface codes. However, OSD requires high-latency and unstable-complexity Gaussian elimination (GE), limiting its practicality. In this letter, we propose BP-LCGCD, a GE-free and high-performance decoder that replaces the GE-based OSD with the GE-free LC-GCD. Moreover, in contrast to the original BP-OSD, which adopts a single fixed normalization factor $alpha $ , we further propose a list-parameterized variant, BP-LCGCD+$alpha $ , which performs multiple BP decodings with different $alpha $ to generate diverse posterior LLRs. We present complexity analysis, demonstrating that at low physical error rates, the average decoding complexity of the proposed algorithm approaches that of standard BP. Simulation results demonstrate that BP-LCGCD achieves logical error rates close to BP-OSD, while BP-LCGCD+$alpha $ nearly matches the performance of the BP-OSD. They also show that both proposed decoders significantly outperform standard BP and minimum-weight perfect matching (MWPM) in terms of logical error rate and threshold.
{"title":"BP-LCGCD: A Gaussian-Elimination-Free and High-Performance Decoder for Surface Codes","authors":"Qianfan Wang;Jifan Liang;Lvzhou Li;Linqi Song;Xiao Ma","doi":"10.1109/LCOMM.2025.3646724","DOIUrl":"https://doi.org/10.1109/LCOMM.2025.3646724","url":null,"abstract":"Belief propagation (BP) combined with ordered statistics decoding (OSD) can achieve near-optimal logical error rates for surface codes. However, OSD requires high-latency and unstable-complexity Gaussian elimination (GE), limiting its practicality. In this letter, we propose BP-LCGCD, a GE-free and high-performance decoder that replaces the GE-based OSD with the GE-free LC-GCD. Moreover, in contrast to the original BP-OSD, which adopts a single fixed normalization factor <inline-formula> <tex-math>$alpha $ </tex-math></inline-formula>, we further propose a list-parameterized variant, BP-LCGCD+<inline-formula> <tex-math>$alpha $ </tex-math></inline-formula>, which performs multiple BP decodings with different <inline-formula> <tex-math>$alpha $ </tex-math></inline-formula> to generate diverse posterior LLRs. We present complexity analysis, demonstrating that at low physical error rates, the average decoding complexity of the proposed algorithm approaches that of standard BP. Simulation results demonstrate that BP-LCGCD achieves logical error rates close to BP-OSD, while BP-LCGCD+<inline-formula> <tex-math>$alpha $ </tex-math></inline-formula> nearly matches the performance of the BP-OSD. They also show that both proposed decoders significantly outperform standard BP and minimum-weight perfect matching (MWPM) in terms of logical error rate and threshold.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"30 ","pages":"782-786"},"PeriodicalIF":4.4,"publicationDate":"2025-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145929521","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This letter investigates a two-tier Uncrewed Aerial Vehicle (UAV) assisted Cellular Internet of Things (IoT) architecture inspired by a practical LoRa/NB-IoT deployment, where the fronthaul consists of IoT devices accessing a UAV-mounted LoRa gateway via slotted ALOHA with multi-packet reception (MPR), and the backhaul relays decoded packets to a terrestrial base station (BS) over a coded NB-IoT link. We develop an analytical framework that jointly models fronthaul contention with MPR and coded short-packet transmission over a realistic backhaul channel. The results reveal system configurations that maximize end-to-end throughput while maintaining efficient backhaul utilization across varying UAV–BS distances.
{"title":"Two-Tier UAV-Assisted CIoT Networks: Joint Fronthaul and Backhaul Throughput Analysis","authors":"Srdjan Sobot;Milica Petkovic;Marko Beko;Dejan Vukobratovic","doi":"10.1109/LCOMM.2025.3646026","DOIUrl":"https://doi.org/10.1109/LCOMM.2025.3646026","url":null,"abstract":"This letter investigates a two-tier Uncrewed Aerial Vehicle (UAV) assisted Cellular Internet of Things (IoT) architecture inspired by a practical LoRa/NB-IoT deployment, where the fronthaul consists of IoT devices accessing a UAV-mounted LoRa gateway via slotted ALOHA with multi-packet reception (MPR), and the backhaul relays decoded packets to a terrestrial base station (BS) over a coded NB-IoT link. We develop an analytical framework that jointly models fronthaul contention with MPR and coded short-packet transmission over a realistic backhaul channel. The results reveal system configurations that maximize end-to-end throughput while maintaining efficient backhaul utilization across varying UAV–BS distances.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"30 ","pages":"592-596"},"PeriodicalIF":4.4,"publicationDate":"2025-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145830797","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-18DOI: 10.1109/LCOMM.2025.3645846
Xiaojing Yan;Saeed Razavikia;Carlo Fischione
Recently, over-the-air computation (AirComp) leverages the superposition property of wireless channels to enable efficient function computation over a multiple access channel (MAC). However, existing digital AirComp methods either rely on single-symbol modulation, which limits flexibility and robustness, or on multi-symbol extensions that suffer from high complexity or approximation errors. To overcome these limitations, we propose a new multi-symbol modulation framework, termed sequential modulation for AirComp (SeMAC), which encodes each input into a sequence of symbols with distinct constellation diagrams across multiple time slots. This approach increases design flexibility and robustness against channel noise. Specifically, the modulation design is formulated as a non-convex optimization problem and efficiently solved through a successive convex approximation (SCA) combined with stochastic subgradient descent (SSD). For fixed modulation formats, we further develop SeMAC with power adaptation (SeMAC-PA) to adjusts transmit power and phase while preserving the modulation structure. Notably, numerical results show that SeMAC improves computation accuracy by up to 14 dB compared to the existing methods for computing nonlinear functions such as the product function.
{"title":"Multi-Symbol Digital AirComp via Modulation Design and Power Adaptation","authors":"Xiaojing Yan;Saeed Razavikia;Carlo Fischione","doi":"10.1109/LCOMM.2025.3645846","DOIUrl":"https://doi.org/10.1109/LCOMM.2025.3645846","url":null,"abstract":"Recently, over-the-air computation (AirComp) leverages the superposition property of wireless channels to enable efficient function computation over a multiple access channel (MAC). However, existing digital AirComp methods either rely on single-symbol modulation, which limits flexibility and robustness, or on multi-symbol extensions that suffer from high complexity or approximation errors. To overcome these limitations, we propose a new multi-symbol modulation framework, termed sequential modulation for AirComp (SeMAC), which encodes each input into a sequence of symbols with distinct constellation diagrams across multiple time slots. This approach increases design flexibility and robustness against channel noise. Specifically, the modulation design is formulated as a non-convex optimization problem and efficiently solved through a successive convex approximation (SCA) combined with stochastic subgradient descent (SSD). For fixed modulation formats, we further develop SeMAC with power adaptation (SeMAC-PA) to adjusts transmit power and phase while preserving the modulation structure. Notably, numerical results show that SeMAC improves computation accuracy by up to 14 dB compared to the existing methods for computing nonlinear functions such as the product function.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"30 ","pages":"602-606"},"PeriodicalIF":4.4,"publicationDate":"2025-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145830812","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-18DOI: 10.1109/LCOMM.2025.3645792
Jiawen Li;Yu Jin;Yonghua Wang
Spectrum sensing in 3D environments is critical for reliable autonomous aerial vehicle (AAV) communications. However, in realistic spectrum availability-heterogeneous environments, the complex spatiotemporal coupling characteristic challenges extracting both temporal and spatial features simultaneously. Therefore, this letter proposes a temporal-spatial decoupled local cooperative framework, decomposing the complex sensing task into two relatively simpler subtasks. Specifically, a composite feature representation integrating auto-correlation and cross-correlation matrices is introduced to enrich sample information. Furthermore, a multi-residual convolutional neural network (CNN) with a channel attention mechanism is designed as a universal classifier, maintaining superior nonlinear fitting capability while controlling the network scale. Experiments demonstrate that the proposed strategy achieves superior sensing performance compared to existing methods.
{"title":"Local Cooperative Sensing With Temporal–Spatial Decoupling","authors":"Jiawen Li;Yu Jin;Yonghua Wang","doi":"10.1109/LCOMM.2025.3645792","DOIUrl":"https://doi.org/10.1109/LCOMM.2025.3645792","url":null,"abstract":"Spectrum sensing in 3D environments is critical for reliable autonomous aerial vehicle (AAV) communications. However, in realistic spectrum availability-heterogeneous environments, the complex spatiotemporal coupling characteristic challenges extracting both temporal and spatial features simultaneously. Therefore, this letter proposes a temporal-spatial decoupled local cooperative framework, decomposing the complex sensing task into two relatively simpler subtasks. Specifically, a composite feature representation integrating auto-correlation and cross-correlation matrices is introduced to enrich sample information. Furthermore, a multi-residual convolutional neural network (CNN) with a channel attention mechanism is designed as a universal classifier, maintaining superior nonlinear fitting capability while controlling the network scale. Experiments demonstrate that the proposed strategy achieves superior sensing performance compared to existing methods.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"30 ","pages":"632-636"},"PeriodicalIF":4.4,"publicationDate":"2025-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145886534","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Physical Layer Authentication (PLA) is a promising strategy for wireless security. Most existing PLA schemes have relied on real-valued neural networks, where complex-valued channel impulse response (CIR) is processed by separating the real and imaginary components into dual-channel inputs. This conversion disrupts the inherent coupling between magnitude and phase, thereby constraining authentication accuracy. Importantly, the spatial position of each user inherently serves as a reliable identity fingerprint. In this letter, a complex-valued network-based multi-task learning (CVN-MTL) model is proposed for multi-user authentication. By leveraging the spatiotemporal characteristics of both CIR and position, the CVN-MTL model simultaneously performs user authentication and fine-grained localization. Experiment results show that the CVN-MTL model performs superiority on authentication performance and is robust to different communication scenarios.
{"title":"Deep Complex Network Architecture for Multi-User Physical Layer Authentication in Wireless Communication","authors":"Xiaoying Qiu;Xiaoyu Ma;Jinwei Yu;Wenbao Jiang;Zhaozhong Guo;Maozhi Xu","doi":"10.1109/LCOMM.2025.3645190","DOIUrl":"https://doi.org/10.1109/LCOMM.2025.3645190","url":null,"abstract":"Physical Layer Authentication (PLA) is a promising strategy for wireless security. Most existing PLA schemes have relied on real-valued neural networks, where complex-valued channel impulse response (CIR) is processed by separating the real and imaginary components into dual-channel inputs. This conversion disrupts the inherent coupling between magnitude and phase, thereby constraining authentication accuracy. Importantly, the spatial position of each user inherently serves as a reliable identity fingerprint. In this letter, a complex-valued network-based multi-task learning (CVN-MTL) model is proposed for multi-user authentication. By leveraging the spatiotemporal characteristics of both CIR and position, the CVN-MTL model simultaneously performs user authentication and fine-grained localization. Experiment results show that the CVN-MTL model performs superiority on authentication performance and is robust to different communication scenarios.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"30 ","pages":"637-641"},"PeriodicalIF":4.4,"publicationDate":"2025-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145886679","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-17DOI: 10.1109/LCOMM.2025.3645348
Heng Fu;Weijian Si;Ruizhi Liu
We propose a novel deep learning (DL)-based neural network that ingeniously merges a tailored attention mechanism and wavelet transform to jointly optimize non-orthogonal pilot design and channel estimation in multiple-input multiple-output orthogonal frequency-division multiplexing (MIMO-OFDM) systems. To this end, we develop a pilot designer that leverages customized attention-based layers dedicated to identifying and selecting the optimal time slots and pilot subcarrier positions within a subframe and a channel estimator incorporating specialized wavelet blocks to perform denoising on the raw channel estimates. Simulation results demonstrate that our proposed scheme significantly outperforms traditional linear estimation methods and several state-of-the-art DL-based techniques.
{"title":"A Novel Deep Learning-Based Wavelet-Assisted Joint Pilot Design and Channel Estimation for MIMO-OFDM Systems","authors":"Heng Fu;Weijian Si;Ruizhi Liu","doi":"10.1109/LCOMM.2025.3645348","DOIUrl":"https://doi.org/10.1109/LCOMM.2025.3645348","url":null,"abstract":"We propose a novel deep learning (DL)-based neural network that ingeniously merges a tailored attention mechanism and wavelet transform to jointly optimize non-orthogonal pilot design and channel estimation in multiple-input multiple-output orthogonal frequency-division multiplexing (MIMO-OFDM) systems. To this end, we develop a pilot designer that leverages customized attention-based layers dedicated to identifying and selecting the optimal time slots and pilot subcarrier positions within a subframe and a channel estimator incorporating specialized wavelet blocks to perform denoising on the raw channel estimates. Simulation results demonstrate that our proposed scheme significantly outperforms traditional linear estimation methods and several state-of-the-art DL-based techniques.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"30 ","pages":"607-611"},"PeriodicalIF":4.4,"publicationDate":"2025-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145830895","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Free-space optical (FSO) communications technology has been widely applied in uncrewed aerial vehicle (UAV) networks to offer the ambitious large-capacity, high-security, and interference-immuned links. However, due to atmospheric disturbances at low-altitude airspace as well as flexible-mobility and jitter of the UAV platform, the FSO link between UAVs often suffers from frequent beam misalignment, leading to undesired interruption of communications. Therefore, in this letter, we conceive a UAV-to-UAV (U2U) FSO beam alignment system, where an adaptive exploration driven deep deterministic policy gradient (AED-DDPG) algorithm is proposed to enhance the FSO link quality. By jointly optimizing transmit power and divergence angle at the transmitter site, associated to the field-of-view (FoV) angle at the receiver site, the minimized outage probability can be consequently attained. Our simulation results demonstrate that the proposed method effectively improves the FSO beam alignment of the U2U link under dynamic conditions, which further enhances the robustness of the UAV-FSO system.
{"title":"Adaptive Beam Alignment for UAV Free-Space Optical Communications With Low-Altitude Dynamics Consideration","authors":"Wanting Wang;Simeng Feng;Chenyan Gao;Jinchao Qin;Baolong Li;Chao Dong;Qihui Wu","doi":"10.1109/LCOMM.2025.3644867","DOIUrl":"https://doi.org/10.1109/LCOMM.2025.3644867","url":null,"abstract":"Free-space optical (FSO) communications technology has been widely applied in uncrewed aerial vehicle (UAV) networks to offer the ambitious large-capacity, high-security, and interference-immuned links. However, due to atmospheric disturbances at low-altitude airspace as well as flexible-mobility and jitter of the UAV platform, the FSO link between UAVs often suffers from frequent beam misalignment, leading to undesired interruption of communications. Therefore, in this letter, we conceive a UAV-to-UAV (U2U) FSO beam alignment system, where an adaptive exploration driven deep deterministic policy gradient (AED-DDPG) algorithm is proposed to enhance the FSO link quality. By jointly optimizing transmit power and divergence angle at the transmitter site, associated to the field-of-view (FoV) angle at the receiver site, the minimized outage probability can be consequently attained. Our simulation results demonstrate that the proposed method effectively improves the FSO beam alignment of the U2U link under dynamic conditions, which further enhances the robustness of the UAV-FSO system.","PeriodicalId":13197,"journal":{"name":"IEEE Communications Letters","volume":"30 ","pages":"662-666"},"PeriodicalIF":4.4,"publicationDate":"2025-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145886680","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","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：