Pub Date : 2026-03-01Epub Date: 2026-01-05DOI: 10.1016/j.phycom.2026.102998
Fusheng Li , Fan Zhang , Bin Qian , Xiaodong Zhou , Yi Luo , Xiangyong Feng
Traditional three-stage power system protection faces inherent conflicts among its four features. When protection settings avoid mal-operation during severe external faults without boundary elements, internal fault sensitivity is compromised. This limitation causes potential over-reach or under-reach mis-operation in conventional under-reach schemes. In this paper, a novel underreach local measurement-based protection scheme is proposed using zero-mode band time-delay dynamics. First, abrupt voltage changes detected in real-time by a Kalman filter initiate the proposed protection. Second, wavelet packet decomposition processes the zero-mode reverse traveling wave signal across multiple frequency bands. Two specific bands are extracted, Hilbert-transformed, and their first wave-head arrival time difference is calculated as the adaptive characteristic criterion. This value dynamically adjusts to fault locations. The theoretical travel time difference of arrival (TTDoA) serves as the dynamic action threshold. Simulations confirm accurate identification of abrupt changes and activation criteria for single-phase-to-ground faults at varying distances. The scheme reliably protects over 80% of the line length, precisely distinguishes internal from external faults, and operates correctly under high-resistance grounding faults.
{"title":"Adaptive underreach protection relay using zero-mode band time-delay dynamics","authors":"Fusheng Li , Fan Zhang , Bin Qian , Xiaodong Zhou , Yi Luo , Xiangyong Feng","doi":"10.1016/j.phycom.2026.102998","DOIUrl":"10.1016/j.phycom.2026.102998","url":null,"abstract":"<div><div>Traditional three-stage power system protection faces inherent conflicts among its four features. When protection settings avoid mal-operation during severe external faults without boundary elements, internal fault sensitivity is compromised. This limitation causes potential over-reach or under-reach mis-operation in conventional under-reach schemes. In this paper, a novel underreach local measurement-based protection scheme is proposed using zero-mode band time-delay dynamics. First, abrupt voltage changes detected in real-time by a Kalman filter initiate the proposed protection. Second, wavelet packet decomposition processes the zero-mode reverse traveling wave signal across multiple frequency bands. Two specific bands are extracted, Hilbert-transformed, and their first wave-head arrival time difference is calculated as the adaptive characteristic criterion. This value dynamically adjusts to fault locations. The theoretical travel time difference of arrival (TTDoA) serves as the dynamic action threshold. Simulations confirm accurate identification of abrupt changes and activation criteria for single-phase-to-ground faults at varying distances. The scheme reliably protects over 80% of the line length, precisely distinguishes internal from external faults, and operates correctly under high-resistance grounding faults.</div></div>","PeriodicalId":48707,"journal":{"name":"Physical Communication","volume":"75 ","pages":"Article 102998"},"PeriodicalIF":2.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145915145","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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 : 2026-03-01Epub Date: 2026-02-19DOI: 10.1016/j.phycom.2026.103052
Moonil Kim, Jaewoo So
In massive multiple-input–multiple-output (MIMO) systems, as the number of transmit antennas increases, the number of transmit pilots increases for the channel estimation of user equipment. To reduce pilot overheads, generative-model-based channel estimation methods have been studied recently. In this paper, we propose a lightweight generative adversarial network (GAN)-based channel estimation scheme with adaptive regularization. Additionally, the proposed scheme groups users based on the channel collinearity matrix obtained using pre-acquired channel realizations for each user, and uses GANs trained on a per-user group basis. We design lightweight GAN architectures based on the locally centralized sparse characteristics of the beamspace channel. Here, we develop a novel objective function that adaptively determines the relative importance between the received pilots and the pre-trained generator. The simulation results show that the proposed scheme significantly improves performance in terms of the estimation accuracy and complexity when compared with conventional GAN-based channel estimation schemes. Moreover, the proposed scheme can achieve a flexible trade-off between the performance and the complexity of the training network.
{"title":"Lightweight generative channel estimation with adaptive regularization in massive MIMO systems","authors":"Moonil Kim, Jaewoo So","doi":"10.1016/j.phycom.2026.103052","DOIUrl":"10.1016/j.phycom.2026.103052","url":null,"abstract":"<div><div>In massive multiple-input–multiple-output (MIMO) systems, as the number of transmit antennas increases, the number of transmit pilots increases for the channel estimation of user equipment. To reduce pilot overheads, generative-model-based channel estimation methods have been studied recently. In this paper, we propose a lightweight generative adversarial network (GAN)-based channel estimation scheme with adaptive regularization. Additionally, the proposed scheme groups users based on the channel collinearity matrix obtained using pre-acquired channel realizations for each user, and uses GANs trained on a per-user group basis. We design lightweight GAN architectures based on the locally centralized sparse characteristics of the beamspace channel. Here, we develop a novel objective function that adaptively determines the relative importance between the received pilots and the pre-trained generator. The simulation results show that the proposed scheme significantly improves performance in terms of the estimation accuracy and complexity when compared with conventional GAN-based channel estimation schemes. Moreover, the proposed scheme can achieve a flexible trade-off between the performance and the complexity of the training network.</div></div>","PeriodicalId":48707,"journal":{"name":"Physical Communication","volume":"75 ","pages":"Article 103052"},"PeriodicalIF":2.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147397591","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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 : 2026-03-01Epub Date: 2026-01-27DOI: 10.1016/j.phycom.2026.103024
Zheng Xu , Meng Wang , Zihao Pan , Ning Yang , Daoxing Guo
Adaptive beamforming technology plays a crucial role in modern communication systems, but existing deep learning methods lack robustness against data acquisition outliers. We propose an outlier-tolerant adaptive beamforming method based on the Transformer architecture for a 16-element linear antenna array with uniform inter-element spacing. First, an array signal model accounting for mutual coupling errors and data acquisition outliers is established, and an in-depth analysis is conducted of the performance degradation mechanism caused by data outliers arising from multiple factors, including computational precision, quantization errors, and system implementation. Second, a Transformer-based outlier signal classifier is designed that intelligently recognizes different types of outlier signals by fusing signal angle information and antenna weight features. On a large-scale dataset containing 56,373,835 samples, the classifier achieves an accuracy of 99.9990%. Finally, a two-stage Transformer adaptive beamforming method incorporating an outlier-aware mechanism is proposed. By combining the outlier-aware preprocessing module with the Transformer-based beamforming method, the system’s robustness to datasets with outliers is significantly enhanced. Experimental results demonstrate that under ideal conditions, the Transformer-based method achieves improvements in main lobe accuracy of approximately 15% and 16% compared to the traditional Null Steering Beamforming (NSB) and the Gated Recurrent Unit (GRU)-based adaptive beamforming methods, respectively, with approximately 10% improvement in the Signal to Interference plus Noise Ratio (SINR) performance. More importantly, under outlier levels of 10%-30%, the proposed outlier-tolerant method achieves significant performance improvement of approximately 75% in both main lobe accuracy and null accuracy compared to the conventional Transformer method, with main lobe accuracy stably maintained within 0.5° and null accuracy controlled within 0.1°, effectively addressing the data outlier robustness problem faced by deep learning beamforming algorithms in practical applications.
{"title":"Transformer-based outlier-tolerant adaptive beamforming algorithm","authors":"Zheng Xu , Meng Wang , Zihao Pan , Ning Yang , Daoxing Guo","doi":"10.1016/j.phycom.2026.103024","DOIUrl":"10.1016/j.phycom.2026.103024","url":null,"abstract":"<div><div>Adaptive beamforming technology plays a crucial role in modern communication systems, but existing deep learning methods lack robustness against data acquisition outliers. We propose an outlier-tolerant adaptive beamforming method based on the Transformer architecture for a 16-element linear antenna array with uniform inter-element spacing. First, an array signal model accounting for mutual coupling errors and data acquisition outliers is established, and an in-depth analysis is conducted of the performance degradation mechanism caused by data outliers arising from multiple factors, including computational precision, quantization errors, and system implementation. Second, a Transformer-based outlier signal classifier is designed that intelligently recognizes different types of outlier signals by fusing signal angle information and antenna weight features. On a large-scale dataset containing 56,373,835 samples, the classifier achieves an accuracy of 99.9990%. Finally, a two-stage Transformer adaptive beamforming method incorporating an outlier-aware mechanism is proposed. By combining the outlier-aware preprocessing module with the Transformer-based beamforming method, the system’s robustness to datasets with outliers is significantly enhanced. Experimental results demonstrate that under ideal conditions, the Transformer-based method achieves improvements in main lobe accuracy of approximately 15% and 16% compared to the traditional Null Steering Beamforming (NSB) and the Gated Recurrent Unit (GRU)-based adaptive beamforming methods, respectively, with approximately 10% improvement in the Signal to Interference plus Noise Ratio (SINR) performance. More importantly, under outlier levels of 10%-30%, the proposed outlier-tolerant method achieves significant performance improvement of approximately 75% in both main lobe accuracy and null accuracy compared to the conventional Transformer method, with main lobe accuracy stably maintained within 0.5° and null accuracy controlled within 0.1°, effectively addressing the data outlier robustness problem faced by deep learning beamforming algorithms in practical applications.</div></div>","PeriodicalId":48707,"journal":{"name":"Physical Communication","volume":"75 ","pages":"Article 103024"},"PeriodicalIF":2.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147397925","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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 : 2026-03-01Epub Date: 2026-02-24DOI: 10.1016/j.phycom.2026.103046
Xinqi He , Yun Li , Rongling Zhang
Enhancing multi-task performance in unmanned aerial vehicle (UAV)-enabled urban communication systems remains challenging due to conflicting objectives, particularly the trade-off between trajectory-planning efficiency and communication fairness. This paper addresses this issue by jointly optimizing UAV path planning and hovering communication tasks. A UAV Network Fairness-Efficiency Model (UFEM) is proposed to quantify overall system performance by integrating an energy-efficiency metric for trajectory planning with a communication-fairness index for user scheduling, thereby capturing the inherent trade-off between these objectives. Building on this framework, a reinforcement learning (RL)-based urban downlink communication system is developed to track dynamic operating conditions through three-dimensional position observations and state-transition functions, while incorporating key environmental uncertainties such as a random wind model and a probabilistic line-of-sight (LoS) model. Task-specific reward functions are further designed to balance competing objectives and enable adaptive task switching. Based on these components, we introduce the Multi-Task Reinforcement Learning for UAV Maneuvers (MRLUM) algorithm, which jointly optimizes path planning and communication scheduling by fusing flight-state information and communication-channel data through an adaptive task-switching strategy. Simulation results demonstrate that MRLUM significantly improves both trajectory-planning efficiency and communication fairness under the UFEM metric, offering a promising solution for UAV-enabled urban communication systems facing multi-task conflicts and environmental uncertainties.
{"title":"Multi – task reinforcement learning for UAV-enabled urban systems: Balancing trajectory planning and communication fairness","authors":"Xinqi He , Yun Li , Rongling Zhang","doi":"10.1016/j.phycom.2026.103046","DOIUrl":"10.1016/j.phycom.2026.103046","url":null,"abstract":"<div><div>Enhancing multi-task performance in unmanned aerial vehicle (UAV)-enabled urban communication systems remains challenging due to conflicting objectives, particularly the trade-off between trajectory-planning efficiency and communication fairness. This paper addresses this issue by jointly optimizing UAV path planning and hovering communication tasks. A UAV Network Fairness-Efficiency Model (UFEM) is proposed to quantify overall system performance by integrating an energy-efficiency metric for trajectory planning with a communication-fairness index for user scheduling, thereby capturing the inherent trade-off between these objectives. Building on this framework, a reinforcement learning (RL)-based urban downlink communication system is developed to track dynamic operating conditions through three-dimensional position observations and state-transition functions, while incorporating key environmental uncertainties such as a random wind model and a probabilistic line-of-sight (LoS) model. Task-specific reward functions are further designed to balance competing objectives and enable adaptive task switching. Based on these components, we introduce the Multi-Task Reinforcement Learning for UAV Maneuvers (MRLUM) algorithm, which jointly optimizes path planning and communication scheduling by fusing flight-state information and communication-channel data through an adaptive task-switching strategy. Simulation results demonstrate that MRLUM significantly improves both trajectory-planning efficiency and communication fairness under the UFEM metric, offering a promising solution for UAV-enabled urban communication systems facing multi-task conflicts and environmental uncertainties.</div></div>","PeriodicalId":48707,"journal":{"name":"Physical Communication","volume":"75 ","pages":"Article 103046"},"PeriodicalIF":2.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147397948","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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 : 2026-03-01Epub Date: 2026-01-31DOI: 10.1016/j.phycom.2026.103029
Deyang Zhou, Ke Huang, Jingyi Guan, Yang Wang, Jianhe Du
Extremely large antenna arrays (ELAA) is an important technology for future sixth-generation (6G) wireless networks and enables significantly high data transmission rates. However, existing beam training methods either require high overhead or perform poorly under limited training resources due to the joint estimation of angle and distance in the near-field. To address this problem, we design a novel three-stage beam training method for near-field wideband ELAA systems. Specifically, the base station (BS) first employs wide beams designed based on beam split analysis and sub-array partitioning for initial angle estimation to narrow the angle search space. Refined angle estimation of the user equipment (UE) is then achieved using symmetric narrow beams in the second stage. Finally, distance estimation is performed by leveraging the refined angle estimates to identify the optimal beam in the near-field. Simulation results show that our method achieves a near-optimal achievable rate with low training overhead. In addition, the proposed method exhibits smaller angle estimation errors compared with the existing beam training schemes.
{"title":"A novel beam training method for near-field wideband extremely large antenna arrays","authors":"Deyang Zhou, Ke Huang, Jingyi Guan, Yang Wang, Jianhe Du","doi":"10.1016/j.phycom.2026.103029","DOIUrl":"10.1016/j.phycom.2026.103029","url":null,"abstract":"<div><div>Extremely large antenna arrays (ELAA) is an important technology for future sixth-generation (6G) wireless networks and enables significantly high data transmission rates. However, existing beam training methods either require high overhead or perform poorly under limited training resources due to the joint estimation of angle and distance in the near-field. To address this problem, we design a novel three-stage beam training method for near-field wideband ELAA systems. Specifically, the base station (BS) first employs wide beams designed based on beam split analysis and sub-array partitioning for initial angle estimation to narrow the angle search space. Refined angle estimation of the user equipment (UE) is then achieved using symmetric narrow beams in the second stage. Finally, distance estimation is performed by leveraging the refined angle estimates to identify the optimal beam in the near-field. Simulation results show that our method achieves a near-optimal achievable rate with low training overhead. In addition, the proposed method exhibits smaller angle estimation errors compared with the existing beam training schemes.</div></div>","PeriodicalId":48707,"journal":{"name":"Physical Communication","volume":"75 ","pages":"Article 103029"},"PeriodicalIF":2.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147397955","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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 : 2026-03-01Epub Date: 2026-01-21DOI: 10.1016/j.phycom.2026.103016
Yiming Xiang , Han Yang
The operational effectiveness of drone swarms in complex electromagnetic environments is fundamentally limited by autonomous decision-making capabilities, particularly under dynamic interference and stringent real-time constraints. This study develops an autonomous decision-making system centered on an enhanced Multi-Agent Proximal Policy Optimization (MA-PPO) algorithm, with a core focus on joint communication-control optimization. A hierarchical policy network architecture is designed to tightly couple global task planning with local anti-interference control. Crucially, a dynamic interference model is integrated to co-optimize communication power allocation and flight trajectory planning in real-time, thereby enhancing robustness against channel uncertainty and adversarial jamming. Experimental results under -80 dBm interference intensity demonstrate a 9.4% improvement in task completion rate over MADDPG, a communication interruption rate reduced to 7.1% (19.5% of traditional PID methods), and a 107% enhancement in energy efficiency (8.9 tasks/kWh). The primary contributions are threefold: (1) a hierarchical decision architecture that enables deep coupling between planning and interference-aware control; (2) a joint optimization framework that dynamically balances communication quality with motion constraints; (3) quantitative validation in a realistic electromagnetic environment, confirming the engineering feasibility of the proposed approach for reliable swarm operations. This work provides a scalable and robust solution for autonomous drone swarms, advancing the state-of-the-art in physical-layer aware cooperative control.
{"title":"MA-PPO driven autonomous decision system for UAV swarms: Integrating semantic parsing and anti-jamming RL control","authors":"Yiming Xiang , Han Yang","doi":"10.1016/j.phycom.2026.103016","DOIUrl":"10.1016/j.phycom.2026.103016","url":null,"abstract":"<div><div>The operational effectiveness of drone swarms in complex electromagnetic environments is fundamentally limited by autonomous decision-making capabilities, particularly under dynamic interference and stringent real-time constraints. This study develops an autonomous decision-making system centered on an enhanced Multi-Agent Proximal Policy Optimization (MA-PPO) algorithm, with a core focus on joint communication-control optimization. A hierarchical policy network architecture is designed to tightly couple global task planning with local anti-interference control. Crucially, a dynamic interference model is integrated to co-optimize communication power allocation and flight trajectory planning in real-time, thereby enhancing robustness against channel uncertainty and adversarial jamming. Experimental results under -80 dBm interference intensity demonstrate a 9.4% improvement in task completion rate over MADDPG, a communication interruption rate reduced to 7.1% (19.5% of traditional PID methods), and a 107% enhancement in energy efficiency (8.9 tasks/kWh). The primary contributions are threefold: (1) a hierarchical decision architecture that enables deep coupling between planning and interference-aware control; (2) a joint optimization framework that dynamically balances communication quality with motion constraints; (3) quantitative validation in a realistic electromagnetic environment, confirming the engineering feasibility of the proposed approach for reliable swarm operations. This work provides a scalable and robust solution for autonomous drone swarms, advancing the state-of-the-art in physical-layer aware cooperative control.</div></div>","PeriodicalId":48707,"journal":{"name":"Physical Communication","volume":"75 ","pages":"Article 103016"},"PeriodicalIF":2.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146079109","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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 : 2026-03-01Epub Date: 2025-12-30DOI: 10.1016/j.phycom.2025.102990
Ying Lin, Haomin Li, Bowen Zheng, Xuefeng Jing, Xiangcheng Wang
In recent years, with the continuous deepening of research in the field of communication, the utilization rate of spectrum resources and the performance improvement of communication systems in specific scenarios have become the focus of attention. In this context, the integration of non-orthogonal multiple access (NOMA) technology for multi-user spectrum resource sharing with the groundbreaking innovation of reconfigurable intelligent surfaces (RIS) represents a promising direction for in-depth exploration in the era of 6 G wireless communications.This study addresses the challenges posed by complex channel environments and introduces deep reinforcement learning into RIS-NOMA systems.By achieving real-time optimization in ultra-high-dimensional spaces, the aim is to determine novel and effective transmission strategies.Specifically, the Deep Q-Network (DQN) algorithm is employed to optimize high-dimensional decision-making in the dynamic environment of RIS-NOMA systems. By leveraging the adaptive optimization capability of DQN for dynamic channel reconstruction, this method is integrated into the RIS-NOMA system.Simulation results demonstrate that the proposed DQN-based RIS-NOMA system achieves significant improvements in key performance metrics such as achievable data rate, system throughput, and energy efficiency, substantially outperforming traditional schemes. The system throughput is increased by approximately 29 % compared to conventional methods, thereby validating the effectiveness and advancement of the proposed design. The synergistic mechanism between RIS phase regulation and NOMA power allocation provides both theoretical support and practical guidance for the future deployment of RIS-NOMA systems.
{"title":"DQN-based optimization for enhancing the performance of RIS-NOMA system","authors":"Ying Lin, Haomin Li, Bowen Zheng, Xuefeng Jing, Xiangcheng Wang","doi":"10.1016/j.phycom.2025.102990","DOIUrl":"10.1016/j.phycom.2025.102990","url":null,"abstract":"<div><div>In recent years, with the continuous deepening of research in the field of communication, the utilization rate of spectrum resources and the performance improvement of communication systems in specific scenarios have become the focus of attention. In this context, the integration of non-orthogonal multiple access (NOMA) technology for multi-user spectrum resource sharing with the groundbreaking innovation of reconfigurable intelligent surfaces (RIS) represents a promising direction for in-depth exploration in the era of 6 G wireless communications.This study addresses the challenges posed by complex channel environments and introduces deep reinforcement learning into RIS-NOMA systems.By achieving real-time optimization in ultra-high-dimensional spaces, the aim is to determine novel and effective transmission strategies.Specifically, the Deep Q-Network (DQN) algorithm is employed to optimize high-dimensional decision-making in the dynamic environment of RIS-NOMA systems. By leveraging the adaptive optimization capability of DQN for dynamic channel reconstruction, this method is integrated into the RIS-NOMA system.Simulation results demonstrate that the proposed DQN-based RIS-NOMA system achieves significant improvements in key performance metrics such as achievable data rate, system throughput, and energy efficiency, substantially outperforming traditional schemes. The system throughput is increased by approximately 29 % compared to conventional methods, thereby validating the effectiveness and advancement of the proposed design. The synergistic mechanism between RIS phase regulation and NOMA power allocation provides both theoretical support and practical guidance for the future deployment of RIS-NOMA systems.</div></div>","PeriodicalId":48707,"journal":{"name":"Physical Communication","volume":"75 ","pages":"Article 102990"},"PeriodicalIF":2.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145980715","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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 : 2026-03-01Epub Date: 2026-01-13DOI: 10.1016/j.phycom.2026.103002
Ahmed S. Alwakeel , Mohamed H. Saad , Mohamed S. Elbakry
Fluid Antenna System (FAS) have emerged as a promising solution for improving wireless communication by allowing an antenna’s placement within a device to dynamically adjust to its surroundings. This flexibility improves signal quality, link stability, and spectrum efficiency without requiring the deployment of extra antennas. However, realizing the full potential of FAS necessitates determining the ideal antenna arrangement, which is a difficult, multidimensional challenge driven by user locations and signal propagation parameters. To address this issue, this research proposes using the Whale Optimization Algorithm (WHO) for efficient FAS tuning. WHO automatically searches the solution space for ideal antenna placements that improve network performance while reducing deployment complexity. Simulation results show that WHO outperforms traditional methods such as Gaussian approximation (GA) and Particle Swarm Optimization (PSO), achieving better connection with fewer antennas–only three vs four and five for GA and PSO, respectively. WHO improves convergence by 49.6% compared to GA and reduces inference time by 35% compared to Differential Evolution (DE), making it suitable for real-time, adaptive, and resource-efficient wireless networks.
{"title":"Adaptive fluid antenna deployment for improved wireless reliability","authors":"Ahmed S. Alwakeel , Mohamed H. Saad , Mohamed S. Elbakry","doi":"10.1016/j.phycom.2026.103002","DOIUrl":"10.1016/j.phycom.2026.103002","url":null,"abstract":"<div><div>Fluid Antenna System (FAS) have emerged as a promising solution for improving wireless communication by allowing an antenna’s placement within a device to dynamically adjust to its surroundings. This flexibility improves signal quality, link stability, and spectrum efficiency without requiring the deployment of extra antennas. However, realizing the full potential of FAS necessitates determining the ideal antenna arrangement, which is a difficult, multidimensional challenge driven by user locations and signal propagation parameters. To address this issue, this research proposes using the Whale Optimization Algorithm (WHO) for efficient FAS tuning. WHO automatically searches the solution space for ideal antenna placements that improve network performance while reducing deployment complexity. Simulation results show that WHO outperforms traditional methods such as Gaussian approximation (GA) and Particle Swarm Optimization (PSO), achieving better connection with fewer antennas–only three vs four and five for GA and PSO, respectively. WHO improves convergence by 49.6% compared to GA and reduces inference time by 35% compared to Differential Evolution (DE), making it suitable for real-time, adaptive, and resource-efficient wireless networks.</div></div>","PeriodicalId":48707,"journal":{"name":"Physical Communication","volume":"75 ","pages":"Article 103002"},"PeriodicalIF":2.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145980717","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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 : 2026-03-01Epub Date: 2026-01-13DOI: 10.1016/j.phycom.2025.102972
Zahid Zaman , Yousaf Khan , Farman Ali , Ammar Armghan , Muhammad Kamran Shereen , Sultan S. Aldkeelalah , Mardeni Roslee
Long-haul optical transmission (LHOT) systems are affected by nonlinear impairments (NIs), including self-phase modulation (SPM), cross-phase modulation (XPM), four-wave mixing (FWM), amplified spontaneous emission (ASE) noise, and Kerr nonlinearities, which limit achievable data rates and system reach. Conventional methods, such as digital back-propagation (DBP), optical phase conjugation (OPC), and DSP-assisted receivers, have demonstrated mitigation capabilities but suffer from high computational complexity, latency, and power consumption, making them impractical for large-scale networks. Machine learning (ML) approaches, including label propagation and transformer-based schemes, reduce some processing overhead yet do not perform dimensionality reduction for feature compression and lack a mechanism to jointly handle multiple nonlinear effects across LHOT. Furthermore, most reported works do not align with optical communication standards, such as ITU-T G.652.D or OS1/OS2 fibers, which limits their practical implementation in standardized infrastructures.
This work proposes an autoencoder-based pelican optimization algorithm (APOA) for NIs mitigation in LHOT systems. The autoencoder compresses high-dimensional signal distortions into a latent space that preserves nonlinear mappings, reducing computational load while maintaining representation accuracy. The POA performs parameter tuning to optimize signal recovery in the presence of nonlinear effects and noise. The transmission channel is modeled using the nonlinear Schrŏdinger equation (NLSE), with propagation distortions characterized by ITU-T G.652.D single-mode fiber (SMF) parameters: attenuation of 0.20 dB/km, chromatic dispersion of ∼ 17 ps/nm/km at 1550 nm, effective area of 80 µm2, and nonlinear coefficient γ ≈ 1.3 Wkm. Simulations are conducted using parameter settings aligned with OS1/OS2 fiber specifications (9 µm core diameter) and representative optical communication terminal (OCT) configurations, to reflect realistic long-haul transmission environments. Performance evaluation across multiple OSNR levels, fiber lengths, and modulation formats uses FEC thresholds and operating ranges that are consistent with IEEE 802.3 Ethernet and ITU-T G.709 OTN reference values, showing that APOA achieves BER values below the adopted FEC thresholds, increases spectral efficiency, and extends transmission reach.
{"title":"Autoencoder-Pelican optimization for nonlinear impairment mitigation in long-haul optical fiber systems","authors":"Zahid Zaman , Yousaf Khan , Farman Ali , Ammar Armghan , Muhammad Kamran Shereen , Sultan S. Aldkeelalah , Mardeni Roslee","doi":"10.1016/j.phycom.2025.102972","DOIUrl":"10.1016/j.phycom.2025.102972","url":null,"abstract":"<div><div>Long-haul optical transmission (LHOT) systems are affected by nonlinear impairments (NIs), including self-phase modulation (SPM), cross-phase modulation (XPM), four-wave mixing (FWM), amplified spontaneous emission (ASE) noise, and Kerr nonlinearities, which limit achievable data rates and system reach. Conventional methods, such as digital back-propagation (DBP), optical phase conjugation (OPC), and DSP-assisted receivers, have demonstrated mitigation capabilities but suffer from high computational complexity, latency, and power consumption, making them impractical for large-scale networks. Machine learning (ML) approaches, including label propagation and transformer-based schemes, reduce some processing overhead yet do not perform dimensionality reduction for feature compression and lack a mechanism to jointly handle multiple nonlinear effects across LHOT. Furthermore, most reported works do not align with optical communication standards, such as ITU-T G.652.D or OS1/OS2 fibers, which limits their practical implementation in standardized infrastructures.</div><div>This work proposes an autoencoder-based pelican optimization algorithm (APOA) for NIs mitigation in LHOT systems. The autoencoder compresses high-dimensional signal distortions into a latent space that preserves nonlinear mappings, reducing computational load while maintaining representation accuracy. The POA performs parameter tuning to optimize signal recovery in the presence of nonlinear effects and noise. The transmission channel is modeled using the nonlinear Schrŏdinger equation (NLSE), with propagation distortions characterized by ITU-T G.652.D single-mode fiber (SMF) parameters: attenuation of 0.20 dB/km, chromatic dispersion of ∼ 17 ps/nm/km at 1550 nm, effective area of 80 µm<sup>2</sup>, and nonlinear coefficient <em>γ</em> ≈ 1.3 W<span><math><msup><mrow></mrow><mrow><mo>−</mo><mn>1</mn></mrow></msup></math></span>km<span><math><msup><mrow></mrow><mrow><mo>−</mo><mn>1</mn></mrow></msup></math></span>. Simulations are conducted using parameter settings aligned with OS1/OS2 fiber specifications (9 µm core diameter) and representative optical communication terminal (OCT) configurations, to reflect realistic long-haul transmission environments. Performance evaluation across multiple OSNR levels, fiber lengths, and modulation formats uses FEC thresholds and operating ranges that are consistent with IEEE 802.3 Ethernet and ITU-T G.709 OTN reference values, showing that APOA achieves BER values below the adopted FEC thresholds, increases spectral efficiency, and extends transmission reach.</div></div>","PeriodicalId":48707,"journal":{"name":"Physical Communication","volume":"75 ","pages":"Article 102972"},"PeriodicalIF":2.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145980712","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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 : 2026-03-01Epub Date: 2026-01-08DOI: 10.1016/j.phycom.2026.103004
Bin Li , Jie Ding , Hui Li , Jinlong Shi , Xin Zuo
With the rapid development of 5G and the forthcoming B5G/6G networks, unmanned aerial vehicles (UAVs) have been widely adopted in communication systems for their flexible deployment and integrated air-space-ground coverage capabilities. However, UAV communications are highly vulnerable to eavesdropping and jamming attacks, posing a severe threat to communication security. To address this problem, we construct a joint resource and position optimization framework based on the soft Actor-Critic (SAC) algorithm for a secure Two-Way Relay (TWR) system of UAV enabled with Non-Orthogonal Multiple Access (NOMA) technology. In this framework, NOMA technology is incorporated into the TWR relay transmission to achieve spectrum reuse and multi-user parallel communication. The UAV’s position and power allocation are modeled as a Markov Decision Process (MDP), which is intelligently optimized using deep reinforcement learning. We aim to maximize the overall secrecy rate of the system in a dynamic environment while minimizing constraint violations and eavesdropping risks. Simulation results demonstrate that, compared with A2C and PPO algorithms, the proposed SAC-based approach achieves superior convergence speed, stability, and anti-eavesdropping performance, providing technical references for NOMA-based secure UAV communications in B5G/6G networks.
{"title":"Joint optimization of resource and position for UAV secure two-Way relay systems using reinforcement learning","authors":"Bin Li , Jie Ding , Hui Li , Jinlong Shi , Xin Zuo","doi":"10.1016/j.phycom.2026.103004","DOIUrl":"10.1016/j.phycom.2026.103004","url":null,"abstract":"<div><div>With the rapid development of 5G and the forthcoming B5G/6G networks, unmanned aerial vehicles (UAVs) have been widely adopted in communication systems for their flexible deployment and integrated air-space-ground coverage capabilities. However, UAV communications are highly vulnerable to eavesdropping and jamming attacks, posing a severe threat to communication security. To address this problem, we construct a joint resource and position optimization framework based on the soft Actor-Critic (SAC) algorithm for a secure Two-Way Relay (TWR) system of UAV enabled with Non-Orthogonal Multiple Access (NOMA) technology. In this framework, NOMA technology is incorporated into the TWR relay transmission to achieve spectrum reuse and multi-user parallel communication. The UAV’s position and power allocation are modeled as a Markov Decision Process (MDP), which is intelligently optimized using deep reinforcement learning. We aim to maximize the overall secrecy rate of the system in a dynamic environment while minimizing constraint violations and eavesdropping risks. Simulation results demonstrate that, compared with A2C and PPO algorithms, the proposed SAC-based approach achieves superior convergence speed, stability, and anti-eavesdropping performance, providing technical references for NOMA-based secure UAV communications in B5G/6G networks.</div></div>","PeriodicalId":48707,"journal":{"name":"Physical Communication","volume":"75 ","pages":"Article 103004"},"PeriodicalIF":2.2,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145980716","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号