Pub Date : 2026-08-01Epub Date: 2026-08-19DOI: 10.23919/JCN.2025.000136
Ruibin Wang;Huaifeng Shi;Chaofan Liu;Yibin Feng
The allocation of resources for bottleneck links in emergency communication networks, particularly under time-varying channel conditions, presents a critical challenge. Most existing studies predominantly focus exclusively on the independent optimization of either frame generation time or bandwidth allocation, overlooking the strong interdependence between these two factors. To address this gap, this paper proposes a joint optimization algorithm for frame generation time and bandwidth allocation (JFBA) based on a double deep Q-network (DDQN). Our approach formulates the problem as a Markov decision process (MDP), where a DDQN-based agent perceives real-time network states to iteratively refine policies for both parameters. Furthermore, a tailored prioritized experience replay (PER) mechanism, driven by both immediate rewards and temporal-difference (TD) errors, is incorporated to accelerate learning from rare but critical network anomalies, such as sudden traffic bursts or link failures. Extensive simulation results demonstrate that JFBA exhibits superior robustness compared to state-of-the-art baselines, including AFSA, DQN, PPO, and Dueling DQN. Specifically, under extreme resource constraints (e.g., 20% bandwidth availability), JFBA achieves an end-to-end delay reduction of up to 93.8% and maintains a bandwidth utilization rate exceeding 95%, successfully guaranteeing quality of service (QoS) where traditional methods fail to meet the constraints.
{"title":"Joint optimization algorithm for frame generation time and bandwidth allocation in emergency communication networks","authors":"Ruibin Wang;Huaifeng Shi;Chaofan Liu;Yibin Feng","doi":"10.23919/JCN.2025.000136","DOIUrl":"https://doi.org/10.23919/JCN.2025.000136","url":null,"abstract":"The allocation of resources for bottleneck links in emergency communication networks, particularly under time-varying channel conditions, presents a critical challenge. Most existing studies predominantly focus exclusively on the independent optimization of either frame generation time or bandwidth allocation, overlooking the strong interdependence between these two factors. To address this gap, this paper proposes a joint optimization algorithm for frame generation time and bandwidth allocation (JFBA) based on a double deep Q-network (DDQN). Our approach formulates the problem as a Markov decision process (MDP), where a DDQN-based agent perceives real-time network states to iteratively refine policies for both parameters. Furthermore, a tailored prioritized experience replay (PER) mechanism, driven by both immediate rewards and temporal-difference (TD) errors, is incorporated to accelerate learning from rare but critical network anomalies, such as sudden traffic bursts or link failures. Extensive simulation results demonstrate that JFBA exhibits superior robustness compared to state-of-the-art baselines, including AFSA, DQN, PPO, and Dueling DQN. Specifically, under extreme resource constraints (e.g., 20% bandwidth availability), JFBA achieves an end-to-end delay reduction of up to 93.8% and maintains a bandwidth utilization rate exceeding 95%, successfully guaranteeing quality of service (QoS) where traditional methods fail to meet the constraints.","PeriodicalId":54864,"journal":{"name":"Journal of Communications and Networks","volume":"28 4","pages":"536-546"},"PeriodicalIF":3.0,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11659817","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097447","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The rapid growth of connected devices and data traffic in modern wireless networks has made efficient resource management increasingly challenging. Applications such as smart grids, industrial IoT, autonomous transportation, and smart city infrastructures require high-performance, reliable communication. Effective link scheduling is crucial for optimizing spectrum allocation, prioritizing transmissions, and minimizing interference in these dynamic environments. This paper introduces a novel topology-aware greedy link scheduling algorithm, which leverages lightweight deep neural networks (DNNs) and explainable AI (XAI) techniques. Our approach is designed for networks with known topologies and dynamically changing link priorities, typical in environments such as smart grids and industrial IoT systems. It enhances scheduling by learning a network's topological importance offline and applying a dual-level sorting mechanism in real-time. Extensive simulations demonstrate significant improvements over benchmark algorithms, such as Local Greedy Scheduling and Greedy Maximal Scheduling, in terms of total weight and active link count, indicating better spectrum and bandwidth usage. The simulations further show that our algorithm's scheduling performance is on par with state-of-the-art machine learning (ML) methods. Additionally, the algorithm consistently performs real-time scheduling computations much faster than ML methods. These results highlight our algorithm's robustness, scalability, and practical applicability in dynamic wireless environments.
现代无线网络中连接设备和数据流量的快速增长使得有效的资源管理越来越具有挑战性。智能电网、工业物联网、自主交通和智慧城市基础设施等应用需要高性能、可靠的通信。在这些动态环境中，有效的链路调度对于优化频谱分配、传输优先级和最小化干扰至关重要。本文介绍了一种新颖的拓扑感知贪婪链路调度算法，该算法利用轻量级深度神经网络（dnn）和可解释人工智能（XAI）技术。我们的方法专为具有已知拓扑和动态变化链路优先级的网络而设计，典型的环境包括智能电网和工业物联网系统。它通过离线学习网络拓扑重要性和实时应用双级排序机制来增强调度能力。大量的模拟表明，在总权重和活动链路数方面，比基准算法（如Local Greedy Scheduling和Greedy maximum Scheduling）有了显著的改进，表明频谱和带宽的使用得到了改善。仿真进一步表明，我们的算法的调度性能与最先进的机器学习（ML）方法相当。此外，该算法始终执行实时调度计算比ML方法快得多。这些结果突出了我们的算法在动态无线环境中的鲁棒性、可扩展性和实用性。
{"title":"Topology-aware greedy link scheduling in wireless networks using explainable AI","authors":"Maryam Abbasalizadeh;Pranathi Rayavaram;Krishnaa Vellamchety;Sashank Narain","doi":"10.23919/JCN.2025.000128","DOIUrl":"https://doi.org/10.23919/JCN.2025.000128","url":null,"abstract":"The rapid growth of connected devices and data traffic in modern wireless networks has made efficient resource management increasingly challenging. Applications such as smart grids, industrial IoT, autonomous transportation, and smart city infrastructures require high-performance, reliable communication. Effective link scheduling is crucial for optimizing spectrum allocation, prioritizing transmissions, and minimizing interference in these dynamic environments. This paper introduces a novel topology-aware greedy link scheduling algorithm, which leverages lightweight deep neural networks (DNNs) and explainable AI (XAI) techniques. Our approach is designed for networks with known topologies and dynamically changing link priorities, typical in environments such as smart grids and industrial IoT systems. It enhances scheduling by learning a network's topological importance offline and applying a dual-level sorting mechanism in real-time. Extensive simulations demonstrate significant improvements over benchmark algorithms, such as Local Greedy Scheduling and Greedy Maximal Scheduling, in terms of total weight and active link count, indicating better spectrum and bandwidth usage. The simulations further show that our algorithm's scheduling performance is on par with state-of-the-art machine learning (ML) methods. Additionally, the algorithm consistently performs real-time scheduling computations much faster than ML methods. These results highlight our algorithm's robustness, scalability, and practical applicability in dynamic wireless environments.","PeriodicalId":54864,"journal":{"name":"Journal of Communications and Networks","volume":"28 4","pages":"422-444"},"PeriodicalIF":3.0,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11606625","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097761","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-08-01Epub Date: 2026-10-01DOI: 10.23919/JCN.2025.000154
{"title":"Information for authors","authors":"","doi":"10.23919/JCN.2025.000154","DOIUrl":"https://doi.org/10.23919/JCN.2025.000154","url":null,"abstract":"","PeriodicalId":54864,"journal":{"name":"Journal of Communications and Networks","volume":"28 4","pages":"548-552"},"PeriodicalIF":3.0,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11718926","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097758","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-08-01Epub Date: 2026-10-01DOI: 10.23919/JCN.2025.000155
{"title":"Open access publishing agreement","authors":"","doi":"10.23919/JCN.2025.000155","DOIUrl":"https://doi.org/10.23919/JCN.2025.000155","url":null,"abstract":"","PeriodicalId":54864,"journal":{"name":"Journal of Communications and Networks","volume":"28 4","pages":"553-555"},"PeriodicalIF":3.0,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11718927","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097838","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-08-01Epub Date: 2026-07-13DOI: 10.23919/JCN.2025.000121
Pedro Cumino;Miguel Luís;Denis Rosário;Eduardo Cerqueira;Susana Sargento
Incorporating unmanned aerial vehicle as a flying base stations (UAV-BSs) within the open radio access network (Open-RAN) framework presents a transformative shift in unmanned aerial vehicle (UAV)-assisted networks, enhancing network coverage for ground devices while improving adaptability to dynamic scenarios. In this context, it is important to design an intelligent proactive UAV-BS positioning approach, which might consider ML algorithms to predict user movement and quality of service (QoS) to improve the network operation. In this article, we introduce PURSUIT, an artificial intelligence (AI)-driven proactive positioning approach to manage UAV-BS position to improve the QoS of ground users. The key contributions include a user equipment (UE) mobility prediction model using the Kalman filter to estimate UE positions, a proactive UAV-BS deployment method employing Weighted K-Means and Hungarian algorithms for optimal positioning, and a QoS-aware estimation model using neural networks to optimize UAV-BS placement based on UE application demands and network conditions. We conducted simulations using the ns3-ORAN module and SUMO with realistic mobility traces to evaluate the performance of PURSUIT. Simulation results demonstrate that PURSUIT achieves a 30% reduction in delay compared to state-of-the-art reactive solutions, with specific improvements of 23% over Kalman Filter-only prediction, and 36% over a no-prediction approach. Furthermore, PURSUIT enhances packet delivery ratio (PDR) by over 5% across prediction strategies and up to 10% compared to reactive methods, alongside a 16% throughput improvement over Kalman Filter-only and 9% over no-prediction approaches.
{"title":"Open-RAN based proactive positioning approach to enhance UAV-assisted mobile networks","authors":"Pedro Cumino;Miguel Luís;Denis Rosário;Eduardo Cerqueira;Susana Sargento","doi":"10.23919/JCN.2025.000121","DOIUrl":"https://doi.org/10.23919/JCN.2025.000121","url":null,"abstract":"Incorporating unmanned aerial vehicle as a flying base stations (UAV-BSs) within the open radio access network (Open-RAN) framework presents a transformative shift in unmanned aerial vehicle (UAV)-assisted networks, enhancing network coverage for ground devices while improving adaptability to dynamic scenarios. In this context, it is important to design an intelligent proactive UAV-BS positioning approach, which might consider ML algorithms to predict user movement and quality of service (QoS) to improve the network operation. In this article, we introduce PURSUIT, an artificial intelligence (AI)-driven proactive positioning approach to manage UAV-BS position to improve the QoS of ground users. The key contributions include a user equipment (UE) mobility prediction model using the Kalman filter to estimate UE positions, a proactive UAV-BS deployment method employing Weighted K-Means and Hungarian algorithms for optimal positioning, and a QoS-aware estimation model using neural networks to optimize UAV-BS placement based on UE application demands and network conditions. We conducted simulations using the ns3-ORAN module and SUMO with realistic mobility traces to evaluate the performance of PURSUIT. Simulation results demonstrate that PURSUIT achieves a 30% reduction in delay compared to state-of-the-art reactive solutions, with specific improvements of 23% over Kalman Filter-only prediction, and 36% over a no-prediction approach. Furthermore, PURSUIT enhances packet delivery ratio (PDR) by over 5% across prediction strategies and up to 10% compared to reactive methods, alongside a 16% throughput improvement over Kalman Filter-only and 9% over no-prediction approaches.","PeriodicalId":54864,"journal":{"name":"Journal of Communications and Networks","volume":"28 4","pages":"445-461"},"PeriodicalIF":3.0,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11606627","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097159","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Open RAN (O-RAN) enables multi-vendor interoperability and data-driven RAN control through independently developed xApps, yet concurrent xApps can still issue conflicting actions even when each model is trained and validated offline. This paper proposes a context-aware scheduler in the Near-RT RIC that mitigates xApp conflicts by selecting which pre-trained xApp policies are allowed to update RAN control parameters under the current network context and operator intent. The scheduler is trained offline using advantage actor-critic (A2C) while treating the xApps as immutable components. We study an indirect conflict between a power allocation xApp and a resource block group (RBG) allocation xApp and evaluate two scheduling policies: (i) dynamic prioritization with action retention and (ii) baseline-augmented coordination that includes deterministic equal allocation controllers as safe modes. Simulation results in a multi-cell downlink OFDM setting show that uncoordinated concurrent deployment can incur substantial throughput loss relative to single xApp baselines, whereas the proposed scheduler consistently improves normalized throughput and reduces discarded traffic across diverse traffic and mobility contexts. The baseline-augmented policy yields the best performance by enlarging the scheduler action repertoire and enabling context-dependent composition of learned and baseline decisions. Overall, the results highlight the context-dependent nature of xApp conflicts and demonstrate that coordination can be achieved without joint xApp training, digital twin action scoring, or postdeployment model modification.
{"title":"xApp conflict mitigation with context-aware scheduler","authors":"Idris Cinemre;Toktam Mahmoodi;Amirmohammad Farzaneh","doi":"10.23919/JCN.2025.000131","DOIUrl":"https://doi.org/10.23919/JCN.2025.000131","url":null,"abstract":"Open RAN (O-RAN) enables multi-vendor interoperability and data-driven RAN control through independently developed xApps, yet concurrent xApps can still issue conflicting actions even when each model is trained and validated offline. This paper proposes a context-aware scheduler in the Near-RT RIC that mitigates xApp conflicts by selecting which pre-trained xApp policies are allowed to update RAN control parameters under the current network context and operator intent. The scheduler is trained offline using advantage actor-critic (A2C) while treating the xApps as immutable components. We study an indirect conflict between a power allocation xApp and a resource block group (RBG) allocation xApp and evaluate two scheduling policies: (i) dynamic prioritization with action retention and (ii) baseline-augmented coordination that includes deterministic equal allocation controllers as safe modes. Simulation results in a multi-cell downlink OFDM setting show that uncoordinated concurrent deployment can incur substantial throughput loss relative to single xApp baselines, whereas the proposed scheduler consistently improves normalized throughput and reduces discarded traffic across diverse traffic and mobility contexts. The baseline-augmented policy yields the best performance by enlarging the scheduler action repertoire and enabling context-dependent composition of learned and baseline decisions. Overall, the results highlight the context-dependent nature of xApp conflicts and demonstrate that coordination can be achieved without joint xApp training, digital twin action scoring, or postdeployment model modification.","PeriodicalId":54864,"journal":{"name":"Journal of Communications and Networks","volume":"28 4","pages":"478-494"},"PeriodicalIF":3.0,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11659815","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097289","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-08-01Epub Date: 2026-08-19DOI: 10.23919/JCN.2025.000135
George Nii Martey Colley;Kwame Opuni-Boachie Obour Agyekum;Kenneth Coker;Abigail Dzidzor Anku;Mohammed Saraju Abdul-Nasir;Sylvester Selase Agorbortu;Evans Tetteh Owusu;Charles Roland Haruna;Justice Owusu Agyemang;Francisca Adoma Acheampong
Device-to-device (D2D) communication has emerged as a vital paradigm within fifth-generation (5G) wireless networks, improving system capacity, spectrum performance and energy efficiency. However, the introduction of D2D links poses challenges such as interference with cellular links, complicating spectrum allocation and network quality assurance. This paper presents a novel approach that employs the temporal fusion transformer (TFT) model, an attention-based architecture, to forecast a number of locations of user equipment within D2D networks. The TFT model provides interpretable insights into temporal dynamics, enabling precise mobility forecasting. These forecast results are then used to optimize resource allocation, revealing the significant impact of mobility forecasting on resource management. Furthermore, our study demonstrates the optimal performance of the our model as against traditional ones, offering improved accuracy and efficiency in mobility forecasting and resource allocation.
{"title":"Efficient D2D resource allocation with temporal fusion transformer","authors":"George Nii Martey Colley;Kwame Opuni-Boachie Obour Agyekum;Kenneth Coker;Abigail Dzidzor Anku;Mohammed Saraju Abdul-Nasir;Sylvester Selase Agorbortu;Evans Tetteh Owusu;Charles Roland Haruna;Justice Owusu Agyemang;Francisca Adoma Acheampong","doi":"10.23919/JCN.2025.000135","DOIUrl":"https://doi.org/10.23919/JCN.2025.000135","url":null,"abstract":"Device-to-device (D2D) communication has emerged as a vital paradigm within fifth-generation (5G) wireless networks, improving system capacity, spectrum performance and energy efficiency. However, the introduction of D2D links poses challenges such as interference with cellular links, complicating spectrum allocation and network quality assurance. This paper presents a novel approach that employs the temporal fusion transformer (TFT) model, an attention-based architecture, to forecast a number of locations of user equipment within D2D networks. The TFT model provides interpretable insights into temporal dynamics, enabling precise mobility forecasting. These forecast results are then used to optimize resource allocation, revealing the significant impact of mobility forecasting on resource management. Furthermore, our study demonstrates the optimal performance of the our model as against traditional ones, offering improved accuracy and efficiency in mobility forecasting and resource allocation.","PeriodicalId":54864,"journal":{"name":"Journal of Communications and Networks","volume":"28 4","pages":"505-522"},"PeriodicalIF":3.0,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11659816","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149096991","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-08-01Epub Date: 2026-07-13DOI: 10.23919/JCN.2025.000120
Fuad M. Abinader;Sérgio R. Barros;Eduardo Melão;Edelberto Franco Silva;Francisco Raimundo Albuquerque Parente;João Guilherme;Weskley Mauricio;Sérgio M. Sakai
Integrated access and backhaul (IAB) offers a practical solution for extending network coverage in scenarios where deploying fiber-optic infrastructure is challenging, such as remote rural areas or crowded urban environments. This review examines IAB implementations across three key domains: terrestrial (ground-based), non-terrestrial (satellite), and low-altitude platforms (LAPs, like drones), focusing on recent technological advancements, operational challenges, and open research questions. We delve into advanced optimization strategies—such as Bayesian approaches to backhaul design and load-efficiency-balance (LEB) policies—that enhance IAB performance by improving traffic management and resource allocation. Through a comparative analysis of these platforms, we identify their strengths and limitations, providing actionable insights to guide the development of efficient and scalable 6G network architectures.
{"title":"Integrated access and backhaul (IAB) across terrestrial, non-terrestrial, and low-altitude platforms","authors":"Fuad M. Abinader;Sérgio R. Barros;Eduardo Melão;Edelberto Franco Silva;Francisco Raimundo Albuquerque Parente;João Guilherme;Weskley Mauricio;Sérgio M. Sakai","doi":"10.23919/JCN.2025.000120","DOIUrl":"https://doi.org/10.23919/JCN.2025.000120","url":null,"abstract":"Integrated access and backhaul (IAB) offers a practical solution for extending network coverage in scenarios where deploying fiber-optic infrastructure is challenging, such as remote rural areas or crowded urban environments. This review examines IAB implementations across three key domains: terrestrial (ground-based), non-terrestrial (satellite), and low-altitude platforms (LAPs, like drones), focusing on recent technological advancements, operational challenges, and open research questions. We delve into advanced optimization strategies—such as Bayesian approaches to backhaul design and load-efficiency-balance (LEB) policies—that enhance IAB performance by improving traffic management and resource allocation. Through a comparative analysis of these platforms, we identify their strengths and limitations, providing actionable insights to guide the development of efficient and scalable 6G network architectures.","PeriodicalId":54864,"journal":{"name":"Journal of Communications and Networks","volume":"28 4","pages":"462-477"},"PeriodicalIF":3.0,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11606628","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097669","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-08-01Epub Date: 2026-07-13DOI: 10.23919/JCN.2025.000132
Nguyen Thi Yen Linh;Pham Ngoc Son;Vo Nguyen Quoc Bao
This paper addresses the optimization of power allocation in a downlink short-packet communication system, where simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) is integrated with non-orthogonal multiple access (NOMA) to enhance the performance of multi-user networks. The proposed system jointly optimizes the source transmit power, power allocation coefficients for each user, and STAR-RIS energy coefficients and phase shifts, under a mode-switching protocol. By utilizing both the transmission and reflection capabilities of STAR-RIS, the system significantly extends signal coverage and improves overall efficiency. Additionally, the base station (BS) employs maximum-ratio transmission (MRT) beamforming to optimize the effective channel for each user, further enhancing system performance. To solve the resulting complex non-convex optimization problem, we apply deep reinforcement learning (DRL), specifically the soft actor-critic (SAC) algorithm. The SAC-based approach enables the system to adaptively optimize power allocation and STAR-RIS parameters using channel state information (CSI). Numerical simulations demonstrate that the proposed DRL solution substantially reduces computational complexity while achieving near-optimal performance, outperforming traditional optimization methods.
{"title":"Deep reinforcement learning for power allocation in STAR-RIS-assisted multi-user short-packet NOMA networks","authors":"Nguyen Thi Yen Linh;Pham Ngoc Son;Vo Nguyen Quoc Bao","doi":"10.23919/JCN.2025.000132","DOIUrl":"https://doi.org/10.23919/JCN.2025.000132","url":null,"abstract":"This paper addresses the optimization of power allocation in a downlink short-packet communication system, where simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) is integrated with non-orthogonal multiple access (NOMA) to enhance the performance of multi-user networks. The proposed system jointly optimizes the source transmit power, power allocation coefficients for each user, and STAR-RIS energy coefficients and phase shifts, under a mode-switching protocol. By utilizing both the transmission and reflection capabilities of STAR-RIS, the system significantly extends signal coverage and improves overall efficiency. Additionally, the base station (BS) employs maximum-ratio transmission (MRT) beamforming to optimize the effective channel for each user, further enhancing system performance. To solve the resulting complex non-convex optimization problem, we apply deep reinforcement learning (DRL), specifically the soft actor-critic (SAC) algorithm. The SAC-based approach enables the system to adaptively optimize power allocation and STAR-RIS parameters using channel state information (CSI). Numerical simulations demonstrate that the proposed DRL solution substantially reduces computational complexity while achieving near-optimal performance, outperforming traditional optimization methods.","PeriodicalId":54864,"journal":{"name":"Journal of Communications and Networks","volume":"28 4","pages":"495-504"},"PeriodicalIF":3.0,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11606629","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097239","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In electronic countermeasure scenarios, wireless communication systems are highly susceptible to co-channel interference (CCI), making effective CCI mitigation essential for ensuring the normal operation of the system. However, the traditional adaptive methods are difficult to effectively suppress interference when the desired signal is overwhelmed by high-power, broadband interference. To tackle this issue, we first investigated the spatiotemporal correlation discrepancy of received signals, revealing that the narrowband signal of interest (SOI) exhibits significantly stronger spatiotemporal correlation compared with broadband interference. Based on this insight, we developed a spatiotemporal adaptive broadband interference cancellation (STABC) algorithm by innovatively adapting the alternating direction method of multipliers (ADMM) framework. Unlike deep learning-based interference cancellation methods that rely on large amounts of training data, the proposed approach operates without prior knowledge of signal directions or adaptive array training data, requiring only the bandwidth information of the SOI, making it suitable for real-time and resource-constrained scenarios. Furthermore, the algorithm circumvents the computationally expensive inversion of high-dimensional matrices, thereby achieving reduced computational complexity. Additionally, we conducted a theoretical analysis of the impact of multiple transmission paths on the STABC algorithm for antenna arrays. Extensive simulation results confirm that the proposed STABC algorithm achieves faster convergence and approaches the theoretical maximum signal to interference plus noise ratio (SINR) solution more closely. Additionally, under multipath conditions, the proposed algorithm demonstrates superior performance.
{"title":"Adaptive broadband co-channel interference cancellation method based on spatiotemporal correlation","authors":"Jiaqi Liang;Yaxing Li;Yufeng Ma;Jinling Xing;Fangmin He;Jin Meng","doi":"10.23919/JCN.2025.000129","DOIUrl":"https://doi.org/10.23919/JCN.2025.000129","url":null,"abstract":"In electronic countermeasure scenarios, wireless communication systems are highly susceptible to co-channel interference (CCI), making effective CCI mitigation essential for ensuring the normal operation of the system. However, the traditional adaptive methods are difficult to effectively suppress interference when the desired signal is overwhelmed by high-power, broadband interference. To tackle this issue, we first investigated the spatiotemporal correlation discrepancy of received signals, revealing that the narrowband signal of interest (SOI) exhibits significantly stronger spatiotemporal correlation compared with broadband interference. Based on this insight, we developed a spatiotemporal adaptive broadband interference cancellation (STABC) algorithm by innovatively adapting the alternating direction method of multipliers (ADMM) framework. Unlike deep learning-based interference cancellation methods that rely on large amounts of training data, the proposed approach operates without prior knowledge of signal directions or adaptive array training data, requiring only the bandwidth information of the SOI, making it suitable for real-time and resource-constrained scenarios. Furthermore, the algorithm circumvents the computationally expensive inversion of high-dimensional matrices, thereby achieving reduced computational complexity. Additionally, we conducted a theoretical analysis of the impact of multiple transmission paths on the STABC algorithm for antenna arrays. Extensive simulation results confirm that the proposed STABC algorithm achieves faster convergence and approaches the theoretical maximum signal to interference plus noise ratio (SINR) solution more closely. Additionally, under multipath conditions, the proposed algorithm demonstrates superior performance.","PeriodicalId":54864,"journal":{"name":"Journal of Communications and Networks","volume":"28 4","pages":"409-421"},"PeriodicalIF":3.0,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11606626","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097668","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","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：