TNSM Searchable Index

Author(s)	Title	Year	Publication	Keywords
Qichen Luo, Zhiyun Zhou, Ruisheng Shi, Lina Lan, Qingling Feng, Qifeng Luo, Di Ao	Revisit Fast Event Matching-Routing for High Volume Subscriptions	2026	Early Access	Real-time systems Vectors Search problems	Although many scalable event matching algorithms have been proposed to achieve scalability for publish/subscribe services, the content-based pub/sub system still suffer from performance deterioration when the system has large numbers of subscriptions, and cannot support the requirements of real-time pub/sub data services. In this paper, we model the event matching problem as an existence problem which only care about whether there is at least one matching subscription in the given subscription set, differing from existing works that try to speed up the time-consuming search operation to find all matching subscriptions. To solve this existence problem efficiently, we propose DLS (Discrete Label Set), a novel subscription and event representation model. Based on the DLS model, we propose an event matching algorithm with O(Nd) time complexity to support real-time event matching for a large volume of subscriptions and high event arrival speed, where Nd is the node degree in overlay network. Experimental results show that the event matching performance can be improved by several orders of magnitude compared with traditional algorithms.	10.1109/TNSM.2026.3664517
Zhiwei Yu, Chengze Du, Heng Xu, Ying Zhou, Bo Liu, Jialong Li	REACH: Reinforcement Learning for Efficient Allocation in Community and Heterogeneous Networks	2026	Early Access	Graphics processing units Computational modeling Reliability	Community GPU(Graphics Processing Unit) platforms are emerging as a cost-effective and democratized alternative to centralized GPU clusters for AI(Artificial Intelligence) workloads, aggregating idle consumer GPUs from globally distributed and heterogeneous environments. However, their extreme hardware/software diversity, volatile availability, and variable network conditions render traditional schedulers ineffective, leading to suboptimal task completion. In this work, we present REACH (Reinforcement Learning for Efficient Allocation in Community and Heterogeneous Networks), a Transformer-based reinforcement learning framework that redefines task scheduling as a sequence scoring problem to balance performance, reliability, cost, and network efficiency. By modeling both global GPU states and task requirements, REACH learns to adaptively co-locate computation with data, prioritize critical jobs, and mitigate the impact of unreliable resources. Extensive simulation results show that REACH improves task completion rates by up to 17%, more than doubles the success rate for high-priority tasks, and reduces bandwidth penalties by over 80% compared to state-of-the-art baselines. Stress tests further demonstrate its robustness to GPU churn and network congestion, while scalability experiments confirm its effectiveness in large-scale, high-contention scenarios.	10.1109/TNSM.2026.3663316
Abdinasir Hirsi, Mohammed A. Alhartomi, Lukman Audah, Mustafa Maad Hamdi, Adeb Salah, Godwin Okon Ansa, Salman Ahmed, Abdullahi Farah	Hybrid CNN-LSTM Model for DDoS Detection and Mitigation in Software-Defined Networks	2026	Early Access	Prevention and mitigation Denial-of-service attack Feature extraction	Software-Defined Networking (SDN) enhances programmability and control but remains highly vulnerable to distributed denial-of-service (DDoS) attacks. Existing solutions often adapt conventional methods without leveraging SDN’s native features or addressing real-time mitigation. This study introduces a novel hybrid deep learning framework for DDoS detection and mitigation in SDN, significantly advancing the state of the art. We develop a custom dataset in a Mininet–Ryu testbed that reflects realistic SDN traffic conditions, and employ a multistage feature selection pipeline to reduce redundancy and highlight the most discriminative flow attributes. A hybrid Convolutional Neural Network–Long Short-Term Memory (CNN-LSTM) model is then applied, capturing both spatial and temporal traffic patterns. The proposed system achieves 99.5% accuracy and a 97.7% F1-score, demonstrating a significant improvement over baseline ML and DL approaches. In addition, a lightweight and scalable mitigation module embedded in the SDN controller dynamically drops or reroutes malicious flows, enabling real-time, low-latency responsiveness. Experimental results across diverse topologies confirm the framework’s scalability and applicability in real-world SDN environments.	10.1109/TNSM.2026.3662819
Mohammad Amir Dastgheib, Hamzeh Beyranvand, Jawad A. Salehi	Shannon Entropy for Load-Balanced Cellular Network Planning: Data-Driven Voronoi Optimization of Base-Station Locations	2026	Early Access	Shape Entropy Costs	In this paper, we introduce a stochastic shape optimization technique for base-station placement in cellular wireless communication networks. We formulate the data-driven facility location problem in a gradient-based framework and propose an algorithm that computes stochastic gradients efficiently via nearest-neighbor evaluations on Voronoi diagrams. This enables the use of Shannon-entropy objectives that promote balanced coverage and yield more than two orders of magnitude reduction in per-iteration runtime compared to a conventional integral-based optimization that assumes full knowledge of the under-lying density, making the proposed approach practical for real deployments. We highlight the requirements of facility location balancing problems with the introduction of the Adjusted Entropy Ratio and show a significant improvement in load balancing compared to the baseline algorithms, particularly in scenarios where baseline algorithms fall short in subdividing crowded areas for more equitable coverage. A downlink telecom evaluation with realistic propagation and interference models further shows that the proposed method configuration substantially improves user-rate fairness and load balance. Our results also show that Self-Organizing Maps (SOMs) provide an effective initialization by capturing the structure of the users’ location data.	10.1109/TNSM.2026.3663045
Rajasekhar Dasari, Sanjeet Kumar Nayak	PR-Fog: An Efficient Task Priority-based Reliable Provisioning of Resources in Fog-Enabled IoT Networks	2026	Early Access	Reliability Internet of Things Costs	As the demand for real-time data processing grows, fog computing emerges as an alternative to cloud computing, which brings computation and storage closer to IoT devices. In Fog-enabled IoT networks, provisioning of fog nodes for task processing must consider factors, such as latency, energy consumption, cost, and reliability. This paper presents PR-Fog, a scheme for optimizing the provisioning of heterogeneous fog nodes in fog-enabled IoT networks, considering parameters such as task priority, energy efficiency, cost efficiency, and reliability. At first, we create an analytical framework using M/M/1/C priority queuing system to assess the reliability of these heterogeneous fog nodes. Building on this analysis, we propose an algorithm that determines the optimal number of reliable fog nodes while satisfying latency, energy, and cost constraints. Extensive simulations show significant enhancements in key performance metrics when comparing PR-Fog to existing schemes, including a 36% decrease in response time and an 8% improvement in satisfaction ratio, resulting in minimized 23% fog node provisioning costs. Additionally, PR-Fog’s effectiveness is validated through real testbed experiments.	10.1109/TNSM.2026.3661745
Jing Zhang, Chao Luo, Rui Shao	MTG-GAN: A Masked Temporal Graph Generative Adversarial Network for Cross-Domain System Log Anomaly Detection	2026	Early Access	Anomaly detection Adaptation models Generative adversarial networks	Anomaly detection of system logs is crucial for the service management of large-scale information systems. Nowadays, log anomaly detection faces two main challenges: 1) capturing evolving temporal dependencies between log events to adaptively tackle with emerging anomaly patterns, 2) and maintaining high detection capabilities across varies data distributions. Existing methods rely heavily on domain-specific data features, making it challenging to handle the heterogeneity and temporal dynamics of log data. This limitation restricts the deployment of anomaly detection systems in practical environments. In this article, a novel framework, Masked Temporal Graph Generative Adversarial Network (MTG-GAN), is proposed for both conventional and cross-domain log anomaly detection. The model enhances the detection capability for emerging abnormal patterns in system log data by introducing an adaptive masking mechanism that combines generative adversarial networks with graph contrastive learning. Additionally, MTG-GAN reduces dependency on specific data distribution and improves model generalization by using diffused graph adjacency information deriving from temporal relevance of event sequence, which can be conducive to improve cross-domain detection performance. Experimental results demonstrate that MTG-GAN outperforms existing methods on multiple real-world datasets in both conventional and cross-domain log anomaly detection.	10.1109/TNSM.2026.3654642
Muhammad Fahimullah, Michel Kieffer, Sylvaine Kerboeuf, Shohreh Ahvar, Maria Trocan	Decentralized Coalition Formation of Infrastructure Providers for Resource Provisioning in Coverage Constrained Virtualized Mobile Networks	2026	Early Access	Indium phosphide III-V semiconductor materials Resource management	The concept of wireless virtualized networks enables Mobile Virtual Network Operators (MVNOs) to utilize resources made available by multiple Infrastructure Providers (InPs) to set up a service. Nevertheless, existing centralized resource provisioning approaches fail to address such a scenario due to conflicting objectives among InPs and their reluctance to share private information. This paper addresses the problem of resource provisioning from several InPs for services with geographic coverage constraints. When complete information is available, an Integer Linear Program (ILP) formulation is provided, along with a greedy solution. An alternative coalition formation approach is then proposed to build coalitions of InPs that satisfy the constraints imposed by an MVNO, while requiring only limited information sharing. The proposed solution adopts a hedonic game-theoretic approach to coalition formation. For each InP, the decision to join or leave a coalition is made in a decentralized manner, relying on the satisfaction of service requirements and on individual profit. Simulation results demonstrate the applicability and performance of the proposed solution.	10.1109/TNSM.2026.3663437
Jordan F. Masakuna, Djeff K. Nkashama, Arian Soltani, Marc Frappier, Pierre M. Tardif, Froduald Kabanza	Enhancing Anomaly Alert Prioritization through Calibrated Standard Deviation Uncertainty Estimation with an Ensemble of Auto-Encoders	2026	Early Access	Uncertainty Standards Measurement	Deep auto-encoders (AEs) are widely employed deep learning methods in the field of anomaly detection across diverse domains (e.g., cybersecurity analysts managing large volumes of alerts, or medical practitioners monitoring irregular patient signals). In such contexts, practitioners often face challenges of scale and limited processing resources. To cope, strategies such as false positive reduction, human-in-the-loop review, and alert prioritization are commonly adopted. This paper explores the integration of uncertainty quantification (UQ) methods into alert prioritization for anomaly detection using ensembles of AEs. UQ models highlight doubtful classification decisions, enabling analysts to address the most certain alerts first, since higher certainty typically correlates with greater accuracy. Our study reveals a nuanced issue where applying UQ to ensembles of AEs can produce skewed distributions of large reconstruction errors (errors exceeding a pre-defined threshold), which may falsely suggest high uncertainty when standard deviation is used as the metric. Conventionally, a high standard deviation indicates high uncertainty. However, contrary to intuition, large reconstruction errors often reflect AE is strongly confident that an input is anomalous—not uncertainty about it. Moreover, ensembles of AEs generate reconstruction errors with varying ranges, complicating interpretation. To address this, we propose an extension that calibrates the standard deviation distribution of uncertainties, mitigating erroneous prioritization. Evaluation on 10 benchmark datasets demonstrates that our calibration approach improves the effectiveness of UQ methods in prioritizing alerts, while maintaining favorable trade-offs across other key performance metrics.	10.1109/TNSM.2026.3664298
Domenico Scotece, Giuseppe Santaromita, Claudio Fiandrino, Luca Foschini, Domenico Giustiniano	On the Scalability of Access and Mobility Management Function: the Localization Management Function Use Case	2026	Early Access	5G mobile communication Scalability Location awareness	The adoption of Service-Based Architecture (SBA) in 5G Core Networks (5GC) has significantly transformed the design and operation of the control plane, enabling greater flexibility and agility for cloud-native deployments. While the infrastructure has initially evolved by implementing key functions, there remains significant potential for additional services, such as localization, paving the way for the integration of the Location Management Function (LMF). However, the extensive functional decomposition within SBA leads to consequences, such as the increase of control plane operations. Specifically, we observe that the additional signaling traffic introduced by the presence of the LMF overwhelms the Access and Mobility Management Function (AMF) which is responsible for authentication and mobility. In fact, in mobile positioning, each connected mobile device requires a significant amount of control traffic to support location algorithms in the 5GC. To address this scalability challenge, we analyze the impact of three well-known optimization techniques on location procedures to reduce control message traffic in the specific context of the 5GC, namely a caching system, a request aggregation system, and a service scalability system. Our solutions are evaluated in an OpenAirInterface (OAI) emulated environment with real hardware. After the analysis in the emulated environment, we select the caching system – due to its feasibility – for being analyzed in a real 5G testbed. Our results demonstrate a significant reduction in the additional overhead introduced by the LMF, improving scalability by minimizing the impact on AMF processing time up to a 50% reduction.	10.1109/TNSM.2026.3664546
Liang Kou, Xiaochen Pan, Guozhong Dong, Meiyu Wang, Chunyu Miao, Jilin Zhang, Pingxia Duan	Dynamic Adaptive Aggregation and Feature Pyramid Network Enhanced GraphSAGE for Advanced Persistent Threat Detection in Next-Generation Communication Networks	2026	Early Access	Feature extraction Adaptation models Computational modeling	Advanced Persistent Threats (APTs) pose severe challenges to Next-Generation Communication Networks (NGCNs) due to their stealthiness and NGCNs’ dynamic topology, while conventional GNN-based intrusion detection systems suffer from static aggregation and poor adaptability to unseen nodes. To address these issues, this paper proposes DAA-FPN-SAGE, a lightweight graph-based detection framework integrating Dynamic Adaptive Aggregation (DAA) and Multi-Scale Feature Pyramid Network (MSFPM). Leveraging GraphSAGE’s inductive learning capability, the framework effectively models unseen nodes or subgraphs and adapts to NGCN’s dynamic changes (e.g., elastic network slicing, online AI model updates)—a key advantage for handling NGCN’s real-time topological variations. The DAA module employs multi-hop attention to dynamically assign weights to neighbors at different hop distances, enhancing capture of hierarchical dependencies in multi-stage APT attack chains. The MSFPM module fuses local-global structural information via a gated feature selection mechanism, resolving dimensional inconsistency and enriching attack behavior representation. Extensive experiments on StreamSpot, Unicorn, and DARPA TC#3 datasets demonstrate superior performance, meeting detection requirements of large-scale NGCNs.	10.1109/TNSM.2026.3660650
Deemah H. Tashman, Soumaya Cherkaoui	Trustworthy AI-Driven Dynamic Hybrid RIS: Joint Optimization and Reward Poisoning-Resilient Control in Cognitive MISO Networks	2026	Early Access	Reconfigurable intelligent surfaces Reliability Optimization	Cognitive radio networks (CRNs) are a key mechanism for alleviating spectrum scarcity by enabling secondary users (SUs) to opportunistically access licensed frequency bands without harmful interference to primary users (PUs). To address unreliable direct SU links and energy constraints common in next-generation wireless networks, this work introduces an adaptive, energy-aware hybrid reconfigurable intelligent surface (RIS) for underlay multiple-input single-output (MISO) CRNs. Distinct from prior approaches relying on static RIS architectures, our proposed RIS dynamically alternates between passive and active operation modes in real time according to harvested energy availability. We also model our scenario under practical hardware impairments and cascaded fading channels. We formulate and solve a joint transmit beamforming and RIS phase optimization problem via the soft actor-critic (SAC) deep reinforcement learning (DRL) method, leveraging its robustness in continuous and highly dynamic environments. Notably, we conduct the first systematic study of reward poisoning attacks on DRL agents in RIS-enhanced CRNs, and propose a lightweight, real-time defense based on reward clipping and statistical anomaly filtering. Numerical results demonstrate that the SAC-based approach consistently outperforms established DRL base-lines, and that the dynamic hybrid RIS strikes a superior trade-off between throughput and energy consumption compared to fully passive and fully active alternatives. We further show the effectiveness of our defense in maintaining SU performance even under adversarial conditions. Our results advance the practical and secure deployment of RIS-assisted CRNs, and highlight crucial design insights for energy-constrained wireless systems.	10.1109/TNSM.2026.3660728
Jing Huang, Yabo Wang, Honggui Han	SCFusionLocator: A Statement-Level Smart Contract Vulnerability Localization Framework Based on Code Slicing and Multi-Modal Feature Fusion	2026	Early Access	Smart contracts Feature extraction Location awareness	Smart contract vulnerabilities have led to over $20 billion in losses, but existing methods suffer from coarse-grained detection, two-stage “detection-then-localization” pipelines, and insufficient feature extraction. This paper proposes SCFusionLocator, a statement-level vulnerability localization framework for smart contracts. It adopts a novel code-slicing mechanism (via function call graphs and data-flow graphs) to decompose contracts into single-function subcontracts and filter low-saliency statements, paired with source code normalization to reduce noise. A dual-branch architecture captures complementary features: the code-sequence branch uses GraphCodeBERT (with data-flow-aware masking) for semantic extraction, while the graph branch fuses call/control-flow/data-flow graphs into a heterogeneous graph and applies HGAT for structural modeling. SCFusionLocator enables end-to-end statement-level localization by framing tasks as statement classification.We release BJUT_SC02, a large dataset of over 240,000 contracts with line-level labels for 58 vulnerability types. Experiments on BJUT_SC02, SCD, and MANDO datasets show SCFusionLocator outperforms 8 conventional tools and nearly 20 ML baselines, achieving over 90% average F1 at the statement level, with better generalization to similar unknown vulnerabilities, and remains competitive in contract-level detection.	10.1109/TNSM.2026.3664599
Shiyu Yang, Qunyong Wu, Zhanchao Huang, Zihao Zhuo	SGA-Seq: Station-aware Graph Attention Sequence Network for Cellular Traffic Prediction	2026	Early Access	Adaptation models Predictive models Spatiotemporal phenomena	Cellular traffic prediction is crucial for optimizing network resources and enhancing service quality. Despite progress in existing traffic prediction methods, challenges remain in capturing periodic features, spatial heterogeneity, and abnormal signals. To address these challenges, we propose a Station-aware Graph Attention Sequence Network (SGA-Seq). The core idea is to achieve accurate cellular traffic prediction by adaptively modeling station-specific spatiotemporal patterns and effectively handling complex traffic dynamics. First, we introduce a learnable temporal embedding mechanism to capture temporal features across multiple scales. Second, we design a station-aware graph attention network to model complex spatial relationships across stations. Additionally, by progressively separating regular and abnormal signals layer by layer, we enhance the model’s robustness. Experimental results demonstrate that SGA-Seq outperforms existing methods on five diverse mobile network datasets spanning different scales, including cellular traffic, mobility flow, and communication datasets. Notably, on the V-GCT dataset, our method achieves an 8.04% improvement in Root Mean Squared Error compared to the Spatiotemporal-aware Trend-Seasonality Decomposition Network. The code of SGA-Seq is available at https://github.com/OvOYu/SGA-Seq.	10.1109/TNSM.2026.3664401
Fengqi Li, Yudong Li, Lingshuang Ma, Kaiyang Zhang, Yan Zhang, Chi Lin, Ning Tong	Integrated Cloud-Edge-SAGIN Framework for Multi-UAV Assisted Traffic Offloading Based On Hierarchical Federated Learning	2026	Early Access	Resource management Autonomous aerial vehicles Heuristic algorithms	The growing number of mobile devices used by terrestrial users has significantly amplified the traffic load on cellular networks. Especially in urban environments, the high traffic demand brought about by dense user populations has bottlenecked network resources. The Space-Air-Ground-Integrated Network (SAGIN) provides a new solution to cope with this demand, enhancing data transmission efficiency through a multi-layered network structure. However, the heterogeneous and dynamic nature of SAGIN also poses significant management and resource allocation challenges. In this paper, we propose a cloud-edge-SAGIN framework for multi-UAV assisted traffic offloading based on Hierarchical Federated Learning (HFL), aiming to improve the traffic offloading ratio while optimizing the offloading resource allocation. HFL is used instead of traditional Federated Learning (FL) to solve problems such as irrational resource allocation due to heterogeneity in SAGIN. Specifically, the framework applies a hierarchical federated average algorithm and sets a reward function at the ground level, aiming to obtain better model parameters, improve model accuracy at aggregation, enhance UAV traffic offloading ratio, and optimize its scheduling and resource allocation. In addition, an improved Reinforcement Learning (RL) algorithm TD3-A4C is designed in this paper to assist UAVs in realizing intelligent decision-making, reducing communication latency, and further improving resource utilization efficiency. Simulation results demonstrate that the proposed framework and algorithms display superior performance across all dimensions and offer robust support for the comprehensive investigation of intelligent traffic offloading networks.	10.1109/TNSM.2026.3658833
Yuhao Chen, Jinyao Yan, Yuan Zhang, Lingjun Pu	WiLD: Learning-based Wireless Loss Diagnosis for Congestion Control with Ultra-low Kernel Overhead	2026	Early Access	Packet loss Kernel Linux	Current congestion control algorithms (CCAs) are inefficient in wireless networks due to the lack of distinction of congestion and wireless packet losses. In this work, we propose a simple yet effective learning-based wireless loss diagnosis (WiLD) solution for enhancing wireless congestion control. WiLD uses a neural network (NN) to accurately distinguish between wireless packet loss and congestion packet loss. To seamlessly cooperate with rule-based CCAs and make real-time decisions, we further implement WiLD in Linux kernel to avoid the frequent kernel-space communication. Specifically, we use a lightweight NN for inference and propose an integer quantization for WiLD deployment in various Linux versions. Real-world experiments and simulations demonstrate that WiLD can accurately differentiate the wireless and congestion packet loss with negligible CPU overhead (around 1% of WiLD vs. around 100% of learning-based algorithms such as Vivace and Aurora) and fast inference time (45% less compared to TensorFlow Lite). When combined with Cubic, WiLD-Cubic can achieve around 792%, 536%, 412%, 231%, 218%, 108%, 85% and 291% throughput improvement compared with BBRv2, Cubic, Westwood, Copa, Copa+, Vivace, Aurora and Indigo in the real network environment.	10.1109/TNSM.2026.3664422
Shagufta Henna, Upaka Rathnayake	Hypergraph Representation Learning-Based xApp for Traffic Steering in 6G O-RAN Closed-Loop Control	2026	Vol. 23, Issue	Open RAN Resource management Ultra reliable low latency communication	This paper addresses the challenges in resource allocation within disaggregated Radio Access Networks (RAN), particularly when dealing with Ultra-Reliable Low-Latency Communications (uRLLC), enhanced Mobile Broadband (eMBB), and Massive Machine-Type Communications (mMTC). Traditional traffic steering methods often overlook individual user demands and dynamic network conditions, while multi-connectivity further complicates resource management. To improve traffic steering, we introduce Tri-GNN-Sketch, a novel graph-based deep learning approach employing Tri-subgraph sampling to enhance link prediction in Open RAN (O-RAN) environments. Link prediction refers to accurately forecasting optimal connections between users and network resources using current and historical measurements. Tri-GNN-Sketch is trained on real-world 4G/5G RAN monitoring data. The model demonstrates robust performance across multiple metrics, including precision, recall, F1 score, and ROC-AUC, effectively modeling interfering nodes for accurate traffic steering. We further propose Tri-HyperGNN-Sketch, which extends the approach to hypergraph modeling, capturing higher-order multi-node relationships. Using link-level simulations based on Channel Quality Indicator (CQI)-to-modulation mappings and LTE transport block size specifications, we evaluate throughput and packet delay for Tri-HyperGNN-Sketch. Tri-HyperGNN-Sketch achieves an exceptional link prediction accuracy of 99.99% and improved network-level performance, including higher effective throughput and lower packet delay compared to Tri-GNN-Sketch (95.1%) and other hypergraph-based models such as HyperSAGE (91.6%) and HyperGCN (92.31%) for traffic steering in complex O-RAN deployments.	10.1109/TNSM.2026.3654534
Apurba Adhikary, Avi Deb Raha, Yu Qiao, Md. Shirajum Munir, Mrityunjoy Gain, Zhu Han, Choong Seon Hong	Age of Sensing Empowered Holographic ISAC Framework for nextG Wireless Networks: A VAE and DRL Approach	2026	Vol. 23, Issue	Array signal processing Resource management Integrated sensing and communication	This paper proposes an AI framework that leverages integrated sensing and communication (ISAC), aided by the age of sensing (AoS) to ensure the timely location updates of the users for a holographic MIMO (HMIMO)-assisted base station (BS)-enabled wireless network. The AI-driven framework aims to achieve optimized power allocation for efficient beamforming by activating the minimal number of grids from the HMIMO BS for serving the users. An optimization problem is formulated to maximize the sensing utility function, aiming to maximize the communication signal-to-interference-plus-noise ratio (SINR ${_{c}}$ ) of the received signals and beam-pattern gains to improve the sensing SINR of reflected echo signals, which in turn maximizes the achievable rate of users. A novel AI-driven framework is presented to tackle the formulated NP-hard problem that divides it into two problems: a sensing problem and a power allocation problem. The sensing problem is solved by employing a variational autoencoder (VAE)-based mechanism that obtains the sensing information leveraging AoS, which is used for the location update. Subsequently, a deep deterministic policy gradient-based deep reinforcement learning scheme is devised to allocate the desired power by activating the required grids based on the sensing information achieved with the VAE-based mechanism. Simulation results demonstrate the superior performance of the proposed AI framework compared to advantage actor-critic and deep Q-network-based methods, achieving a cumulative average SINR ${_{c}}$ improvement of 8.5 dB and 10.27 dB, and a cumulative average achievable rate improvement of 21.59 bps/Hz and 4.22 bps/Hz, respectively. Therefore, our proposed AI-driven framework guarantees efficient power allocation for holographic beamforming through ISAC schemes leveraging AoS.	10.1109/TNSM.2026.3654889
Jian Ye, Lisi Mo, Gaolei Fei, Yunpeng Zhou, Ming Xian, Xuemeng Zhai, Guangmin Hu, Ming Liang	TopoKG: Infer Internet AS-Level Topology From Global Perspective	2026	Vol. 23, Issue	Business Topology Routing	Internet Autonomous System (AS) level topology includes AS topology structure and AS business relationships, describes the essence of Internet inter-domain routing, and is the basis for Internet operation and management research. Although the latest topology inference methods have made significant progress, those relying solely on local information struggle to eliminate inference errors caused by observation bias and data noise due to their lack of a global perspective. In contrast, we not only leverage local AS link features but also re-examine the hierarchical structure of Internet AS-level topology, proposing a novel inference method called topoKG. TopoKG introduces a knowledge graph to represent the relationships between different elements on a global scale and the business routing strategies of ASes at various tiers, which effectively reduces inference errors resulting from observation bias and data noise by incorporating a global perspective. First, we construct an Internet AS-level topology knowledge graph to represent relevant data, enabling us to better leverage the global perspective and uncover the complex relationships among multiple elements. Next, we employ knowledge graph meta paths to measure the similarity of AS business routing strategies and introduce this global perspective constraint to infer the AS business relationships and hierarchical structure iteratively. Additionally, we embed the entire knowledge graph upon completing the iteration and conduct knowledge inference to derive AS business relationships. This approach captures global features and more intricate relational patterns within the knowledge graph, further enhancing the accuracy of AS-level topology inference. Compared to the state-of-the-art methods, our approach achieves more accurate AS-level topology inference, reducing the average inference error across various AS link types by up to 1.2 to 4.4 times.	10.1109/TNSM.2026.3652956
Ze Wei, Rongxi He, Chengzhi Song, Xiaojing Chen	Differentiated Offloading and Resource Allocation With Energy Anxiety Level Consideration in Heterogeneous Maritime Internet of Things	2026	Vol. 23, Issue	Internet of Things Resource management Carbon footprint	The popularity of maritime activities not only exacerbates the carbon footprint (CF) but also places higher demands on Maritime Internet of Things (MIoTs) to support heterogeneous MIoT devices (MIoTDs) with different prioritized tasks. High-priority tasks can be processed cooperatively via local computation, offloading to nearby MIoTDs (helpers), or offloading to edge servers to ensure their timely and successful completion. Due to the differences in energy availability and rechargeability, MIoTDs exhibit distinct energy states, impacting their operational behaviors. We propose the Energy Anxiety Level (EAL) to quantify these states: Higher EAL tends to lead to increased packet dropping and earlier shutdown. Although low-EAL MIoTDs seem preferable as helpers, their scarce residual computational resources after local task completion may cause offloaded high-priority tasks to drop or time out. Therefore, helper selection should jointly consider candidate MIoTDs’ EALs and loads to evaluate their unsuitability. This paper addresses the problem of differentiated task offloading and resource allocation in MIoTs by formulating it as a mixed integer nonlinear programming model. The objective is to minimize system-wide carbon footprint (CF), packet loss, helper unsuitability risk, and high-priority task latency. To solve this complex problem, we decompose it into two subproblems. We then design algorithms to determine optimal offloading patterns, task partitioning factors, MIoTD transmission powers, and computation resource allocation for MIoTDs and edge servers. Simulation results demonstrate that our proposal outperforms benchmarks in reducing CF and EAL, lowering high-priority task latency, and improving task completion ratio.	10.1109/TNSM.2026.3655385
Xiaofeng Liu, Naigong Zheng, Fuliang Li	Don’t Let SDN Obsolete: Interpreting Software-Defined Networks With Network Calculus	2026	Vol. 23, Issue	Delays Calculus Analytical models	Although Software-Defined Network (SDN) has gained popularity in real-world deployments for its flexible management paradigm, its centralized control principle leads to various known performance issues. In this paper, we propose SDN-Mirror, a novel generalized delay analytical model based on network calculus, to interpret how the performance is affected and to illustrate how to accelerate the performance as well. We first elaborate the impact of parameters on packet forwarding delay in SDN, including device capacity, flow features and cache size. Then, building upon the analysis, we establish SDN-Mirror, which acts like a mirror, capable of not only precisely representing the relation between packet forwarding delay and each parameter but also verifying the effectiveness of optimization policies. At last, we evaluate SDN-Mirror by quantifying how each parameter affects the forwarding delay under different table matching states. We also verify a performance improvement policy with the optimized SDN-Mirror and experiment results show that packet forwarding delays of kernel space matching flow, userspace matching flow and unmatched flow can be reduced by 39.8%, 20.7% and 13.2%, respectively.	10.1109/TNSM.2026.3655704