Last updated: 2026-11-19 05:01 UTC
All documents
Number of pages: 179
| Author(s) | Title | Year | Publication | Keywords | ||
|---|---|---|---|---|---|---|
| Messaoud Ait-Yahia, Wael Jaafar, Rami Langar | Joint Design of Blockchain-Enabled Service Placement and Task Assignment in Vehicular Fog Computing Networks | 2026 | Early Access | Delays Timing Optimization Autonomous aerial vehicles Modeling Gallium Central Processing Unit Joints Bandwidth Elementary particles Resource allocation Blockchain VNF placement task assignment vehicular fog computing PSO GA IoV | Driven by the evolution of blockchain and fog computing, vehicular networks are increasingly capable of supporting latency-sensitive applications with enhanced security and trust guarantees. However, the joint resource allocation for task offloading and blockchain services has been insufficiently investigated in existing works. To address this gap, this paper proposes a framework for jointly allocating resources of blockchain, users’ virtualized services, and Mobile Edge Computing (MEC) task assignment in Vehicular Fog Computing (VFC) networks. Specifically, we formulate the optimization problem as an integer nonlinear programming model aiming to maximize the satisfaction rate of users’ service requests while minimizing the corresponding blockchain operation time under mobility, queuing, instantiation, and resource constraints. To solve it in a timely manner, we design two-stage hierarchical low-complexity solutions, namely a Particle Swarm Optimization-based Joint Blockchain-enabled Service placement and Task Assignment algorithm (PSO-JBSTA), and a Genetic Algorithm-based approach (GA-JBSTA). Through extensive simulations, we demonstrate the effectiveness of PSO-JBSTA (resp. GA-JBSTA) and their adaptability to network conditions, achieving an average 35% (resp. 24%) improvement in users’ service satisfaction rate and 9.5% (resp. 10.2%) reduction in average blockchain validation delay compared with the baselines. | 10.1109/TNSM.2026.3737068 |
| Mohammad Saberi, Ali Ahmadi Esfidi, Mahdi Dolati, Naeimeh Omidvar | FlexINA: In-Network Aggregation for Accelerating Distributed Machine Learning with Flexible Routing | 2026 | Early Access | Modeling Switches Timing Routing Machine learning Training Runtime Memory Loading Topology Distributed Machine Learning Programmable Networks In-Network Computing | The growing scale and complexity of modern machine learning (ML) models have rendered distributed training indispensable. However, as model dimensions expand, communication overhead increasingly dominates the overall training time, creating a critical performance bottleneck. While techniques such as gradient compression offer partial relief, they often incur substantial computational overhead or require specialized hardware. In-network aggregation (INA) has emerged as a compelling alternative, offloading partial computations—such as gradient reduction—directly onto programmable network switches. Yet, current INA frameworks predominantly rely on rigid, static routing schemes or uncoordinated, opportunistic aggregation, fundamentally limiting their capacity to exploit the full potential of programmable data planes. To address this limitation, we formulate the Joint Scheduling-Routing for In-Network Aggregation (JINA) problem. JINA introduces a time-slotted execution model to enable fine-grained temporal scheduling synchronously with spatial routing. By leveraging source routing, it dictates perpacket forwarding paths while explicitly coordinating multi-hop partial aggregation across the network. Furthermore, we propose FlexINA, a scalable optimization framework that solves the JINA problem through a three-phase dimensionality reduction strategy: host-level pre-aggregation, topological switch filtration, and temporal window partitioning. Extensive evaluations across fifteen diverse network topologies demonstrate that FlexINA reduces the total network load by up to 8.3% compared to INA baselines, while maintaining high computational efficiency. | 10.1109/TNSM.2026.3740503 |
| 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 Security MISO Array signal processing Vectors Satellites Reflection Interference Beamforming cascaded channels cognitive radio networks deep reinforcement learning dynamic hybrid reconfigurable intelligent surfaces energy harvesting poisoning attacks | 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 |
| Shengye Gong, Hui Yang, Qiuyan Yao, Xin Li, Tiankuo Yu, Wenxin Liu, Yang Zhao, Yucong Liu, Jie Zhang, Mohamed Cheriet | Resilient Hierarchical Polyhedron-based Configuration Protection for Large-Scale Multi-Domain Optical Networks | 2026 | Early Access | High performance computing Joining processes Protection Topology Costing Optical fiber networks Algorithms Modeling Architecture Computer architecture Network survivability multi-domain optical network network protection hierarchical polyhedron-based protection | Large-scale multi-domain optical networks are increasingly exposed to spatially correlated and concurrent failures, while monolithic pre-configured protection structures incur rapidly increasing global search complexity and protection-resource costs under heterogeneous physical constraints. To address this challenge, this paper proposes a resilient Hierarchical Polyhedron-based Configuration (HPC) architecture that decomposes a monolithic global survivability requirement into adaptive intra-domain connectivity constraints and a compact inter-domain connectivity constraint. To alleviate resource imbalance caused by topology-only network partitioning, a Topology-Resource Aware Domain Partitioning (TRADP) algorithm is developed to construct protection-supportable sub-domains by jointly considering topological structure and physical resource distribution. To avoid imposing a rigid protection level on heterogeneous domains, HPC assigns adaptive intra-domain connectivity targets according to local failure exposure and physical resource supportability. To reduce the complexity of cross-domain protection while preserving physical feasibility, a super-node abstraction and physical bridge-link mapping mechanism is employed to construct the inter-domain protection backbone under capacity, spectrum, and SRLG constraints. Extensive evaluations on networks of up to 1000 nodes and representative GEANT and NSFNET topologies demonstrate that HPC-TRADP maintains a recovery rate of 92.94% at 1000 nodes and 85.82% even when 30% of physical links fail concurrently. It further reduces protection overhead by up to 79.60% relative to p-KECS while maintaining efficient recovery paths, demonstrating a favorable balance between survivability, resource efficiency, and scalability. | 10.1109/TNSM.2026.3750417 |
| Franck Messaoudi, Luhan Wang, Abdelkader Mekrache, Adlen Ksentini, Bingxuan Li, Jialei Su, Sofiane Messaoudi, Salim El Ghalbzouri | The Brewing Storm in 5G’s Data Plane: Design and Evaluation of a High-Performance eBPF/XDP-Based User Plane Function | 2026 | Early Access | Quality of service Fluid flow Kernel Information rates Throughput Planing 5G mobile communication Linux Filtering Filters 5 th Generation Mobile Networks (5G) User Plane Function (UPF) QoS Enforcement Rule (QER) Quality of Service (QoS) extended Berkeley Packet Filter (eBPF) eXpress Data Path (XDP) Traffic Control (tc) Queuing Discipline (qdisc) | This paper presents the design and implementation of a novel 5G UPF leveraging eBPF technology to meet the stringent performance and programmability requirements of emerging 6G systems. Traditional UPF implementations often struggle to balance performance, flexibility, and resource efficiency-challenges particularly critical in CPU- and I/O-constrained edge environments. The proposed eBPF-based UPF architecture mitigates these limitations by embedding core functionalities, such as packet classification, forwarding, and QoS enforcement, directly within the Linux kernel via eBPF programs attached through XDP and tc hook points. Performance evaluation using TRex demonstrates that the proposed solution achieves competitive throughput, low packet loss, and efficient CPU utilization across traffic profiles. Moreover, it maintains full compliance with 5G Core Network standards. Comparative analysis with well-established open-source UPF implementations further underscores its advantages. This work highlights the potential of eBPF as a foundational technology for building next-generation, programmable UPFs optimized for edge cloud deployments in the 6G era. | 10.1109/TNSM.2026.3720812 |
| Ting-Yu Chang, Cooper Cheng-Yuan Ku | Two-tier Framework with AutoML for Detection and Classification of Multiple Types of Anomalies in Intrusion Attacks | 2026 | Early Access | Modeling Optimization Probability Automated machine learning Labeling Training Algorithms Stacking Accuracy Tuning Intrusion Detection Anomaly Classification Cybersecurity Data Imbalance Computational Efficiency Two-tier Framework Machine Learning Probability Stacking Method | Ensuring cybersecurity is paramount for protecting sensitive data and defending against increasingly sophisticated cyberattacks. Consequently, intrusion detection (ID) has become a critical area of research in network security. This paper proposes a two-tier framework that leverages efficient automated machine learning (AutoML) techniques to address data imbalance and optimize feature combinations for ID and classification of multiple types of anomalies. In the first tier, two complementary models are selected: a primary model optimized for overall dataset performance and a secondary model specifically chosen for its effectiveness on balanced data distributions. In the second tier, a probability stacking approach, supported by Out-of-Fold (OOF) cross-validation, integrates insights from the first-tier models. It acts as a binary safety net that successfully recovers rare minority attacks while preventing irreversible information loss. The proposed framework effectively mitigates the adverse effects of data imbalance while requiring only a minimal runtime memory footprint of approximately 44 MB (NSL-KDD) and a total process footprint of 165.52 MB (CIC-IIoT-2025), and achieves a rapid cold-start initialization of 0.85 seconds. These advantages make it well-suited for edge computing. Experimental results on the NSL-KDD dataset demonstrate that the proposed approach achieves an overall accuracy of 99.73%, outperforming many state-of-the-art methods by 0.4-20.6%. Furthermore, evaluations on the CIC-IDS-2017 dataset show a 6.3% accuracy improvement and a significant 36% increase in macro-average recall compared with a random-forest-only (RF-only) model. Moreover, extensive validation on the contemporary CIC-IIoT-2025 dataset reveals a significant 4.20% improvement in Macro F1-score over up-to-date baselines. Finally, evaluations on an independent set with novel attack types (KDDTest+) confirm strong generalization capability, achieving 77.10% accuracy and underscoring the framework's robustness in modern industrial scenarios. | 10.1109/TNSM.2026.3747311 |
| Hongyuan Cheng, Lihua Yin, Tianqing Zhu, Hongyu Yang, Dexin Zhu, Weixiang Jiang, Nan Wei | Pattern2Bot: A malicious server IP detection model based on self-trained heterogeneous graph neural network | 2026 | Early Access | Labeling Modeling Signal detection Training Botnet Servers IP networks Sequential analysis Conferences Security Botnet detection Self-supervised Graph neural network Command & Control service | Botnets play a key role in network attacks such as Distributed Denial-of-Service (DDoS) attacks, spamming and click fraud. Command & Control server is an important node for botmaster to control bots and distribute attack commands. Bot disguise as normal domain requests through DNS traffic, but leave malicious records in DNS logs containing client IP, query domain, server IP and other complex interactions. This information provides important clues for detecting those botnets. In the current study, researchers detect botnets through multiple perspectives, including abstracting DNS communication records into graphs and using graph neural network models for detection. Conventional approaches often necessitate massive labeled datasets for model training, which substantially incurs training costs. Moreover, despite enriching node embeddings via topological relations, graph models often suffer performance degradation when confronted with structural semantic obfuscation from evasion techniques like double-flux. In order to understand the abstract and complex relationship patterns in DNS records while reducing label usage to lower training costs, we propose a botnet Command & Control server detection model based on DNS traffic. This is a self-training heterogeneous graph neural network model that does not require a large number of labels. By integrating the high-order relational semantics derived from multiple meta-paths with the local topologies of target nodes, the model achieves finer-grained structural awareness and semantic abstraction, thereby enhancing detection performance. We validate the effectiveness of the model in a real dataset, and the results show that the model has a better understanding of the special structure possessed by the IPs of Command & Control servers. | 10.1109/TNSM.2026.3741111 |
| Soonbeom Kwon, Yusu Noh, Youngwoo Jang, Illyoung Choi, Byungchul Tak, In-geol Chun, Young-Kyoon Suh | Scalable and Robust Resource Provisioning via Adaptive Task Scheduling for Edge Devices | 2026 | Early Access | Schedules Scheduling Cloning Timing Educational institutions Computers Transcoding Videos Tail Edge computing Edge devices Edge server Resource augmentation Task distribution Kubernetes | Edge devices, such as wearables, drones, and CCTV systems, are vital for real-time data collection in urban intelligence. However, their limited computational and storage capacities pose significant challenges. While offloading to public clouds offers scalability, it often incurs high latency and operational costs. Conversely, centralizing workloads on edge servers may result in the underutilization of high-performance edge devices. To address these limitations, we introduce ERPF, a Kubernetes-based Edge Resource Provisioning Framework that augments the capabilities of heterogeneous edge environments. ERPF orchestrates dynamic volume provisioning, GPU-aware resource allocation, execution context migration, and adaptive task distribution to improve system flexibility and efficiency. Building on this, we propose a novel adaptive task scheduling technique, termed eATS, composed of three key mechanisms: (i) Partition Smoothing Scheme for stable task granularity control, (ii) Resilient Edge Reintegration for failure detection and task reassignment, and (iii) Competitive Task Cloning for speculative execution with fastest-result commitment. The proposed eATS scheme reduces task execution time by up to 27.6%, lowers partition size variability by 8.7×, and improves scheduling robustness across heterogeneous edge devices over the baseline. | 10.1109/TNSM.2026.3694238 |
| Yichen Zhang, Di Chen, Kaijie Zhu, Zekun Tao, Wei Lin, Rui Zheng | Beyond Valley-Free: Transformer-based AS Path Inference Using Path Embedding | 2026 | Early Access | Border Gateway Protocol Routing Ranking (statistics) Modeling Training Transformers Measurement Conferences Heart rate Probability AS path inference inter-domain routing Border Gateway Protocol network traffic analysis | Gaining insight into autonomous system (AS)-level paths is essential for understanding Internet routing behaviors and enhancing inter-domain routing security. Due to increasingly complex Internet topology and limited measurement access (e.g., router-side ICMP restrictions), few AS paths can be accurately observed, making AS path inference a necessity. However, most existing inference methods are developed based on the valley-free constraint. This limits their ability to capture real-world dynamic routing behaviors. In this paper, we propose PathRank, a Transformer-based method that infers AS paths from a source-AS to a destination-prefix through probability-based ranking, thereby closely reflecting real-world inter-domain routing complexities. From observable BGP data, PathRank generates candidate paths, encodes them as embeddings for a self-attention mechanism to capture cross-hop dependencies, and employs a prefix-length-weighted loss function during training to reflect real-world traffic impacts.We conduct experiments on large-scale public BGP datasets covering IPv4 and IPv6. PathRank places the observed BGP path among the top-10 ranked candidates in 96.82% (IPv4) and 96.65% (IPv6) of test cases, outperforming the strongest external baseline by 4.20 and 11.72 percentage points, respectively. On non-valley-free cases, where valley-free-constrained methods degrade significantly, PathRank maintains inference performance. | 10.1109/TNSM.2026.3752819 |
| Vincent Sheh, Yao Chiang, Hung-Yu Wei | Two-Timescale Service Orchestration for Dependable Multi-Region Edge Analytics under Adversarial Workloads | 2026 | Early Access | Modeling Delays Routing Costing Inspection Central Processing Unit Receivers Signal detection Degradation Accuracy Edge computing resource management task offloading intrusion detection systems Yo-Yo attacks multi-agent reinforcement learning | Adversarial workloads can saturate the shared CPU budget of edge nodes, undermining the continuous availability that safety-critical analytics require. Co-locating an inline intrusion detection system (IDS) can filter malicious traffic but creates contention with analytics inference over the same budget, producing a defense-service resource tradeoff. This tradeoff is destabilized by two mechanisms: adaptive Yo-Yo attacks that exploit container scaling delay, and load-based offloading that ignores cross-region IDS mismatch. We propose a two-timescale orchestration framework that jointly minimizes service-level objective (SLO) violations, residual malicious leakage, and benign quality degradation. A long-timescale multi-agent reinforcement learning policy partitions CPU between inspection and inference, internalizing scaling delay and coordinating across regions to suppress oscillatory reallocation. A short-timescale heuristic routes inspection traffic to receivers with compatible detection models, preventing the mismatched-IDS errors that load-based routing would induce. Compared with a representative state-of-the-art baseline, the framework achieves up to 68.8% lower SLO violation rate, 90.9% lower residual malicious leakage, and 64.6% fewer reallocations. | 10.1109/TNSM.2026.3753027 |
| Arshee Naz, Sakshi Maurya, Karan Verma, Geeta Sikka | GRLDR: Space Debris-Aware Adaptive Routing for LEO Satellite Networks Using Graph Reinforcement Learning | 2026 | Early Access | Routing Satellites Low earth orbit satellites Modeling Joining processes Interrupters Timing Delays Learning (artificial intelligence) Space debris Graph Neural Network (GNN) Deep Reinforcement Learning (DRL) Space Debris LEO Satellite Network | The growing density of space debris in Low Earth Orbit (LEO) poses a serious challenge to the reliability of satellite communication networks. Existing LEO routing protocols primarily optimize hop count or latency, overlooking debris-induced risks that lead to frequent link disruptions. This paper proposes a Graph Reinforcement Learning-based Debris-Aware Adaptive Routing (GRLDR) framework that integrates Graph Neural Networks (GNNs) and Deep Reinforcement Learning (DRL) to enable intelligent, risk-aware routing in dynamic LEO satellite networks. Real satellite and debris orbital data from Space-Track.org are propagated using the SGP4 model to construct a debris-aware dynamic network graph. Debris risk is quantified using interruption time and radar cross-section features and categorized into low, medium, and high-risk levels. A Graph Attention Network extracts spatial and risk-aware features, while a DRL agent learns routing policies that jointly minimize debris risk, hop count, and end-to-end delay. Simulation results show that the proposed approach significantly reduces debris-exposed routing paths while maintaining low delay, achieving 98.8% hop optimality, up to 28% risk reduction, and a 100% routing success rate compared with conventional routing schemes. This work provides a scalable learning-driven solution for safe and resilient routing in LEO satellite networks. | 10.1109/TNSM.2026.3753808 |
| 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 Feature extraction Data models Load modeling Accuracy Robustness Contrastive learning Chaos Log Anomaly Detection Generative Adversarial Networks (GANs) Temporal Data Analysis | 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 |
| Umair Ullah Tariq, Fariza Sabrina, Steven Gordon, Ahsan Morshed, Yufeng Lin, Mohammad Mamunur Rashid, Mubashir Hussain | SLA-Driven Network Planning for Hybrid QKD–PQC Security in Smart Grids | 2026 | Early Access | Technology Costing Seeds (agriculture) Maintenance engineering Gallium Educational institutions Planning Joining processes Quantum key distribution Timing Network planning service-level agreements quantum-safe security quantum key distribution post-quantum cryptography smart grid networks infrastructure management feasibility optimization | Operational deployment of hybrid QKD–PQC security in smart grids requires coordinated planning under coupled service-level agreement (SLA) constraints, including startup latency, sustained key availability, real-time bounds, technology budget, and site storage capacity. This paper presents an SLA-driven network-planning framework solved using feasibility-first bounded local search (FF-BLS). A broad 36,300-run campaign across seven benchmark networks (14–6,495 nodes) maps deployment regimes and algorithmic ablations. Full FF-BLS attains 60.9% feasibility under fixed installed site capacity, while relaxing the site-cap constraint yields 100%. Focused studies further vary storage, technology budget, QKD-adoption target, and startup–traffic stress. FF-BLS reaches 100% feasibility at the highest tested storage multiplier (γ = 0.40), while a restrictive technology budget (b = 0.60) remains independently binding once storage is sufficient. On 246 comparison scenarios, FF-BLS achieves 100% feasibility, whereas unassisted GA, SA, Tabu, and VNS achieve 24.4–58.9%; feasibility-aware initialization and repair substantially improve the generic baselines. A separate 100-instance topology/storage stress benchmark and an aligned CPU–GPU study evaluate robustness and computational scaling. The results show that site storage is the dominant practical bottleneck under fixed installed capacity, while its importance depends on the provisioning regime. Low-to-moderate QKD adoption is most robust under constrained storage, whereas higher adoption becomes feasible when sufficient storage head-room is provisioned. These findings provide practical guidance for scalable quantum-safe smart-grid deployment under stringent SLAs. | 10.1109/TNSM.2026.3751647 |
| Hailong Cheng, Shi Ying, Xiaoyu Duan, Wanli Yuan | MTCNLog: A System Log Anomaly Detection Method with Fast Updates via Multi-Head TCN and Knowledge Distillation | 2026 | Early Access | Modeling Anomaly detection Training Sequences Sequential analysis Signal detection Timing Head Labeling Bit error rate Anomaly detection Knowledge distillation Temporal Convolutional Network (TCN) Data analysis Software engineering | Anomaly detection is essential for maintaining the stability and reliability of software systems. However, many automatic log anomaly detection methods rely primarily on template indexes and therefore discard semantic and parameter information that may be relevant to abnormal behavior. In addition, retraining a deployed detector from scratch can be costly when log distributions evolve. This paper proposes MTCNLog, a log anomaly detection method that combines a position-wise multi-head Temporal Convolutional Network (TCN) with a knowledge-distillation-based update strategy. MTCNLog first tokenizes raw logs using Byte-Level Byte Pair Encoding (BPE) and uses a BERT model adapted to the log domain to construct contextual representations of complete log entries. Attention pooling merges subword representations, and the multi-head TCN models temporal dependencies at different structural positions in a log sequence. For model updating, an early teacher snapshot initializes the student model, while a selective distillation loss transfers reliable historical knowledge. Experiments on HDFS, BGL, and Thunderbird show that MTCNLog achieves the highest F-measure among the evaluated methods under the adopted experimental protocol. Under the same validation-based rule, the complete update strategy also reaches stable performance in fewer epochs and requires less recurring detector-update time than the compared alternatives. | 10.1109/TNSM.2026.3752466 |
| Pengbo Li, Xingwei Wang, Hao Lu, Qiang He, Donghong Han, Saru Kumari, Keqin Li, Sajal K. Das | FedC3P: Compatibility Cost Sharing and Congestion-Aware Posted Pricing for Heterogeneous Multi-Cloud Federations | 2026 | Early Access | Resource management Clouds Costing Pricing Investment Optimization Modeling Routing Delays Virtual machines Cloud federation compatibility investment congestion-aware posted pricing cost sharing provider participation resource allocation | Heterogeneous multi-cloud federations pool resources across providers. Compatibility investment reduces service costs caused by incompatibility, but returns depend on workload allocation under capacity and congestion. Existing allocation and pricing studies generally fix compatibility, leaving investment and cost sharing undetermined. We propose a mechanism for compatibility cost sharing and congestion-aware posted pricing in heterogeneous multi-cloud federations (FedC3P). FedC3P updates compatibility investment across providers on the slower time scale and allocates elastic workloads on the faster time scale. For fixed investment, FedC3P maximizes federation welfare subject to demand and regional capacity constraints and derives resource prices from optimality conditions. Given these prices and service costs from incomplete compatibility, independent service quantity and routing decisions by workload classes implement the welfare-maximizing allocation. FedC3P then shares compatibility costs, checks the feasibility of provider participation under budget balance, and determines provider payoffs through weighted Nash bargaining when distributable surplus is positive. We establish an O(T−1/2) saddle-gap bound for inner averages over T iterations and first-order stationarity of every outer accumulation point under sufficient conditions. At the default setting, semi-synthetic experiments on 277 cloud-region records show welfare gains of 18.9% and 30.8% over Routing-NUM and TD3-Routing; median runtime remains below 5 s at the largest scales. | 10.1109/TNSM.2026.3754272 |
| Shyam Kumar Shrestha, Shiva Raj Pokhrel, Jonathan Kua | Adapting Large Language Models for TCP Fairness over Wi-Fi | 2026 | Early Access | Large language models TCP Modeling Training Fluid flow Information rates Throughput Wireless fidelity Learning (artificial intelligence) Management Transmission Control Protocol Congestion Control Algorithms Fairness Wi-Fi | Designing Transmission Control Protocol (TCP) Congestion Control Algorithms (CCAs) for heterogeneous Wi-Fi networks remains a challenge due to rapidly varying delay, loss, and contention dynamics. These effects often lead to CCA incompatibility, flow unfairness, and starvation among competing TCP flows. Although Deep Reinforcement Learning (DRL) has shown promise in mitigating these challenges, its slow convergence, high training costs, and limited generalization hinder practical deployments. In this paper, we propose TCP-LLM, a learning-augmented transport framework that leverages Large Language Models (LLMs) for compatibility-aware CCA selection. TCP-LLM encodes multivariate TCP time-series into token embeddings and performs single-step discrete CCA decisions through a lightweight LLM decision head. Parameter-efficient low-rank adaptation (LoRA) reduces the number of trainable parameters by approximately two orders of magnitude. Evaluation using traces collected from a physicalWi-Fi testbed with competing TCP Cubic, Bottleneck Bandwidth and Round-trip propagation time (BBR), and Performance-oriented Congestion Control (PCC) flows shows that TCP-LLM achieves the highest mean, geometric-mean, and minimum per-flow throughput among the evaluated schemes. TCP-LLM also exhibits faster and more stable training convergence and supports low-latency bounded inference. These results demonstrate the feasibility of LLM-based sequence adaptation for compatibility-aware transport-layer supervision under heterogeneous wireless conditions. | 10.1109/TNSM.2026.3739364 |
| Junxiong Lin, Xiuyi Zhao, Pan Li, Tian-Yu Zuo, Mingyi Liu, Hailiang Zhao, Yichuan Jiang, Jiuchuan Jiang, Kai Di, Ning Luo | Hallucination-Aware Teaming for Reliable Service Composition in LLM-Driven Industrial Agent Networks | 2026 | Early Access | Modeling Large language models Educational institutions Costing Algorithms Conferences Collaboration Multi-agent systems Voting Social networking (online) LLM-driven industrial agent hallucination teaming reliable service composition multi-agent system | Large-language-model-driven (LLM-driven) industrial agents increasingly exchange intermediate results through service-composition pipelines, so an upstream hallucination can corrupt several downstream decisions. We formulate hallucination-aware teaming (HATP), which jointly considers capability coverage, distinct-base-family redundancy, resource budgets, and chain-level error propagation, and prove that its deterministic special case is NP-hard. We then propose HAT, a polynomial-time heuristic that combines master-driven recruitment with self-consistency, cross-agent agreement, external-constraint signals, and bounded fallback. In five simulator settings with 200 paired trials each, HAT has the highest mean Acc and lowest mean HPL in four settings; LLM Debate leads in Easy, and the HAT–Debate Acc differences in Easy and Complex are not significant after Holm correction. A 100-instance exact-enumeration study yields a 0.95% median relative utility gap and an approximately 10× median speedup for the tractable HATP instantiation with upstream discount and fallback disabled and a fixed scalar utility with normalized propagation length. Paired ablations show clear contributions from Phase B, bounded fallback, and the combined trust mechanism, whereas most individual trust-signal effects overlap with uncertainty. In a fixed 50-task live-LLM check using five 8B–30B model families, HAT attains Acc 0.280 versus 0.300 for Beta-Reputation and does not lead every comparator on propagation length. The live study is therefore a limited test outside the simulator and does not show that HAT is generally better in deployment. | 10.1109/TNSM.2026.3752977 |
| Zhaogang Shu, Dawei Lin, Haihui Xie, Shuwu Chen | PeriSTNet: A Topology-Anchored Residual Graph Evolution Model for Multi-Step Traffic Matrix Forecasting | 2026 | Early Access | Forecasting Modeling Matrices Learning (artificial intelligence) Timing Topology Educational institutions Conferences Sequences Sequential analysis Traffic Matrix Forecasting Spatio-Temporal Graph Neural Networks Residual Graph Evolution Topology Anchoring Wide Area Networks | Accurate multi-step Traffic Matrix (TM) forecasting enables Wide Area Network (WAN) operators to plan capacity, anticipate congestion, and assess traffic-engineering actions before service quality is affected. Existing spatio-temporal graph neural networks often rely on a fixed physical topology, whereas fully data-driven and long-sequence models may not explicitly retain network-structure priors. These choices can miss demand correlations induced by routing and application behavior, while recursive decoding can accumulate error at longer horizons. We propose PeriSTNet, a topology-anchored residual graph evolution framework that learns a sparse, phase-conditioned predictive dependency graph around a physical topology prior. This graph is integrated into a Dual-Graph Fusion Gated Recurrent Unit, and a Spatio-Temporal Shortcut stabilizes recursive rollouts. Across Abilene, GÉANT, and CERNET, PeriSTNet achieves lower aggregate MAE, MAPE, and RMSE than the evaluated graph-based and Transformer baselines; horizon-wise, multi-seed, and efficiency analyses support this result under one reproducible protocol. By coupling dynamic predictive dependencies with a stable physical backbone, PeriSTNet provides a lightweight forecasting component for proactive capacity planning and traffic-engineering workflows. | 10.1109/TNSM.2026.3753266 |
| Jinzhe Wu, Quansheng Guan, Shugang Hao, Shengming Jiang, F. Richard Yu | Buffer-Induced Optimization Flow Control for Communication Networks | 2026 | Early Access | Joining processes Delays Throughput Fluid flow Pricing Optimization Bagging Information rates Algorithms Flow production systems Optimize Flow Control Buffer Bloat Mitigation Network Throughput Maximization | Congestion is the main bottleneck for throughput improvement in communication networks. Since link buffer is an essential and early indicator for congestion, we formulate a buffer-induced optimization (BIO) flow control problem using the network utilization maximization framework. BIO uses link buffer dynamics to regulate source rates. We then derive a buffer-induced asynchronous gradient (BAG) algorithm using Lagrange duality. BAG allows links to price their buffer and allows sources to compute their rates based on path prices distributedly and iteratively. We prove the convergence and optimality of the source-link iterations under asynchronous price and rate updates. To prevent buffer bloat happening in practical networks, we also adopt a buffer shrink mechanism for BAG. Simulation results show that BAG can quickly sense the changes of network status and dynamically capture the optimal network throughput. BAG also achieves higher throughput and stronger robustness to bursts than the existing rate-based flow control and congestion control algorithms. | 10.1109/TNSM.2026.3751275 |
| Byungchang Kim, Shinyoung Lue, Seonyeong Hwang, Youhee Park, Yeji Lee, Jaemin Jeong, Peter Bloodsworth, Euiseok Hwang | GRIDS: Generalized Representation-based Intrusion Detection System via Federated Contrastive Learning | 2026 | Early Access | Modeling Labeling Intrusion detection Training Federated learning Fluid flow Internet of Things Contrastive learning Artificial intelligence Signal detection Intrusion detection system federated learning contrastive learning anomaly detection network security transformer encoder | Existing AI-based intrusion detection systems are typically trained for specific network environments, leading to significant performance degradation when deployed in different settings or exposed to evolving attack strategies. We propose GRIDS (Generalized Representation-based Intrusion Detection System), a federated contrastive learning framework for cross-environment intrusion detection that keeps raw traffic data local. GRIDS employs a Transformer-based encoder trained with supervised contrastive learning across distributed network environments, learning a shared representation without exchanging sensitive traffic data. The encoder embeds network flow features into a latent space where semantically similar traffic patterns cluster together, enabling effective anomaly detection via k-nearest neighbor scoring. Evaluated on four heterogeneous NetFlow datasets, GRIDS outperforms existing federated IDS baselines on average with a single unified model. In leave-one-out cross-validation, a substantial portion of the detection capability of GRIDS transfers to network environments unseen during training, and the level of transfer varies across target networks. Deployment at such a network requires no labeled attack data or fine-tuning. It uses the benign traffic of the network as the kNN reference set and its unlabeled traffic for normalization and threshold calibration. The framework targets deployments in which a single model protects multiple heterogeneous networks. | 10.1109/TNSM.2026.3748922 |