TNSM Searchable Index

Author(s)	Title	Year	Publication	Keywords
Dhiraj Pandey, Pranav Singla, Siddharth Pal, Prasenjit Chanak, Manish Pratap Singh, Om Jee Pandey	HFSL-CUNs: A Hierarchical Federated Split Learning Framework for Cluster-Based and UAV-Assisted Edge-Fog-Cloud Networks	2026	Early Access	Autonomous aerial vehicles Modeling Internet of Things	The increasing deployment of Internet of Things (IoT) applications has created a growing need for distributed learning frameworks that can operate efficiently across resource-constrained edge environments while preserving data privacy. Federated Learning (FL) enables collaborative model training without sharing raw data. However, its communication overhead, computational burden, and limited scalability make it less suitable for large-scale hierarchical edge networks. In this paper, we propose Hierarchical Federated Split Learning (HFSL), a unified Unmanned Aerial Vehicle (UAV)-assisted edge-fog-cloud framework that combines the complementary strengths of FL and Split Learning (SL) to improve communication efficiency, scalability, and privacy. HFSL introduces activation similarity-based clustering and spatio-temporal activation filtering to reduce redundant communication, adaptive UAV altitude optimization to improve wireless connectivity under dynamic network conditions, and a privacy-preserving training strategy based on Differential Privacy (DP) and activation-level leakage mitigation. Extensive experiments across eight image and tabular benchmark datasets demonstrate that HFSL outperforms state-of-the-art FL and SL methods on the more challenging heterogeneous benchmarks, reducing energy consumption by up to 50%, training latency by 40%, and communication overhead by 35%, while improving classification accuracy by up to 6%. These results show that HFSL provides an effective and scalable distributed learning framework for next-generation UAV-assisted edge networks.	10.1109/TNSM.2026.3738968
Chengsheng Pan, Yingzhi Wang, Huaifeng Shi, Lishang Qin, Xiaosong Cui	DBSDD-AQM: Dynamic Buffer Sizing-Based Deep Deterministic Active Queue Management for Edge IoT Networks	2026	Early Access		Bursty heterogeneous traffic can build persistent queues at edge IoT gateways when the offered load converges on a lower-rate bottleneck. Conventional active queue management (AQM) regulates packet dropping under a fixed buffer capacity, whereas adaptive buffer sizing alone does not coordinate capacity adjustment with queue-removal control. We propose Dynamic Buffer Sizing-Based Deep Deterministic Active Queue Management (DBSDD-AQM), which combines a bounded buffersizing loop with a faster continuous queue-removal controller. DBS adjusts the admissible capacity according to sustained queue evolution, while the DDPG Actor selects packet-granular removal actions for the resident backlog. A class-aware extension maps three concurrent service classes to logical FIFO queues sharing the same dynamic physical buffer. DBSDD-AQM is implemented using an NS3-PyTorch framework. Aggregate experiments compare it with RED, ARED, PIE, CoDel, and DQN-AQM, while the class-aware evaluation additionally includes FQ-CoDel and FQ-PIE. Matched-DBS comparisons show similar throughput but different delay–loss operating points among the aggregate controllers, and component ablation distinguishes the effects of capacity adaptation and learned queue removal. Relative to a fixed 50 KB buffer, DBS reduces average queueing delay by 16.23% for UDP and 17.70% for TCP Westwood in controlled transport experiments. In the evaluated three-class overload scenarios, all classes retain nonzero throughput. Class-aware DBSDD-AQM provides stronger D- and T-class differentiation, whereas FQ-CoDel and FQ-PIE produce more uniform class-level outcomes and stronger R-class performance. The measured 95th-percentile batch-one Actor inference latency is 0.109 ms on the reported x86-64 platform.	10.1109/TNSM.2026.3741334
Shyam Kumar Shrestha, Shiva Raj Pokhrel, Jonathan Kua	Adapting Large Language Models for TCP Fairness over Wi-Fi	2026	Early Access		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
Yonglin Huang, Ping Du, Xixuan Zhou, Mingji Dong, Jiayu Zhou, Yu Cen, Min Shi, Hongbo Li, Xiaoliang Chen, Zuqing Zhu	Two-Tier Cooperative Routing Leveraging GSL Diversity for Large-Scale LEO Satellite Networks	2026	Early Access	Satellites Routing Low earth orbit satellites	Nowadays, the fast development of large-scale low Earth orbit (LEO) satellite networks has been pushing for highly-efficient routing schemes that can realize quality-of-service (QoS) aware routing adaptively. However, the dynamic nature of LEO satellite networks and the capacity mismatch between their inter-satellite links (ISLs) and ground-satellite links (GSLs) make QoS-aware routing very challenging. In this work, we propose a two-tier cooperative routing framework (namely, 2T-CoR) to leverage GSL diversity and deflection routing for effectively relieving congestion, thereby improving QoS parameters such as packet loss rate and end-to-end (E2E) latency. We first develop a time-sliced model to utilize the orbital periodicity of LEO satellite networks for accelerating their routing calculations. Then, a two-tier cooperative routing algorithm is designed to seamlessly synergize orbital periodicity with GSL-state awareness to efficiently reduce congestion as well as improving GSL utilization. Extensive simulations with a constellation of 3; 840 LEO satellites verify the effectiveness of our proposal over the state-of-the-arts.	10.1109/TNSM.2026.3740700
Le Zhang, Yu Gu, Ye Du, Xin Liu, Jikai Zhang, Junyan Guo	EasySatSim: Enabling Researchers to Build Scalable LEO Satellite Network Experimental Environments on Personal Computing Devices	2026	Early Access	Satellites Protocols Low earth orbit satellites	Global communication networks based on LEO satellite constellations are within reach, attracting the attention and efforts of many researchers. However, creating the required experimental environments under the complex and vast satellite network architecture remains a challenge. As of now, open-source experimental platforms generally face limited adaptability, high resource consumption, and difficulties in environment deployment. Therefore, this paper introduces the EasySatSim experimental platform, which allows researchers to build large-scale LEO satellite network experimental environments on personal computing devices. EasySatSim consists of three core components: entities, behaviors, and protocol stacks, and constructs a highly modular architecture through the Controller Layer, Manager Layer, Execution Layer, Global Services Layer, and API Support Layer. Researchers can configure specific tasks for individual satellites and users, and even create entities like ground stations and central servers as needed, supporting adaptability from the parameter level to the scenario level. EasySatSim also considers packet-level system overhead and provides configurable support for practical network-level performance evaluation. Finally, three cases from the distinct fields of intrusion detection, machine learning, and network routing in LEO satellite networks are used to demonstrate the flexibility of EasySatSim.	10.1109/TNSM.2026.3739052
Heng He, Qin Xu, Hai Yu, Lei Nie, Jianfeng Lu	LFNC: A Lightweight and Fine-Grained Two-Stage Network Flow Classification Framework with Programmable Data Planes	2026	Early Access	Fluid flow Planing Modeling	Flow classification is a crucial component of network intrusion detection systems. Existing approaches mainly fall into two categories: in-network classification and control-data plane collaborative classification. The former is constrained by the computing and memory resources of programmable switches, often sacrificing classification accuracy and efficiency. The latter requires transmitting large volumes of packets to the control plane, leading to high processing latency, excessive control-channel overhead, and limited flow coverage. To address these challenges, we propose LFNC, a Lightweight and Fine-grained two-stage Network flow Classification framework with programmable data planes. In the first stage, LFNC introduces a Decision Tree Segmentation (DTS) algorithm to train resource-aware models in the control plane. The trained DTS models are converted into switch-compatible matching rules and deployed in the data plane to perform line-rate binary classification for preliminary anomaly detection. In the second stage, LFNC employs a cuckoo filter together with dual circular queues to selectively buffer essential packet features of preliminarily anomalous flows in the data plane and efficiently transfer them to the control plane. A multi-class energy-based flow classifier is then applied in the control plane to achieve accurate and fine-grained classification of anomalous flows. Experimental results on the Tofino hardware switch demonstrate that LFNC outperforms eight state-of-the-art baselines, improving flow collection rate by 1.07% and classification accuracy by 3.34%, while significantly reducing hardware resource consumption and maintaining low packet processing latency.	10.1109/TNSM.2026.3738578
Nilesh Chakraborty, Petar Djukic, Burak Kantarci	Aggressive-YoYo: Exploiting Intent-Semantic Misalignment in AI-Native 6G Management Planes	2026	Early Access	Central Processing Unit Management Modeling	Intent-Based Networking (IBN) enables operators to express high-level service objectives that are automatically translated into low-level control and orchestration policies. In AI-native 6G management planes, semantic misalignment during this translation can induce unsafe configurations that amplify conventional resource-exhaustion attacks. We investigate this vulnerability through aggressive-YoYo, a compound threat combining YoYo-style burst traffic with prematurely configured Kubernetes readiness probes. We implement an end-to-end Intent-to-Configuration pipeline that resolves natural-language service intents into structured policies, compiles them into Kubernetes probe settings, and evaluates the resulting behavior using a representative slice-assurance management function on Google Kubernetes Engine (GKE). Controlled readiness-delay experiments show that premature readiness can increase replica provisioning, aggregate CPU and memory consumption, storage activity, and request failures, while inducing non-trivial service-level tradeoffs. Similar resource amplification under a different N1-family machine type and deployment zone indicates that the effect is not specific to a single configuration.We further analyze readiness misconfiguration across multiple Kubernetes scaling mechanisms and derive service-specific safe and amplifying configuration regions. From the detection perspective, we show-case that aggressive-YoYo is detectable using fully supervised temporal classifiers evaluated with cycle-disjoint testing and feature-set ablation; the best configuration achieves an average accuracy of 92.6%. Under scarce aggressive-YoYo supervision, i.e., limited exposure to aggressive-YoYo traces, the supervised approach improves detection over the one-class setting. These results show that intent-semantic misalignment creates measurable cross-layer management risks and motivate semantic validation and telemetry-aware monitoring for trustworthy AI-native 6G orchestration.	10.1109/TNSM.2026.3736983
Siyu Jiang, Feng Guo, Di Chen, Yuan Liu, Ying Chen, Weijun Sun, Yu Wang, Shen Su	Smart Contract Vulnerability Detection via Mask Consistency with Dynamic Margin Adjustment	2026	Early Access	Labeling Modeling Smart contracts	With the rise of smart contract applications, new attacks that exploit contract vulnerabilities continue to emerge, and effective vulnerability detection methods are urgently needed. Deep learning-based methods have shown excellent performance. However, for new types of vulnerabilities, due to the lack of real labels to help the model learn subtle code differences, previous methods have difficulty distinguishing between vulnerable contracts and safe contracts with similar key code segments, resulting in false negatives. To address this problem, this paper proposes a smart contract vulnerability detection method that uses mask consistency (MC) and dynamic margin adjustment (DMA). Unlike traditional Masked Language Modeling (MLM) in CodeBERT that performs token-level reconstruction for general representation learning, our MC enforces classification-level consistency between a masked student network and an unmasked EMA teacher network at the semantic graph block level under semi-supervised domain adaptation. This enhances the model’s discriminative ability by adding contextual information of similar code segments as additional clues. Specifically, we define a student network to learn masked contracts, a teacher network to learn complete contracts, and implement few-shot learning through semi-supervised domain adaptation. In this process, the student network is helped to learn to correctly distinguish similar contracts by fusing contextual information. In order to guide students more effectively, we use DMA to screen high-quality pseudo-labels. We conduct extensive experiments on open source real-world vulnerability datasets, and the results show that our method significantly outperforms current mainstream deep learning methods in detecting six types of vulnerabilities. This approach also pioneers the application of domain adaptation and integrates MC with DMA in vulnerability detection, providing guidance for detecting different types of vulnerabilities.	10.1109/TNSM.2026.3733072
Shuang Zheng, Xing Zhang, Michael Sheng, Haixu Wang, Wenbo Wang	Beam Hopping Low Earth Orbit Satellite Resource Allocation for Differentiated Services and Robustness Analysis under Model Attacks	2026	Early Access	Beams Satellites Resource management	Beam hopping (BH)-enabled Low Earth Orbit (LEO) satellites play a pivotal role in next-generation communication networks, providing global coverage, improving spectrum efficiency, and supporting flexible adaptation to heterogeneous service demands. To fully exploit these capabilities, artificial intelligence (AI) techniques are increasingly employed for dynamic resource allocation and power management. However, limited onboard resources and potential adversarial perturbations pose challenges to both efficiency and robustness. To address these issues, we leverage digital twin technology to accurately capture the spatio-temporal dynamics of user–satellite visibility, providing precise state information for decision-making. Building on this, we formulate a joint optimization framework for BH scheduling and power allocation as a Markov Decision Process and propose the BRIDGE—BH with Reinforcement learning incorporating Integrated Dirichlet and Gumbel-TopK Exploration—which integrates a quality of service (QoS)-driven subchannel scheduling mechanism to ensure efficient and differentiated resource allocation. The model’s robustness is systematically evaluated under three classical adversarial attacks. Simulation results demonstrate that our approach achieves superior energy efficiency, service throughput, and fairness, while the robustness analysis shows stable performance under the considered bounded adversarial perturbations.	10.1109/TNSM.2026.3710750
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	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
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 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
Mohammad Khosravi, Setareh Maghsudi	A Robust Optimization Approach for Regenerator Placement in Fault-Tolerant Networks Under Discrete Cost Uncertainty	2026	Early Access	IP networks Costing Costs	We focus on robust, survivable communication networks, where network links and nodes are affected by an uncertainty set. In this sense, any network links might fail. Besides, a signal can only travel a maximum distance before its quality falls below a certain threshold, necessitating its regeneration by regenerators installed at network nodes. In addition, the price of installing and maintaining regenerators belongs to a discrete uncertainty set. Robust optimization seeks a solution with guaranteed performance against all scenarios modeled in an uncertainty set. Thus, the problem is to find a subset of nodes with minimum cost for the placement of the regenerator, ensuring that all nodes can communicate even if a subset of network links fails. To solve the problem optimally, we propose two solution approaches, including one flow-based and one cut-based integer programming formulation, as well as their iterative exact method. Our theoretical and experimental results show the effectiveness of our methods.	10.1109/TNSM.2026.3740028
João Gabriel Pazinato De Bittencourt, Fábio Gonçalves De Oliveira, Edson José Pacheco, Carlos Marcelo Pedroso	Packet-Level Causal Certification of Tail-Latency and Reliability Control in O-RAN Slicing	2026	Early Access	Radio access networks Regional area networks Context	An O-RAN slice controller holds two levers, the resource-block budget and the scheduling discipline, and reads an aggregate proxy that can pass a slice dropping packets or overrunning its latency bound. A lever that correlates with a key performance indicator need not control it. We answer, at the packet level, which lever an operator may act on. We evaluate compliance over every generated packet and lower-bound the probability that a lever both achieved compliance and was necessary for it. The bound carries information only when computed within each operating context and then standardized. The other order reduces to the average treatment effect, and the two coincide whenever the lever effect keeps its sign. A zero-sum allocation lever breaks that condition: the budget it grants one slice is taken from another. Over 3,720 runs one lever effect reverses from +0.32 to −0.66 with the neighbour’s load while averaging −0.008, so the pooled bound is zero and the stratified bound 0.156. Two contrasts on that lever, averaging −0.008 and 0.000, certify at 0.156 and at zero, which the pooled average effect cannot separate. The error guarantee covers false declarations of an effect, not the safety of acting on one.	10.1109/TNSM.2026.3740306
Hamidreza Mazandarani, Masoud Shokrnezhad, Tarik Taleb	A Semantic-Aware Multiple Access Scheme Leveraging Spatial Redundancy for Uplink-Dominant Network Services	2026	Early Access	Timing Titanium Modeling	The transition toward semantic-aware communication offers a paradigm shift for next-generation mobile networks, promising to decouple information significance from raw data transmission. Despite advances in semantic extraction, the integration of semantic intelligence into the Medium Access Control (MAC) layer remains underexplored, particularly in exploiting spatial correlations among users. To address this, we introduce a novel multiple access scheme designed for uplink-dominant network services. This framework optimizes the trade-off between spectrum utilization and sustainability by formulating variable-packet-length access as distinct α-fairness and energy efficiency problems. A key innovation of our approach is the quantification of spatial redundancies through novel metrics of self-throughput and assisted-throughput, which account for the semantic correlation of data across user equipment. We analyze these formulations to identify optimal bounds before proposing PRISM (Protocol for Redundancy Identification in Semantic Multiple-access). Grounded in Model-free Multi-Agent Deep Reinforcement Learning (MADRL), PRISM enables devices to autonomously govern spectrum access using only local observations. Extensive evaluations demonstrate that PRISM successfully leverages redundancies to outperform semantic-oblivious schemes, achieving up to 90% of the centralized optimal benchmark and improving both objectives by up to 2× across diverse user-semantic association matrices. These results validate PRISM as a viable candidate for future distributed mobile network applications, complemented by orthogonal Multiple Access Schemes where signals are multiplexed in the semantic domain.	10.1109/TNSM.2026.3737571
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	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
Mubashir Murshed, Glaucio H. S. Carvalho, Robson E. De Grande	Holistic Intelligent Traffic Steering Management in Multi-RAT Vehicular Networks	2026	Early Access	Radio access technologies Rats Vehicles	Multiple Radio Access Technology (multi-RAT) environments provide a promising foundation for service-aware communication in intelligent transportation systems (ITS) and smart cities. However, traffic steering (TS) in highly mobile and ultra-dense vehicular networks remains challenging due to dynamic network conditions, heterogeneous RAT capabilities, varying vehicle requirements, packet loss, latency, and frequent ping-pong RAT switching. In this context, we propose Holistic Intelligent Traffic Steering (HITS), a proactive bi-level TS management framework for multi-RAT vehicular networks. HITS integrates centralized network-wide guidance with local vehicleside decision-making. At the central level, a Graph Convolutional Network–Long Short-Term Memory (GCN–LSTM) model captures holistic spatio-temporal network dynamics and evaluates RAT optimality. At the local level, a State-Action-Reward- State-Action (SARSA) reinforcement learning agent performs adaptive, vehicle-specific RAT selection using local observations and central-level optimality guidance. Results show that HITS achieves up to 6.5% higher average throughput, reduces packet loss ratio by more than 30.2%, lowers latency by nearly 12.2%, and reduces the ping-pong RAT switching rate by over 24% compared with baseline and state-of-the-art (SoTA) TS approaches.	10.1109/TNSM.2026.3729840
Stephen Jasina, Loqman Salamatian, Joshua Mathews, Scott Anderson, Paul Barford, Mark Crovella, Walter Willinger	Matisse: Visualizing Measured Internet Latencies as Manifolds	2026	Early Access	Manifolds Internet Measurement	Manifolds are complex topological spaces that can be used to represent datasets of real-world measurements. Visualizing such manifolds can help with illustrating their topological characteristics (e.g., curvature) and providing insights into important properties of the underlying data (e.g., anomalies in the measurements). In this paper, we describe a new methodology and system for generating and visualizing manifolds that are inferred from actual Internet latency measurements between different cities and are projected over a 2D Euclidean space (e.g., a geographic map). Our method leverages a series of graphs that capture critical information contained in the data, including well-defined locations (for vertices) and Ricci curvature information (for edges). Our visualization approach then generates a curved surface (manifold) in which (a) geographical locations of vertices are maintained and (b) the Ricci curvature values of the graph edges determine the curvature properties of the manifold. The resulting manifold highlights areas of critical connectivity and defines an instance of “Internet delay space” where latency measurements manifest as geodesics. We describe details of our method and its implementation in a tool, which we call Matisse, for generating, visualizing and manipulating manifolds projected onto a base map. We illustrate Matisse with three case studies: a simple example to demonstrate key concepts, and visualizations of the US and Europe public Internet to show Matisse’s utility.	10.1109/TNSM.2026.3730274
Ahmed Rjiba, Hicham Lakhlef, Joachim Bruneau-Queyreix, Meriem Afif	Federated Learning in Fog Computing within IoT Environments: An up-to-date and comprehensive survey	2026	Early Access	Federated learning Internet of Things Edge computing	The Internet of Things (IoT) connects diverse, resource-constrained devices, driving innovation in domains such as healthcare, smart cities, and industrial automation. However, the exponential growth of IoT devices poses critical challenges in data processing, privacy, security, and latency. Fog Computing (FC) mitigates these issues by decentralizing computational resources, processing and storing data locally to enable low-latency, high-quality services. This makes FC an ideal platform for integrating Federated Learning (FL), a decentralized machine learning paradigm that trains models locally on IoT devices and shares only aggregated updates, preserving data privacy. Since its introduction, FL has garnered considerable attention for enabling privacy-preserving collaborative model training in distributed environments. The convergence of IoT, FC, and FL offers substantial opportunities to advance IoT system performance, but it also presents challenges in resource allocation, security, energy efficiency, computational complexity, and system heterogeneity. This survey provides a comprehensive and up-to-date analysis of the integration of FL and FC within IoT environments, exploring their synergies, challenges, and state-of-the-art advancements.We review critical aspects, including infrastructure enhancements, security mechanisms, and the emerging role of Digital Twin (DT) technology, which creates virtual replicas of IoT devices to optimize system efficiency and real-time performance. Through case studies in healthcare and smart cities, we highlight practical applications of FL-FC integration. We compare our work with existing surveys, highlight its specific focus on the FL-FC-IoT-DT convergence, and identify open challenges and future research directions toward secure, scalable, and intelligent IoT ecosystems.	10.1109/TNSM.2026.3731410
Amr Aboeleneen, Mohamed Abdallah, Aiman Erbad, Amr Mohamed	ZTCI: Zero-Touch Cooperative Immersion, a Plug-and-Deploy Deep Reinforcement Learning-Based Framework for Resource Allocation and Cooperation in the Metaverse	2026	Early Access	Resource management Modeling Metaverse	The Metaverse requires edge providers, termed Metaverse Service Stations (MSSs), to provision high-quality virtual environments (VEs) and faithful digital twins (DTs) for heterogeneous virtual venues under tight compute and network budgets. In multi-MSS deployments, localized demand surges can overwhelm one station while neighboring stations remain underutilized. Cooperation is therefore essential but challenging because venue requirements are heterogeneous, demand is bursty, and proximity-based neighborhood sets change over time. These dynamics motivate zero-touch operation that requires neither retraining nor reconfiguration at deployment. We introduce the General Optimized Agent (GOA), a plug-and- deploy Deep Reinforcement Learning (DRL) agent that jointly optimizes per-venue VE/DT service levels and inter- MSS resource sharing. GOA is trained through staged curriculum learning and uses a position-aware set encoder with learned positional embeddings and attention-based pooling to map variable-size neighbor sets to fixed-dimensional representations. This design yields a single policy that generalizes across MSS types, budget levels, and dynamic team sizes. Extensive evaluation shows that GOA improves request satisfaction, load balancing, and cost efficiency over representative baselines, supporting scalable, zero-touch Metaverse cooperation under realistic infrastructure constraints.	10.1109/TNSM.2026.3737187