TNSM Searchable Index

Author(s)	Title	Year	Publication	Keywords
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	Early Access	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 (SINRc) 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 SINRc 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
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
Somchart Fugkeaw, Kittipat Tangtanawirut, Pakapon Rattanasrisuk, Archawit Changtor	MK-WISE: Secure and Efficient Multi-Keyword Wildcard ABSE with Keyword-Level Revocation for Device–Edge–Cloud EHRs Data Sharing	2026	Early Access	Encryption Cryptography Access control	The rapid proliferation of Internet of Things (IoT) in healthcare has transformed the management of Electronic Health Records (EHRs), but also introduced critical challenges in secure retrieval, dynamic revocation, and verifiable integrity over encrypted data. Existing Searchable Encryption (SE) and Attribute-Based Searchable Encryption (ABSE) models remain limited: (i) most support only exact or prefix keyword matching and cannot handle flexible wildcard or substring queries common in medical search; (ii) revocation is coarse-grained, often requiring costly key redistribution or ciphertext re-encryption; and (iii) integrity verification either incurs heavy blockchain overhead or exposes access structures, undermining privacy. To address these gaps, we propose MK-WISE, a secure and efficient multi-keyword wildcard ABSE framework for IoT–EHR systems. MK-WISE integrates an Index–Wildcard Tree (IWT) with Substring Bloom Filters (SBF) to enable expressive wildcard and substring queries, employs a puncturable PRF–based revocation workflow with edge-local enforcement, hierarchical key updates, and optional blockchain anchoring, and incorporates homomorphic MACs for lightweight correctness and completeness verification. Security analysis proves that MK-WISE achieves confidentiality, keyword privacy, unlinkability, and revocability under standard assumptions. Experimental results demonstrate that MK-WISE significantly outperforms state-of-the-art schemes in trapdoor generation, search scalability, and revocation cost, achieving millisecond-level revocation without user disruption. These results highlight MK-WISE as a practical and comprehensive solution for privacy-preserving EHR retrieval in IoT-enabled healthcare.	10.1109/TNSM.2026.3657982
Xiujun Xu, Qi Wang, Qingshan Wang, Yinlong Xu	Contract-Based Incentive Mechanism for Long-term Participation in Federated Learning	2026	Early Access	Contracts Data models Computational modeling	Federated learning (FL), as a newly-developing technique, brings the advantage of organizing multiple participants to learn together, while avoiding the leakage of their privacy information. Contract theory provides an effective incentive mechanism to encourage participants to participate in FL. Existing contract-based incentive mechanisms consider participants’ types but ignore the different contributions of participants within the same type during the training.This paper first introduces a metric, reputation, to evaluate the contribution of participants in each iteration, and then proposes a hybrid contract mechanism consisting of a short-term contract and a long-term contract. Only the participants with reputations higher than a pre-defined threshold can sign the long-term contract. We formulate the solution of the long-term contract mechanism as an optimization problem with constraints. We further simplify the constraints of the long-term contract optimization problem, and theoretically analyze the correctness of the simplification to greatly reduce its computational complexity. We prove that the model owner achieves more profit with the hybrid contract mechanism. Simulations with the MNIST dataset show that the long-term contract improves the model accuracy by at least 5% compared with the existing contracts. Furthermore, compared with the short-term contract, participants signing the long-term contract are granted more rewards.	10.1109/TNSM.2026.3657419
Suyong Eum, Shin’ichi Arakawa, Masayuki Murata	Deterministic and Probabilistic Scheduling for Latency Guarantees in B5G/6G Network Management	2026	Early Access	Delays Probabilistic logic Ultra reliable low latency communication	In the era of Beyond 5G (B5G) and 6G networks, ensuring efficient resource management and meeting stringent quality of service (QoS) requirements are crucial. This paper proposes the Deterministic and Probabilistic Scheduling for Latency Guarantees (DPSLG) algorithm, which provides Worst-Case Delay (WCD) guarantees, both deterministically and probabilistically, to support Ultra-Reliable Low-Latency Communication (URLLC) applications. Deterministic guarantees ensure strict delay bounds for mission-critical scenarios, while probabilistic guarantees offer flexibility by accommodating dynamic traffic conditions with controlled threshold violations. The proposed algorithm leverages the Lyapunov optimization framework for deterministic delay bounds in dynamic environments and integrates Extended Conformal Quantile Regression (ECQR) to enable probabilistic guarantees. This combination enhances reliability and adaptability under diverse traffic conditions. Furthermore, constraint mechanisms are incorporated to mitigate the impact of misbehaving users and improve overall system performance. This work significantly advances the management of radio resources in B5G and 6G networks by addressing key challenges related to latency and efficiency. It establishes a robust framework for optimizing scheduling mechanisms, paving the way for future innovations in managing next-generation networks to meet stringent performance and reliability demands.	10.1109/TNSM.2026.3657735
Zhenyang Guo, Jin Cao, XiongPeng Ren, Yuchen Zhou, Lifu Cheng, Peijie Yin, Hui Li	LDST-UAVS: A Lightweight Data Secure Transmission Protocol for Unmanned Aerial Vehicle Swarms in Emergency Rescue Scenarios	2026	Early Access	Autonomous aerial vehicles Security Protocols	Currently, Unmanned Aerial Vehicles (UAV) groups can quickly build a multi-hop transmission network, which have been widely utilized in emergency communication scenarios to perform search and rescue, environmental monitoring, personnel positioning, rapid networking, etc. In such emergency rescue situations, strict demands on real-time communication, security, and minimal resource consumption become paramount. Higher requirements for security, bandwidth, and real-time performance necessitate a secure and lightweight data transmission protocol. Additionally, due to the lack of personnel supervision in these scenarios, the probability of malicious nodes increases. Therefore, it is essential to quickly and proximally block malicious nodes’ data to prevent it from affecting subsequent network propagation, and to accurately identify the malicious nodes. To address these issues, in this paper, we propose a traceable, lightweight, and secure data transmission protocol for UAV multi-hop networks in emergency rescue scenarios. The proposed protocol can verify the integrity of data transmitted by a large number of nodes in real time, detect erroneous transmissions, and trace malicious users. Experimental results show that our protocol consistently outperforms the comparison schemes in terms of computational overhead. Moreover, in scenarios involving smaller groups (m=5) and fewer hops (n=4), it exhibits significantly lower communication bandwidth overhead than the reference methods. Security analysis using BAN logic and the formal verification tool Scyther indicates that the proposed scheme meets security requirements. Additionally, comparative analysis results demonstrate that the proposed scheme is highly effective and outperforms other related schemes under the unique constraints of emergency rescue scenarios, where rapid, secure decision-making and data transmission are critical.	10.1109/TNSM.2026.3656973
Marija Gajić, Marcin Bosk, Stanislav Lange, Thomas Zinner	QoE-Aware Transport Slicing Configuration: Improving Application Performance in Beyond-5G Networks	2026	Early Access	Quality of service Quality of experience Resource management	5G and beyond provides connectivity for a variety of heterogeneous, often mission-critical services, placing stringent performance requirements on these systems. Providing satisfactory Quality of Experience (QoE) for diverse, coexisting applications prompts the network operators to enforce application-aware, efficient resource allocation schemes that can improve user-satisfaction, efficiency, and system utilization. For these purposes, QoS Flows and network slicing have been identified as key enablers. Those concepts move away from economy of scale, towards a fine-grained slice and flow handling with customized resource control for each application, application type, or slice. This work is particularly focused on transport slicing, where the shift towards fine-grained resource control has important implications for how network resources are scaled and optimally allocated. These aspects have been largely ignored in the existing literature. Furthermore, while capacity has been recognized as a key resource, selecting the appropriate queue size, granularity of the resource allocation scheme, and their relations with the number of clients are often neglected in the process of resource dimensioning. To address these shortcomings, we perform an in-depth evaluation of the effects that impact factors have on the overall QoE and system utilization using the OMNeT++ simulator. We show the optimization potential for QoE and resource utilization, and further formulate guidelines for efficient and QoE-aware resource allocation.	10.1109/TNSM.2026.3656605
Divya D Kulkarni, Manit Baser, Mohan Gurusamy	ARCANE: Adversarial Resilience and Adaptive Network Slicing for UAV-based MEC	2026	Early Access	Autonomous aerial vehicles Servers Power demand	Network slicing and Multi-access Edge Computing (MEC) are pivotal elements of 5G communication technology, enabling diverse, low-latency services to distributed users. Unmanned Aerial Vehicles (UAVs) are being increasingly explored in delivering these services temporarily to remote locations, supporting surveillance in regions with restricted ground connectivity, monitoring urban traffic, and disaster relief. However, the resource constraints of UAVs demand efficient optimization strategies. While Artificial Intelligence (AI)-driven methods like Deep Reinforcement Learning (DRL) offer promising potential in optimizing service delays and minimizing power consumption with fewer UAVs, they remain vulnerable to adversarial attacks. This study evaluates two adversarial attacks against DRL baselines: a targeted service disruption attack that impacts the DRL environment to degrade decision-making and service quality, and an action bit-flipping attack that alters UAV selection, resulting in suboptimal provisioning. To address these vulnerabilities, we propose ARCANE, a resilient DRL-based multi-slice MEC framework for UAVs. ARCANE introduces the Exploratory-Thompson Deep-Q Network (ET-DQN), which leverages Thompson Sampling to effectively balance exploration and exploitation under adversarial conditions, optimizing UAV selection for MEC provisioning. Extensive experiments demonstrate that ARCANE outperforms baseline approaches, achieving ~ 4× faster mitigation of the environmental attack and ~ 2× quicker recovery from the attack on the actions. Moreover, we illustrate that ARCANE demonstrates strong resilience by effectively limiting the degradation in hovering time caused by the attacks.	10.1109/TNSM.2026.3656271
Qian Yang, Suoping Li, Jaafar Gaber, Sa Yang	An Optimal Matching Channel Selection Strategy Based on (K+1)-layer 3-D CTMC for Suppressing Spectrum Fragmentation in 5G/B5G Cognitive Radio Ad Hoc Networks	2026	Early Access	Copper Three-dimensional displays Cognitive radio	Dynamic spectrum access (DSA) is one of the pivotal technologies that is widely recognized to be able to cope with the massive demand for limited spectrum resources by massive data in 5G/B5G networks. To address spectrum fragmentation and sharing in 5G/B5G cognitive radio ad hoc networks (CRAHNs), based on the DSA technique, this paper proposes an optimal matched channel selection strategy with finite buffer (OMCS-FB). In the OMCS-FB, a cognitive user (CU) with the transmission request selects the channel whose idle time optimally matches its transmission time rather than selecting the channel with the longest idle time; if the CU fails to access the channel, the CU enters the buffer and waits for the next transmission opportunity. A (K+1)-layer continuous-time Markov chain (CTMC) with the number of primary users (PUs) and CUs in primary channels and the number of CUs in the buffer as 3-D metrics is established, which can effectively portray the activity behavior of users and the occupancy states of primary channels under the OMCS-FB. The CTMC rate steady-state equations are then solved using the successive over-relaxation (SOR) iterative algorithm to obtain the system steady-state probability distributions and performance metrics. The results show that the OMCS-FB effectively suppresses spectrum fragmentation of the MAC layer in the time dimension and enables efficient spectrum sharing among CUs and PUs, as verified by Monte Carlo simulation.	10.1109/TNSM.2026.3656378
Awaneesh Kumar Yadav, An Braeken, Madhusanka Liyanage	A Provably Secure Lightweight Three-factor 5G-AKA Authentication Protocol relying on an Extendable Output Function	2026	Early Access	Authentication Protocols Security	Compared to 4G, the designed authentication and key agreement protocol for 5G communication (5G-AKA) offers better security. State-of-the-art shows that various protocols indicate the flaws in the 5G-AKA and suggest solutions primarily for the desynchronization attack, traceability attack, and perfect forward secrecy. However, most authentication protocols fail to facilitate the device stolen attack and are expensive; they also do not consider the prominent security issues such as post-compromise security and non-repudiation. Considering the above demerits of these protocols and the necessity to offer additional security, a provably secure lightweight 5G-AKA multi-factor authentication protocol relying on an extendable output function is proposed. The security of the proposed work has been confirmed informally and formally (ROR logic, GNY logic, and Scyther tool) to ensure that the proposed work handles all types of attacks and offers additional security features, such as post-compromise features and non-repudiation. Furthermore, we compute the performance of the proposed work and compare it with its counterparts to show that our work is less costly and more suitable for lightweight devices than others in terms of computational, communication, storage, and energy consumption cost.	10.1109/TNSM.2026.3656167
Xinshuo Wang, Lei Liu, Baihua Chen, Yifei Li	ENCC: Explicit Notification Congestion Control in RDMA	2026	Early Access	Bandwidth Data centers Heuristic algorithms	Congestion control (CC) is essential for achieving ultra-low latency, high bandwidth, and network stability in high-speed networks. However, modern high-performance RDMA networks, crucial for distributed applications, face significant performance degradation due to limitations of existing CC schemes. Most conventional approaches rely on congestion notification signals that must traverse the queuing data path before congestion signals can be sent back to the sender, causing delayed responses and severe performance collapse. This study proposes Explicit Notification Congestion Control (ENCC), a novel high-speed CC mechanism that achieves low latency, high throughput, and strong network stability. ENCC employs switches to directly notify the sender of precise link load information and avoid notification signal queuing. This allows precise sender-side rate control and queue regulation. ENCC also ensures fairness and easy deployment in hardware. We implement ENCC based on FPGA network interface cards and programmable switches. Evaluation results show that ENCC achieves substantial through-put improvements over representative baseline algorithms, with gains of up to 16.6× in representative scenarios, while incurring minimal additional latency.	10.1109/TNSM.2026.3656015
Xiaofeng Liu, Naigong Zheng, Fuliang Li	Don’t Let SDN Obsolete: Interpreting Software-Defined Networks with Network Calculus	2026	Early Access	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
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	Early Access	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
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
Shagufta Henna, Upaka Rathnayake	Hypergraph Representation Learning-Based xApp for Traffic Steering in 6G O-RAN Closed-Loop Control	2026	Early Access	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
Muhammad Umar Farooq Qaisar, Weijie Yuan, Lin Zhang, Shehzad Ashraf Chaudhry, Guangjie Han, Yunyang Zhang	A Robust Trust Management System for V2X Networks Integrating ISAC with Blockchain Smart Contracts	2026	Early Access		Vehicle-to-everything (V2X) networks face critical security challenges due to their dynamic nature, stringent latency requirements, and susceptibility to malicious attacks. Traditional trust management approaches often rely on centralized authorities or historical data, creating vulnerabilities and scalability limitations. This paper presents a new trust management system that leverages integrated sensing and communication (ISAC) technology and blockchain-based smart contracts to provide secure and decentralized trust evaluation in V2X networks. The proposed framework leverages real-time ISAC signal processing to compute five comprehensive trust metrics: behavior score, reputation score, safety score, uptime score, and response time score. These metrics are derived through advanced Kalman filtering and statistical anomaly detection applied to physical-layer measurements, enabling immediate detection of malicious activities that traditional approaches might miss. Trust records are securely stored and validated through smart contracts deployed on 5G base station blockchains, ensuring tamper-proof storage and automated policy enforcement. Numerical results demonstrate that the proposed protocol achieves faster trust convergence, higher communication reliability, significant reduction in false positive rates, improved detection accuracy, acceptable end-to-end latency, and lower computational overhead compared to state-of-the-art approaches.	10.1109/TNSM.2026.3658589
Fekri Saleh, Abraham O. Fapojuwo, Diwakar Krishnamurthy	vEdge: Flow-based Network Slicing for Smart Cities in Edge Cloud Environments	2026	Early Access		Smart city applications require diverse fifth generation network services with stringent performance and isolation requirements, necessitating scalable and efficient network slicing mechanisms. This paper proposes a novel framework for flow-based network slicing in edge cloud environments, termed virtual edge (vEdge). The framework leverages virtual medium access control addresses to identify flows at the data link layer (Layer 2), achieving robust flow-based slice isolation and efficient resource management. The proposed solution integrates a vEdge software module within the software defined networking controller to create, manage, and isolate network slices for both Third Generation Partnership Project (3GPP) and non-3GPP devices. By isolating traffic at Layer 2, the framework simplifies address matching and eliminates the computational overhead associated with deep packet inspection at upper layers (e.g., Layer 3/4 or Layer 7). The proposed vEdge further provides customizable flow-based network slices, each managed by a dedicated controller, providing self-contained virtual networks tailored to diverse applications within the smart city sector. Experimental evaluations demonstrate the efficacy of vEdge in enhancing network performance, achieving a 30% reduction in latency compared to flow-based network slicing that uses non-Layer 2 parameters to identify flows.	10.1109/TNSM.2026.3656925
Haftay Gebreslasie Abreha, Ilora Maity, Youssouf Drif, Christos Politis, Symeon Chatzinotas	Revenue-Aware Seamless Content Distribution in Satellite-Terrestrial Integrated Networks	2026	Vol. 23, Issue	Satellites Topology User experience	With the surging demand for data-intensive applications, ensuring seamless content delivery in Satellite-Terrestrial Integrated Networks (STINs) is crucial, especially for remote users. Dynamic Ad Insertion (DAI) enhances monetization and user experience, while Mobile Edge Computing (MEC) in STINs enables distributed content caching and ad insertion. However, satellite mobility and time-varying topologies cause service disruptions, while excessive or poorly placed ads risk user disengagement, impacting revenue. This paper proposes a novel framework that jointly addresses three challenges: (i) service continuity- and topology-aware content caching to adapt to STIN dynamics, (ii) Distributed DAI (D-DAI) that minimizes feeder link load and storage overhead by avoiding redundant ad-variant content storage through distributed ad stitching, and (iii) revenue-aware content distribution that explicitly models user disengagement due to ad overload to balance monetization and user satisfaction. We formulate the problem as two hierarchical Integer Linear Programming (ILP) optimizations: one content caching that aims to maximize cache hit rate and another optimizing content distribution with DAI to maximize revenue, minimize end-user costs, and enhance user experience. We develop greedy algorithms for fast initialization and a Binary Particle Swarm Optimization (BPSO)–based strategy for enhanced performance. Simulation results demonstrate that the proposed approach achieves over a 4.5% increase in revenue and reduces cache retrieval delay by more than 39% compared to the benchmark algorithms.	10.1109/TNSM.2025.3629810
Hai Anh Tran, Nam-Thang Hoang	Towards Efficient and Adaptive Traffic Classification: A Knowledge Distillation-Based Personalized Federated Learning Framework	2026	Vol. 23, Issue	Adaptation models Training Federated learning	Traffic classification plays a crucial role in optimizing network management, enhancing security, and enabling intelligent resource allocation in distributed network systems. However, traditional Federated Learning (FL) approaches struggle with domain heterogeneity, as network traffic characteristics vary significantly across different domains due to diverse infrastructure, applications, and usage patterns. This results in degraded performance when applying a single global model across all domains. To overcome this challenge, we propose KD-PFL-TC, a Knowledge Distillation-based Personalized Federated Learning framework for Traffic Classification, aimed to balance global knowledge sharing with personalized model adaptation in heterogeneous network environments. Our approach leverages knowledge distillation to enable collaborative learning without directly sharing raw data, preserving privacy while mitigating the negative effects of domain shifts. Each domain refines its local model by integrating insights from a global model and peer domains while maintaining its unique traffic distribution. To further enhance performance, we introduce an adaptive distillation strategy that dynamically adjusts the influence of global, peer, and local knowledge based on the similarity between traffic distributions, ensuring optimal knowledge transfer designed to each domain’s characteristics. Extensive experiments on real-world traffic datasets show that KD–PFL–TC maintains 88.0% accuracy under high heterogeneity (vs. 75.0% for FedAvg) while reducing communication overhead by ~60%, delivering an efficient and robust solution for large-scale, heterogeneous networks.	10.1109/TNSM.2025.3629241
F. Busacca, L. Galluccio, S. Palazzo, A. Panebianco, R. Raftopoulos	Bandits Under the Waves: A Fully-Distributed Multi-Armed Bandit Framework for Modulation Adaptation in the Internet of Underwater Things	2026	Vol. 23, Issue	Throughput Scalability Training	Acoustic communications are the most exploited technology in the so-called Internet of Underwater Things (IoUT). UnderWater (UW) environments are often characterized by harsh propagation features, limited bandwidth, fast-varying channel conditions, and long propagation delay. On the other hand, IoUT nodes are usually battery-powered devices with limited processing capabilities. Accordingly, it is necessary to design optimization algorithms to address the challenging propagation features while balancing them with the limited device capabilities. To address the constraints of the nodes in energy and processing resources, it is crucial to adjust the transmission parameters based on the channel conditions while also developing communication procedures that are both lightweight and energy-efficient. In this work, we introduce a novel Multi-Player Multi-Armed Bandit (MP-MAB) framework for modulation adaptation in Multi-Hop IoUT Acoustic Networks. As opposed to widely used, computation-demanding Deep Reinforcement Learning (DRL) techniques, MP-MAB algorithms are simple and lightweight and allow to iteratively make decisions by selecting one among multiple choices, or arms. The framework is fully-distributed and is able to dynamically select the best modulation technique at each IoUT node by leveraging on high-level statistics (e.g., network throughput), without the need to exploit hard-to-extract channel features (e.g., channel state). We evaluate the performance of the proposed framework using the DESERT UW simulator and compare it with state-of-the-art centralized solutions based on Deep Reinforcement Learning (DRL) for cognitive and heterogeneous networks, namely DRL-MCS, DRL-AM, PPO, SAC, as well as with a multiple-agent, distributed version of the PPO. The results highlight that, despite its simplicity and fully-distributed nature, the proposed framework achieves superior performance in UW networks in terms of throughput, convergence speed, and energy efficiency. Compared to DRL-MCS and DRL-AM, our approach improves network throughput by up to 33% and 20%, respectively, and reduces energy consumption by up to 18% and 16%. When compared to PPO, SAC, and Multi-PPO, the proposed solution achieves up to 11%, 34%, and 38% higher throughput, and up to 7%, 17%, and 33% lower energy consumption, respectively.	10.1109/TNSM.2025.3629240