TNSM Searchable Index

Author(s)	Title	Year	Publication	Keywords
Xu Liu, Zheng-Yi Chai, Yan-Yang Cheng, Ya-Lun Li, Tao Li	Evolutionary Multi-Objective Deep Reinforcement Learning for Task Offloading in Industrial Internet of Things	2025	Early Access	Delays Energy consumption Heuristic algorithms	Mobile Edge Computing (MEC) plays a pivotal role in optimizing the Industrial Internet of Things (IIoT), where the Industrial Task Offloading Problem (ITOP) is crucial for ensuring optimal system performance by balancing conflicting objectives such as delay, energy consumption, and cost. However, existing approaches often oversimplify multi-objective optimization by aggregating conflicting goals into a single objective, while also suffering from limited exploration and robustness in uncertain MEC scenarios within IIoT. To overcome this limitation, we propose EMDRL-ITOP, an Evolutionary Multi-Objective Deep Reinforcement Learning algorithm that synergizes an evolutionary algorithm with deep reinforcement learning (DRL). Firstly, we formulate a multi-objective task scheduling model for IIoT-MEC and design a three-dimensional vector reward function within a Multi-Objective Markov Decision Process framework, enabling simultaneous optimization of delay, energy, and cost. Then, EMDRL-ITOP integrates evolutionary mechanisms to enhance exploration and robustness: a dynamic elite selection strategy prioritizes high-quality policies, a distillation crossover operator fuses advantageous traits from elite strategies, and a proximal mutation mechanism maintains population diversity. These components collectively improve learning efficiency and solution quality in dynamic environments. Extensive simulations across six instances demonstrate that EMDRL-ITOP achieves a superior balance among conflicting objectives compared to state-of-the-art methods, while also outperforming existing algorithms in several key performance metrics.	10.1109/TNSM.2025.3585148
Zhe Sun, Shangzhe Li, Lihua Yin, Yahong Chen, Aohai Zhang, Meifan Zhang, Yuanyuan He	SuperMPFL: A Supermask-Based Mechanism for Personalized Federated Learning	2025	Early Access	Federated learning Adaptation models Privacy	Personalized federated learning (PFL) is a specialized application of the federated learning paradigm designed to support personalized use cases. Unlike traditional federated learning, which aims to train a high-quality global model, the goal of PFL is to tailor a model that best fits each individual user. Most existing PFL approaches adopt training architectures similar to those used in traditional federated learning, relying on global or partial model sharing during training. While this helps improve model personalization across clients, it also introduces a range of challenges, including risks of data leakage and increased communication overhead. To address these challenges, we propose a novel personalized federated learning (PFL) framework called SuperMPFL, which leverages supermasks to effectively tackle issues related to accuracy, privacy, and efficiency. In particular, the SuperMPFL technique utilizes masking and ranking strategies to obscure the true gradient information. By converting gradients into ranked numerical representations, this approach enhances privacy protection during the training process. Furthermore, this approach reduces communication overhead by transmitting significantly less information compared to conventional methods. In SuperMPFL, each client receives the global model and then emphasizes its personalized parameters, particularly at the model’s edges. This design not only improves accuracy but also strengthens robustness against privacy attacks. Evaluations on standard federated learning benchmarks demonstrate the superiority of our approach, which outperforms state-of-the-art methods in terms of accuracy, privacy, and efficiency.	10.1109/TNSM.2025.3587663
Fan Zhang, Pengfei Yu, Shaoyong Guo, Weicong Huang, Feng Qi	Computing Sandbox Driven Secure Edge Computing System for Industrial IoT	2025	Early Access	Industrial Internet of Things Edge computing Security	With the initiation of the Internet of Everything, edge computing has emerged as a pivotal paradigm, shifting from cloud computing to better address the growing data demands and latency issues in Industrial Internet of Things (IIoT). However, securing edge computing systems remains a critical challenge as malicious attackers can compromise the IIoT systems, gain control over edge servers, and tamper with computation programs and results. Existing solutions, such as cryptographic encryption, intrusion detection, and blockchain-based methods, have been widely used to enhance security. Yet, these approaches often suffer from high computational overhead, limited adaptability to dynamic IIoT environments, and a lack of foundational trusted assurance mechanisms. Although Trusted Execution Environment (TEE)-based solutions provide a hardware-enhanced secure execution environment, they face scalability and usability challenges and cannot fully support the parallel execution requirements of multiple and diverse IIoT applications. To overcome these limitations, a novel secure edge computing system is proposed for IIoT that strengthens security from the physical layer. By establishing a computing sandbox model, we extend the trust boundaries of the TEE using a virtual Trusted Platform Module (TPM), enabling secure and efficient execution for diverse IIoT applications. The proposed approach integrates a trust guarantee mechanism with decentralized adaptive attestation, ensuring real-time integrity verification while reducing performance overhead. Through security analysis and experimental validation, it is shown that our system improves Non-Volatile Random-Access Memory (NVRAM) launch time by approximately 1,700 times compared to hardware TPM-based virtual TPM implementations, while enhancing protection against attacks such as rollback.	10.1109/TNSM.2025.3587956
Jyoti Shokhanda, Utkarsh Pal, Aman Kumar, Soumi Chattopadhyay, Arani Bhattacharya	SafeTail: Tail Latency Optimization in Edge Service Scheduling via Redundancy Management	2025	Early Access	Servers Telecommunication traffic Communication switching	Optimizing tail latency while efficiently managing computational resources is crucial for delivering high-performance, latency-sensitive services in edge computing. Emerging applications, such as augmented reality, require low-latency computing services with high reliability on user devices, which often have limited computational capabilities. Consequently, these devices depend on nearby edge servers for processing. However, inherent uncertainties in network and computation latencies—stemming from variability in wireless networks and fluctuating server loads—make service delivery on time challenging. Existing approaches often focus on optimizing median latency but fall short of addressing the specific challenges of tail latency in edge environments, particularly under uncertain network and computational conditions. Although some methods do address tail latency, they typically rely on fixed or excessive redundancy and lack adaptability to dynamic network conditions, often being designed for cloud environments rather than the unique demands of edge computing. In this paper, we introduce SafeTail, a framework that meets both median and tail response time targets, with tail latency defined as latency beyond the percentile threshold. SafeTail addresses this challenge by selectively replicating services across multiple edge servers to meet target latencies. SafeTail employs a reward-based deep learning framework to learn optimal placement strategies, balancing the need to achieve target latencies with minimizing additional resource usage. Through trace-driven simulations, SafeTail demonstrated near-optimal performance and outperformed most baseline strategies across three diverse services.	10.1109/TNSM.2025.3587752
Zhuoyue Fang, Huiqun Yu, Guisheng Fan, Zengpeng Li, Jiayin Zhang	Energy, Cost and Reliability-Aware Workflow Scheduling on Multi-Cloud Systems: A Multi-Objective Evolutionary Approach	2025	Early Access	Scheduling Costs Reliability	Nowadays, cloud computing has become a suitable platform for hosting and executing workflow applications. As the diversity and scale of these applications continue to increase, single-cloud environments are becoming insufficient to meet users’ requirements. Instead, multi-cloud environments have emerged as an ideal solution. However, the complexity of workflow scheduling in multi-cloud environments increases significantly due to the diversified billing mechanisms, heightened reliability demands, and the requirements for reducing energy consumption. To address these challenges, this paper proposes a multi-objective evolutionary algorithm called ECRWSM for workflow scheduling on multi-cloud systems. First, ECRWSM utilizes the population initialization strategy to generate a population with excellent uniformity and sufficient randomness. Then, the diversification strategy is employed to thoroughly explore the solution space. Next, the individual enhancement strategy is used to further improve the solutions. Additionally, an external archive is maintained to store non-dominated solutions throughout the evolutionary process. Comprehensive experiments are conducted to validate the performance of ECRWSM. The experimental results demonstrate that our proposed algorithm ECRWSM outperforms both classical and recent scheduling algorithms.	10.1109/TNSM.2025.3587108
Fabio Palmese, Alessandro E. C. Redondi, Matteo Cesana	Resource Optimization for Evidence Collection and Preservation in IoT Forensics-Ready Access Points	2025	Early Access	Internet of Things Forensics Feature extraction	The rapid proliferation of Internet of Things (IoT) devices across diverse sectors has given rise to the field of IoT Forensics, which focuses on analyzing digital traces of IoT appliances for legally significant insights. This field extends traditional digital forensic methods to address the unique characteristics of IoT devices, with the goal of identifying security breaches and reconstructing human activities based on data retrieved from IoT systems. Due to the limited memory and processing capabilities of IoT devices, innovative methods for data collection and analysis are required. As an example, in the Smart Home or Smart Office scenarios intermediate network devices such as Wi-Fi access points may be leveraged for such goals, including monitoring and analysis of IoT network traffic. In this context, this paper proposes a resource optimization model for forensics tasks based on network traffic monitoring and analysis on consumer Wi-Fi access points. The model maximises the expected performance achieved for forensic tasks while balancing the storage and processing capabilities required for data collection in Wi-Fi access points. The proposed model can determine the optimal aggregation window used to group network packets for traffic analysis, the number of statistical features to extract from such packets and the bits per feature to use for data storage, in order to achieve optimal accuracy and maintain low impact on the computing device. Experimental results demonstrate the models efficacy in constrained environments, allowing us to decide on the resource allocation in network devices when a high number of tasks is involved.	10.1109/TNSM.2025.3586336
Seyed Salar Sefati, Bahman Arasteh, Simona Halunga, Octavian Fratu	Adaptive Service Recommendation in Internet of Things Using a Reinforcement Learning and Optimization Algorithm	2025	Early Access	Internet of Things Real-time systems Optimization	A recent technology trend known as the Internet of Things (IoT) involves using devices like smartphones, smart TVs, medical and healthcare equipment, and home appliances to generate data. This paper introduces a novel framework, Reinforcement Learning with Black Widow Optimization (RL-BWO), to enhance IoT service recommendations through responsiveness to evolving service requests and optimized resource usage. Unlike prior hybrid approaches that rely on static recommendation strategies or single-pass learning, RL-BWO uniquely integrates incremental Reinforcement Learning (RL) with evolutionary optimization, enabling continuous policy refinement in dynamic environments. The framework features a multi-batch data partitioning mechanism, and a service-request interactive simulator based on Markov Decision Processes (MDP) to support real-time adaptation. The Black Widow Optimization (BWO) algorithm is used to fine-tune service selection through fitness-based ranking, ensuring high-quality recommendations under resource constraints. Experimental results in a smart city simulation show that RL-BWO improves the solved request rate by up to 12.8%, reduces latency by 17%, and enhances reliability by 9.6% compared to leading methods such as Genetic Algorithm–Simulated Annealing–Particle Swarm Optimization (GASAPSO), Time Correlation Coefficient with Cuckoo Search–K-means (TCCF), and Artificial Bee Colony with Genetic Algorithm (ABCGA). These results demonstrate RL-BWO’s superior scalability, accuracy, and responsiveness, making it a robust solution for large-scale, real-time IoT service recommendation.	10.1109/TNSM.2025.3585995
Rafael Pires, Jere Malinen, Pawani Porambage, Pol Alemany, Daniel Adanza, Raul Muñoz, Ricard Vilalta, Pietro G. Giardina, Michael De Angelis, Giada Landi	Intent-Based Service Provisioning and Closed-Loop Automation for Cobot Service Migration in a Multi-Stakeholder Environment	2025	Early Access	Collaborative robots 6G mobile communication Automation	This paper presents a Proof-of-Concept (PoC) focused on intent-based service provisioning and closed-loop automation for collaborative robot (cobot) use case. The PoC demonstrates the integration of two key IBN enablers: the Intent-Based Network Intent Management Entity (IBN-IME) and CL Automation and Coordination, both aligned with 3GPP and ETSI Zero-Touch Service and Network Management (ZSM) standards. These enablers support the seamless interpretation of user intents, service deployment, and migration. The testbed, designed to emulate certain functionalities present in a 6G end-to-end system, highlights the potential for automation in future networks. The work addresses the need for an ecosystem that allows for the interaction of multiple stakeholders in a secure platform. The PoC presented can adapt to increasingly complex use cases, laying the groundwork for future improvements and broader deployments.	10.1109/TNSM.2025.3585806
Huaqing Tu, Ziqiang Hua, Qi Xu, Jun Zhu, Tao Zou, Hongli Xu, Qiao Xiang, Zuqing Zhu	Achieving Efficient SFC Proactive Reconfiguration through Deep Reinforcement Learning in Programmable Networks	2025	Early Access	Noise measurement Predictive models Throughput	Service function chain (SFC) consists of multiple ordered network functions (e.g., firewall, load balancer) and plays an important role in improving network security and ensuring network performance. Offloading SFCs onto programmable switches can bring significant performance improvement, but it suffers from unbearable reconfiguration delays, making it hard to cope with network workload dynamics in a timely manner. To bridge the gap, this paper presents OptRec, an efficient SFC proactive reconfiguration optimization framework based on deep reinforcement learning (DRL). OptRec predicts future traffic and places SFCs on programmable switches in advance to ensure the timeliness of the SFC reconfiguration, which is a proactive approach. However, it is non-trivial to extract effective features from historical traffic information and global network states, while ensuring efficient and stable model training. To this end, OptRec introduces a multi-level feature extraction model for different types of features. Additionally, it combines reinforcement learning and autoregressive learning to enhance model efficiency and stability. Results of in-depth simulations based on real-world datasets show the average prediction error of OptRec is less than 3 can increase the system throughput by up to 69.6 compared with other alternatives.	10.1109/TNSM.2025.3585590
Bing Xiong, Guanglong Hu, Songyu Liu, Jinyuan Zhao, Jin Zhang, Baokang Zhao, Keqin Li	TECache: Traffic-Aware Energy-Saving Cache With Optimal Utilization for TCAM Flow Tables in SDN Data Plane	2025	Early Access	Telecommunication traffic Energy consumption Table lookup	In the paradigm of Software-Defined Networking (SDN), its data plane generally perform packet forwarding based on flow table lookup on TCAM with high energy consumption. Popular energy-saving methods employ caching techniques for most packets to bypass energy-intensive TCAM lookups. However, existing energy-saving caches cannot adapt to network traffic fluctuation with sufficient utilization of cache space due to non-negligible hash conflicts. To overcome this issue, we design a traffic-aware energy-saving cache with optimal utilization for TCAM flow tables in SDN data plane. In particular, we first devise a nearly conflict-free hashing algorithm for the cache called FelisCatus, which provides three candidate locations for each incoming flow by adjacent hopping, and searches for an empty or replaceable entry for each conflicting flow by co-directional kicking. Then, we propose an adaptive adjustment mechanism of flow activity criterion, i.e., packet inter-arrival time threshold, for enabling the cache to consistently accommodate the most active exact flows in network traffic. Furthermore, we build an energy-efficient SDN flow table storage architecture by applying the above cache and exploiting the accessing features of different memories. Finally, we verify the performance of our designed energy-saving cache and flow table storage architecture by experiments with backbone network traffic traces. Experimental results indicate that, our designed energy-saving cache obtains stable and high hit rates around 75% even under network traffic fluctuation, and our proposed flow table storage architecture achieve high energy saving rates around 71%, with the increase of 7.89% compared to state-of-the-art ones.	10.1109/TNSM.2025.3585703
Huanlin Liu, Bing Ma, Yong Chen, Jianjian Zhang, Bo Liu, Haonan Chen, Di Deng	Blockchain Assisted Secure Embedding of Virtual Networks in Multi-Domain Elastic Optical Network	2025	Early Access	Blockchains Resource management Quality of service	With the continuous advancement of network virtualization (NV) technology, virtual network embedding (VNE) has played a crucial role in solving network resource allocation problem. However, multi-domain elastic optical networks (MD-EONs) are increasingly facing privacy and security challenges. The centralized VNE methods lead to significant communication overhead due to their excessive reliance on central servers. Additionally, network attacks, such as eavesdropping, pose severe threats to data security. So, we propose a blockchain-assisted virtual network secure embedding (BA-VNSE) framework MD-EONs. This framework employs quantum key distribution (QKD) technology to ensure data security during transmission and leverages the blockchain technology to enhance the transparency and security of the VNE process. Furthermore, we propose a blockchain-assisted minimum cost virtual network secure embedding (BAMC-VNSE). During the virtual node embedding (VNM), the multidimensional resources of nodes are comprehensively considered to ensure effective embedding. In the virtual link embedding (VLM), the QKD paths are allowed to differ from the encrypted data transmission paths, ultimately resulting in the selection of the most cost-effective valid embedding scheme. The simulation results demonstrate that the BAMC-VNSE effectively reduces request blocking probability, embedding cost and average number of message while improving the key utilization ratio.	10.1109/TNSM.2025.3583898
Gulshan Kumar, Rahul Saha, Mauro Conti, Tai-hoon Kim	DAWS: A Comprehensive Solution Against De-anonymization Attacks in Blockchains	2025	Early Access	Blockchains Privacy Peer-to-peer computing	De-anonymization attacks in blockchains are significant concerns as they compromise the privacy of users on a public ledger. Such attacks, in the form of network analysis and transaction patterns, aim to link a blockchain address to the identity of its owner, potentially revealing sensitive information. Though researchers introduce various solutions using Tor, VPN, and i2P to protect against de-anonymization in blockchains, they have certain limitations: i) non-verification of the private transactions, ii) reveal of the transaction graph, and iii) requirement of a trusted setup that is itself vulnerable to the adversary. All these lead to the revocation of de-anonymization problems. In this paper, we show a novel privacy assurance framework for blockchains. The proposed framework is called De-Anonymization Withstanding Solution (DAWS). DAWS is the first privacy-preserved blockchain framework against de-anonymization attacks. DAWS uses privacy-classifying smart contract execution and a novel consensus called Proof-of-Privacy (PoPri). A set of experiments is executed on PoPri as well as DAWS. The blockchain transactions are modified by including user-defined privacy labels. DAWS can handle attacker advantage ≥0.008 with a privacy breach probability < 0.01% under our threat model. Besides, an improvement in the throughput of DAWS is noticed as compared to Ethereum (almost 80 times) with the Hyperledger configuration for consensus. The gas consumption improvement is 20%. All the listed features enhance the appeal of the proposed DAWS as a robust privacy-preserving solution against blockchain de-anonymization attacks.	10.1109/TNSM.2025.3588273
Yizhi Huang, Jiayi Liu, Chen Wang, Xuemei Xie, Guangming Shi	Reconfiguring Satellite CDNs With Dynamic Uncertain User Requests Based on Multi-Agent DRL	2025	Early Access	Satellites Costs Optimization	The Satellite-Terrestrial Integrated Network (STIN) is a key paradigm to achieve global coverage and ubiquitous connection in the 6G era. Integrating the network slice technology based on Software Defined Networking (SDN) and Network Function Virtualization (NFV) into STIN is recognized as an effective solution to achieve a rapid flexible service provisioning. Specifically, the Content Delivery Network (CDN) service, which is storage resource intensive, is suitable to be deployed on STIN to provide a global range content service suppply. Most existing research on the resource deployment of STIN focuses on static requests, ignoring the dynamic changes in requests caused by the high-speed movement of satellites. Especially, the reconfiguration of CDN slices and the variation of STIN are asynchronous in different time scales: this makes the reconfiguration of CDN slices to cope with faster changing user requests a challenging task. In this paper, we adopt a periodic reconfiguration strategy to configure CDN slices on the edge LEO satellite network of STIN in discrete time intervals. Within each time interval, we formulate the reconfiguration optimization problem to cope with the dynamically changing user requests, wherein the Stochastic Network Calculus (SNC) is used to measure the deployment performance within this time interval. Then, we describe the optimization problem as a Decentralized Partially Observable Markov Decision Process (Dec-POMDP), and propose a reconfiguration algorithm based on Multi-agent Deep Reinforcement Learning (MADRL) to determine the optimal adjustment strategy. Finally, intensive simulations are implemented to verify the performance of the algorithm. Compared with the baselines, the QoS of the proposed algorithm is increased by about 5.8%, while the operation cost and reconfiguration cost are decreased by about 8.5% and 35.3% respectively.	10.1109/TNSM.2025.3584396
Marwan Dhuheir, Aiman Erbad, Ala Al-Fuqaha, Bechir Hamdaoui, Mohsen Guizani	AoI-Aware Intelligent Platform for Energy and Rate Management in Multi-UAV Multi-RIS System	2025	Early Access	Autonomous aerial vehicles Internet of Things Optimization	Recently, unmanned aerial vehicles (UAVs) have demonstrated exemplary performance in various scenarios, such as search and rescue, smart city services, and disaster response applications. UAVs can facilitate wireless power transfer (WPT), resource offloading, and data collection from ground IoT devices. However, employing UAVs for such applications poses several challenges, including limited flight duration, constrained energy resources, and the age of information of the data collected. To address these challenges, we employ a UAV swarm to maximize energy harvesting (EH) and data rates for IoT devices by optimizing UAV paths and integrating reconfigurable intelligent surfaces (RIS) technology. We tackle critical constraints, including UAV energy consumption, flight duration, and data collection deadlines, by formulating an optimization problem to find optimal UAV paths and RIS phase shifts. Given the complexity of the problem, its combinatorial nature, and the challenges of obtaining an optimal solution through conventional optimization methods, we decompose the problem into two sub-problems, employing deep reinforcement learning (DRL) to optimize EH and particle swarm optimization (PSO) to optimize RIS phase shifts. Our extensive simulations show that the proposed solution outperforms competitive algorithms, including Brute-Force-PSO, AC-PSO, and PPO-PSO algorithms, providing a robust solution for modern IoT applications.	10.1109/TNSM.2025.3584883
Muhammad Sulaiman, Mahdieh Ahmadi, Bo Sun, Mohammad A. Salahuddin, Raouf Boutaba, Aladdin Saleh	MicroOpt: Model-driven Slice Resource Optimization in 5G and Beyond Networks	2025	Early Access	Quality of service Resource management Optimization	A pivotal attribute of 5G networks is their capability to cater to diverse application requirements. This is achieved by creating logically isolated virtual networks, or slices, with distinct service level agreements (SLAs) tailored to specific use cases. However, efficiently allocating resources to maintain slice SLA is challenging due to varying traffic and quality-of-service (QoS) requirements. Traditional peak traffic-based resource allocation leads to over-provisioning, as actual traffic rarely peaks. Additionally, the complex relationship between resource allocation and QoS in end-to-end slices spanning different network segments makes conventional optimization techniques impractical. Existing approaches in this domain use mathematical network models (e.g., queueing models) or simulations, and various optimization methods but struggle with optimality, tractability, and generalizability across different slice types. In this paper, we propose MicroOpt, a novel framework that leverages a differentiable neural network-based slice model with gradient descent for resource optimization and Lagrangian decomposition for QoS constraint satisfaction. We evaluate MicroOpt against two state-of-the-art approaches using an open-source 5G testbed with real-world traffic traces. Our results demonstrate up to 21.9% improvement in resource allocation compared to these approaches across various scenarios, including different QoS thresholds and dynamic slice traffic.	10.1109/TNSM.2025.3584257
Junjun Li, Shi Ying, Tiangang Li, Xiangbo Tian	TraceDAE: Trace-Based Anomaly Detection in Micro-Service Systems via Dual Autoencoder	2025	Early Access	Anomaly detection Autoencoders Location awareness	Micro-service systems have become a popular architecture for modern web applications owing to their scalability, modularity, and maintainability. However, with the increasing complexity and size of these systems, anomaly detection emerges as a critical task. In this paper, we introduce TraceDAE, a trace-based anomaly detection approach in micro-service systems. The approach initially constructs a Service Trace Graph (STG) to depict service invocation relationships and performance metrics, subsequently introducing a dual autoencoder framework. In this framework, the structure autoencoder employs Graph Attention Networks (GAT) to analyze the structure, while the attribute autoencoder leverages the Long Short-Term Memory Network (LSTM) for processing time series data. This approach is capable of effectively identifying Service Response Abnormal and Service Invocation Abnormal. Moreover, the final experimental results on datasets show that TraceDAE is an efficient anomaly detection approach which outperforms the SOTA trace-based anomaly detection methods with f1-scores of 0.970 and 0.925, respectively.	10.1109/TNSM.2025.3583213
Chenlu Zhang, Akio Kawabata, Eiji Oki	Robust Distributed Server Selection Model Against Delay Uncertainty	2025	Early Access	Delays Servers Uncertainty	In real-time applications under wide-area networks, providing a demanded quality of service for end users is an issue. Recent studies adopt distributed processing for server selection problems to reduce data synchronization delay and total interaction delay, assuming that link delays over the distributed system are exactly known. No study has addressed the problem of such a distributed server selection in properly handling the delay uncertainty. This paper proposes a robust optimization model for the distributed server selection problem against the delay uncertainty. We handle the delay uncertainty of user-server and server-server links by defining two -ellipsoidal uncertainty sets. The proposed model determines allocated servers for multiple users to minimize the weighted sum of data synchronization delay and total interaction delay over the distributed system. We formulate the proposed model as a mixed integer second-order cone programming problem. We prove that the distributed server selection problem with uncertain delays is NP-complete. We compare the proposed model with baseline models, focusing on delay uncertainty and distributed processing. The numerical results show that the proposed model can achieve a lower objective value than the baseline models, indicating the benefit of utilizing -ellipsoidal uncertainty sets to handle delay uncertainty.	10.1109/TNSM.2025.3582933
Sergi Alcalà-Marín, Weili Wu, Aravindh Raman, Marcelo Bagnulo, Ozgu Alay, Fabián E. Bustamante, Marco Fiore, Andra Lutu	A Comparative Analysis of Global Mobile Network Aggregators	2025	Early Access	Internet of Things Performance evaluation Streaming media	The mobile telecommunication industry is undergoing continuous evolution to cope with ever increasing service requirements and expectations of end users. This has recently led to the rise of Mobile Network Aggregators (MNAs), a new type of global virtual operators that deliver mobile communication services by utilizing multiple Mobile Network Operators (MNOs), dynamically connecting to the one that best meets their customers’ needs based on location and time. MNAs can then offer optimized global coverage by connecting to local MNOs that have limited (e.g., national) geographic service. In this paper, we provide a first in-depth analysis of the operations of three major MNAs: Google Fi, Twilio, and Truphone. We conduct performance measurements across these MNAs for critical applications spanning DNS, web browsing, and video streaming, and compare their performance against that of a traditional MNO from two very diverse geographical locations, US and Spain. We find that MNAs may introduce some delay compared to local MNOs in the region where the user is roaming, yet they offer significant performance improvements over the traditional MNOs roaming model, such as home-routed roaming. To fully assess the potential benefits of the MNA model, we also carry out emulation studies assessing the potential performance gains that MNAs could achieve by deploying both control and user plane functions of open-source 5G implementations across different Amazon Web Services locations.	10.1109/TNSM.2025.3582089
Satoru Kobayashi, Ryusei Shiiba, Shinsuke Miwa, Toshiyuki Miyachi, Kensuke Fukuda	Topology-Driven Configuration of Emulation Networks With Deterministic Templating	2025	Early Access	Network topology Emulation Data models	Network emulation is an important component of a digital twin for verifying network behavior without impacting on the service systems. Although we need to repeatedly change network topologies and configuration settings as a part of trial and error for verification, it is not easy to reflect the change without failures because the change affects multiple devices, even if it is as simple as adding a device. We present topology-driven configuration, an idea to separate network topology and generalized configuration to make it easy to change them. Based on this idea, we aim to realize a scalable, simple, and effective configuration platform for emulation networks. We design a configuration generation method using simple and deterministic config templates with a new network parameter data model, and implement it as dot2net. We evaluate three perspectives, scalability, simplicity, and efficacy, of the proposed method using dot2net through measurement and user experiments on existing test network scenarios.	10.1109/TNSM.2025.3582212
Pengfei Zhang, Junhuai Li, Dong Ding, Huaijun Wang, Kan Wang, Xiaofan Wang	A Two-Step Cellular Network Traffic Forecasting Method Integrating Decomposition and Deep Neural Networks based on Bayesian Joint Parameter Optimization	2025	Early Access	Cellular networks Optimization Accuracy	Accurate cellular network traffic prediction is crucial for intelligent network planning and management in 6G. However, the non-stationary characteristics of cellular network traffic present significant challenges when training deep neural networks for traffic forecasting. To address this issue, we propose a two-stage deep learning framework, JO-DPNet, based on Bayesian joint parameter optimization, which integrates data decomposition techniques with Bayesian joint optimization to effectively mitigate the adverse impacts of non-stationarity and error accumulation on prediction accuracy. In the first stage, a data decomposition module uses Variational Mode Decomposition (VMD) to decompose the original data into network traffic subset series(TSS), thereby alleviating the negative effects of non-stationarity. In the second stage, a prediction and construction module leverages a bi-directional LSTM (Bi-LSTM) network to extract deep spatial-temporal features from the TSS in a bidirectional manner. A fully connected layer then captures the relationships between the TSS and reconstructs the predicted results into the final output. The JO module employs the Tree-structured Parzen Estimator based Bayesian optimization algorithm(TP-BO) simultaneously determines the optimal VMD mode number k and the hyperparameters of the Bi-LSTM network through probabilistic surrogate model. Extensive experiments on three real-world cellular traffic datasets demonstrate that the proposed method significantly mitigates the non-stationary characteristics of the traffic data. Compared to state-of-the-art methods, JO-DPNet achieves reductions in MAE by 29%, 3%, and 19% for three type prediction tasks on the Telecom Italia dataset. The source code is available to the public at: https://github.com/VicentZhang259/JO-DPNet.	10.1109/TNSM.2025.3582533