TNSM Searchable Index

Author(s)	Title	Year	Publication	Keywords
Alisson Medeiros, Antonio Di Maio, Torsten Braun	FLATWISE: Flow Latency and Throughput Aware Sensitive Routing for 6DoF VR over SDN	2025	Early Access	Routing Throughput Videos	The next generation of Virtual Reality (VR) applications is expected to provide advanced experiences through Six Degree-of-Freedom (6DoF) technology. However, 6DoF VR applications require latency and throughput guarantees. This article presents a novel intra-domain routing algorithm with throughput guarantees for minimizing the overall end-to-end (E2E) latency for all flows deployed in the network.We investigate the Joint Flow Allocation (JFA) problem to find paths for all flows in a network such that it determines the optimal path for each flow in terms of throughput and latency. The JFA problem is NP-hard. We use a mixed integer linear programming to model the system, along with a heuristic, Flow Latency and Throughput Aware Sensitive Routing (FLATWISE), which is one order of magnitude faster than optimally solving the JFA problem. FLATWISE introduces an adaptive routing approach that dynamically adjusts the path calculation based on E2E latency. The novelty of FLATWISE lies in its unique ability to precisely tune the routing path by either constraining or relaxing the path criteria to align the E2E latency of the selected path with the latency demands of each VR flow. This approach ensures that the latency of the calculated path approximates the latency of each VR flow, enabling more flexible and efficient network routing to meet diverse latency requirements. Our evaluation considers 6DoF VR application flows, which demand high throughput and ultra-low E2E latency. Extensive simulations demonstrate that FLATWISE significantly reduces flow latency, over-provisioned latency, E2E latency, and algorithm execution time when network flows are processed randomly. FLATWISE improves flow throughput and frame rate compared to related work approaches.	10.1109/TNSM.2025.3600365
Dániel Unyi, Ernő Rigó, Bálint Gyires-Tóth, Róbert Lovas	Explainable GNN-Based Approach to Fault Forecasting in Cloud Service Debugging	2025	Early Access	Debugging Microservice architectures Cloud computing	Debugging cloud services is increasingly challenging due to their distributed, dynamic, and scalable nature. Traditional methods struggle to handle large state spaces and the complex interactions between microservices, making it difficult to diagnose failures and identify critical components. This paper presents a Graph Neural Network (GNN)-based approach that enhances cloud service debugging by predicting system-level fault probabilities and providing interpretable insights into failure propagation. Our method models microservice interactions as graphs, where failures propagate probabilistically. Using Markov Decision Processes (MDPs), we simulate failure behaviors, capturing the probabilistic dependencies that influence system reliability. The trained GNN not only predicts fault probabilities but also identifies the most failure-prone microservices and explains their impact. We evaluate our approach on various service mesh structures, including feature-enriched, tree-structured, and general directed acyclic graph (DAG) architectures. Results indicate that our method is effective in the operational phase of cloud services, enabling proactive debugging and targeted optimization. This work represents a step toward more interpretable, reliable, and maintainable cloud infrastructures.	10.1109/TNSM.2025.3602223
Ahan Kak, Van-Quan Pham, Huu-Trung Thieu, Nakjung Choi	HexRAN: A Programmable Approach to Open RAN Base Station System Design	2025	Early Access	Open RAN Base stations Protocols	In recent years, the radio access network (RAN) domain has seen significant changes with increased virtualization and softwarization, driven by the Open RAN (O-RAN) movement. However, the fundamental building block of the cellular network, i.e., the base station, remains unchanged and ill-equipped to handle this architectural evolution. In particular, there exists a general lack of programmability and composability along with a protocol stack that grapples with the intricacies of the 3GPP and O-RAN specifications. Recognizing the need for an “O-RAN-native” approach to base station design, this paper introduces HexRAN– a novel base station architecture characterized by key features relating to RAN disaggregation and composability, 3GPP and O-RAN protocol integration and programmability, robust controller interactions, and customizable RAN slicing. Furthermore, the paper also includes a concrete systems-level prototype and comprehensive experimental evaluation of HexRAN on an over-the-air testbed. The results demonstrate that HexRAN uses only 8% more computing resources compared to the baseline, while managing twice the user plane traffic, delivering control plane processing latency of under 120μs, and achieving 100% processing reliability. This underscores the scalability and performance advantages of the proposed architecture.	10.1109/TNSM.2025.3600587
Maruthi V, Kunwar Singh	Enhancing Security and Privacy of IoMT Data for Unconscious Patient With Blockchain	2025	Early Access	Cryptography Security Polynomials	IoMT enables continuous monitoring through connected medical devices, producing real-time health data that must be protected from unauthorised access and tampering. Blockchain ensures this security with its decentralised, tamper-resistant, and access-controlled ledger. A critical challenge arises when patients are unconscious, making timely access to their IoMT data essential for emergency treatment. To address this, we have created and designed a novel Threshold Proxy Re-Encryption+ (TPRE+) framework that integrates threshold cryptography with unidirectional, non-transitive proxy re-encryption(PRE) with Shamir’s secret sharing to distribute re-encryption capabilities among multiple proxies, reducing single-point failure and collision risks. Our contributions are threefold: (i) We first proposed a semantically secure TPRE+ scheme with Shamir-secret sharing, (ii) Construction of an IND-CCA secure TPRE+ scheme, and (iii) Development of a secure, distributed medical record storage system for unconscious patients, combining blockchain infrastructure, IPFS-based encrypted storage, and our proposed TPRE+ schemes. This integration ensures confidentiality, integrity, and fault-tolerant access to critical patient data, enabling secure and efficient deployment in real-world emergency healthcare scenarios.	10.1109/TNSM.2025.3602117
Yadi He, Zhou Wu, Linfeng Liu	Deep Learning Based Link Prediction Method Against Strong Sparsity for Mobile Social Networks	2025	Early Access	Feature extraction Social networking (online) Predictive models	Link prediction refers to the prediction of the potential relationships between nodes through exploring the evolution of the historical network topologies. In mobile social networks, the topologies change frequently due to the appearance/disappearance of nodes over time, and the links between nodes are typically very sparse (i.e., mobile social networks are with strong sparsity), which could affect the accuracy of link prediction in mobile social networks seriously. Therefore, this paper proposes a deep learning based Link Prediction Method against Strong Sparsity (LPMSS). LPMSS integrates the graph convolutional network output with encounter matrices to mitigate the negative impact of strong sparsity. Additionally, LPMSS employs the random negative sampling to alleviate the impact of imbalanced link distributions. We also adopt a Times module to capture the temporal topological changes in mobile social networks to enhance the prediction accuracy. Based on three datasets with different sparsity, extensive experiment results demonstrate that LPMSS can significantly improve AUC values while reducing MAE values, confirming its effectiveness in handling the link prediction in the mobile social networks with strong sparsity.	10.1109/TNSM.2025.3601389
Zhi-Bin Zuo, De-Min Wang, Mi-Mi Ma, Miao-Lei Deng, Chun Wang	An Adaptive Contention Window Backoff Scheme Differentiating Network Conditions Based on Deep Q-Learning Network	2025	Early Access	Throughput Data communication Wireless sensor networks	In IEEE 802.11 networks, the Contention Window (CW) is a crucial parameter for wireless channel sharing among numerous stations, directly influencing overall network performance. In order to mitigate the performance degradation caused by the increasing number of stations in the network, we propose a novel adaptive CW backoff scheme, termed the ACWB-DQN algorithm. This algorithm leverages the Deep Q-Leaning Network (DQN) to explore a CW threshold, which is utilized as a boundary to differentiate the network load circumstances and learn the best configurations for different network conditions. When stations transmit data frames, different CW optimization strategies are employed based on station transmission status and the CW threshold. This approach aims to enhance network performance by adjusting the CW to increase transmission efficiency when there are fewer competing stations, and lower collision probabilities when there are more competing stations. Simulation results indicate that this approach can optimize station CW, reduce network collision rates, maintain constant throughput and significantly enhance the performance of Wi-Fi networks by means of adjusting the CW threshold according to real-time network conditions.	10.1109/TNSM.2025.3600861
Mingyang Yu, Haorui Yang, Shengwei Fu, Desheng Kong, Xiaoxuan Xu, Jun Zhang, Jing Xu	Improved Coverage and Redundancy Management in WSN Using ENMDBO: An Enhanced Metaheuristic Solution	2025	Early Access	Optimization Wireless sensor networks Heuristic algorithms	The widespread deployment of Wireless Sensor Networks (WSN) has made network coverage optimization crucial for improving coverage rates. However, traditional methods struggle with challenges such as energy constraints and environmental uncertainties. Metaheuristic (MH) algorithms offer promising solutions. Dung Beetle Optimization (DBO) algorithm is a well-regarded MH approach, but it suffers from slow convergence and a propensity for local optima entrapment in WSN coverage optimization. To overcome these limitations, this study proposes the Enhanced Dung Beetle Optimization with Neighborhood Mutation (ENMDBO). ENMDBO incorporates three key mechanisms: (1) the Exploring Cosine Similarity Transformation (ECST) strategy, which dynamically adjusts individual similarity to balance global exploration and local exploitation, mitigating the risk of local optima; (2) the Neighborhood Solution Mutation Sharing (NSMS) mechanism, which enhances population diversity by sharing positional information among neighbors, improving search efficiency; and (3) the Tolerance Threshold Detection Mutation (TTDM) mechanism, which detects stagnation in fitness to strengthen the algorithm’s global search capabilities. Experiments on the CEC2017 benchmark suite (Dim = 30, 50, 100) show that ENMDBO achieves superior performance compared to state-of-the-art algorithms, approaching the global optimum. Finally, in WSN coverage optimization, ENMDBO achieves an 86.88% coverage rate, representing an 8.92% improvement over the original DBO, while effectively reducing redundancy. These results underscore ENMDBO’s robustness and effectiveness, establishing it as a practical and reliable solution. (Matlab codes of ENMDBO are available at https://ww2.mathworks.cn/matlabcentral/fileexchange/181820-enhanced-dung-beetle-optimization-with-neighborhood-mutation.	10.1109/TNSM.2025.3600631
Peng Qin, Yang Fu, Zhigang Yu, Jing Zhang, Zhou Lu	Cross-Domain Resource Allocation for Information Retrieving Delay Minimization in UAV-Empowered 6G Network	2025	Early Access	Sensors Autonomous aerial vehicles Resource management	The deep integration of sensing, communication, caching, and computation (SC3) is emerging as a key feature of 6G network, designed to support ubiquitous intelligent applications and enhance human quality of life. Simultaneously, unmanned aerial vehicles (UAVs) have been identified as promising edge nodes to bolster terrestrial wireless networks. To harness the coordination benefits of SC3 and address potential conflicts, we propose a UAV-empowered joint SC3 6G network, in which UAVs are outfitted with edge servers to cache and process sensing data from integrated sensing and communication devices before delivering the results to users. To maintain the freshness of sensing data in such network, we formulate an average information retrieving delay minimization problem, coordinating cross-domain resources while considering performance constraints in sensing, communication, and energy. We then develop a cross-domain resource optimization algorithm to jointly design UAV 3D deployment, subcarrier assignment, power control, caching update, and computational resource allocation. This approach combines block coordinate descent, matching theory, and successive convex approximation to iteratively solve the optimization problem. Experimental evaluations demonstrate that the proposed scheme converges rapidly and outperforms benchmark methods in reducing average information retrieving delay through the coordination of SC3 cross-domain resources.	10.1109/TNSM.2025.3600768
Menaka Pushpa Arthur, Ganesan Ramachandran, Keshav Sood, Pavan Kaarthik, Srivarshinee Sridhar, Morshed Chowdhury	Empirical Study of Hierarchical Intrusion Detection Systems for Unknown Attacks	2025	Early Access	Classification algorithms Adaptation models Intrusion detection	The attack detection models of the traditional Intrusion Detection Systems (IDSs) IDSsIntrusion Detection Systems are trained on closed-set problems which reduces the classifiers’ performance on detecting unknown attacks in the open-set problem space. Mostly adapted, one-short learning in the classifier does not allow the traditional IDS to be an open-set recognizer. The alternate continuous learning-based IDS in unknown attack detection claims ongoing suggestions from experts to retrain the model with newly identified samples. Hence, using the multi-layer hierarchical IDS (HIDS) HIDSHierarchical IDS with optimized classifier models, the unknown attacks can be classified by comparing their patterns with benign and known attacks. However, we have identified many challenges in the existing HIDS system on various datasets though it provides a solid foundation in this design category for unknown attack identification. As a result, in this paper, we designed an enhanced multi-tier IDS for zero-day attack detection with optimized heterogeneous classifiers in its major two phases like basic framework demands. We have examined the enhanced proposed hierarchical IDS on various benchmark Intrusion Detection Systems datasets such as WUSTL, CIC_IDS_2017, 5G and UNR to analyze the efficiency in unknown attacks classification. When compare to existing multi-tier IDS, the proposed IDS achieved highest detection 96.2%,87%,96.8% and 100% in 5G, WUSTL, UNR and CIC_IDS_2017 datasets for unknown attacks. The optimized model in the proposed IDS reduces the time complexity into 50% than the existing. Implementation results show the proposed enhanced IDS performs better than the existing hierarchical IDS with a high true positive rate for benign, known and unknown attack labels on various datasets.	10.1109/TNSM.2025.3600378
José Santos, Bibin V. Ninan, Bruno Volckaert, Filip De Turck, Mays Al-Naday	A Comprehensive Benchmark of Flannel CNI in SDN/non-SDN Enabled Cloud-Native Environments	2025	Early Access	Containers Benchmark testing IP networks	The emergence of cloud computing has driven advancements in software virtualization, particularly microservice containerization. This in turn led to the development of Container Network Interfaces (CNIs) such as Flannel to connect microservices over a network. Despite their objective to provide connectivity, CNIs have not been adequately benchmarked when containers are connected over an external network. This creates uncertainty about the operation reliability of CNIs in distributed edge-cloud ecosystems. Given the multitude of available CNIs and the complexity of comparing different ones, this paper focuses on the widely adopted CNI, Flannel. It proposes the design of novel benchmarks of Flannel across external networks, Software Defined Networking (SDN)-based and non-SDN, characterizing two of the key backend types of Flannel: User Datagram Protocol (UDP) and Virtual Extensible LAN (VXLAN). Unlike existing benchmarks, this study analysis the overhead introduced by the external network and the impact of network disruptions. The paper outlines the systematic approach to benchmarking a set of Key Performance Indicators (KPIs), including: speed, latency and throughput. A variety of network disruptions have been induced to analyse their impact on these KPIs, including: delay, packet loss, and packet corruption. The results show that VXLAN consistently outperforms UDP, offering superior bandwidth with efficient resource consumption, making it more suitable for production environments. In contrast, the UDP backend is suitable for real-time video streaming applications due to its higher data rate and lower jitter, though it requires higher resource utilization. Moreover, the results show less variation in KPIs over SDN, compared to non-SDN. The benchmark data are made publicly available in an open-source repository, enabling researchers to replicate the experiments, and potentially extend the study to other CNIs. This work contributes to the network management domain by providing an extensive benchmark study on container networking highlighting the main advantages and disadvantages of current technologies.	10.1109/TNSM.2025.3602607
Feng Liu, Zhenyu Li, Chunfang Yang, Daofu Gong, Fenlin Liu, Rui Ma, Adrian G. Bors	BotCF: Improving the Social bot Detection Performance by Focusing on the Community Features	2025	Early Access	Chatbots Feature extraction Social networking (online)	Various malicious activities performed by social bots have brought a crisis of trust to online social networks. Existing social bot detection methods often overlook the significance of community structure features and effective fusion strategies for multimodal features. To counter these limitations, we propose BotCF, a novel social bot detection method that incorporates community features and utilizes cross-attention fusion for multimodal features. In BotCF, we extract community features using a community division algorithm based on deep autoencoder-like non-negative matrix factorization. These features capture the social interactions and relationships within the network, providing valuable insights for bot detection. Furthermore, we employ cross-attention fusion to integrate the features of the account’s semantic content, properties, and community structure. This fusion strategy allows the model to learn the interdependencies between different modalities, leading to a more comprehensive representation of each account. Extensive experiments conducted on three publicly available benchmark datasets (Twibot20, Twibot22, and Cresci-2015) demonstrate the effectiveness of BotCF. Compared to state-of-the-art social bot detection models, BotCF achieves significant improvements in accuracy, with an average increase of 1.86%, 1.67%, and 0.47% on the respective datasets. The detection accuracy is boosted to 86.53%, 81.33%, and 98.21%, respectively.	10.1109/TNSM.2025.3600474
Iwan Setiawan, Binayak Kar, Shan-Hsiang Shen	Energy-Efficient Softwarized Networks: A Survey	2025	Early Access	Energy efficiency Cloud computing Surveys	With the dynamic demands and stringent requirements of various applications, networks need to be high-performance, scalable, and adaptive to changes. Researchers and industries view network softwarization as the best enabler for the evolution of networking to tackle current and prospective challenges. Network softwarization must provide programmability and flexibility to network infrastructures and allow agile management, along with higher control for operators. While satisfying the demands and requirements of network services, energy cannot be overlooked, considering the effects on the sustainability of the environment and business. This paper discusses energy efficiency in modern and future networks with three network softwarization technologies: SDN, NFV, and NS, introduced in an energy-oriented context. With that framework in mind, we review the literature based on network scenarios, control/MANO layers, and energy-efficiency strategies. Following that, we compare the references regarding approach, evaluation method, criterion, and metric attributes to demonstrate the state-of-the-art. Last, we analyze the classified literature, summarize lessons learned, and present ten essential concerns to open discussions about future research opportunities on energy-efficient softwarized networks.	10.1109/TNSM.2025.3599919
Akhirul Islam, Manojit Ghose, Sudeep Pasricha	An RL-based Framework for Task Offloading and Resource Allocation in Energy Harvesting-based Multi-Access Edge Computing	2025	Early Access	Resource management Energy harvesting Energy consumption	With the growing awareness of sustainability concerns in many application domains, energy-harvesting (EH) devices are increasingly being used with traditional non-energy-harvesting (non-EH) devices. This paper proposes a reinforcement learning (RL)-based task offloading and scheduling strategy called DTORA for a hybrid EH and non-EH enabled multi-access edge computing environment where EH devices harvest energy from solar radiation. The applications running on user devices can have varying levels of criticality (mixed-criticality). We formulate a mixed-integer energy and latency minimization programming problem based on the system and application model. To solve this, we use a recurrent neural network based long short-term memory (LSTM) model for solar energy prediction, and a Double Deep Q-learning is used for task-offloading decisions. The proposed strategy (DTORA) is benchmarked against several state-of-the-art (SOA) strategies and other baseline approaches, including SCOPE, OCO (Offloading Cost Optimization), a hybrid Particle Swarm Optimization and Genetic Algorithm (PSOGA), and Selective-Greedy (SG). The proposed strategy outperforms these strategies in terms of latency, energy consumption of user devices, task failure rate, and critical task failures by 39%, 77.51%, 60.98%, and 69.94%, respectively (on average). Compared to the existing best-performing strategy, DTORA achieves improvements of 17.45% for latency, 58.54% for energy consumption, 23.34% for task failure rate, and 27.77% for critical task failures. This improvement can be attributed to improved edge-cloud cooperation, an efficient energy prediction model, and efficient RL-based task offloading and scheduling in our proposed strategy.	10.1109/TNSM.2025.3600109
Mohammad Saleh Mahdizadeh, Behnam Bahrak, Mohammad Sayad Haghighi	A GNN-Based Autopilot Recommendation Strategy to Mitigate Payment Channel Imbalance Problem in Bitcoin Lightning Network	2025	Early Access	Autopilot Bitcoin Routing	The Bitcoin Lightning Network, as a second-layer solution for enhancing the scalability of Bitcoin transactions, facilitates transactions through payment channels between nodes. However, the rapid growth of the network and rising transaction volumes have exacerbated the challenge of managing payment channel imbalances. Payment channel imbalance, characterized by the concentration of liquidity in one direction, leads to a decrease in payment success rates, a reduction in the effective lifespan of payment channels, and a decline in the network’s overall efficiency and throughput. This study introduces a graph neural network-based recommendation strategy designed to enhance the Lightning Network’s autopilot system. The proposed approach proactively mitigates channel imbalances by optimizing channel recommendations, enabling dynamic and scalable liquidity management for network users. Simulations conducted using the CLoTH tool demonstrate a 45% increase in payment success rates, a 46% reduction in imbalanced channels, and a 14% increase in the lifespan of payment channels across the network compared to the existing autopilot recommendation strategies, and when compared with the commonly adopted circular rebalancing method, the proposed strategy achieves a 27% improvement in payment success rates. Additionally, we offer a comparative topological analysis between two snapshots of the LN, taken in November 2021 and August 2023, to facilitate unsupervised learning tasks. The results highlight an increase in network centralization alongside a decrease in the number of network size, emphasizing the growing need for decentralization strategies in the LN, such as the approach proposed in this study.	10.1109/TNSM.2025.3599393
Anna Prado, Fidan Mehmeti, Wolfgang Kellerer	Reducing Mobility-Related Signaling With Network Sum Throughput Maximization in 5G	2025	Early Access	Handover Throughput 5G mobile communication	Signal quality fluctuates significantly due to blockages of Line of Sight, shadowing, and user mobility. This renders mobility management in 5G quite challenging. To improve it, 3GPP introduced Conditional Handover (CHO), which reduces handover failures by preparing target Base Stations (BSs) in advance. CHO adapts to the varying channel conditions and constantly prepares/releases cells, which leads to an increased exchange of control messages between the user and BSs. Connecting to the BS with the strongest signal is not always beneficial because the available resources and other users’ channels should be considered for a successful network operation. Hence, the need to carefully decide when to hand over, and when that happens, to select the best target BS. In this paper, we first formulate an optimization problem that minimizes network signaling by reducing the number of unprepared handovers and wasted cell preparations while providing a minimum rate to everyone. As the problem is NP-hard, we relax it and obtain a lower bound. Then, we propose a Cost-Efficient CHO (CECHO) algorithm with performance guarantees. Using 5G datasets, we compare CECHO with two baselines and show that it outperforms them by at least 45% while being near-optimal. However, reducing the signaling decreases the total throughput, which is an important metric for the network operator. Thus, we expand our initial problem into a Multi-Objective (MO) optimization, where we additionally maximize the network sum throughput. Results show that CECHO-MO increases the sum throughput more than 3× with only a 4% increase in signaling.	10.1109/TNSM.2025.3599203
Ning Zhao, Dongke Zhao, Huiyan Zhang, Yongchao Liu, Liang Zhang	Resilient Dynamic Event-Triggered Fuzzy Tracking Control for Nonlinear Systems Under Hybrid Attacks	2025	Early Access	Event detection Fuzzy systems Denial-of-service attack	This article investigates the issue of event-triggered tracking control for Takagi–Sugeno fuzzy systems subject to hybrid attacks. First, the deception attacks occurring on the feedback channel are considered using a Bernoulli process, in which an attacker injects state-dependent malicious signals. Next, the minimal ‘silent’ and maximal ‘active’ periods are defined to describe the duration of aperiodic denial-of-service (DoS) attacks. To take advantage of communication bandwidth and resist DoS attacks, a sampled data-based resilient dynamic event-triggered strategy is designed. Then, an event-based fuzzy tracking controller is designed to guarantee the stability of error system under hybrid attacks. Subsequently, sufficient conditions for the stability analysis are proposed by utilizing a fuzzy-basis-dependent Lyapunov-Krasovskii functional. Meanwhile, the control gains and event-triggering parameters are co-designed by applying linear matrix inequalities. Furthermore, the proposed method is extended to address the tracking control problem of multi-agent systems. Finally, the feasibility of the presented approach is validated by two examples.	10.1109/TNSM.2025.3625395
Huigyu Yang, Jeongjun Park, Syed M. Raza, Moonseong Kim, Min Young Chung, Hyunseung Choo	Urban Mobile Data Prediction With Geospatial Clustering and Dual Residual Learning	2025	Early Access	Predictive models Accuracy Telecommunication traffic	The mobile network traffic patterns in urban areas significantly diverge depending on commercial and residential establishments. These regional traffic patterns provide crucial clues for predicting traffic patterns precisely. Previous studies have employed a combination of time-series and convolutional Deep Learning (DL) models to effectively capture the correlation of the regional features and traffic patterns. Despite promising results, these approaches are limited in identifying pattern similarities among sparsely located regions and can be further improved. To this end, this study proposes a GEospatial clustering and residual COnvolutional temporal long Short-term memory (GECOS) framework consisting of clustering and DL components. The proposed Urbanflow Peak Clustering (UPC) component exploits the peak traffic times of daily mobile data to obtain the groups of cells with similar traffic patterns apart from their geographical diversity. The UPC improves the scalability of existing algorithms and enables DL components to improve their accuracy by recognizing unique regional patterns and localizing the training targets. The proposed Residual Convolutional TCN-LSTM (RCTL) serves as the DL component of GECOS that improves TCN-LSTM structure through layer-wise feature transfer and enhances long-term dependency learnability. The RCTL ensures more accurate capturing of extensive spatiotemporal features through structural enhancements. The experiments conducted on real-world mobile traffic data showcase 43% improvement by GECOS compared to state-of-the-art models, enabling precise traffic engineering policies by operators.	10.1109/TNSM.2025.3599168
Jia Xu, Mengmeng Zhu, Xiao Liu, Xuejun Li, Yun Yang	Cost-Aware Heterogeneous Service Placement Strategies for MEC-Based Unmanned Delivery	2025	Early Access	Costs Drones Servers	Unmanned delivery utilizes autonomous vehicles, such as drones or unmanned ground vehicles (UGVs), to transport goods, parcels, or other materials without human intervention which can significantly reduce delivery costs and time. Servitised drones and UGVs provide flexible, on-demand delivery services that optimize resource usage, improve logistics efficiency. Drone-as-A-Service (DaaS), as a typical paradigm of unmanned delivery, can maximize delivery efficiency while minimizing costs. Most existing DaaS systems only support modeling for a single type of delivery service, overlooking the diversity of available delivery services. In fact, the collaboration between different types of heterogeneous delivery services can not only reduce delivery costs but also enhance user satisfaction. However, heterogeneous services require necessitating effective service placement strategies to optimize the allocation and coordination of service resources, ultimately improving delivery efficiency and cost-effectiveness. Therefore, how to generate a suitable service placement plan with the objective of minimizing costs, has become a significant challenge. In this paper, a multi-access edge computing based heterogeneous delivery service framework (HDaaS) is proposed for effectively managing heterogeneous delivery resources. Building upon this framework, we design a cost-aware delivery service placement strategy (CDS) consisting of two phases: recommendation phase using CDSR-GA to identify optimal service and placement phase employing CDSP-RL to generate and refine placement plans. Experimental results show that the CDS strategy can generate delivery service placement plans that effectively reduce service provider costs under deadline constraints by about 29.84% on average.	10.1109/TNSM.2025.3598812
Erhe Yang, Zhiwen Yu, Yao Zhang, Helei Cui, Zhaoxiang Huang, Hui Wang, Jiaju Ren, Bin Guo	Joint Semantic Extraction and Resource Optimization in Communication-Efficient UAV Crowd Sensing	2025	Early Access	Sensors Autonomous aerial vehicles Optimization	With the integration of IoT and 5G technologies, UAV crowd sensing has emerged as a promising solution to overcome the limitations of traditional Mobile Crowd Sensing (MCS) in terms of sensing coverage. As a result, UAV crowd sensing has been widely adopted across various domains. However, existing UAV crowd sensing methods often overlook the semantic information within sensing data, leading to low transmission efficiency. To address the challenges of semantic extraction and transmission optimization in UAV crowd sensing, this paper decomposes the problem into two sub-problems: semantic feature extraction and task-oriented sensing data transmission optimization. To tackle the semantic feature extraction problem, we propose a semantic communication module based on Multi-Scale Dilated Fusion Attention (MDFA), which aims to balance data compression, classification accuracy, and feature reconstruction under noisy channel conditions. For transmission optimization, we develop a reinforcement learning-based joint optimization strategy that effectively manages UAV mobility, bandwidth allocation, and semantic compression, thereby enhancing transmission efficiency and task performance. Extensive experiments conducted on real-world datasets and simulated environments demonstrate the effectiveness of the proposed method, showing significant improvements in communication efficiency and sensing performance under various conditions.	10.1109/TNSM.2025.3603194
Menna Helmy, Alaa Awad Abdellatif, Naram Mhaisen, Amr Mohamed, Aiman Erbad	Slicing for AI: An Online Learning Framework for Network Slicing Supporting AI Services	2025	Early Access	Artificial intelligence Training Resource management	The forthcoming 6G networks will embrace a new realm of AI-driven services that requires innovative network slicing strategies, namely slicing for AI, which involves the creation of customized network slices to meet Quality of Service (QoS) requirements of diverse AI services. This poses challenges due to time-varying dynamics of users’ behavior and mobile networks. Thus, this paper proposes an online learning framework to determine the allocation of computational and communication resources to AI services, to optimize their accuracy as one of their unique key performance indicators (KPIs), while abiding by resources, learning latency, and cost constraints. We define a problem of optimizing the total accuracy while balancing conflicting KPIs, prove its NP-hardness, and propose an online learning framework for solving it in dynamic environments. We present a basic online solution and two variations employing a pre-learning elimination method for reducing the decision space to expedite the learning. Furthermore, we propose a biased decision space subset selection by incorporating prior knowledge to enhance the learning speed without compromising performance and present two alternatives of handling the selected subset. Our results depict the efficiency of the proposed solutions in converging to the optimal decisions, while reducing decision space and improving time complexity. Additionally, our solution outperforms State-of-the-Art techniques in adapting to diverse environmental dynamics and excels under varying levels of resource availability.	10.1109/TNSM.2025.3603391