Network

As network automation and self-organizing networks (SONs) rapidly evolve, edge devices increasingly demand lightweight, real-time, and high-precision classification algorithms to support critical tasks such as traffic identification, intrusion detection, and fault diagnosis. In recent years, cross-entropy (CE) loss has been widely adopted in deep learning classification tasks due to its computational efficiency and ease of optimization. However, traditional CE methods primarily focus on class separability without explicitly constraining intra-class compactness and inter-class boundaries in the feature space, thereby limiting their generalization performance on complex classification tasks. To address this issue, we propose a novel classification loss framework—Contrastive Geometric Cross-Entropy (CGCE). Without incurring additional computational or memory overhead, CGCE explicitly introduces learnable class representation vectors and constructs the loss function based on the dot-product similarity between features and these class representations, thus explicitly reinforcing geometric constraints in the feature space. This mechanism effectively enhances intra-class compactness and inter-class separability. Theoretical analysis further demonstrates that minimizing the CGCE loss naturally induces clear and measurable geometric class boundaries in the feature space, a desirable property absent from traditional CE methods. Furthermore, CGCE can seamlessly incorporate the prior knowledge of pretrained models, converging rapidly within only a few training epochs (for example, on the CIFAR-10 dataset using the ViT model, a single training epoch is sufficient to reach 99% of the final training accuracy.) Experimental results on both text and image classification tasks show that CGCE achieves accuracy improvements of up to 2% over traditional CE methods, exhibiting stronger generalization capabilities under challenging scenarios such as class imbalance, few-shot learning, and noisy labels. These findings indicate that CGCE has significant potential as a superior alternative to traditional CE methods. Full article

Elastic optical networks (EONs) must allocate resources dynamically to accommodate heterogeneous, high-bandwidth demands. However, the continuous setup and teardown of connections with different bit rates can fragment the spectrum and lead to blocking. The blocking predictors enable proactive defragmentation and resource reallocation within network controllers. In this paper, we propose two novel deep learning models (based on CNN–BiLSTM and CNN–LSTM) to predict blocking in EONs by combining spatial feature extraction from spectrum snapshots using 2D convolutional layers with temporal sequence modeling. This hybrid spatio-temporal design learns how local fragmentation patterns evolve over time, allowing it to detect impending blocking scenarios more accurately than conventional methods. We evaluate our model on the simulated NSFNET topology and compare it against multiple baselines, namely 1D CNN, 2D CNN, k-nearest neighbors (KNN), and support vector machines (SVMs). The results show that the proposed CNN–BiLSTM/LSTM models consistently achieve higher performance. The CNN–BiLSTM model achieved the highest accuracy in blocking prediction, while the CNN–LSTM model shows slightly lower accuracy; however, it has much lower complexity and a faster learning time. Full article

Connected and Autonomous Vehicles are promising for advancing traffic safety and efficiency. However, the increased connectivity makes these vehicles vulnerable to a broad array of cyber threats. This paper presents a novel hybrid approach for intrusion detection in in-vehicle networks, specifically focusing on the Controller Area Network bus. Ensemble learning techniques are combined with sophisticated optimization techniques and dynamic adaptation mechanisms to develop a robust, accurate, and computationally efficient intrusion detection system. The proposed system is evaluated on real-world automotive network datasets that include various attack types (e.g., Denial of Service, fuzzy, and spoofing attacks). With these results, the proposed hybrid adaptive system achieves an unprecedented accuracy of 99.995% with a 0.00001% false positive rate, which is significantly more accurate than traditional methods. In addition, the system is very robust to novel attack patterns and is tolerant to varying computational constraints and is suitable for deployment on a real-time basis in various automotive platforms. As this research represents a significant advancement in automotive cybersecurity, a scalable and proactive defense mechanism is necessary to safely operate next-generation vehicles. Full article

As 5G and beyond networks grow in heterogeneity, complexity, and scale, traditional Intrusion Detection Systems (IDS) struggle to maintain accurate and precise detection mechanisms. A promising alternative approach to this problem has involved the use of Deep Learning (DL) techniques; however, DL-based IDS suffer from issues relating to interpretation, performance variability, and high computational overheads. These issues limit their practical deployment in real-world applications. In this study, CiNeT is introduced as a novel DL-based IDS employing Convolutional Neural Networks (CNN) within a bijective encoding–decoding framework between network traffic features (such as IPv6, IPv4, Timestamp, MAC addresses, and network data) and their RGB representations. This transformation facilitates our DL IDS in detecting spatial patterns without sacrificing fidelity. The bijective pipeline enables complete traceability from detection decisions to their corresponding network traffic features, enabling a significant initiative towards solving the ‘black-box’ problem inherent in Deep Learning models, thus facilitating digital forensics. Finally, the DL IDS has been evaluated on three datasets, UNSW NB-15, InSDN, and ToN_IoT, with analysis conducted on accuracy, GPU usage, memory utilisation, training, testing, and validation time. To summarise, this study presents a new CNN-based IDS with an end-to-end pipeline between network traffic data and their RGB representation, which offers high performance and enhanced interpretability through revisable transformation. Full article

The successful integration of Terrestrial and Non-Terrestrial Networks (T/NTNs) in 6G is poised to revolutionize demanding domains like Earth Observation (EO) and Intelligent Transportation Systems (ITSs). Still, it requires Distributed Machine Learning (DML) frameworks that are scalable, private, and efficient. Existing methods, such as Federated Learning (FL) and Split Learning (SL), face critical limitations in terms of client computation burden and latency. To address these challenges, this paper proposes a novel hierarchical DML paradigm. We first introduce Federated Split Transfer Learning (FSTL), a foundational framework that synergizes FL, SL, and Transfer Learning (TL) to enable efficient, privacy-preserving learning within a single client group. We then extend this concept to the Generalized FSTL (GFSTL) framework, a scalable, multi-group architecture designed for complex and large-scale networks. GFSTL orchestrates parallel training across multiple client groups managed by intermediate servers (RSUs/HAPs) and aggregates them at a higher-level central server, significantly enhancing performance. We apply this framework to a unified T/NTN architecture that seamlessly integrates vehicular, aerial, and satellite assets, enabling advanced applications in 6G ITS and EO. Comprehensive simulations using the YOLOv5 model on the Cityscapes dataset validate our approach. The results show that GFSTL not only achieves faster convergence and higher detection accuracy but also substantially reduces communication overhead compared to baseline FL, and critically, both detection accuracy and end-to-end latency remain essentially invariant as the number of participating users grows, making GFSTL especially well suited for large-scale heterogeneous 6G ITS deployments. We also provide a formal latency decomposition and analysis that explains this scaling behavior. This work establishes GFSTL as a robust and practical solution for enabling the intelligent, connected, and resilient ecosystems required for next-generation transportation and environmental monitoring. Full article

The Internet of Things allows us to implement concepts such as Education 4.0 by connecting sensors, actuators, and applications. In the case of direct and explicit connections, we refer to ensembles that can consist of devices and applications. When realizing spatially distributed applications, there are scenarios in which these ensembles must coordinate with each other. In software development, this process is referred to as orchestration or choreography. This paper describes a software framework that provides orchestration or choreography for self-explaining ensembles using predefined rules based on a self-description of all involved components. The framework is capable of generating user instructions or explanations for smart environments that cover interaction details. The approach also forms a basis to provide information about event-based coordination. In a case study, we investigated the technical perception of a coordinated spatial learning game application (an ambient serious game). Most participants perceived the application as cohesive and found it responsive. These results suggest that our framework provides a solid foundation for implementing coordinated applications within smart environments that appear as unified applications. Full article

The rapid expansion of communication networks and increasingly complex service demands have presented significant challenges to the intelligent management of network resources. To address these challenges, we have proposed a network self-optimization framework integrating the predictive capabilities of the Large Language Model (LLM) with the decision-making capabilities of multi-agent Reinforcement Learning (RL). Specifically, historical network traffic data are converted into structured inputs to forecast future traffic patterns using a GPT-2-based prediction module. Concurrently, a Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm leverages real-time sensor data—including link delay and packet loss rates collected by embedded network sensors—to dynamically optimize bandwidth allocation. This sensor-driven mechanism enables the system to perform real-time optimization of bandwidth allocation, ensuring accurate monitoring and proactive resource scheduling. We evaluate our framework in a heterogeneous network simulated using Mininet under diverse traffic scenarios. Experimental results show that the proposed method significantly reduces network latency and packet loss, as well as improves robustness and resource utilization, highlighting the effectiveness of integrating sensor-driven RL optimization with predictive insights from LLMs. Full article

Network monitoring is becoming increasingly challenging as networks grow in scale, speed, and complexity. The evolution of monitoring approaches reflects a shift from device-centric, localized techniques toward network-wide observability enabled by modern networking paradigms. Early methods like SNMP polling and NetFlow provided basic insights but struggled with real-time visibility in large, dynamic environments. The emergence of Software-Defined Networking (SDN) introduced centralized control and a global view of network state, opening the door to more coordinated and programmable measurement strategies. More recently, programmable data planes (e.g., P4-based switches) and in-band telemetry frameworks have allowed fine grained, line rate data collection directly from traffic, reducing overhead and latency compared to traditional polling. These developments mark a move away from single point or per flow analysis toward holistic monitoring woven throughout the network fabric. In this survey, we systematically review the state of the art in network-wide monitoring. We define key concepts (topologies, flows, telemetry, observability) and trace the progression of monitoring architectures from traditional networks to SDN to fully programmable networks. We introduce a taxonomy spanning local device measures, path level techniques, global network-wide methods, and hybrid approaches. Finally, we summarize open research challenges and future directions, highlighting that modern networks demand monitoring frameworks that are not only scalable and real-time but also tightly integrated with network control and automation. Full article

The hybridization of Near-Field Communication (NFC) with Visible Light Communication (VLC) presents a promising framework for robust, secure, and efficient wireless transmission. By combining proximity-based authentication of NFC with high-speed and interference-resistant data transfer of VLC, this approach mitigates the inherent limitations of each technology, such as the restricted range of NFC and authentication challenges of VLC. The resulting hybrid system leverages NFC for secure handshaking and VLC for high-throughput communication, enabling scalable, real-time applications across diverse domains. This study examines integration strategies, technical enablers, and potential use cases, including smart street poles for secure citizen engagement, patient authentication and record access systems in healthcare, personalized retail advertising, and automated attendance tracking in education. Additionally, this paper addresses key challenges in hybridization and explores future research directions, such as the integration of Artificial Intelligence and 6G networks. Full article

In this paper, we introduce a novel, self-hosted Syslog collection platform designed specifically to address the challenges that small and medium enterprises (SMEs) face in implementing comprehensive syslog monitoring solutions. Our analysis begins with an assessment of current network observability practices, evaluating enterprise solutions, on-premises systems, and Software as a Service (SaaS) offerings to identify features crucial for SME environments. The proposed platform represents an advancement in the field through the incorporation of modern practices, including GitOps and continuous integration and continuous delivery/deployment (CI/CD), and its implementation onto a self-managed Kubernetes platform, which is an approach not commonly explored in SME-focused solutions. We will explore its scalability by leveraging dynamic templates, which allow us to select the number and type of nodes when deploying networks of various sizes. This architecture ensures organisations can deploy a pre-designed, scalable network monitoring solution without extensive external support. The resilience of the proposed platform is assessed by providing empirical evidence of the scaling performance and reliability under various failure scenarios, including node failure and high network throughput stress. Full article

Cascading link failures continue to imperil power grids, transport networks, and cyber-physical systems, yet the relationship between a network’s robustness at the moment of attack and its subsequent resiliency remains poorly understood. We introduce a dynamic framework in which connectivity-based cascades and distributed self-healing act concurrently within each time-step. Failure is triggered when a node’s active-neighbor ratio falls below a threshold $\phi$; healing activates once the global fraction of inactive nodes exceeds trigger $T$ and is limited by budget $B$. Two real data sets—a 332-node U.S. airport graph and a 1133-node university e-mail graph—serve as testbeds. For each graph we sweep the parameter quartet ($\phi ,\hspace{0.17em}B,\hspace{0.17em}T,attackmode$) and record (i) immediate robustness $R$, (ii) 90% recovery time T₉₀, and (iii) cumulative average damage. Results show that targeted hub removal is up to three times more damaging than random failure, but that prompt healing with $B\ge 0.12$ can halve T₉₀. Scatter-plot analysis reveals a non-monotonic correlation: high-$R$ states recover quickly only when $B$ and $T$ are favorable, whereas low-$R$ states can rebound rapidly under ample budgets. A multiplicative fit $T_{90}\propto B^{-\beta }g\left(T\right)h\left(R\right)$ (with $\beta \approx 1$) captures these interactions. The findings demonstrate that structural hardening alone cannot guarantee fast recovery; resource-aware, early-triggered self-healing is the decisive factor. The proposed model and data-driven insights provide a quantitative basis for designing infrastructure that is both robust to failure and resilient in restoration. Full article

Blockchain’s decentralized, immutable, and transparent nature offers a promising solution to enhance security, trust, and efficiency in supply chains. While integrating blockchain into the SCM process poses significant challenges, including technical, operational, and regulatory issues, this review analyzes blockchain’s potential in SCM with a focus on the key challenges encountered when applying blockchain in this domain—such as scalability limitations, interoperability barriers, high implementation costs, and privacy as well as data security concerns. The key contributions are as follows: (1) applications of blockchain across major SCM domains—including pharmaceuticals, healthcare, logistics, and agri-food; (2) SCM functions that benefit from blockchain integration; (3) how blockchain’s properties is reshaping modern SCM processes; (4) the challenges faced by businesses while integrating blockchain into supply chains; (5) a critical evaluation of existing solutions and their limitations, categorized into three main domains; (6) unresolved issues highlighted in dedicated “Critical Issues to Consider” sections; (7) synergies with big data, IoT, and AI for secure and intelligent supply chains, along with challenges of emerging solutions; and (8) unexplored domains for blockchain in SCM. By synthesizing current research and industry insights, this study offers practical guidance and outlines future directions for building scalable and resilient global trade networks. Full article

This paper presents a long-range experimental demonstration of multi-mode multiple-input multiple-output (MIMO) transmission using orbital angular momentum (OAM) waves for Line-of-Sight (LoS) wireless backhaul applications. A 4 × 4 MIMO system employing distinct OAM modes is implemented and shown to support multiplexing data transmission over a single frequency band without inter-channel interference. In contrast, a 2 × 2 plane wave MIMO configuration fails to achieve reliable demodulation due to mutual interference, underscoring the spatial limitations of conventional waveforms. The results confirm that OAM provides spatial orthogonality suitable for high-capacity, frequency-efficient wireless backhaul links. Experimental validation is conducted over an 100 m outdoor path, demonstrating the feasibility of OAM-based MIMO in practical wireless backhaul scenarios. Full article

Nowadays, internet connectivity suffers from instability and slowness due to optical fiber cable attacks across the seas and oceans. The optimal solution to this problem is using the Low Earth Orbit (LEO) satellite network, which can resolve the problem of internet connectivity and reachability, and it has the power to bring real-time, reliable, low-latency, high-bandwidth, cost-effective internet access to many urban and rural areas in any region of the Earth. However, satellite orbital placement (SOP) and navigation should be carefully designed to reduce signal impairments. The challenges of orbital satellite placement for LEO include constellation development, satellite parameter optimization, bandwidth optimization, consideration of signal impairment, and coverage optimization. This paper presents a comprehensive review of SOP and coverage optimization, examines prevalent issues affecting LEO internet connectivity, evaluates existing solutions, and proposes novel solutions to address these challenges. Furthermore, it recommends a machine learning solution for coverage optimization and SOP that can be used to efficiently enhance internet reliability and reachability for LEO satellite networks. This survey will open the gate for developing an optimal solution for global internet connectivity and reachability. Full article

Cloud computing has increasingly adopted multi-tenant infrastructures to enhance cost efficiency and resource utilization by enabling the shared use of computational resources. However, this shared model introduces several security and privacy concerns, including unauthorized access, data redundancy, and susceptibility to malicious activities. In such environments, the effectiveness of cloud-based recommendation systems largely depends on the trustworthiness of participating nodes. Traditional collaborative filtering techniques often suffer from limitations such as data sparsity and the cold-start problem, which significantly degrade rating prediction accuracy. To address these challenges, this study proposes a Trusted Graph-Based Collaborative Filtering Recommender System (TGBCF). The model integrates graph-based trust relationships with collaborative filtering to construct a trust-aware user network capable of generating reliable service recommendations. Each node’s reliability is quantitatively assessed using a trust metric, thereby improving both the accuracy and robustness of the recommendation process. Simulation results show that TGBCF achieves a rating prediction accuracy of 93%, outperforming the baseline collaborative filtering approach (82%). Moreover, the model reduces the influence of malicious nodes by 40–60%, demonstrating its applicability in dynamic and security-sensitive cloud service environments. Full article

The Encrypted Client Hello (ECH) extension to Transport Layer Security (TLS) and the new type of Domain Name System (DNS) records called HTTPS represent the latest efforts to improve user privacy by encrypting the server’s domain name during the TLS handshake. While prior studies have assessed ECH adoption from the server perspective, little is known about its usage in the wild from a passive network standpoint. In this paper, we present the first passive analysis of ECH and HTTPS DNS adoption using a month-long dataset collected from an operational network. We find that HTTPS DNS queries already make up approximately 8% of total DNS traffic, although responses to those queries are often incomplete, leading to increased query volume. Furthermore, 59% of QUIC flows include ECH, although only a negligible fraction is directed to servers supporting it. The remaining ECH flows are composed of GREASE values, intended to prevent protocol ossification. Our findings provide new insights into the current state and challenges in deploying privacy-enhancing protocols at scale. Full article

Critical Internet of Things (IoT) data in Fifth Generation Vehicular Ad Hoc Networks (5G VANETs) demands Ultra-Reliable Low-Latency Communication (URLLC) to support mission-critical vehicular applications such as autonomous driving and collision avoidance. Achieving the stringent Quality of Service (QoS) requirements for these applications remains a significant challenge. This paper proposes a novel framework integrating Software-Defined Networking (SDN) and Network Functions Virtualisation (NFV) as embedded functionalities in connected vehicles. A lightweight SDN Controller model, implemented via vehicle on-board computing resources, optimised QoS for communications between connected vehicles and the Next-Generation Node B (gNB), achieving a consistent packet delivery rate of 100%, compared to 81–96% for existing solutions leveraging SDN. Furthermore, a Software-Defined Wide-Area Network (SD-WAN) model deployed at the gNB enabled the efficient management of data, network, identity, and server access. Performance evaluations indicate that SDN and NFV are reliable and scalable technologies for virtualised and distributed 5G VANET infrastructures. Our SDN-based in-vehicle traffic classification model for dynamic resource allocation achieved 100% accuracy, outperforming existing Artificial Intelligence (AI)-based methods with 88–99% accuracy. In addition, a significant increase of 187% in flow rates over time highlights the framework’s decreasing latency, adaptability, and scalability in supporting URLLC class guarantees for critical vehicular services. Full article

The widespread adoption of cloud computing has amplified the demand for electric power. It is strategically important to address the limitations of reliable sources and sustainability of power. Research and investment in data centres and power infrastructure are therefore critically important for our digital economy. A novel heuristic for the minimisation of energy consumption in cloud computing is presented. It draws similarities to the concept of “network slices”, in which an orchestrator enables multiplexing to reduce the network “churn” often associated with significant losses of energy consumption. The novel network slicing–ring fencing ratio is a heuristic calculated through an iterative procedure for the reduction in cloud energy consumption. Simulation results show how the non-convex equation optimises power by reducing energy from 10,680 kJ to 912 kJ, which is a 91.46% efficiency gain. In comparison, the Heuristic AUGMENT Non-Convex algorithm (HA-NC, by Hossain and Ansari) reported a 312.74% increase in energy consumption from 2464 kJ to 10,168 kJ, while the Priority Selection Offloading algorithm (PSO, by Anajemba et al.) also reported a 150% increase in energy consumption, from 10,738 kJ to 26,845 kJ. The proposed network slicing–ring fencing ratio is seen to successfully balance energy consumption and computing performance. We therefore think the novel approach could be of interest to network architects and cloud operators. Full article