Industrial Internet applications require networks to guarantee deterministic end-to-end latency and zero packet loss at both the data link and network layers. Traditional best-effort communication models in consumer networks are insufficient to meet these stringent demands. To meet these stringent demands, the IEEE 802.1 standards introduce Time-Sensitive Networking (TSN) at the data link layer, while the IETF proposes Deterministic Networking (DetNet) for the network layer. However, enabling seamless cross-domain communication between TSN and DetNet remains a significant challenge. This paper proposes a unified cross-domain network architecture and a time-slot alignment strategy that compensates for synchronization errors between the TSN and DetNet layers. We further develop a Joint Routing and Scheduling algorithm for Deterministic Cross-Domain Transmission (JRS-DCT), which simultaneously addresses routing and scheduling under cross-domain constraints. The algorithm leverages Cycle-Specified Queuing and Forwarding (CSQF) in DetNet and Cycle Queuing and Forwarding (CQF) in TSN to ensure bounded latency and deterministic transmission. Extensive simulations demonstrate that the proposed JRS-DCT algorithm significantly improves the scheduling success rate and effectively reduces network resource utilization compared to two baseline algorithms. These results validate the effectiveness and robustness of the proposed framework in supporting time-sensitive communication across heterogeneous network environments.

Network slicing, which enables multiple services to coexist on the shared physical infrastructure, has been recognized as a key technology in networks. Leveraging the high processing capability of programmable data plane (PDP) devices, network slicing within PDPs can lead to efficient traffic isolation, priority management, and significantly reduced forwarding delays. However, existing inflexible and coarse-grained network slicing orchestration approaches struggle to address the challenges posed by diversified slicing scenarios and the constrained resources of PDP devices. In this paper, we propose AtlasPro, a framework for network slicing orchestration in PDPs, where each network slice is regarded as an independent Service Function Chain (SFC) routing entity. Thus, it enables the allocation of physical resources at a finer granularity. Additionally, we introduce a novel heuristic approach, the Chained Hyper-Generative Algorithm, which jointly optimizes Virtual Network Function (VNF) deployment and routing costs, minimizing total cost while meeting the performance requirements of all network slices. We implement our framework using BMv2 switches in a Mininet environment and evaluated our algorithm. Compared to existing solutions, our framework and algorithm reduce the number of VNF deployments, lower routing delays by up to 34.2 %, and cut overall costs by up to 48.5%.

Edge devices increasingly require efficient, on-device intelligence for diverse applications in IoT networks. In order to bring the advanced capabilities of large foundation models directly to the point of data generation, there is a growing interest in deploying these models on edge devices. However, due to their inherent resource constraints and the diverse, heterogeneous nature of the data and tasks they encounter, deploying large foundation models directly on these devices remains a significant challenge. To address these challenges, we propose a novel Federated Learning Fine-Tuning (FLFT) framework that leverages adapter-based fine-tuning with a similarity-driven selection mechanism, enabling personalized model adaptation with minimal computational overhead. Furthermore, we introduce the Diffusion-based Soft Actor-Critic (FTFL2DSAC) algorithm, which optimizes real-time resource allocation by balancing energy consumption and latency across heterogeneous edge devices. Our experiments on CIFAR-100 using a pre-trained multimodal model demonstrate that FLFT achieves 82.5% accuracy while reducing model parameters by 14%, outperforming baseline methods with faster convergence and enhanced stability in complex environments.

The rapid growth of 5G and 6G networks has introduced complex traffic patterns and stringent real-time demands. Traditional SDN architectures struggle to meet the low-latency and dynamic requirements of wireless environments due to high communication overhead and rigid hardwares. Programmable switches, with their ability to dynamically cus-tomize data plane behavior, offer a more flexible solution for real-time traffic management at the network edge. However, most existing solutions rely on offline models with limited real-time detection capabilities, resulting in increased overhead and suboptimal performance. In this paper, we present Gendetect, a generative-AI enabled lightweight traffic detection architec-ture for programmable wireless gateways. Gendetect employs generative knowledge distillation to train decision tree-based models, enabling efficient online training and adaptive updates. By generating synthetic training data in real-time, it reduces the need for frequent control plane interactions, mitigating north-south overhead. Additionally, a feature selection mechanism optimizes resource utilization, balancing table entry consumption and detection accuracy. Extensive simulations demonstrate that Gendetect significantly improves traffic detection performance while reducing match-action table entries, making it well-suited for dynamic and resource-constrained wireless networks.

In-band network telemetry (INT) is an emerging network measurement technique that offers real-time and fine-grained visualization capabilities for networks. However, the utilization of INT for network measurement introduces additional overheads to the network. The process of data collection consumes extra bandwidth resources, and adjustments to the data collection scheme can impact network stability. Additionally, the INT orchestration scheme requires adaptation to dynamics in the network to improve measurement accuracy. Therefore, striking a balance between accuracy and stability becomes a critical problem. In this paper, our focus lies in the trade-off between measurement accuracy and network stability. We consider the long-term orchestration of multiple telemetry tasks, rationally deploying distinct telemetry tasks to different application flows. To address the challenge, we propose a self-adaptive Dynamic INT Orchestration scheme, D-INTO. Specifically, we formulate a stochastic optimization problem for dynamic INT orchestration. Then we employ Lyapunov optimization to decouple the stochastic optimization problem and use surrogate Lagrangian relaxation to construct a polynomial-time approximation algorithm. Theoretical analysis and experimental results demonstrate that our proposed D-INTO outperforms existing schemes in terms of adaptability to the network dynamics.

In order to ensure reliable transmission of important traffic in industrial networks, time-sensitive network (TSN) technology and fifth-generation mobile communication technology (5G) are introduced into the industrial network. However, there are still challenges in integrating TSN networks with 5G networks, especially in terms of end-to-end scheduling in hybrid systems. Considering the diverse range of traffic types and their end-to-end transmission requirements within the industrial Internet, we propose a differentiated traffic scheduling model and develop a population generation algorithm, termed Genetic Algorithm (GA) based two-stage population generation algorithm (PTPG). Notably, the algorithm utilizes a non-target training approach to generate the initial population and integrate Proximal Policy Optimization (PPO) to improve algorithm convergence and facilitate the inheritance of advantages across generations. The simulation results demonstrate notable enhancements in end-to-end delay, the number of occupied queues, and algorithm convergence status compared to other algorithms.

Recently, diverse emerging scenarios have precipitated a substantial surge in the variety of devices and applications, which has consequently imposed more stringent demands on Quality of Service (QoS) prerequisites. As a burgeoning emerging network measurement method, In-band network telemetry (INT), can provide detailed metrics for QoS by obtaining fine-grained network status information. However, INT only outlines device-level operations, which fails to provide an entire network view for monitoring. To address this, INT orchestration based on network topology and application requirements to achieve network-level monitoring is necessary. In this paper, we propose an INT orchestration model that efficiently measures the entire network while minimizing measuring overhead. The model outputs the probe path and collects requirements for the devices it passes through. Our method effectively reduces network bandwidth consumption caused by INT process and ensures telemetry items remain fresh. Experiment results support the effectiveness of our approach.

The integration of unmanned aerial vehicles (UAVs) with 5G networks presents a promising opportunity to revolutionize wireless communication and provide high-speed internet access to remote areas. Nevertheless, the vast quantity of data generated by UAVs requires the implementation of efficient distributed learning techniques. In this study, we present a novel hybrid approach that merges Federated Learning (FL) and Split Learning (SL) to optimize the performance of UAV swarms in 5G networks. While FL is capable of reducing communication overhead and preserving privacy, SL can enhance the accuracy of the model through the utilization of the local computational resources of each device. To realize the hybrid approach, we first locally train the model on each UAV using split learning. Subsequently, the encrypted model parameters are transmitted to a central server for federated averaging. Finally, the updated model is dispatched back to each UAV for local fine-tuning, and this cycle is repeated until convergence is achieved. The hybrid approach capitalizes on the strengths of both FL and SL to minimize communication overhead and increase accuracy. To tackle the challenge of selecting the most suitable UAVs for participation in the learning process, we propose a multiagent algorithm that considers factors such as communication latency and training time. Our experimental results indicate that the proposed approach leads to substantial improvements in communication overhead and accuracy compared to conventional methods.

Cyclic queuing and forwarding (CQF), proposed in IEEE 802.1 Qch, is a practical mechanism for guaranteeing deterministic transmission for time-sensitive networks (TSNs). However, only the queue model and the workflow for terrestrial networks are defined in IEEE 802.1 Qch. To make TSNs practical for future 6G applications, a general scheduling model that maps time-sensitive flows (TSFs) to the underlying resources of low-Earth-orbit satellite-terrestrial integration networks (LEOSTINs) is urgently needed. The networking conditions of STINs are quite different from those of terrestrial networks due to the large-scale spatial coverage of STINs. Hence, in order to determine the feasibility of deploying TSNs in LEO-STINs, we evaluate the CQF performance for LEO-STINs in this paper. Then, a software-defined-network-based LEO-STIN architecture for the entire lifecycle of TSFs is designed. To address the drawbacks of the LEO-STIN scenario, we propose a cyclic priority and forwarding (CPF) mechanism to improve the performance of time-sensitive services. CPF removes the bandwidth limitation of CQF for TSFs, which makes TSNs practical for LEO-STINs. We perform a simulation of a Walker constellation to test the proposed algorithm and existing TSN techniques using OMNET ++. The results show that the proposed algorithm reduces the packet loss ratio by an order of magnitude and the service time-out ratio by 70% compared to existing mechanisms.

Nowadays, the compelling applications of the Internet of Things (IoT) bring unexpected economic benefits to our daily lives. But at the same time, it also poses huge challenges to service providers. Diverse proprietary hardware (i.e., firewall and code conversion) have to be deployed in networks for meeting different applications’ requirements. Recently, network functions virtualization (NFV) is considered a promising technique. In the NFV-enabled architecture, network services can be implemented via a set of orderly virtual network functions (VNFs) on standardized compute nodes, which is termed service function chains (SFCs). However, with the explosion of IoT applications, embedding multiple SFCs in a shared NFV-enabled infrastructure becomes a challenging problem. Centralized schemes suffer from the scalability and private issue, while distributed schemes suffer from the nonconvergence problem. In this article, we propose a hybrid intelligent control architecture, which adopts the centralized training and distributed execution paradigm. A centralized critic is introduced to ease the training process of the distributed network nodes. Besides, considering the competitive behavior of users, we formulate the resource allocation problem as a multiuser competition game model. Based on this, we proposed a multiagent reinforcement learning-based SFCs deployment algorithm.

With the growth of the number of Internet of Things (IoT) devices and the emergence of new applications, satisfying distinct QoS in the same physical network becomes more challenging. Recently, with the advance of network functions virtualization and software-defined networking (SDN) technologies, the network slicing technique has emerged as a promising solution. It can divide a physical network into multiple virtual networks, therefore providing different network services. In this article, to meet distinct QoS in industrial IoT, we design a network slicing architecture over the SDN-based long-range wide area network. The SDN controller can dynamically split the network into multiple virtual networks according to different business requirements. On this basis, we proposed a deep deterministic policy gradient (DDPG) based slice optimization algorithm. It enables LoRa gateways to intelligently configure slice parameters (e.g., transmission power and spreading factor) to improve the slice performance in terms of QoS, energy efficiency, and reliability. In addition, to accelerate the training process across multiple LoRa gateways, we leverage the transfer learning framework and design a transfer learning-based multiagent DDPG algorithm.

The past few years have witnessed the compelling applications of the Internet of Things (IoT) in our daily life. The explosive growth of the number of IoT devices also presents a great challenge in network security, especially the DDoS attack. Current DDoS defense mechanisms adopted out-of-band architecture, which is accomplished by a process that receives monitoring data from routers and switches, then analyzes that flow data to detect attacks. However, facing IoT devices growing rapidly, this out-of-band architecture confronted with limited processing capacity, bandwidth resources, and service assurance problems. Recently, with the development of the programming switch, it opens up new possibilities for in-network DDoS detection, where the detection algorithms could be directly implemented inside the routers and switches. Benefit from switch processing performance, the in-network mechanism could achieve high scalability and line speed performance. Therefore, in this article, we design a machine learning-based in-network DDoS detection framework. We implement the lightweight variational Bayes algorithm in each switch to detect the anomaly traffic. Besides, considering the shortage of training data in each switch, a centralized platform is introduced to synchronize parameters among distributed switches to realize collaborative learning. Extensive simulations are conducted to evaluate our proposed algorithm in comparison to some state-of-the-art schemes.