Link Flooding Attack (LFA) can disconnect target links or network areas to cause the disruption of legitimate services by flooding network traffic. The centralized control makes Software Defined Network (SDN) vulnerable to LFA attacks. Most of existing LFA defense solutions based on statistic analysis and machine learning have the limitations on obtaining sufficient samples, detection accuracy and mitigation effect. In this paper, an AI-enabled intelligent defense framework for LFA in SDN networks is proposed to improve LFA detection accuracy and mitigation effect. Specifically, we present a Generative Adversarial Network (GAN) based LFA Detection (GLD) mechanism to obtain traffic patterns through adversarial training between generator and discriminator to improve detection accuracy. To enhance detection effectiveness, we design a data collection and processing mechanism to collect finer grained network status and switch status information in real time by leveraging in band network telemetry technology. Furthermore, we design a Double Deep Q-Network (DDQN) based LFA mitigation (DLM) mechanism, to effectively mitigate LFA traffic through the proposed rerouting algorithm and identify the suspicious IP addresses to block the attackers by using the proposed LFA source identification method. Simulation results demonstrate that compared with benchmark mechanisms, GLD mechanism can get higher detection accuracy and DLM mechanism can better mitigate LFA with smaller resource consumption cost.

Network Function Virtualization (NFV) facilitates on-demand and flexible service provisioning to meet the escalating demands of Internet of Things (IoT) applications, enabled by Service Function Chain (SFC) technique. The widespread deployment of 5G has connected a massive number of devices and users to IoT networks, accelerating the expansion of IoT scales. IoT users’ service requirements exhibit heightened diversity and dynamism. Consequently, the SFC placement problem in Next Generation Multi-domain IoT (NGMIoT) networks has garnered significant attention. How to efficiently place SFCs under uncertain resource demands to adapt to evolving service request dynamics poses substantial challenges. Therefore, this paper investigates the Robust SFC Placement (RSFCP) problem in NGMIoT networks under resource demand uncertainty. Specifically, we formulate the RSFCP problem as an integer linear programming model to minimize overall SFC placement cost while ensuring service quality. We further prove the RSFCP problem is NP-hard and propose a greedy strategy based heuristic SFC placement algorithm to solve it. Finally, extensive simulation experiments are conducted to evaluate performance, demonstrating that the proposed algorithm outperforms benchmark mechanisms in terms of service acceptance rate and placement cost.

This paper addresses the task offloading problem in Mobile Edge Computing (MEC) enabled Vehicular Medical (MVM) networks, where stringent requirements for service quality and low latency are critical due to the time-sensitive nature of medical applications. To cope with dynamic task requests, we formulate a joint optimization model to maximize task success rate while minimizing processing delay. A Task Offloading (PTO) mechanism based on Proximal Policy Optimization (PPO) algorithm is proposed to enable each vehicle to make intelligent offloading decisions by only using the local observations. Simulation results show that the PTO mechanism outperforms baseline methods by reducing task dropped ratio and task delay.

Latency-sensitive services across the end-edge-cloud continuum require not only low mean latency but explicit control of tail latency and data freshness. We propose Control-Loop Freshness-aware Service Function Chain orchestration (CLFSFC), a freshness-aware orchestration framework for Service Function Chains (SFCs) that jointly selects model variants and function placements. We define a Control-Loop Freshness (CLF) objective that combines 95th/99th-percentile (P95/P99) end-toend latency with an Age of Information (AoI) proxy. To make this objective operational under uncertainty, we allocate per-stage risk budgets via the union bound and convert mean/variance profiles into percentile constraints using Cantelli's inequality, yielding a two-stage greedy solver with interpretable quotas. We implement CLF-SFC with offline profiling of YOLOv5 n/s/m variants across end/edge/cloud devices, and evaluate it with profiling-driven measurements on COCO 2017 under synthesized network regimes. Across bandwidth and round-trip time settings, CLF-SFC reduces P95/P99 latency and Service Level Objective (SLO) violations relative to Edge-only, Cloud-only, and a riskagnostic heuristic; at high bandwidth it remains comparable to the Shortest-Latency-Path (SLP) baseline. The proposed CLF-SFC framework naturally fits embodied-AI pipelines where perception, fusion, and policy modules operate in a closed loop. By explicitly incorporating the Age-of-Information (AoI), our orchestration ties data freshness to control stability, complementing tail-latency minimization.

As an emerging network technology, Network Function Virtualization (NFV) enables network functions decoupling from dedicated hardware by replacing traditional middleboxes with software implemented Virtual Network Functions (VNFs). In NFV-enabled Internet of Things (IoT) networks, each IoT service can be represented as an ordered sequence of VNFs, referred to as Service Function Chain (SFC). Through NFV, operating expenditure and capital expenditure can be significantly reduced, thereby achieving flexible provisioning of IoT services. However, with the arriving of 6G era, the network scale of IoTs continuously expands, and service requirements of IoT users become more diversified. Particularly, 6G enabled IoT services have stringent delay requirements. How to efficiently place the SFCs in multi-domain IoT networks to satisfy the specific delay requirements while guaranteeing quality of service becomes a serious challenge. To this end, in this paper, we investigate the problem of delay guaranteed SFC placement in multi-domain IoT networks. Specifically, by taking in account QoS requirements and VNF dependency relationships, we formulate the problem of delay guaranteed SFC placement in multi-domain IoT networks as a multi-objective optimization model to maximize service acceptance ratio and minimize operational cost, while satisfying the delay requirements of SFC requests. To solve the problem, we further design a Delay Guaranteed heuristic SFC Placement (DGSP) algorithm with VNF parallelization. In the proposed DGSP algorithm, the VNFs without dependency relationships are placed in parallel in an adaptive and cost efficient manner, and virtual link mapping is performed based on the shortest path algorithm. Finally, we conduct simulation experiments for performance evaluation, and simulation results demonstrate the proposed DGSP algorithm can get higher service acceptance ratio and lower operational cost than comparison algorithms.

With the rapid development of the Internet of Things (IoT) and Artificial Intelligence (AI) technologies, the Artificial Intelligence of Things (AIoT) has become a key driving force for realizing intelligent and automated applications. The deployment of Service Function Chains (SFCs) is crucial in dynamic AIoT environments, where efficiently and flexibly deploying SFCs to meet real-time application demands is a research focus. However, existing SFC deployment methods often face challenges such as dynamic variations and uncertainty in contextual information, resource allocation inefficiencies, and limited adaptability to changing network conditions. To address these issues, we propose a learning-based context-aware dynamic SFC deployment method tailored for AIoT environments. Specifically, we introduce an attention-based contextual feature extraction method to capture dynamic changes (e.g., link latency variations) and prioritize key contextual information, improving the rate of served requests by 17.90% (69.60% vs. 59.03% for MADDPG) and enhancing the flexibility of SFC deployment decisions. Additionally, to address resource allocation bottlenecks and adaptability challenges in SFC deployment, we propose a distributed learning-based context-aware approach that uses collaborative learning and periodic updates (every 200 ms) to adjust SFC deployment strategies in response to topology changes and load variations and optimize system performance. Extensive experimental results demonstrate the efficacy of the proposed algorithm. Numerical results demonstrate that our algorithm reduces SFC deployment latency by 8% (46 ms vs. 50 ms for MADDPG), achieves 98.3% computational resource utilization, processes 211 Mbit/s service data volume, and improves adaptability to network changes, as validated in simulations.

Network Function Virtualization (NFV) has recently emerged as a highly cost-effective paradigm for flexibly provisioning services in next-generation Internet of Things (IoT) networks, by introducing Service Function Chain (SFC) technology. However, the rapid expansion of network scales and increasing diversification of service requirements in recent years pose significant challenges to ensuring the Quality of Experience (QoE) of users in Next-generation Multi-domain IoT (NMIoT) networks. The effective deployment of SFCs in NMIoT networks to satisfy diversified resource demands while enhancing QoE of users is crucial. The recent breakthroughs in Generative Artificial Intelligence (GAI) technologies bring a new opportunity to deliver customized services and guarantee enhanced service quality in NMIoT networks. To tackle the challenges, in this paper, we investigate the problem of Resource and QoE aware SFC Placement (RQSP) in NMIoT networks. Firstly, we formulate the RQSP problem as a mixed integer linear programming model, taking into account resource demands and Quality of Service (QoS) constraints, aiming to minimize the service cost, which is composed of resource consumption cost, cross-domain operational cost and penalty cost for unsuccessful placement. Then, we prove that the RQSP problem is NP-hard. To solve it, we incorporate GAI technology to devise a novel Generative genetic Algorithm based heuristic SFC Placement (GAP) method. Furthermore, we devise a greedy strategy based population initialization mechanism as well as an elitist and roulette wheel joint selection strategy, to speed up algorithm convergence and reduce runtime overhead. Finally, simulation results demonstrate that compared to benchmark algorithms, the proposed GAP algorithm can achieve better performances on service acceptance ratio, service cost, server utilization and average service delay.

In medical vehicular networks, medical vehicles can serve as efficient mobile medical service points to provide necessary and critical medical services for patients while in motion. The delay requirement is very vital for medical services to guarantee service quality and save the lives of patients. Mobile Edge Computing (MEC), as an emerging network paradigm, enables the computation extensive tasks to be offloaded to edge servers, efficiently reducing the delay and bandwidth demands. MEC technology is a promising solution to provide high-quality medical services for users in medical vehicular networks. However, task offloading and resource allocation incurs additional service delay and energy consumption, affecting the overall service performance and Quality of Experience (QoE) of users. Thus, realizing the optimal task offloading and resource allocation in MEC-enabled medical vehicular networks, to reduce task completion time and energy consumption, becomes a potential challenge. To address the challenge, we investigate the joint task offloading and resource allocation problem in MEC-enabled medical vehicular networks to improve the QoE of users. Considering the resource requirements and QoS constraint, we formulate a multi-objective optimization model, with the target of average task completion time and average energy consumption minimization. On this basis, we propose a MOEAD-based task offloading and resource allocation (IMO) algorithm to solve it. Furthermore, in order to obtain the optimal solution and speed up the algorithm convergence, we design a greedy strategy-based population initialization algorithm. The extensive simulations demonstrate that compared to existing algorithms, our proposed IMO algorithm can obtain a smaller average completion time, and achieve better tradeoff between task completion time and energy consumption.

With the recent advancement in network technologies, the vehicle based medical networks extend medical services to mobile vehicles, thereby offering flexible and efficient healthcare services for vehicle users in need. The integration of vehicle based medical network and edge computing enables computation intensive medical service tasks to be offloaded on edge servers, to provide fast service response for vehicle users. An efficient task offloading and resource allocation strategy is critical for Vehicle based Medical Edge Computing System (VMECS) to satisfy real-time and reliability requirements while ensuring service performance. To this end, in this paper, we investigate the problem of task computation allocation in VMECS networks. By introducing deep reinforcement learning, we first present a novel VMECS architecture to automatically achieve the optimal task offloading and resource allocation through the multi-agent collaboration, thereby improving service performance. Then, we formulate the problem of task offloading and resource allocation in VMECS networks as an optimization model with the aim of maximizing task success rate by jointly considering communication interferences, resource allocation and delay requirements. To solve it, we further devise a Distributed distributional deterministic policy gradients based Task offloading and Resource allocation (DTR) algorithm. Final simulation results demonstrate that compared with benchmark algorithms, DTR algorithm can obtain higher task success rate, smaller service time, and less task processing time.

As an emerging architecture, edge computing enables resource limited terminal devices to offload their computation tasks to edge servers in the vicinity, to efficiently reduce delay and energy consumption. However, the continuous expansion of network scale and rapid growth of network traffic in recent years have brought huge challenges to task offloading and resource allocation. To tackle the challenges, by integrating Knowledge Defined Networking (KDN) and edge computing technologies, we design a novel Knowledge defined Edge Computing (KEC) architecture, to achieve intelligent resource allocation and task offloading in dynamic large-scale edge computing networks. We formulate the task offloading and resource allocation optimization problem, to minimize delay and energy consumption, by considering resource requirements and controller deployment. To solve it, we present an intelligent Resource Allocation based Task Offloading (TORA) mechanism, where a Multi-Agent SD3 based resource allocation (MASD3) algorithm is devised to perform efficient resource allocation. To adapt to the rapid expansion of network scale, we design a resource Allocation based Controller Deployment and task offloading Decision (DACD) algorithm, to perform the optimal controller deployment and task offloading. Extensive simulation experiments demonstrate the effectiveness and efficiency of our proposed solution, and TORA mechanism outperforms comparison mechanisms on delay and energy consumption.

With the rapid advancement of networks, the number of mobile devices requiring real-time data processing in mobile edge computing (MEC) systems is escalating. For emergency tasks with strict delay constraints, failure to process them within the deadline can lead to serious cascading effects and safety risks. As an emerging technology, Knowledge-Defined Networking (KDN) provides core support for intelligent scheduling and management by constructing a global network view. However, traditional strategies struggle with dynamic environments, hindering timely completion of highly unpredictable and delay-sensitive emergency tasks. To tackle this problem, we introduce a Knowledge-Defined Mobile Edge Computing (KD-MEC) architecture, which leverages real-time network data and global perception capability of KDN to dynamically model network load and task types. We also propose the joint optimization scheme based on deep reinforcement learning and attention mechanism (JODRA) for emergency task scheduling. Simulations demonstrate that JODRA improves emergency task completion rates and system performance by focusing on task-specific characteristics.

The bipartite consensus problem in multi-agent systems (MASs), as a crucial foundation in the field of cooperative control, has become a hot topic in numerous research areas. Collaborative control of MASs can be threatened by information leakage, so this paper conducts an in-depth study on this. Firstly, in this paper, we design a privacy-preserving control protocol to encrypt and protect the original data to prevent information leakage in MASs. Secondly, due to the existence of cooperative competition within the MASs, this paper adds an adaptive strategy to the privacy-preserving control protocol and realizes the system's adaptive bipartite consensus. Then, the theoretical analysis shows that the method is able to achieve system convergence while providing privacy preservation for system information. Finally, the effectiveness of this method is validated through simulation experiments on MASs with a fixed topology structure.

The Fifth-Generation mobile networks (5G) and Beyond 5G (B5G) have been proposed to support a variety of application scenarios, such as enhanced Mobile Broadband (eMBB), ultra-Reliable Low-Latency Communications (uRLLC), and massive Machine Type Communications (mMTC). On the other hand, Mobile Edge Computing (MEC) and Network Functions Virtualization (NFV) technologies have been widely advocated by service providers to meet diverse service demands and reduce operational costs. To alleviate the pressure on the edge network, resource consumption can be minimized by considering the reuse of Virtual Network Function (VNF) instances. However, implementing VNF chain deployment with latency guarantees and resource efficiency in a distributed network architecture remains an urgent issue to be addressed. In this paper, we explore the Service Function Chains (SFCs) orchestration problem with distributed edge network resources, aiming to design efficient service flow routing and resource allocation schemes to significantly respond to local user requests. We propose a low-complexity Distributed SFCs Orchestration algorithm with VNF Reuse (DSOR), which initially uses local information at the edge to explore the VNFs orchestration scheme and executes the distributed service orchestration. Subsequently, service chains are deployed based on asynchronous consensus to enhance network utility and reduce resource costs. Finally, the performance of DSOR is evaluated through extensive simulation experiments. The experimental results indicate that DSOR can improve the utilization of network resources, as well as the response rate to edge service requests.

Influence maximization in online social networks is used to select a set of influential seed nodes to maximize the influence spread under a given diffusion model. However, most existing proposals have huge computational costs and only consider the dyadic influence relationship between two nodes, ignoring the higher-order influence relationships among multiple nodes. It limits the applicability and accuracy of existing influence diffusion models in real complex online social networks. To this end, in this paper, we present a novel information diffusion model by introducing hypergraph theory to determine the most influential nodes by jointly considering adjacent influence and higher-order influence relationships to improve diffusion efficiency. We mathematically formulate the influence maximization problem under higher-order influence relationships in online social networks. We further propose a hypergraph sampling greedy algorithm (HSGA) to effectively select the most influential seed nodes. In the HSGA, a random walk-based influence diffusion method and a Monte Carlo-based influence approximation method are devised to achieve fast approximation and calculation of node influences. We conduct simulation experiments on six real datasets for performance evaluations. Simulation results demonstrate the effectiveness and efficiency of the HSGA, and the HSGA has a lower computational cost and higher seed selection accuracy than comparison mechanisms.

The increasing service demands in 5G networks have led to the emergence of Network Function Virtualization (NFV) technology. Through the virtualization technique, NFV enables on-demand and flexible service provisioning and deployment by implementing networks functions in forms of software instances, called Virtual Network Functions (VNFs). With the rapid development and implementation of 5G, the Service Function Chain (SFC) placement problem in multi-domain network scenarios is gaining significant attentions due to the sudden and dynamic patterns of resource demands from a diversity of service requests. Most existing proposals attempt to optimize the SFC placement in multi-domain networks, under the assumption that resource demand required each service request is given in prior and keeps unchanged during the SFC execution period. However, it is impractical in real network scenarios due to the evolving dynamic changes of service requests. The uncertainty of service demands has an important effect on service reliability, service quality and network performance. To this end, in this paper, we study the problem of robust SFC placement in multi-domain networks under the assumption that resource demands of SFC requests are uncertain. We first formulated the problem of robust SFC placement in multi-domain networks as an integer programming model with the aim to minimize the SFC placement cost while considering the Quality of Service (QoS) guarantee. Then, we develop a three-stage heuristic placement algorithm to solve the problem. The extensive simulation results demonstrate that our proposed heuristic algorithm is efficient and can save more placement cost than comparison mechanisms.

The distributed H_∞ fusion filtering of multi-sensor network systems by False Data Injection (FDI) attack in the presence of sensor saturation is investigated. Firstly, a system model is designed to set up a discrete-time multi-sensor network system, and the distributed H_∞ fusion filtering is designed based on the local filtering parameters by splicing real matrix inequalities using functions, optimizing the filtering design and parameters, and making the filtering exhibit exponential stability in the mean square sense. The experimental simulations validate, the designed distributed H_∞ fusion filtering for wireless sensor networks designed in this paper has lower computational complexity, more obvious optimisation and better system stability than the traditional fusion filtering.

This paper studies the bipartite consensus in multi-agent systems with an emphasis on privacy-preserving measures in collaborative-competitive networks. Firstly, we employ state decomposition to secure the initial state values of each node, preventing the disclosure of individual state information during the bipartite consensus process. For each node, the first sub-state is involved in computation and interacts with internal nodes, while the other sub-state interacts exclusively with its corresponding first sub-state. Then, based on the decomposed state values of the nodes, we propose an event-triggered bipartite consensus control method, assuring effective utilization of communication resources. Finally, a simulation experiment is given to demonstrate the validity of the theoretical results.

Collaborative control in multi-agent systems has appeared as a subject of considerable interest in the control science, and the binary consensus in multi-agent systems has received extensive attention. This paper focuses on the binary consensus problem in discrete multi-agent systems under uncertain random communication noises environments, where every intelligent agent can only use its own information and the information from its neighbors for information exchange or observation. In order to improve consensus accuracy, an algorithm is proposed that can achieve asymptotic convergence of the agents, minimizing the covariance of the consensus error when the privacy level reaches a certain condition. The paper employs matrix theory and automatic control theory to analyze the system’s consistency and privacy. Finally, the results prove that the control protocol delivered in this paper achieves a certain level of privacy protection while the consensus accuracy of the multi-agent systems is also improved.

Network function virtualization (NFV) implements network functions as Virtual Network Functions (VNFs) to address the challenges faced by traditional network infrastructures. Service Function Chaining (SFC) chains VNFs in a specific order to process packets, but placing SFCs across multiple domains while ensuring reliability is challenging. Existing methods are time-consuming and error-prone. In this paper, we study the reliability aware multi-domain SFC placement problem. The reliability aware multi-domain SFC placement problem is formulated as a multi-objective optimization model to minimize SFC placement resource consumption cost (SPRC) and SFC Placement operating cost (SPOC) while satisfying the specific reliability requirements. Then, we propose a Deep Reinforcement Learning-based SFC placement algorithm, called DRL-SFCP, to optimize the reliability of SFC placement in multi-domain networks. Finally, we conduct extensive experiments and results demonstrate that our proposed placement method outperforms existing approaches in terms of SPRC and SPOC.

The emergence of virtualization technologies such as Software Defined Networking (SDN) and Network Function Virtualization (NFV) has enabled efficient service delivery by Service Function Chains (SFCs) deployment. SFCs deployment involves the optimal placement of Virtual Network Functions (VNFs) to satisfy service requirements and minimize deployment cost. Deep Reinforcement Learning (DRL) method could learn optimal decision-making policies in dynamic and uncertain environments. Therefore, we propose a DRL approach to solve the adaptive SFC deployment problem (DRL-SFCD) in multi-domain networks. First, the adaptive SFC deployment problem in multi-domain networks is formulated as a multi-objective optimization model with the aim of maximizing Service Deployment Successful Ratio (SDSR) and minimizing SFC Deployment Rescource Cost (SDRC). Then, a DRL algorithm is constructed based on Markov Decision Process (MDP) model to select the optimal servers and map virtual links cost-efficiently. Finally, we evaluate our approach and the results demonstrate that our approach out-performs comparison algorithms in terms of SDSR and SDRC.