To address the problems of low resource utilization and deployment efficiency caused by sudden changes in network states due to large-scale complex network access and the random arrival of service requests during dynamic service function chain (SFC) deployment, a novel SFC deployment method for IoT networks based on large language model (LLM) policy distillation is proposed. First, an SFC deployment framework based on teacher-student agent policy distillation using LLM is constructed. Through the policy distillation mechanism, the MARL-based student agents are guided to efficiently learn the SFC deployment policies generated by the LLM-driven teacher agents. Second, we design a teacher agent composed of three modules: a state perceiver, a task-planning decision-maker, and a result evaluator. The state perceiver predicts node resource availability using an LLM-based spatiotemporal forecasting method. The decision-maker leverages LLM reasoning to generate candidate deployment policies. The evaluator selects policies based on load-balancing metrics. Finally, the student agents, considering constraints such as network resources and latency, build an optimization model aimed at maximizing resource utilization and SFC deployment rewards, and introduce a Teacher-Student Policy Distillation-based Multi-Agent Soft Actor-Critic (TSPD-MASAC) algorithm to solve this optimization problem. Simulation results demonstrate that, in complex network environments with dynamic resource states and diverse service requests, the proposed method achieves more accurate resource state perception, accelerates algorithm convergence, and significantly improves resource utilization and overall deployment performance compared with baseline schemes.

To address the issues of lagging virtual network function (VNF) migration caused by the dynamic changes in resource requirements in Industrial Internet of Things (IIoT) and the unsatisfactory prediction effect due to the neglect of the connection relationships between nodes in resource requirement prediction, a digital twin(DT)-assisted VNF migration algorithm with spatiotemporal large language model-based resource demand prediction is proposed. Firstly, a large language model-based resource prediction method that combines graph convolutional networks and multi-head self-attention mechanism is introduced to effectively capture spatio-temporal correlations and predict future resource requirements. Next, in order to ensure a deterministic quality of service (QoS) and optimize migration decisions, a DT-assisted VNF migration model composed of energy consumption, latency, and load balancing is constructed, and a joint optimization model for VNF migration and DT re-association aimed at maximizing the long-term utility of the system is established. Finally, a migration algorithm based on heterogeneous multi-agent proximal policy optimization is proposed to solve the VNF migration problem according to the resource requirements predicted by the model. To address the problem of excessive synchronization delays of DT nodes originally associated with nodes after migration, a counterfactual multi-agent algorithm is proposed to solve the problem of DT re-association. Simulation results show that the proposed algorithm improves prediction accuracy, ensures load balancing, and reduces system energy consumption and synchronization delays.

To address the issue of inaccurate synchronization between physical devices and their corresponding digital twins (DT) in Industrial Internet of Things (IIoT), which is caused by sensing errors, unreliable wireless transmission, and outdated information, we propose a DT information synchronization strategy for IIoT based on dual time scale network slicing (NS) orchestration. Firstly, a DT-driven IIoT slicing architecture is proposed to provide isolation for heterogeneous Quality of Service (QoS) requirements. On this basis, to quantify synchronization performance, a DT fidelity model is established, incorporating sensing accuracy, data transmission reliability, and the Age of Information (AoI). To fully utilize the network resources and improve the accuracy of DT synchronization information, a dual time-scale model is constructed, where the large time scale handles DT association and inter-slice resource allocation according to the users’ demand, while the small time scale is responsible for intra-slice scheduling of power, bandwidth, and observation frequency. To solve the formulated optimization problem, we design a hierarchical deep reinforcement learning framework that adopts Deep Recurrent Q-Network (DRQN) and Counterfactual Multi-Agent Prioritized Experience Replay Compound-Action Actor-Critic (COMA-PER-CA2C) algorithms. Simulation results demonstrate that the proposed method significantly improves DT fidelity and resource utilization in various IIoT scenarios.

The identification of the root causes of failures in complex Internet of Things (IoT) systems has always presented a significant challenge. Despite the extensive range of algorithms and technologies already available for Root Cause Analysis (RCA) in various fields, there remains a lack of RCA methods specifically designed for IoT systems. The present paper proposes an IoT system root cause analysis framework based on dynamic causal graphs, assisted by Large Language Models (LLMs), called LLMs-DCGRCA. Firstly, in response to the issues with traditional causal hypothesis methods, which rely on human experience and suffer from key variable omission and incorrect causal direction assumptions, this paper proposes a method for generating causal hypotheses for IoT systems by using knowledge graphs to enhance the performance of LLMs. Secondly, in response to the challenge that traditional causal learning methods in IoT scenarios struggle to capture causal relationships across the temporal dimension, this paper proposes a dynamic causal graph learning method that incorporates causal constraints. Finally, in response to the limitations of traditional root cause analysis methods in IoT scenarios in accurately capturing the dynamic characteristics of anomaly propagation, this paper proposes a cumulative root cause localization method based on dynamic causal graphs. The evaluation of LLMs-DCGRCA is conducted using IoT trace data collected from simulation environments and GAIA, a widely-used public dataset in the field of intelligent operations and maintenance. The evaluation results demonstrate that LLMs-DCGRCA achieves average HR@7 improvements of 14.04% and 9.35% compared to baseline methods on the two datasets, respectively.

To address the diverse user service requirements in network slicing (NS) and the challenges of synchronization accuracy and low latency in Digital Twin (DT) deployment, this paper proposes a joint optimization strategy for digital twin-based dual-time domain slice resource management and DT deployment in the Internet of Vehicles (IoV). First, a demand-driven slice resource management scheme is introduced to mitigate Quality of Service (QoS) degradation caused by insufficient resource allocation under fluctuating user demands. Network performance indicator weights are dynamically adjusted using demand enhancement factors. Second, to minimize the impact of DT synchronization on resource allocation and address challenges like low latency and delay bias, DT utility is quantified from three perspectives: completeness, load contribution, and resource reliability. Finally, a price incentive mechanism with dynamic load adjustment is designed to balance the supply and demand of DT and service resources. This joint optimization problem is an NP-hard mixed-integer nonlinear problem with dual time-domain coupling, which can be decomposed into utility maximization strategies in different time domains. In the long-time domain, a Q-value-based Deep Transfer Reinforcement Learning (QDTRL) algorithm is used for DT deployment, while in the short-time domain, a Long Short-Term Memory - Multi-Agent Proximal Policy Optimization (LSTM-MAPPO) algorithm is applied for resource allocation and DT synchronization weight adjustment. Simulation results show that, compared to baseline schemes, the proposed strategy achieves higher utility, accelerates convergence, and effectively allocates resources and synchronizes DT.

With the rapid development of the Internet of Things (IoT), many IoT devices are accessing the network. However, existing networks cannot fully meet the strict and diverse requirements for delay and reliability in delay-sensitive services. Dynamic changes in service requests and the states of service nodes cause a lack of guaranteed end-to-end (E2E) network slicing delay determinism. To address this issue, we propose a digital twin (DT)-assisted network slicing resource allocation scheme. By integrating DT and network slicing, we first construct a DT-assisted E2E network architecture, and construct the base and mapping models in the proposed architecture. Second, we use the stochastic network calculus (SNC) theory to analyze the E2E delay violation probability and characterize the relationship between delay and service reliability under given traffic arrival distributions and delay constraints. Then, we construct a joint resource allocation problem of time-frequency, computation, storage, and bandwidth resources to maximize the utility of the infrastructure provider while guaranteeing the deterministic delay. Furthermore, a multiagent deep reinforcement learning algorithm in a distributed architecture is used to solve the complex optimization problem, achieving efficient network resource allocation. Simulation results demonstrate that the proposed resource allocation scheme meets the requirements for deterministic delay and enhances system utility.

To address the challenges faced by vehicles using integrated sensing and communication (ISAC) devices in maintaining sensing quality while maximizing the timeliness of sensing information, as well as the allocation of limited edge computing resources when large amounts of sensing data are uploaded to edge servers (ESs), we propose an integrated sensing, communication resource allocation, and digital twin (DT) placement scheme based on DT in IoV. First, a frame structure with an adjustable ISAC slot ratio was designed. Under the constraints of sensing mutual information and uplink communication rate, the timeliness of sensed data is enhanced by minimizing the Age of Information (AoI) during data transmission. Second, a vehicle DT (VDT) placement cost model, incorporating both latency and energy consumption, was constructed. The optimal VDT placement strategy was derived by minimizing placement costs, leading to efficient allocation of edge computing resources. Furthermore, considering the impact of vehicle mobility on real-time interaction between vehicles and VDTs, a migration utility based on vehicle migration latency and migration energy consumption between edge nodes was designed. On this basis, a joint system utility maximization optimization model was established, integrating sensing data AoI utility, VDT placement cost, and migration utility. Due to the continuous and discrete variables in the optimization problem, we develop an algorithm based on multiagent deep reinforcement learning (MADRL) to solve the problem, called SCDTP-MPDQN. Simulation results demonstrate the superiority of the proposed scheme in enhancing sensing information utility and system utility.

As industrial IoT networks evolve, they become increasingly vulnerable to cyberattacks, such as Denial of Service and backdoor attacks, which lead to anomalies in data streams (e.g., unusual spikes or drops in traffic, sudden changes in device behavior, or irregular communication patterns). To address the challenge of detecting these anomalies amidst dynamic data distributions and diverse abnormal patterns, this article proposes a supervised contrastive learning-based spatiotemporal variational autoencoder (SC-STVAE) for anomaly detection in online data streams. A multihead graph attention network (MD-GAT) is utilized to capture feature correlations, while a temporal convolution network serves as the hidden layer in the variational autoencoder. This enables SC-STVAE to learn both feature correlations and temporal dependencies. To resolve the issue of ambiguous positive and negative boundaries, supervised contrastive learning is introduced within the STVAE, improving boundary distinction and detection accuracy. To mitigate performance degradation due to data drift, an event-triggered elastic weight consolidation algorithm is introduced, which updates model parameters based on reliability thresholds. Additionally, a fuzzy entropy-weighted anomaly score, which measures the error between reconstructed data and original inputs by computing the weighted sum of the mean squared error across each dimension, is introduced. Experimental results demonstrate superior performance in terms of accuracy, recall, and F1 score compared to benchmark algorithms.

Aiming at the problems of data synchronization and resource limitation in smart driving on Internet of Vehicles (IoV), we investigate the construction of digital twins (DTs) and resource allocation on IoVs with the aim of achieving the optimal system performance. DT is a key technology in the future of autonomous driving. By digitizing physical components, it can effectively predict, analyze, and optimize various services of intelligent driving. First, we propose an accurate DT construction scheme (SL-ADTC) based on swarm learning (SL), which uses distributed learning algorithms to predict the queuing waiting time at relay nodes and the update frequency of DTs to solve data deviation and desynchronization for constructing DTs. Second, to address the problem of insufficient local computational resources of the task vehicles, a DT-based task division cooperative processing (DT-TDCP) mechanism is proposed. Then, considering the contradiction between task delay and system energy consumption, a joint optimization problem of computational offloading decision and resource allocation is proposed to minimize the total system cost under the premise of guaranteeing the high accuracy of DTs. Regarding the problem that the state space dimension is too high in reinforcement learning and the algorithm has difficulty in convergence, a DT-assisted multiagent classification proximal policy optimization (MACPPO) algorithm is proposed. Numerical results show that the proposed schemes outperform several benchmark schemes in terms of DTs construction accuracy, service latency, and system energy consumption.

The average peak age of information (PAoI) and the average age of information (AoI) are crucial for control policies in the satellite Internet of Things (S -IoT) observation environment. However, most existing studies fail to accurately analyze AoI in specific scenarios, and the impact of backoff algorithms on AoI and PAoI remains to be thoroughly investigated. To optimize these two metrics simultaneously and improve access performance, this paper proposes a joint backoff algorithm based on information freshness and NE equalization. First, to address the issues of low data transmission efficiency and inaccurate decision making in satellite IoT, discrete time Markov chains are introduced to assess the information freshness under satellite IoT, and the relationship between the node’s retreat phase and PAoI is depicted. Second, to solve the problem of access congestion in satellite IoT, the satellite coverage area is divided into different levels according to the threshold value of the spreading factor. A access strategy consistent with the NE equilibrium is defined, a revenue function based on the probability of successful transmission is designed, and a closed form mixed strategy Nash equilibrium (NE) is found using an optimization method. Finally, a value differentiated joint backoff algorithm based on information freshness and NE equalization is proposed. The simulation results show that the algorithm can improve the system throughput rate and reduce the average PAoI and AoI under satellite IoT.

To address issues related to reduced neural training accuracy, increased latency, and high energy consumption due to resource limitations of edge servers in the Internet of Vehicles (IoV), this article proposes a joint optimization scheme for edge collaboration and resource allocation in the digital twin-assisted IoV (DT-IoV) with integrated sensing and communication (ISAC). First, a digital twin-assisted environment-aware collaborative mechanism (DT-EACM) is proposed. The DT system makes edge collaboration decisions based on task requirements and available resources, selecting either the ISAC mode or the coordinated environment-aware instruction transmission (InsT) mode. Second, an analysis of deviations in communication, sensing, and computing resources within the collaboration mechanism has been conducted, and a joint optimization problem for edge collaboration and resource allocation is formulated with the goal of minimizing cumulative latency and energy consumption. Finally, since the above problem is a mixed-integer programming problem, it is transformed into a Markov decision process (MDP). A resource scheduling algorithm based on twin-delayed deep deterministic policy gradient (TD3) is proposed, combined with the prioritized experience replay (PER) mechanism to improve algorithm convergence speed and stability, thus minimizing cumulative latency and energy consumption in edge task processing. The simulation results demonstrate that the proposed algorithm effectively reduces cumulative training latency and energy consumption in edge task collaboration compared to other algorithms.

In the complex dynamic environment of the Internet of Things (IoT), the massive terminal devices generating stochastic network service requests pose significant challenges to Service Function Chain (SFC) deployment, particularly in dynamic configuration and resource utilization efficiency. To address these issues, this paper proposes an SFC deployment algorithm incorporating incremental learning with resource-aware mechanisms. First, an incremental learning-based deep-width neural network model is designed, which integrates the spatiotemporal feature extraction capabilities of Graph Convolutional Networks (GCN) and Temporal Convolutional Networks (TCN) with the continuous learning ability of the Broad Learning System (BLS), enabling dynamic prediction of Virtual Network Function (VNF) resource demands. Then, based on the prediction results, resource capacity awareness is used to assess the VNF deployment potential of nodes. Under the constraints of delay and network resources, an optimization problem is formulated with the objectives of maximizing the benefit-cost ratio of SFC deployment and minimizing deployment energy consumption. Finally, to solve this optimization problem, a multi-agent generative adversarial imitation learning algorithm is proposed, which guides the agents’ policy learning through expert experience to improve algorithm performance. Simulation results show that the proposed algorithm performs well in terms of enhancing node resource awareness, SFC deployment benefits, and acceptance rates.

Vehicle digital twin (VDT) can support multiple different vehicle services through updating, and the updating of VDT faces two fundamental issues: one is the isolation of VDT, that is VDTs can run various services without being affected by others; the other one is the timeliness of VDT updates for low latency services. In this paper, we first propose to ensure the isolation of VDTs with the assistance of intelligent reflecting surface (IRS) and network slicing (NS), and obtain better update time of the VDTs within limited resources. Specifically, we divide resources for VDTs with different update requirements to ensure the isolation of VDTs and the resources required for update. On the other hand, considering that the communication performance between vehicles and base stations is affected by urban building density, we propose using an intelligent controller to achieve intelligent control of the physical channel by adjusting the phase shift of passive reflective elements to ensure better transmission performance during VDTs updating. Secondly, considering the dynamic variability of vehicles and the environment, we propose an improved deep reinforcement learning algorithm based on the actor-critic framework to allocate communication, computing resources, and adjust the phase shift of the IRS. Finally, a large number of simulation results indicate that our proposed algorithm performs better than the benchmark algorithms.

To address the low utility of resource management strategy due to diversified user Quality of Service (QoS) requirements and inaccurate information synchronization in Digital Twin Networks (DTN), we propose a dynamic slice resource management and information synchronization strategy in Internet of Vehicles (IoV) based on Digital Twin (DT). First, to realize the dynamic resource allocation between slices and users respectively to adapt to network dynamics, we propose a two-level dynamic resource management strategy based on the DT-assisted slicing architecture of IoV. Second, to guarantee the timeliness of user information transmission and realize the accuracy of the resource management strategy, we propose a DT satisfaction evaluation model including DT mapping granularity, DT timeliness, and resource residual rate to quantify the users’ satisfaction with their DTs association. Finally, we establish a joint optimization model for resource management and DT association to maximize system utility. To address the coupling between strategies, we split the optimization problem into service utility and information synchronization utility subproblems. In the service utility subproblem, we propose a Counterfactual Multi-Agents Twin-Actors Soft Actor-Critic (COMATASAC) algorithm, which can perform slice-level and user-level resource allocation and scheduling actions separately. In the information synchronization utility subproblem, we utilize the Branching Dueling Q-network (BDQ) algorithm to solve the dimensionality explosion problem, and implement the association policy between users’ DTs and servers. Simulation results show that the proposed scheme can effectively reduce the latency and improve the satisfaction of DTs deployment while guaranteeing the QoS.

Abstract Medical image colouring techniques enable to colourize grey‐scale medical images for assisting doctors in diagnosis. Benefiting from the non‐linear fitting ability of deep neural network, deep medical image colouring techniques have achieved remarkable results. However, existing methods are still facing content and structure feature leakage, unrealistic colouring and poor scale invariability. Thus, this paper, proposes a Transformer‐based medical image colouring algorithm with long‐term dependency to avoid feature leakage of coloured images. To be specific, this method employs two different Transformer encoders to generate and encode feature sequences for grey‐scale medical images and real human colour slice images, respectively. Then, a novel multi‐layer Transformer decoder is used to stylize grey‐scale map image features based on the real physical colour feature sequences. For colouring images at different scales, we implement content‐ aware positional encoding with scale invariance and propose style‐aware positional encoding strategy to take realistic and physical colour prior into account. Extensive experimental results indicate our method has achieved better colourization effects than recent state‐of‐the‐art medical image colourization methods.

The development of industry 4.0 relies on emerging technologies of digital twin, machine learning, blockchain and Internet of Things (IoT) to build autonomous self-configuring systems that maximize manufactory efficiency, precision and accuracy. In this paper, we propose a new distributed and secure digital twin driven IIoT framework that integrates federated learning and Directed Acyclic Graph (DAG) blockchain with sharding. The proposed framework includes three planes: the data plane, the blockchain plane and the digital twin plane. Specifically, the data plane performs federated learning through a set of cluster heads to train models at network edges for twin model construction. The blockchain plane, which supports sharding, utilizes a hierarchical consensus scheme based on DAG blockchain to verify both local model updates and global model updates. The digital twin plane is responsible for constructing and maintaining twin model. Then, an efficient resource scheduling scheme is designed by considering performance of both federated learning and DAG blockchain with sharding. Accordingly, an optimization problem is formulated to maximize long-term utility of the digital twin driven IIoT. To cope with mapping error in the digital twin plane, a multi-agent Proximal Policy Optimization (MAPPO) approach is developed to solve the optimization problem. Numerical results illustrate that comparing with traditional approach, the proposed MAPPO improves utility by about 37 %, and reduces time latency by about 14%. Moreover, it also can well adapt to the mapping error.

Network slicing (NS) enables flexible allocation of the Internet of Things (IoT) network resources through software-defined networking (SDN) and network function virtualization (NFV) technologies. However, dynamic variations in network traffic and resource demands can lead to node overload and failures, necessitating timely virtual network function (VNF) migration to safeguard IoT business Quality of Service (QoS). Addressing the issue of deteriorating QoS due to untimely VNF migration, we propose a digital-twin (DT)-assisted VNF migration strategy based on resource demand prediction. First, a prediction model combining convolutional neural networks, gated recurrent units, and attention mechanisms is proposed to forecast VNF resource requirements. Second, the granularity of DT synchronization information is adjusted to resolve issues of delay and high cost during DT construction. Then, a VNF migration model is constructed to maximize DT utility while reducing network costs and average resource variance. Finally, a multiagent algorithm combining long short-term memory (LSTM) and double deep Q-network (DDQN) is proposed to perform VNF migration based on their priority-driven predicted future resource demands, and a multiagent algorithm based on dueling DDQN (D3QN) and deep deterministic policy gradient (DDPG) is proposed to address the DT association problem with a mixed action space. The simulation results demonstrate that the proposed algorithm can reduce the synchronization latency of the DT, the violation rate of service-level agreements, and the service outage time rate, while improving the network load balancing capability.

Anomaly detection using multivariate time series (MTS) is critical for detecting abnormal traffic and device failures in 5G Internet of Things (IoT) devices. The current anomaly detection framework lacks the ability to model multidimensional long time series and to address issues, such as resource overhead, privacy protection, and data security in distributed learning modes within the IoT. Therefore, this article proposes an anomaly detection framework integrating knowledge distillation and swarm learning for 5G IoT (IoT-FKGDL-SL). First, to model the correlations between different variables, a new method for capturing correlations between variables through clustering is proposed. Second, to perform long-term modeling of MTS, a long-time-series anomaly detection model called IoT-FKGD is proposed, based on multiscale dilated convolution and locality-sensitive hashing (LSH) attention. Finally, a framework based on IoT-FKGD is proposed to detect traffic anomalies of IoT devices under a swarm learning architecture that incorporates knowledge distillation. The effectiveness of the IoT-FKGDL-SL framework is demonstrated by comparing it with advanced anomaly detection methods on real data sets. Experimental results show that on a long time scale, the precision, recall, and F1-score of anomaly detection using this framework all surpass those of baseline methods.

Network function virtualization (NFV) and software-defined networking (SDN) provide high-quality services to users of the Internet of Things (IoT). However, dynamic changes in network traffic and service function chain (SFC) resource requirements may result in virtual network function (VNF) migration issue and real-time triggering of VNF migration can cause service delay issues in SDN/NVF-enabled IoT networks. In this article, we propose a digital twin (DT)-assisted VNF migration strategy to effectively address this issue. The digital twin of VNF (DT-VNF) is integrated with a multitask DT migration model based on bidirectional-gated recurrent units (DTMBi-GRUs) to achieve accurate resource demands prediction. Based on this, the VNF migration strategy is formulated in advance to avoid network performance degradation. We focus on the post-migration effects on services, networks, and DTs, so migration plans for DT-VNF and a reassociation scheme are formulated to enable real-time monitoring of post-migration VNF by DT-VNF. Then, an optimization problem is formulated to minimize average network energy consumption, network resource differences, and SDN synchronization delay in order to obtain optimal strategies. In addition, considering the problem’s complexity, it is decoupled into the VNF migration problem and the DT association and migration problem. The collaborative solution involves employing the multiagent proximal policy optimization (MAPPO) and asynchronous advantage actor–critic (A3C). Simulation results confirm the superiority of the proposed algorithms over baseline algorithms.

As an important application scenario for 5G, the Internet of Vehicles (IoVs) achieves extensive and stable connections and real-time information interaction and sharing between vehicles and traffic infrastructure. To address the challenges of low-latency synchronization, high computational overhead, and multidimensional resource scheduling faced by the vehicle digital twin (VDT) construction process within IoVs, we propose a construction scheme for variable granularity VDT. First, a variable granularity VDT construction framework for IoVs is proposed to reduce the communication pressure, edge load, and energy consumption in the network. Second, the VDT utility is quantified from four dimensions: 1) completeness; 2) accuracy; 3) timeliness; and 4) energy efficiency. Then, an optimization model is established with the goal of maximizing the average utility of the system VDT, which involves joint optimization of vehicle-edge association, VDT granularity setting and resource allocation. Due to the complexity of the optimization problem, it is decomposed into subproblems of vehicle-edge association, VDT granularity setting and resource allocation, and solved using matching theory and multiagent deep reinforcement learning, respectively. Finally, simulation results verify that the proposed scheme can effectively improve the utility of VDT in different simulation scenarios while reducing system resource consumption.

Digital twins (DTs), as an effective technology for remote monitoring and management of devices, enhances the intelligence of the industrial Internet of Things (IIoT). Nonetheless, the unreliable and delayed transmission of sensory data in wireless access networks hinders the accurate reflection of DTs on the physical world. In this article, we present an intelligent dual time-scale network slicing strategy utilizing the long-term and short-term trends of network, aiming to make fuller use of network resources and improve the synchronization information accuracy of DTs. Specifically, within the dual time scale slicing framework, this strategy collaboratively optimize slice scaling and sensory information synchronization for DTs, aiming to maximize sensory information satisfaction and minimize the cost of slice reconfiguration and synchronization. First, at large time scales, we utilize slices to provide isolation and address deployment issues for DTs with different Quality of Service (QoS) requirements. At small time scales, we aim to enhance the adaptability of estimation tasks to dynamic environments through more flexible wireless resource allocation, further improving communication performance, and establishing DTs that closely resemble physical entities. Furthermore, to solve optimization problems at different time scales, we propose a two-layer deep reinforcement learning (DRL) framework to achieve efficient network resource interactions, in which the lower-layer control algorithms utilize the prioritized experience replay (PER) mechanism to accelerate the convergence speed. Finally, simulation results validate the effectiveness of the proposed strategy.

Network function virtualization (NFV) and software defined network (SDN) technologies enable flexible traffic scheduling and improve the efficiency of physical resources. However, for latency-sensitive Industrial Internet of Things(IIoT) services in Industry 4.0 and beyond, the inability of the SDN controller to synchronize the resource demand information of virtual network functions (VNFs) in a timely manner can lead to delays in VNF mapping and scheduling strategies. To address this issue, we propose a digital twin-assisted VNF mapping and scheduling algorithm that combines digital twin to assist the SDN controller in collecting data of VNFs. Firstly, we designed a digital twin-assisted and SDN/NFV-based network slicing architecture. Secondly, to reduce the synchronization delays of digital twins of VNFs, we propose a twin service node reassociation mechanism. Next, a digital twin-assisted VNF mapping and scheduling model is constructed under constraints such as CPU, storage, bandwidth resources, and quality of service (QoS) to maximize the service provider’s profit. Finally, we propose digital twin-assisted VNF mapping and scheduling algorithms based on greedy and tabu search to solve the problem. Leveraging digital twins, the SDN controller can obtain accurate resource demand information of VNFs, thereby solving the delay issue in VNF mapping and scheduling strategies. Simulation results indicate that the proposed algorithms yield favorable outcomes in terms of total profit, network service acceptance rate, average system delay of digital twins, and QoS satisfaction.

Due to the increasingly complex and dynamic network topology, as well as multiple layers in the cloud–edge–end collaboration scenarios in the Industrial Internet of Things (IIoT), service function chains (SFCs) generated from user requests are more prone to anomalies compared to traditional hardware solutions. In order to timely detect anomalies in the SFC and ensure service quality, we propose a time-series anomaly detection model based on a distributed knowledge distillation framework (DTS-KD) in this article. First, to detect each status of virtual network function (VNF) in the SFC, we propose a distributed teacher–student knowledge distillation architecture to perform anomaly detection on each link containing different VNFs. Second, to address the problem of neglecting spatial topology information of feature nodes in traditional SFC anomaly detection schemes, we propose a feature fusion-based spatial–temporal dilated convolution module encoding scheme, which utilizes spatial convolution with dilated convolution to jointly encode and capture spatial–temporal dependencies. Finally, during the knowledge transfer process between the teacher and student networks, we propose a progressive knowledge distillation algorithm, which automatically adjusts the student network learning stages by adjusting task attention weights. After training, the student network measures the presence of anomalies in the links at each moment through the reconstruction data anomaly scores, thereby completing the SFC anomaly detection at that moment. The effectiveness of this proposed method under model compression conditions is validated on the ITU AI/ML in 5G data set using four performance metrics: 1) F1 score; 2) accuracy; 3) precision; and 4) recall.

Network availability and service continuity are major concerns for network operators to provide reliable communication services for Internet of Things (IoT), which are particularly challenging to achieve in virtualized network slicing environment where network services are exposed to the failure risks of both software (virtual network function (VNF) instances) and hardware (physical nodes). In general, the redundancy-based VNF backup solutions are used to improve the reliability of virtualized network slices. However, backup VNFs require the same amount of resources as the primary VNFs, which will result in high-resource cost. In this article, we propose a joint VNF partition and hybrid backup scheme for VNF orchestration, backup and mapping, whose aim is to construct the reliability-enhanced and delay-guaranteed network slices at minimum cost. Specifically, the VNF partition method divides a single VNF into multiple thinner VNFs with lower processing capacity and is expected to enhance the reliability of network slices with less additional resources. The hybrid backup scheme includes both onsite and offsite backup forms. Then, considering the time-varying network environment and IoT service requirements, we formulate the VNF orchestration, backup and mapping as a dynamic mixed integer linear programming (DMILP) problem, and model the dynamic problem as a Markov decision process (MDP). In view of the large action space of the formulated MDP, we propose a multiagent deep reinforcement learning (DRL) approach with an action space reduction strategy to achieve the dynamic VNF orchestration, backup and mapping solution. Simulation results demonstrate that the proposed joint VNF partition and hybrid backup scheme can obtain superior delay and reliability performance with low-network cost.

Recent research has demonstrated that the heat induced by high data rate transmission could cause low-temperature burns. As a promising application for future wireless networks, unmanned aerial vehicle (UAV) communication is capable of providing high data rate transmission for ground users. Inspired by this progress, this article focuses on the resource allocation for the UAV scenario and proposes a novel framework to consider the newly mentioned phenomenon named by power-consumption outage (PCO). Specifically, we give the analysis of heat transfer model in the smartphone based on which we initially integrate the influence of PCO into the optimization problem of the UAV scenario. Furthermore, to solve the problem with joint optimization of bandwidth allocation and trajectory design, we propose a machine learning model consisting of the position prediction based on echo state network and the joint optimization based on deep reinforcement learning (DRL). Due to the continuity in action space, DRL optimization is specifically implemented by the normalized advantage function algorithm. Besides, considering the restriction for the implementation of machine learning, we propose a digital twin-enabled architecture to provide a virtual environment for the training. Simulation results show the advantage of the proposed scheme in total throughput and the adaptability for trajectory design in the presence of PCO.

Autonomous driving is state-of-the-art technology in the field of Internet of Vehicles (IoVs), considered a revolutionary solution to enhance driving safety and comfort. Collaborative path planning for autonomous driving vehicles has not been practically applied due to the low effectiveness of models trained by traditional machine methods. The Digital Twins (DTs) map the state of the autonomous vehicles (AVs) in the real world to the virtual space in order to analyze the vehicle behavior and optimize vehicle decisions. During the DTs synchronization process, the time-varying nature of the physical environment may result in loss of DTs synchronization data. In order to better ensure the fidelity of DTs and the safety of autonomous driving, we propose a DTs-assisted distributed federated reinforcement training framework with fidelity guarantee. In this framework, the DTs leverage its predictive function to fill the lost data during the vehicle synchronization to its twins, ensuring a high fidelity in mapping the vehicle state. Then the model undergoes training through distributed federated reinforcement learning within the DTs environment. The simulation results indicate that our proposed solution not only ensures high fidelity in modeling the digital twins but also enhances the utilization efficiency of vehicle speeds. Additionally, it reduces the collision probability and average task completion time for the vehicle swarm.

Considering the limited resources, user mobility and unpredictable driving environment in intelligent driving, this paper studies the optimal training efficiency of federated learning for distributed training of collision warning services with the assistance of digital twin (DT). DT is emerging as one of the most promising technologies to make the digital representation of physical components for better prediction, analysis, and optimization of various services in intelligent driving. we first propose a DT-enabled collision warning framework, including physical network layer, digital twin layer, and application layer. Then, for the cooperative training of multi-level warning models combining gate recurrent unit (GRU) and support vector machine (SVM) in the digital twin layer, we propose semi-asynchronous federated learning with adaptive adjustment of parameters (SFLAAP) scheme. We aim at minimizing the training delay of collision warning model by dynamically adjusting the training parameters according to real-time training state and resource conditions of digital space, specifically the local training times and the number of local nodes participating in the aggregation, while ensuring the accuracy of the model. Considering the complexity of the target problem, we propose parameter adjustment algorithm based on asynchronous advantage actor-critic (A3C). Experiments on the classical dataset show high effectiveness of the proposed algorithms. Specifically, SFLAAP can reduce the completion time by about 12% and improve the learning accuracy by about 1%, compared with the state-of-the-art solutions.

An efficient Intrusion Detection System (IDS) model is essential for the protection of Unmanned Aerial Vehicles (UAVs) networks against network intrusion. However, when designing IDS models using distributed data collected by UAVs, it is crucial to ensure the security and privacy of the data. Moreover, most IDS models only focus on one-time learning and lack continuous learning capabilities. To address this, we present a Federated Continuous Learning framework with a Stacked Broad Learning System (FCL-SBLS) that utilizes Digital Twin Network (DTN) to enable quick and continuous learning on new data. To enhance the efficiency and quality of the IDS model during training and aggregation, we adopt an asynchronous federated learning architecture. Additionally, we introduce a Deep Deterministic Policy Gradient (DDPG)-based UAV selection scheme assisted by DTN to aid in global IDS model aggregation. This approach ensures that the IDS model can effectively and efficiently learn from distributed data while preserving the privacy and security of the data. The presented algorithm is validated using the CIC-IDS2017 dataset, and the simulation results reveal that our algorithm achieves higher efficiency and accuracy than the existing FL scheme.

Numerous resource-constrained Internet of Things (IoT) devices make the edge IoT consisting of unmanned aerial vehicles (UAVs) vulnerable to network intrusion. Therefore, it is critical to design an effective intrusion detection system (IDS). However, the differences in local data sets among UAVs show small samples and uneven distribution, further reducing the detection accuracy of network intrusion. This article proposes a conditional generative adversarial net (CGAN)-based collaborative intrusion detection algorithm with blockchain-empowered distributed federated learning to solve the above problems. This study introduces long short-term memory (LSTM) into the CGAN training to improve the effect of generative networks. Based on the feature extraction ability of LSTM networks, the generated data with CGAN are used as augmented data and applied in the detection and classification of intrusion data. Distributed federated learning with differential privacy ensures data security and privacy and allows collaborative training of CGAN models using multiple distributed data sets. Blockchain stores and shares the training models to ensure security when the global model’s aggregation and updating. The proposed method has good generalization ability, which can greatly improve the detection of intrusion data.

The edge of the Internet of Things (IoT), which consists of unmanned aerial vehicles (UAVs), is vulnerable to network intrusion because software and wireless connections are used extensively in the IoT. Designing an efficient intrusion detection system (IDS) model is imperative. However, when creating IDS models with distributed data collected by UAVs, it is necessary to take precautions to protect the data’s security and privacy. Furthermore, most of the IDS models are focused on one-time learning but not on continuous learning. To this end, we propose a federated continuous learning framework with a stacked broad learning system (FCL-SBLS) based on the digital twin network (DTN), which can learn and train the IDS model on new data quickly and continuously. In order to improve the efficiency and quality of the IDS model when training and aggregation, we employ an asynchronous federated learning (FL) architecture, and a deep deterministic policy gradient (DDPG)-based UAV selection scheme assisted by DTN is proposed to help the global IDS model aggregation. The presented algorithm is validated using the CIC-IDS2017 data set, and the simulation results reveal that our algorithm achieves higher efficiency and accuracy than the existing FL scheme.

Network slicing (NS) provides customized services to users of the Internet of Things (IoT) by creating logical virtual networks, and NS combined with multiaccess edge computing (MEC) can significantly minimize the latency for delay-sensitive service. Therefore, it is important to research how to employ NS to achieve low latency for delay-sensitive service in MEC-enabled IoT. In this article, we propose a paradigm of dynamic cooperative slicing based on the digital twin network (DTN) to achieve low latency for delay-sensitive service. Specifically, we first build a DTN for the MEC-enabled IoT, and build basic models and function models, including prediction and decision making in DTN. Then, we realize dynamic cooperative slicing through the built basic models and function models. Second, with the assistance of the ubiquitous computing resources in MEC-enabled IoT based on DTN, we construct joint optimization problem of communication resources, computing resources, and collaboration proportion with the objective of ensuring low delay of delay-sensitive service while maximizing the long-term utility of operators. Third, considering that the different MEC servers participating in the cooperation in each time slot lead to different action spaces in different time slots, we propose a deep deterministic policy gradient algorithm with variable action space, called VADDPG, which draws on the idea of action masking and introduces the action adjustor to realize the hard control of action space. Finally, a large number of simulations demonstrate that the proposed algorithm outperforms the benchmark algorithms in terms of both the long-term utility of operators and the delay obtained by slicing.

As a three-layer association of Internet of Things Equipment (IoTE)–network slicing (NS)–base station (BS) in radio access network (RAN) slicing, handoff control, and resource allocation has become an important but complicated issue. In addition, the centralized controller has a difficult grasping the network situation in real time. In view of this, the problem of handoff control in the RAN slicing is investigated in the digital twin network (DTN), with the goal of maximizing the long-term utility about user satisfaction and handoff cost. Then, an improved algorithm based on the actor–critic framework is suggested, which is called HCRA. Specifically, the actor component contains neural networks for handoff control and an optimizer for resource allocation, and then the critic component evaluates the handoff and resource allocation actions of the actor component to guide the optimization of actions in the actor component. The simulation results show that HCRA can obtain better performance than benchmark algorithms.

The Internet of Things (IoT) enables intelligent services varying with the complex and realtime environment to achieve network benefits, where network function virtualization (NFV) can dynamically provide virtualized network functions (VNFs) for IoT devices. In the NFV-enabled IoT architecture, a service function chain (SFC) consists of an ordered set of VNFs. However, the energy consumption of the VNF migration and SFC reconfiguration is one major issue owing to the dynamic characteristic of the IoT network. In this article, we propose a new paradigm digital twin (DT) to create the virtual twin of physical objects in the IoT network, then, we formalize the problem as a mathematical model, which aims to minimize the energy consumption. To this end, we prove this problem is NP-hard and propose an algorithm bidirectional gated recurrent unit (Bi-GRU) based on federated learning to predict the resource requirement. Further more, according to the prediction result, which utilizing the deep reinforcement learning (DRL) algorithm for decision making of the VNF migration. Simulation results show that our proposed method can effectively reduce the number of VNFs to be migrated and economize the energy consumption of the DT IoT network.

Massive and diversified machine type communication (MTC) service is one of the development trends of MTC in Internet of Things (IoT). Meanwhile, realizing network functions virtualization (NFV) is inseparable from reasonable virtual network function (VNF) scheduling and resource allocation. For VNF scheduling and resource allocation of MTC services, recently, deep reinforcement learning (DRL) has become one of the feasible solutions. However, existing DRL solutions have problems of inapplicability to the environment with both discrete and continuous variables, long training, time and nonequilibrium resource allocation. In this article, we first model the end-to-end (E2E) VNF scheduling and resource allocation of core network nodes, links, and access network subcarriers with different strategies, respectively, and propose a compound variable optimization problem aiming at maximizing the net income of the network provider. Then, we propose the mapping scheme of the absolute value of the signum function (ASgn mapping scheme) to simplify the compound variables into continuous variables of the optimization problem, so that the DRL algorithm is applicable. Moreover, we propose a model paralleling multiagent twin delayed deep deterministic (MPMA-TD3) policy gradient algorithm to handle massive services, reduce training time, and action space of agents. Finally, we improve the MPMA-TD3 algorithm to handle diversified services, solve the problem of nonequilibrium resources allocation, and realize the reasonable resource allocation for each service. Simulation results show that the proposed algorithms are better than other algorithms in reward, delay, cost, and training time for massive services. Further, the Improved MPMA-TD3 algorithm has the best service equilibrating ability.

Personalization is one of the primary emerging trends in Industry 4.0 and Beyond. Highly personalized services will present a significant challenge to the existing algorithms for network slicing (NS) and resource allocation, leading to issues, such as nonequilibratory resource allocation, in which some services are sacrificed for the maximum total reward of the algorithm, excessive cost, and slow algorithm convergence. A digital twin network (DTN) is offered as a novel solution to the challenges listed above. By integrating the DTN and IIoT NS, we propose a DTN-assisted industry Internet of Things NS (DTN-IIoT NS) architecture for personalized IIoT services in Industry 4.0 and Beyond. The DTN-IIoT NS architecture consists of three layers, three modules, and two closed loops. On the basis of the aforementioned architecture, we focus on the resource allocation process in DTN-IIoT NS, model the DT-assisted resource allocation for highly personalized IIoT services, propose the service equilibrium rate, and formulate the optimization problem aiming at maximizing the equilibrium rate weighted net profit of network providers. Then, we propose a dual-channel weighted (DCW) Critic network for service equilibrium in DTN-IIoT NS resource allocation and the matching Improved prioritized experience replay (PER) to enhance convergent speed. In addition, we present a distributed DT-assisted DCW-PER multiagent deep deterministic policy gradient (PER-DCW MADDPG) algorithm for the resource allocation process in DTN-IIoT NS. Simulation results indicate that the PER-DCW MADDPG algorithm can produce a better service equilibrium and accelerate the convergence speed of the algorithm.

Virtualized network slicing allows a multitude of logical networks to be created on a common substrate infrastructure to support diverse services. A virtualized network slice is a logical combination of multiple virtual network functions, which run on virtual machines (VMs) as software applications by virtualization techniques. As the performance of network slices hinges on the normal running of VMs, detecting and analyzing anomalies in VMs are critical. Based on the three-tier management framework of virtualized network slicing, we first develop a federated learning (FL) based three-tier distributed VM anomaly detection framework, which enables distributed network slice managers to collaboratively train a global VM anomaly detection model while keeping metrics data locally. The high-dimensional, imbalanced, and distributed data features in virtualized network slicing scenarios invalidate the existing anomaly detection models. Considering the powerful ability of generative adversarial network (GAN) in capturing the distribution from complex data, we design a new multi-discriminator Bidirectional Wasserstein GAN with Gradient Penalty (BiWGAN-GP) model to learn the normal data distribution from high-dimensional resource metrics datasets that are spread on multiple VM monitors. The multi-discriminator BiWGAN-GP model can be trained over distributed data sources, which avoids high communication and computation overhead caused by the centralized collection and processing of local data. We define an anomaly score as the discriminant criterion to quantify the deviation of new metrics data from the learned normal distribution to detect abnormal behaviors arising in VMs. The efficiency and effectiveness of the proposed collaborative anomaly detection algorithm are validated through extensive experimental evaluation on a real-world dataset.

Emerging digital twin (DT) and mobile-edge computing (MEC) are crucial for enabling the rapid development of 6G. However, the existing works ignore the edge collaboration, which can provide the system with additional performance gain. In this article, we study the problem of mobile users (MUs) intelligently offloading tasks to cooperative mobile-edge servers (MESs) with the assistance of DT. Specifically, a DT-assisted task offloading scheme (DTTOS) that consists of the selection of MESs and intelligent task offloading is proposed. Channel state information (CSI) and blockchain are employed to implement the selection of MESs. Then, we present a solution to enable MU’s task offloading that is modeled as a Markov decision process (MDP) in an intelligent way. After this, a mathematical optimization model aiming at decreasing power and time overhead is formulated. In view of the complexity, it is decomposed into two suboptimization models and solved by the decision tree algorithm (DTA) and double deep-$Q$-learning (DDQN), respectively. Simulations are conducted to prove the superiority of the proposed scheme in terms of data security assurance and network performance improvement.

Applications in the Internet of Vehicles (IoV) are usually accompanied by ultralow network response latency requirement. A promising approach to meet this demand is combining the IoV with mobile edge computing and enabling edge devices to share their communication, computation, and caching (3C) resources via edge intelligent cooperation. However, the allocation of 3C resources supported by artificial intelligence (AI) demands a huge number of training data and strong computing ability which is impossible to achieve on resource-limited on board unit (OBU) or road side unit (RSU). In this article, we propose a digital twin (DT) supported edge intelligent cooperation scheme, which empowers the optimal 3C resource allocation and edge intelligent cooperation possible. We focus on the response delay minimization in order to meet the requirement of latency-sensitive applications in the IoV. Specifically, mathematical expressions of the network response time are formulated according to modeling the workflow of the edge server as an M/M/1/N/FCFS queuing process. Especially, we conduct a detailed analysis of the deviations in 3C resource between the physical world and the DT space, based on which we further discuss the impact of these deviations in offloading decision. Furthermore, a mathematical optimization model aiming at minimizing the latency is formulated. In view of its complexity, we apply a deep deterministic policy gradient algorithm to solve it by modeling the cooperation process between edge nodes as a Markov decision process. Finally, we carry out simulations to demonstrate that our algorithm outperforms the existing schemes in terms of network response latency.

Network Function Virtualization (NFV) is a promising paradigm that enables the employment of novel service types with lower deployment cost and faster time-to-value, but it introduces new fault management problems and challenges. In NFV environment, anomalies occurred in virtual machines (VMs) can be caused by faulty components of their hosting servers or anomaly propagation from other ones. If the performance of VMs degrades, we need to find out the root causes accurately, i.e., locate the exact faulty components, to recover the networks as soon as possible. In this paper, we first use digital twin to establish a virtual instance of the physical network to capture the real-time anomaly-fault dependency relationship. When the network environment changes, transfer learning is leveraged to utilize the learned knowledge of dependency relationship in historical periods to avoid huge time and computation cost of learning from scratch. Assisted by the learned dependency relationship, a dynamic set-covering (DSC) based root caused analysis problem is formulated and modeled with a set of parallel hidden Markov models to capture the dynamics of component states, which can best explain the sequence of anomalous VMs. We use alternating direction method of multipliers to decompose the DSC problem into a set of independent sub-problems and solve it in a distributed fashion. Since the state variables of each component in the DSC problem are coupled between any two successive time epochs, each sub-problem is solved by the Viterbi decoding and an incremental function is designed to construct the feasible solution that covers all anomalous VMs. Simulation results show the availability and superiority of the digital-twin assisted root cause analysis algorithm for NFV environment.

In this paper, we propose a Digital Twin (DT) Supported Resource Allocation Scheme (DTS-RAS), which empowers the intelligent edge cooperation in the Internet of Vehicles (IoV) environment possible. We focus on the latency minimization under the DT-IoV framework. Specifically, we formulate the mathematical expression for the response time of vehicle offloading tasks to cooperative edge nodes according to modeling the edge server as a M/M/1/N queen. Then, we construct the optimization model aiming at reducing the response time. In view of the complexity, we apply a Double Deep Q-learning Network (DDQN) to training the edge server to get an optimal allocation action by modeling the cooperation process as an MDP. Simulation results demonstrate that our proposed scheme outperforms the existing schemes in terms of execution latency.

As the network slicing is one of the critical enablers in communication networks, one anomalous physical node (PN) in substrate networks that carries multiple virtual network elements can cause significant performance degradation of multiple network slices. To recover the substrate networks from anomaly within a short time, rapid and accurate identification of whether or not the anomaly exists in PNs is vital. Online anomaly detection methods that can analyze system data in real-time are preferred. Besides, as virtual nodes mapped to PNs are scattered in multiple slices, the distributed detection modes are required to preserve the data privacy of different slices. According to those requirements, we propose a distributed online PN anomaly detection algorithm based on a decentralized one-class support vector machine (OCSVM), which is realized through analyzing real-time measurements of virtual nodes mapped to PNs in a distributed manner. Specifically, to decouple the OCSVM objective function, we transform the original problem to a group of decentralized quadratic programming problems by introducing the consensus constraints. The alternating direction method of multipliers is adopted to achieve the solution for the distributed online PN anomaly detection. The simulation results on the real-world network dataset show the effectiveness and superiority of the proposed distributed online anomaly detection algorithm.

Millimeter wave (mmWave) communication is one of the key technologies in 5G and beyond systems to address the tremendous growth in mobile data traffic owing to the abundant spectrum resources. Ultra-dense network deployment is a promising solution to combat the limited coverage, high propagation loss and attenuation of mmWave signals. This study investigates the beam management, with focus on beam configuration of mmWave base stations, in the ultra-dense mmWave network. To fulfill adaptive and intelligent beam management while protecting user privacy, we employ a double deep Q-network under a federated learning to tackle the beam management problem which is formulated to maximize the long-term system throughput. Simulation results demonstrate the performance gain of our proposed scheme.

Network Function Virtualization (NFV) enables the employment of novel service types with lower deployment cost and faster time-to-value, but it introduces new fault management problems and challenges. Anomalies of virtual machines (VMs) can be caused by faulty components of their located physical servers or anomaly propagation from other ones. If the data patterns of VMs are detected as anomalous, we need to locate the root causes precisely to recover the networks as soon as possible. In this paper, we first introduce digital twin to capture the real-time anomaly-fault dependency matrix for the networks. Assisted by the dependency matrix, a dynamic set-covering (DSC) problem is formulated and modeled with a set of parallel hidden Markov models to find a minimal set of faulty components at each observation epoch, which can cover all anomalous VMs. We introduce alternating direction method of multipliers to decompose the DSC problem into a set of independent sub-problems and solve it in a distributed fashion. Simulation results show the availability and superiority of the proposed digital-twin assisted root cause analysis algorithm for NFV environment.

Recently, software-defined Industrial Internet of Things (SDIIoT), the integration of software-defined networking (SDN) and Industrial Internet of Things (IIoT), has emerged. It is perceived as an effective way to manage IIoT dynamically. Aiming to improve scalability and flexibility of SDIIoT, multi-SDN has been applied to form a physically distributed control plane to handle the large amount of data generated by industrial devices. However, as the core of multi-SDN, reaching consensus among multiple SDN controllers is a thorny issue. To meet the required design principle, this paper proposes a blockchain-enabled distributed architecture with SDIIoT to synchronize local views between distinct SDN controllers and finally reach the consensus of global view. On the other hand, both the cryptographic operations of blockchain and the noncryptographic computational tasks have access to the same computational resource pool of mobile edge cloud (MEC). In order to simultaneously optimize the throughput of blockchain and the energy consumption caused by computing, we adaptively allocate computational resources and the block size by jointly considering the trust features of SDN controllers and the resource requirements of non-cryptographic operations. To implement the truly distributed manner of blockchain, we describe our problem as a partially observable Markov decision process (POMDP) and propose a novel deep recurrent Q-network (DRQN) approach to solve it. In the simulation results, we compare two different protocols of blockchain and show the effectiveness of our scheme in either of them.

Recently, software-defined Industrial Internet of Things (SDIIoT), the integration of software-defined networking (SDN) and Industrial Internet of Things (IIoT), has emerged. It is perceived as an effective way to manage IIoT dynamically. Aiming to improve the scalability and flexibility of SDIIoT, multi-SDN has been applied to form a physically distributed control plane to handle a large amount of data generated by industrial devices. However, as the core of multi-SDN, reaching consensus among multiple SDN controllers is a thorny issue. To meet the required design principle, this article proposes a blockchain-enabled distributed SDIIoT to synchronize local views between distinct SDN controllers and finally reach the consensus of the global view. On the other hand, both the cryptographic operations of blockchain and the noncryptographic tasks have access to the same computational resource pool of mobile edge cloud (MEC). In order to optimize the system energy efficiency, we adaptively allocate computational resources and the batch size of the block by jointly considering the trust features of SDN controllers and the resource requirements of noncryptographic operations. To implement the truly distributed manner of blockchain, we describe our problem as a partially observable Markov decision process (POMDP) and propose a novel deep reinforcement learning (DRL) approach to solve it. In the simulation results, we compare three different protocols of blockchain and show the effectiveness of our scheme in each of them.

Both mobile edge cloud (MEC) and software-defined networking (SDN) are technologies for next generation mobile networks. In this paper, we propose to simultaneously optimize energy consumption and quality of experience (QoE) metrics in video streaming over software-defined mobile networks (SDMN) combined with MEC. Specifically, we propose a novel mechanism to jointly consider buffer dynamics, video quality adaption, edge caching, video transcoding and transmission. First, we assume that the time-varying channel is a discrete-time Markov chain (DTMC). Then, based on this assumption, we formulate two optimization problems which can be depicted as a constrained Markov decision process (CMDP) and a Markov decision process (MDP). Then, we transform the CMDP problem into regular MDP by deploying Lyapunov technique. We utilize asynchronous advantage actor-critic (A3C) algorithm, one of the model-free deep reinforcement learning (DRL) methods, to solve the corresponding MDP issues. Simulation results are presented to show that the proposed scheme can achieve the goal of energy saving and QoE enhancement with the corresponding constraints satisfied.

Both mobile edge cloud (MEC) and software-defined networking (SDN) are technologies for next generation mobile networks. In this paper, we simultaneously optimize energy consumption and quality of experience (QoE) in video streaming over software-defined mobile networks (SDMN) with MEC. Specifically, we propose to jointly consider buffer dynamics, video quality adaption, edge caching, video transcoding and transmission. We formulate two optimization problems which can be depicted as a constrained Markov decision process (CMDP) and a Markov decision process (MDP). Then we transform the CMDP problem into regular MDP by deploying Lyapunov technique. We utilize asynchronous advantage actor-critic (A3C) algorithm, one of the deep reinforcement learning (DRL) methods, to solve the corresponding MDP problems. Simulation results are presented to show that the proposed scheme can achieve the goal of energy saving and QoE enhancement with the corresponding constraints satisfied.

Mobile edge computing (MEC) has risen as a promising technology to augment computational capabilities of mobile devices. Meanwhile, in-network caching has become a natural trend of the solution of handling exponentially increasing Internet traffic. The important issues in these two networking paradigms are computation offloading and content caching strategies, respectively. In order to jointly tackle these issues, we formulate an optimization problem in wireless cellular networks with mobile edge computing, taking into consideration computation offloading decision, physical spectrum resource allocation, MEC computation resource allocation, and content caching strategy. Furthermore, we transform the original problem into a convex problem and then decompose it in order to solve it in a distributed and efficient way. Finally, with recent advances in distributed convex optimization, we develop an alternating direction method of multipliers (ADMM) based algorithm to solve the optimization problem. The effectiveness of the proposed scheme is demonstrated by simulation results with different system parameters.

Mobile edge computing (MEC) has attracted great interests as a promising approach to augment computational capabilities of mobile devices. An important issue in the MEC paradigm is computation offloading. In this paper, we propose an integrated framework for computation offloading and interference management in wireless cellular networks with mobile edge computing. In this integrated framework, the MEC server makes the offloading decision according to the local computation overhead estimated by all user equipments (UEs) and the offloading overhead estimated by the MEC server itself. Then, the MEC server performs the PRB allocation using graph coloring. The outcomes of the offloading decision and PRB allocation are then used to allocate the computation resource of the MEC server to the UEs. Simulation results are presented to show the effectiveness of the proposed scheme with different system parameters.

Mobile edge computing has risen as a promising technology for augmenting the computational capabilities of mobile devices. Meanwhile, in-network caching has become a natural trend of the solution of handling exponentially increasing Internet traffic. The important issues in these two networking paradigms are computation offloading and content caching strategies, respectively. In order to jointly tackle these issues in wireless cellular networks with mobile edge computing, we formulate the computation offloading decision, resource allocation and content caching strategy as an optimization problem, considering the total revenue of the network. Furthermore, we transform the original problem into a convex problem and then decompose it in order to solve it in a distributed and efficient way. Finally, with recent advances in distributed convex optimization, we develop an alternating direction method of multipliers-based algorithm to solve the optimization problem. The effectiveness of the proposed scheme is demonstrated by simulation results with different system parameters.

User selection for access network is considered to be one of the distinct features of heterogeneous wireless systems, in which users with multi-network interface terminals can freely select access network for better quality of service with lower expense. On the other hand, service providers (SPs) will have to face more intense competition for attracting more subscribers and increasing their profits, which can be achieved through either non-cooperative or cooperative strategies. In this study, the authors propose a unified quantification model for evaluating the access service of heterogeneous systems. The relation between competitive SPs and users is described by different game models, based on general assumptions and practical application scenarios. A novel network selection scheme for maximising user performance–cost ratio (PCR) is proposed. Numerical results demonstrate that all SPs can achieve Nash equilibrium price under non-cooperative game framework and coalition price for cooperative game case to maximise their absolute profits, and the maximal PCR criterion for user network selection scheme is analysed under different scenarios.