Signed Graph Neural Networks (SGNNs) have achieved outstanding performance in Link Sign Prediction (LSP), which involves predicting the existence and polarity of edges, by effectively modeling positive and negative interactions in signed graphs. However, their black-box nature raises transparency concerns, necessitating faithful explanations of model behavior to ensure trustworthiness and accountability. Existing eXplainable GNN (XGNN) methods, primarily designed for unsigned graphs, struggle to provide meaningful and human-understandable explanations for SGNN-based LSP, often generating disconnected subgraph explanations or neglecting the unique sign interactions. To address the gap, we propose SGExplainer, a novel method that leverages balanced paths, a concept rooted in signed graph theory, to provide clear and faithful explanations for LSP. SGExplainer employs a path-enforcing mask learning framework that ensures interpretable balanced path generation while maintaining explanation fidelity. Extensive experiments on real-world signed graphs demonstrate that SGExplainer consistently provides faithful and intuitive explanations for various SGNNs, outperforming state-of-the-art baselines in explanation quality, interpretability, and efficiency.

Graph-structured data effectively captures complex relationships in diverse domains such as social networks, financial transactions, citation networks, and recommendation systems. Graph Neural Networks (GNNs) excel in learning intricate topological patterns, yielding strong performance on tasks like node classification and link prediction. However, real-world graphs often scale to millions of nodes and billions of directed edges, posing significant computational and storage challenges for GNN training that frequently exceed available hardware limits. Although graph sampling and distillation techniques alleviate these issues by subsampling or creating surrogate graphs, they primarily handle undirected graphs, neglecting directional semantics that are crucial for applications like fraud detection and causal analysis. To address these limitations, we introduce the Directed Graph Distillation (Dir-GD) framework, which combines distributed learning with community detection to divide large directed graphs into independent subgraphs for distributed directed GNN training. This process culminates in parameter aggregation to produce a compact global synthetic graph that preserves essential topology and directionality. Extensive experiments on large-scale datasets, such as the million-node soc-pokec-relationships, demonstrate over 91% accuracy at 0.001 distillation ratios, accompanied by substantial memory and runtime savings. This work pioneers directed graph distillation as a key paradigm for analyzing ultra-large directed graphs, offering a scalable solution that maintains high fidelity in compressed representations.

The integration of space, air, and ground segments into unified Space-Air-Ground Integrated Networks (SAGINs) enables low-latency, ubiquitous, and scalable computing. However, such systems face critical challenges: ground terminals suffer from weak satellite links, UAV-based edge nodes have limited resources, and highly dynamic environments make it difficult to make efficient offloading and resource allocation decisions. Prior approaches often optimize either communication or computation in isolation and lack adaptability to real-time environmental feedback. This paper presents a novel perception-aware hybrid-action deep reinforcement learning (DRL) framework for joint optimization of task offloading, beamforming, and resource allocation in SAGINs. To improve tractability, the original non-convex problem is first decomposed using Block Coordinate Descent (BCD) and approximated with Successive Convex Approximation (SCA), generating a structured feasible action space. A Soft Actor-Critic (SAC) agent then learns policies over this space, informed by real-time UAV perception via mmWave radar and vision sensors that detect user density, link quality, and environmental blockages. The DRL agent operates over a hybrid action space, combining discrete offloading decisions with continuous controls such as beamforming weights, CPU frequency, and transmission power. We employ a constraint-aware action masking mechanism that prunes infeasible hybrid actions violating delay, power, or SNR limits, thereby accelerating learning while respecting SAGIN-specific constraints. Extensive simulations show that the proposed framework significantly outperforms greedy, no-perception DRL, and state-of-the-art DRL offloading algorithms in reducing latency and energy consumption, while improving offloading success and resource stability. These results highlight the effectiveness of combining analytical optimization structure with adaptive perception-driven learning for robust and scalable control in future SAGINs.

This paper proposes CADiS, a causality-driven anomaly detection framework, to address the challenges of root cause identification in high-dimensional Industrial Internet of Things (IIoT) multivariate time series. The essential difference between CADiS and existing correlation-driven deep models lies in its core innovation: it fundamentally redefines anomalies as the structural decay of an underlying causal mechanism, rather than merely capturing symptomatic deviations or spurious correlations. Specifically, the framework first learns a directed and lag-aware causal prior from normal data, compiling it into a structured attention mask to constrain information flow. Then, a Causal-Phase Decomposition (CPD) technique treats each time window as a micro-experiment, comparing an ante-phase with a post-phase to explicitly capture the dynamics of causal attenuation. Inference relies on a unified Causal-Change Score (CCS), which quantifies the degradation of causal association strength, directly revealing the breakdown of the system’s causal logic. Furthermore, the decomposed causal change matrix allows for fine-grained and auditable root cause diagnosis. Extensive experiments on real-world industrial datasets demonstrate that CADiS significantly outperforms strong baselines, achieving theVROCof 89.93% andVPRof 76.93% on SWaT; TheAPRof 18.04% andVROCof 78.38% on SMD, thereby validating its robustness and diagnostic precision.

Pre-trained Language Models (PLMs) have demonstrated their superiority and versatility in modern Natural Language Processing (NLP), effectively adapting to various downstream tasks through further fine-tuning. Federated Parameter-Efficient Fine-Tuning (FedPEFT) has emerged as a promising solution to address privacy and efficiency challenges in distributed training for PLMs on resource-constrained local devices. However, our measurements reveal two key limitations of FedPEFT: heterogeneous data across devices exacerbates performance degradation of low-rank adaptation, and a fixed parameter configuration results in communication inefficiency. To overcome these limitations, we propose FedARA, a novel Adaptive Rank Allocation framework for federated parameter-efficient fine-tuning of language models. Specifically, FedARA employs truncated Singular Value Decomposition (SVD) adaptation to enhance similar feature representation across clients, significantly mitigating the adverse effects of data heterogeneity. Subsequently, it utilizes dynamic rank allocation to progressively identify critical ranks, effectively improving communication efficiency. Lastly, it leverages rank-based module pruning to automatically remove inactive modules, steadily reducing local computational cost and memory usage in each federated learning round. Extensive experiments show that FedARA consistently outperforms baselines by an average of 6.95% to 8.49% across various datasets and models under heterogeneous data while significantly improving communication efficiency by 2.40×. Moreover, experiments on various edge devices demonstrate substantial decreases in total training time and energy consumption by up to 48.90% and 46.95%, respectively.

As manufacturing complexity and automation demand increase, predictive maintenance (PdM) becomes increasingly crucial in ensuring the sustainability of smart manufacturing. It can proactively provide tailored maintenance recommendations for each equipment just before failure occurs, preventing breakdowns and thereby avoiding economic losses and potential safety hazards. Nevertheless, challenges, such as intricate machine degradation mechanisms, sparse failure events, and data privacy restrictions, hinder scalable PdM deployment across industrial sites. In this article, we formulate PdM as a decision-centric long-term expenditure minimization (DC-LTEM) problem and present a partially observable Markov decision process (POMDP) model that captures maintenance-critical status and customizes a DC-LTEM-based reward to guide the agent training. We further propose a federated offline–online deep reinforcement learning scheme for adaptive PdM (Fed-O2OAPM), built on a three-tier machine–industrial edge–industrial cloud framework, to guide the agent in developing scalable PdM policy while keeping privacy and maintaining interaction safety. A recurrent actor–critic model is introduced in the policy learning to approximate the required memory in POMDP. Besides, entropy regularization and generalized advantage estimation is integrated to encourage action exploration in a conservative region, while clipped value loss ensures training stability. Extensive experiments on the NASA Commercial Modular Aero-Propulsion System Simulation dataset demonstrate that Fed-O2OAPM achieves near-optimal performance while significantly avoiding machine failures compared to baseline methods.

Quasi-clique is one of the most fundamental models for characterizing cohesive subgraphs in network analysis. However, existing quasi-clique definitions and identification algorithms are designed for unsigned graphs, while many real-world networks are modeled as signed graphs with positive and negative edges representing cooperative and adversarial interactions between entities. Therefore, it remains an open problem to define a quasi-clique model tailored for signed graphs. Motivated by this, we propose the maximal balanced \( (\gamma_{1},\gamma_{2}) \) -quasi-clique (MBQC) model, which not only preserves the essence of quasi-completeness but also aligns with the foremost structural balance theory for signed graphs. Specifically, we formulate the problem of MBQCs enumeration in a given signed graph and prove its NP-hardness. To address this problem, we devise a novel branch-and-bound algorithm to efficiently enumerate all MBQCs in a signed graph, which is further optimized with several carefully-crafted techniques to prune unpromising search spaces and enhance enumeration efficiency. Extensive experiments on real-world datasets demonstrate the efficiency, scalability, and effectiveness of our MBQC model and algorithms.

The convergence of edge computing and Artificial Intelligence (AI) gives rise to Edge-AI, which enables the deployment of real-time AI applications at the network edge. A key research challenge in Edge-AI is edge inference acceleration, which aims to realize low-latency high-accuracy Deep Neural Network (DNN) inference by offloading partitioned inference tasks from end devices to edge servers. However, existing research has yet to adopt a practical Edge-AI market perspective, which would explore the personalized inference needs of AI users (e.g., inference accuracy, latency, and task complexity), the revenue incentives for AI service providers that offer edge inference services, and multi-stakeholder governance within a market-oriented context. To bridge this gap, we propose anAuction-basedEdge Inference Pricing Mechanism (AERIA) for revenue maximization to tackle the multi-dimensional optimization problem of DNN model partition, edge inference pricing, and resource allocation. We develop a multi-exit device-edge synergistic inference scheme for on-demand DNN inference acceleration, and theoretically analyze the auction dynamics amongst the AI service providers, AI users and edge infrastructure provider. Owing to the strategic mechanism design via randomized consensus estimate and cost sharing techniques, the Edge-AI market attains several desirable properties. These include competitiveness in revenue maximization, incentive compatibility, and envy-freeness, which are crucial to maintain the effectiveness, truthfulness, and fairness in auction outcomes. Extensive simulations based on four representative DNN inference workloads demonstrate that AERIA significantly outperforms several state-of-the-art approaches in revenue maximization. This validates the efficacy of AERIA for on-demand DNN inference in the Edge-AI market.

Integrating Generative AI (Gen-AI) into vehicular computing can significantly enhance road safety and driving experience. The performance of Gen-AI inference in vehicular computing is highly sensitive to the number of inference steps, where even minor adjustments can disrupt the balance between delay and inference quality. This raises a critical question: how can inference steps be optimally determined for diverse tasks, given the inherent delay-quality trade-offs? Existing approaches fail to offer an optimal solution due to the lack of flexible inference services and efficient memory bandwidth allocation strategies. To address these challenges, we develop aCriticality-awareResource-efficientInference (CARIN) framework, where inference steps are dynamically adjusted to balance delay and quality for multi-criticality tasks. Leveraging an accurate inference model, CARIN fully exploits in-vehicle resources to accelerate both parameter loading and task computing during inference. The joint optimization problem of step control, memory bandwidth allocation, and compute resource scheduling is formulated as a mixed-integer nonlinear programming (MINLP) problem, and solved by a novel learning-to-optimize (L2O) algorithm efficiently. Experimental results demonstrate that, for high-criticality tasks, the proposed approach achieves$28.4\%$latency reduction and$36\%$quality improvement over baseline methods.

Federated Learning (FL) is a popular privacy-preserving machine learning paradigm, enabling collaborative training among distributed devices coordinated by a central server, without gathering the devices’ local data. Recent studies indicate that device-to-device (D2D) communication technology has the potential to reduce reliance on the central server and enhance the scalability of FL. However, complex heterogeneities in wireless D2D network environments lead to degradation in learning efficiency and hamper global convergence of D2D-assisted FL. To address this important problem, we propose FedAHC, an Asynchronous Hierarchical Clustered FL method based on Graph Convolutional Networks (GCN). To effectively mitigate the impact of computational and communicational heterogeneities on D2D-assisted FL, we utilize a clustering approach for FL devices within the D2D network, formulate it as a graph problem, and design an unsupervised learning strategy powered by GCN to obtain effective cluster assignments adhering to D2D link connectivity. Meanwhile, a global optimizer state is introduced into FedAHC to reduce the training model drift caused by heterogeneous data across devices. We theoretically prove the convergence of this new method by deriving an upper bound on the global loss function. We conduct extensive experiments with various network scenarios and datasets to demonstrate the performance of FedAHC. In comparison to key baselines, FedAHC converges to a higher model accuracy, while exhibiting up to 80% improvement in time efficiency and up to 62% reduction in communication costs.

Federated Learning (FL) has emerged as a promising framework for privacy-preserving machine learning. FL enables distributed data owners (clients) to collaboratively train a global model without sharing their local data with a central server. However, FL is inherently vulnerable to free-rider and poisoning attacks, where free riders dissimulate their participation of training by sending counterfeit yet harmless model updates to the central server, while adversarial clients send poisonous model updates to the server to degrade the global model performance. Their distinctive attacking patterns make the simultaneous defense against both attacks very challenging. To address this challenge, we propose a novel model-agnostic Shapley value-based robust and fair federated learning method (SVRFL), which models FL as a cooperative game and leverages Shapley values of model updates to defend against free riders and adversarial clients. Specifically, a client reputation score and a model utility score are computed using the Shapley value. Based on these scores, we ensure the basic fairness within FL by identifying and eliminating free riders, and realize adversarial robustness through discarding poisonous model updates, with theoretical convergence guaranteed. Extensive experiments show that SVRFL can detect typical free-rider attacks with up to full precision and is resistant to poisoning attacks launched by adversarial clients.

Foundation models (FMs) such as GPT-4 exhibit exceptional generative capabilities across diverse downstream tasks through fine-tuning. Split Federated Learning (SFL) facilitates privacy-preserving FM fine-tuning on resource-constrained local devices by offloading partial FM computations to edge servers, enabling device-edge synergistic fine-tuning. Practical edge networks often host multiple SFL tenants to support diversified downstream tasks. However, existing research primarily focuses on single-tenant SFL scenarios, and lacks tailored incentive mechanisms for multi-tenant settings, which are essential to effectively coordinate self-interested local devices for participation in various downstream tasks, ensuring that each SFL tenant’s distinct FM fine-tuning requirements (e.g., FM types, performance targets, and fine-tuning deadlines) are met. To address this gap, we propose a novel Price-Incentive Mechanism (PRINCE) that guides multiple SFL tenants to offer strategic price incentives, which solicit high-quality device participation for efficient FM fine-tuning. Specifically, we first develop a bias-resilient global SFL model aggregation scheme to eliminate model biases caused by independent device participation.We then derive a rigorous SFL convergence bound to evaluate the contributions of heterogeneous devices to FM performance improvements, guiding the incentive strategies of SFL tenants. Furthermore, we model inter-tenant device competition as a congestion game for Stackelberg equilibrium(SE) analysis, deriving each SFL tenant’s optimal incentive strategy. Extensive simulations involving four representative SFL tenant types (ViT, BERT, Whisper, and LLaMA) across diverse data modalities (text, images, and audio) demonstrate that PRINCE accelerates FM fine-tuning by up to 3.07x compared to state-of-the-art approaches, while consistently meeting fine-tuning performance targets.

Aerial-terrestrial network (ATN) framework is currently the dominant method of the Internet of unmanned agents (IUAs) for integrating both aerial vehicles and terrestrial sensors. In ATN scenarios, existing work shows that route planning utilizing deep reinforcement learning (DRL) is important as it can conserve energy for aerial vehicles or diminish network latency. However, utilizing DRL approaches in a multiagent ATN environment may lead to inefficiencies when sharing original interaction data. In addition, direct data exchange between agents can raise significant privacy concerns. To address these challenges, this work develops a novel federated reinforcement learning (FRL) approach called FRIGE, which takes advantage of ensemble learning for DRL-based methods. Specifically, this article develops a prioritized gradient ensemble technique for local DRL agents, which constructs twin networks to obtain prioritized gradients without incurring additional interactive costs. After aggregating local models on the server, the latest iteration of the global model is used to update the networks of both agents and their twin networks for subsequent rounds of training. Extensive experiments are conducted on two typical ATN route planning tasks to validate FRIGE’s advancement and generalization capabilities. The numerical results demonstrate that FRIGE not only enhances data sharing efficiency among all agents but also maintains privacy while delivering superior solutions for ATN route planning tasks.

Deep learning models are intrinsically susceptible to textual adversarial attacks on social media, where the perturbed text can trigger aberrant behaviours of victim models and threaten security and privacy. In this paper, we present a novel word-level attack called SCALA: a Synonym-based desCending And repLace-back Ascending mechanism. Our focus is on the efficient production of adversarial examples, with a particular emphasis on minimizing human perceptibility while ensuring the visual resemblance and semantic correctness. The merits of our attacking solution lie in being:(i)imperceptible – it keeps a very low word perturbation rate based on the Hamming (L0-norm) distance, thus achieving heightened deceptiveness validated through human evaluations;(ii)efficient – our tensor-based parallelization strategy ensures the attacking efficiency compared with baselines;(iii)effective – it surpasses seven state-of-the-art attacks on five target models in terms of reducing after-attack accuracy;(iv)practical – black-box score-based setting ensures that the adversary only needs to query target models for confidence scores; and(v)transferable – our attack shows competitive transferability on the generated adversarial examples. We release our codeSCALAvia https://github.com/TrustAI/SCALA.

Distributed microgrids are being deployed into our power grids to form large-scale multimicrogrid systems for utilizing growing renewable energy sources. An effective energy management strategy is fundamental to balancing energy supply and demand alongside maintaining the stability of multimicrogrid. In this article, we propose a scalable, privacy-preserving, distributed energy management approach (SPDEM) for multimicrogrid. Specifically, we first formulate the energy management problem in multimicrogrid as a decentralized partially observable Markov decision process (Dec-POMDP). Next, we develop an intelligent energy management algorithm using mean-field multiagent recurrent reinforcement learning to efficiently solve the Dec-POMDP. This approach incorporates a novel fingerprint-based importance sampling technique to address the obsolete experiences induced by mean field approximation. Extensive experiments on real-world datasets demonstrate that SPDEM can make effective energy management decisions under variable renewable energy generation and load demand. Comparisons with five typical baselines illustrate the superb performance of SPDEM in cost reduction and scalability enhancement.

Federated learning (FL) is recognized as a pivotal paradigm for 6G, offering decentralized model training without compromising data privacy. Recent works have proposed deploying FL in cell-free massive MIMO (CF-mMIMO) networks for reliable model transmission between FL clients and the server. Nevertheless, the problem of simultaneous access point (AP) clustering (i.e., dynamically forming AP groups to facilitate client-server communication) and transmit power allocation has not been thoroughly investigated. Furthermore, most existing solutions do not simultaneously consider the fast decision-making requirements brought by user mobility and the scalability of solutions in large-scale networks. To address this gap, we propose DACPA, a multi-agent deep reinforcement learning (DRL)-based scheme that accounts for client mobility (walking speed) and heterogeneous computing capabilities. DACPA strategically assigns each client a customized AP cluster and corresponding transmit power configuration, thereby optimizing model update latency. Extensive simulation results demonstrate the superior performance of DACPA in terms of convergence stability, spectral efficiency, global model update latency, and average energy consumption.

The growth of Electric Vehicles (EVs) places an increasingly heavy burden on the limited charging infrastructure, necessitating an effective charging station recommendation strategy that assists EVs in finding the most suitable charging stations. Deep reinforcement learning is a promising technology that has been applied to optimize EVs’ charging recommendations. However, existing schemes have low scalability and high communication costs as they usually require collecting real-time information on both charging requests and charger availability at various stations during policy training or execution. To address this challenge, we develop a real-time distributed charging station recommendation approach, named ReDirect, to minimize the charging duration experienced by EVs, considering dynamic charging requests of EVs and fluctuating availability at charging stations. ReDirect employs federated meta-reinforcement learning (RL) to empower distributed stations to collaboratively learn effective recommendation strategies and make decisions without sharing their local information, yielding improved scalability, reduced communication overhead, and enhanced data privacy. Furthermore, we conduct a rigorous theoretical analysis of the convergence performance of ReDirect. Extensive experimental results on real-world datasets demonstrate that ReDirect performs closely to the centralized recommendation algorithm and outperforms several state-of-the-art distributed algorithms in EV charging duration while realizing a balanced distribution of charging requests across multiple stations.

Graph neural network (GNN) is a state-of-the-art technique for learning structural information from graph data. However, training GNNs on large-scale graphs is very challenging due to the size of real-world graphs and the message-passing architecture of GNNs. One promising approach for scaling GNNs is distributed training across multiple accelerators, where each accelerator holds a partitioned subgraph that fits in memory to train the model in parallel. Existing distributed GNN training methods require frequent and prohibitive embedding exchanges between partitions, leading to substantial communication overhead and limited the training efficiency. To address this challenge, we propose XDGNN, a novel distributed GNN training method that eliminates the forward communication bottleneck and thus accelerates training. Specifically, we design an explanation-guided subgraph expansion technique that incorporates important structures identified by eXplanation AI (XAI) methods into local partitions, mitigating information loss caused by graph partitioning. Then, XDGNN conducts communication-free distributed training on these self-contained partitions through training the model in parallel without communicating node embeddings in the forward phase. Extensive experiments demonstrate that XDGNN significantly improves training efficiency while maintaining the model accuracy compared with current distributed GNN training methods.

Digital healthcare services have become an integral part of our lives. There is an increasing number of healthcare professionals and patients using medical wearables for diagnosis and treatment, which simplifies and improves the diagnostic and therapeutic process. However, inappropriate use of medical data may result in the disclosure of private patient information. For protecting patients' privacy when using medical wearables, we propose a new blockchain-based data access security scheme. Specifically, the elliptic curve encryption algorithm and zero-knowledge authentication method are used to authenticate the identity of patients and doctors in the blockchain network. Furthermore, we develop a smart recommendation method based on deep reinforcement learning to recommend appropriate doctors for patients. Next, patients allow recommended doctors to access their medical data, and smart contracts specifically designed for secure data access to medical wearables will regulate subsequent data access. The security analysis and experimental results demonstrate that the proposed scheme can effectively protect patients' privacy during treatment through secure authentication and data access for medical wearables.

Since its inception, blockchain technology has found wide-ranging applications in various fields including agriculture, energy, and so on, owing to its immutable and decentralized nature. However, existing blockchains encounter significant challenges in scenarios that demand efficient retrieval of big data. This is primarily because current blockchains cannot directly store and process diverse types of rich media information. Additionally, the semantic relationships between data within the blockchains are weak, complicating the categorization and retrieval of data and transactions. Moreover, the scalability of current blockchains is limited, with the capacity of full nodes continually increasing. Although some semantic-based blockchain solutions that combine off-chain scalability have been proposed, they are limited in effectiveness and applications. To address these issues, this paper introduces a brand-new blockchain sharding technique called Semantic Sharding, which enhances blockchain scalability through a hybrid on/off-chain approach. Building on this, we propose a semantic sharding blockchain architecture, SemantiChain, which enables the on-chain storage and retrieval of transaction semantic features. Furthermore, through the Po2RW consensus protocol, we balance the scalability and security of SemantiChain. Security analysis proves that SemantiChain can resist security risks such as man-in-the-middle attacks, malicious node attacks and on/off-chain data inconsistency. Experimental results demonstrate that SemantiChain can reduce search time and memory usage by at least 32.29% and 77.97% respectively under the same retrieval performance, compared to mainstream approximate nearest neighbour retrieval algorithms. Furthermore, compared to the SOTA semantic blockchain, SemantiChain achieves a retrieval performance improvement of at least 45.88% and reduces retrieval memory usage by 95.76%.

Electric Vehicle-assisted Multi-access Edge Computing (EV-MEC) is a promising paradigm where EVs share their computation resources at the network edge to perform intensive computing tasks while charging. In EV-MEC, a fundamental problem is to jointly decide the charging power of EVs and computation task allocation to EVs, for meeting both the diverse charging demands of EVs and stringent performance requirements of heterogeneous tasks. To address this challenge, we propose a new joint charging scheduling and computation offloading scheme (OCEAN) for EV-MEC. Specifically, we formulate a cooperative two-timescale optimization problem to minimize the charging load and its variance subject to the performance requirements of computation tasks. We then decompose this sophisticated optimization problem into two sub-problems: charging scheduling and computation offloading. For the former, we develop a novel safe deep reinforcement learning (DRL) algorithm, and theoretically prove the feasibility of learned charging scheduling policy. For the latter, we reformulate it as an integer non-linear programming problem to derive the optimal offloading decisions. Extensive experimental results demonstrate that OCEAN can achieve similar performances as the optimal strategy and realize up to 24% improvement in charging load variance over three state-of-the-art algorithms while satisfying the charging demands of all EVs.

One fundamental problem of content caching in edge computing is how to replace contents in edge servers with limited capacities to meet the dynamic requirements of users without knowing their preferences in advance. Recently, online deep reinforcement learning (DRL)-based caching methods have been developed to address this problem by learning an edge cache replacement policy using samples collected from continuous interactions (trial and error) with the environment. However, in practice, the online data collection phase is often expensive and time-consuming, thus hindering the practical deployment of online DRL-based methods. To bridge this gap, we propose a novel Agile edge Cache replacement method based on Offline-online deep Reinforcement learNing (ACORN), which can efficiently learn an edge cache replacement policy offline from a training dataset collected by a behavior policy (e.g., Least Recently Used) and then improve it with fast online fine-tuning. We also design a specific convolutional neural network structure with multiple branches to effectively extract content popularity knowledge from the dataset. Experimental results show that the offline policy generated by ACORN outperforms the behavior policy by up to 38%. Through online fine-tuning, ACORN also achieves the number of cache hits as good as that of several advanced DRL-based methods while significantly reducing the number of training epochs by up to 40%.

Integrating large-scale sensors into the network has become a research hotspot for its promising flexibility in monitoring vitally critical wild areas. However, the existing Internet of Things (IoT) systems are limited due to the lack of a stable power supply, which seriously affects the system’s sustainability. The combination of sensors equipped with cordless power batteries and long-distance power transmission has ushered in a new era. Using the unmanned aerial vehicles (UAVs) to charge the battery ensures the flexibility and sustainability of the sensor in environmental detection. In this work, we aim to provide a solution for maintaining the sustainability of the sensors while optimizing UAV trajectory to minimize the overall energy consumption of UAV. Since deep reinforcement learning successfully solves the NP-hard combinatorial optimization problem, deep reinforcement learning is introduced in this work to obtain a feasible solution. We formulate the trajectory planning of UAV as a Markov decision problem and employ a deep reinforcement learning (DRL) model based on an attention mechanism to find the optimal policy efficiently, named the optimal trajectory planning algorithm based on DRL (OTPDRL). The experimental results suggest the OTPDRL obtains a good trade-off between performance gain and computational time.

The traditional healthcare is overwhelmed by the processing and storage of massive medical data. The emergence and gradual maturation of Internet-of-Things (IoT) technologies bring the traditional healthcare an excellent opportunity to evolve into the IoT-enabled healthcare of massive data storage and extraordinary data processing capability. However, in IoT-enabled healthcare, sensitive medical data are subject to both privacy leakage and data tampering caused by unauthorized users. In this article, an attribute-based secure access control mechanism, coined (SACM), is proposed for IoT-Health utilizing the federated deep learning (FDL). Specifically, we manage to discover the relationship between users’ social attributes and their trusts, which is the trustworthiness of users rely on their social influences. By applying graph convolutional networks to the social graph with the susceptible–infected–recovered model-based loss function, users’ influences are obtained and then are transformed to their trusts. For each occupation, users’ trusts allow them to access specific medical data only if their trusts are higher than the corresponding threshold. Then, the FDL is applied to obtain the optimal threshold and relevant access control parameters for the improvement of access control accuracy and the enhancement of privacy preservation. The experimental results show that the proposed SACM achieves accurate access control in IoT-enabled healthcare with high data integrity and low privacy leakage.

Artificial Intelligence of Things (AIoT), as a fusion of artificial intelligence (AI) and Internet of Things (IoT), has become a new trend to realize the intelligentization of industry 4.0 and the data privacy and security is the key to its successful implementation. To enhance data privacy protection, the federated learning has been introduced in AIoT, which allows participants to jointly train AI models without sharing private data. However, in federated learning, malicious participants might provide malicious models by launching the poisoning attack, which will jeopardize the convergence and accuracy of the global model. To solve this problem, we propose a malicious model detection mechanism based on the isolation forest (iforest), named D2MIF, for the federated learning-empowered AIoT. In D2MIF, an iforest is constructed to compute the malicious score for each model uploaded by the corresponding participant, and then, the models will be filtered if their malicious scores are higher than the threshold, which is dynamically adjusted using reinforcement learning (RL). The validation experiment is conducted on two public data sets Mnist and Fashion_Mnist. The experimental results show that the proposed D2MIF can effectively detect malicious models and significantly improve the global model accuracy in federated learning-empowered AIoT.

Federated learning (FL) has shown its great potential for achieving distributed intelligence in privacy-sensitive IoT. However, popular FL approaches, such as FedAvg and its variants share model parameters among clients during the training process and thus cause significant communication overhead in IoT. Moreover, nonindependent and identically distributed (non-IID) data across learning devices severely affect the convergence and speed of FL. To address these challenges, we propose a communication-efficient FL framework based on Two-step Knowledge Distillation, Fed2KD, which boosts the classification accuracy through privacy-preserving data generation while improving communication efficiency through a new knowledge distillation scheme empowered by an attention mechanism and metric learning. The generalization ability of Fed2KD is analyzed from the view of domain adaption. Extensive simulation experiments are conducted on Fashion-MNIST, CIFAR-10, and ImageNet data sets with various non-IID data distributions. The performance results show that Fed2KD can reduce the communication overhead and improve classification accuracy compared to FedAvg and its latest variants.

Collaborative mobile edge computing (MEC) is a new paradigm that allows cooperative peer offloading among distributed MEC servers to balance their computing workloads. However, the highly dynamic workloads and wireless network conditions pose great challenges to achieving efficient task offloading in collaborative MEC. To address this challenge, digital twin (DT) has emerged as one promising solution by building a high-fidelity virtual mirror of the physical MEC to simulate its behaviors and help make optimal operational decisions. In this paper, we propose a DT-driven intelligent task offloading framework for collaborative MEC, where DT is employed to map the collaborative MEC system into a virtual space and optimize the task offloading decisions. We model the task offloading process as a Markov decision process (MDP) with the objective of maximizing the MEC system’s total income from providing computing services, and then develop a deep reinforcement learning (DRL)-based intelligent task offloading scheme (INTO) to jointly optimize the peer offloading and resource allocation decisions. An efficient action refinement method is proposed to ensure that the action selected by the DRL agent is feasible. Experimental results show that our proposed approach can effectively adapt the task offloading decisions according to the dynamic environment, and significantly improve the MEC system’s income through extensive comparison with three state-of-the-art algorithms.

Federated Learning (FL) has emerged as a privacy-preserving distributed Machine Learning paradigm, which collaboratively trains a shared global model across a number of end devices (clients) without exposing their raw data. However, FL typically assumes that all clients are benign and trust the coordinating central server, which is unrealistic for many real-world scenarios. In practice, clients can harm the FL process by sharing poisonous model updates while the server could malfunction or misbehave. Moreover, the deployment of FL for real-world applications is hindered by the high communication overhead between the server and clients that are often at the network edge with limited bandwidth. To address these key challenges, we propose a lightweight Blockchain-Empowered secure and efficient Federated Learning (BEFL) system. BEFL is built by integrating a communication-efficient and mutual-information guarded training scheme, a cost-effective Verifiable Random Function (VRF)-based consensus mechanism, and Inter-Planetary File System (IPFS)-enabled scalable blockchain architecture. Extensive simulation experiments using two benchmark FL datasets demonstrate that BEFL is resistant against byzantine clients launching data poisoning and model poisoning attacks, fault-tolerant against colluded malicious blockchain nodes, scalable to a large number of blockchain nodes, and communication-efficient at the network edge.

Federated Learning (FL) is a recent development in distributed machine learning that collaboratively trains models without training data leaving client devices, preserving data privacy. In real-world FL, the training set is distributed over clients in a highly non-Independent and Identically Distributed (non-IID) fashion, harming model convergence speed and final performance. To address this challenge, we propose a novel, generalised approach for incorporating adaptive optimisation into FL with the Federated Global Biased Optimiser (FedGBO) algorithm. FedGBO accelerates FL by employing a set of global biased optimiser values during training, reducing ‘client-drift’ from non-IID data whilst benefiting from adaptive optimisation. We show that in FedGBO, updates to the global model can be reformulated as centralised training using biased gradients and optimiser updates, and apply this framework to prove FedGBO's convergence on nonconvex objectives when using the momentum-SGD (SGDm) optimiser. We also conduct extensive experiments using 4 FL benchmark datasets (CIFAR100, Sent140, FEMNIST, Shakespeare) and 3 popular optimisers (SGDm, RMSProp, Adam) to compare FedGBO against six state-of-the-art FL algorithms. The results demonstrate that FedGBO displays superior or competitive performance across the datasets whilst having low data-upload and computational costs, and provide practical insights into the trade-offs associated with different adaptive-FL algorithms and optimisers.

The deep integration of the Internet of Things (IoT) and the medical industry has given birth to the Internet of Medical Things (IoMT). In IoMT, physicians treat a patient's disease by analyzing patient data collected through mobile devices with the assistance of an artificial intelligence (AI)-empowered systems. However, the traditional AI technologies may lead to the leakage of patient privacy data due to its own design flaws. As a privacy-preserving federated learning (FL) can generate a global disease diagnosis model through multiparty collaboration. However, FL is still unable to resist inference attacks. In this article, to address such problems, we propose a privacy-enhanced disease diagnosis mechanism using FL for IoMT. Specifically, we first reconstruct medical data through a variational autoencoder and add differential privacy noise to it to resist inference attacks. These data are then used to train local disease diagnosis models, thereby preserving patients' privacy. Furthermore, to encourage participation in FL, we propose an incentive mechanism to provide corresponding rewards to participants. Experiments are conducted on the arrhythmia database Massachusetts Institute of Technology and Beth Israel Hospital (MIT-BIH). The experimental results show that the proposed mechanism reduces the probability of reconstructing patient medical data while ensuring high-precision heart disease diagnosis.

During the past decade, Industry 4.0 has greatly promoted the improvement of industrial productivity by introducing advanced communication and network technologies in the manufacturing process. With the continuous emergence of new communication technologies and networking facilities, especially the rapid evolution of cellular networks for 5G and beyond, the requirements for smarter, more reliable, and more efficient cellular network services have been raised from the Industry 5.0 blueprint. To meet these increasingly challenging requirements, proactive and effective allocation of cellular network resources becomes essential. As an integral part of the cellular network resource management system, cellular traffic prediction faces severe challenges with stringent requirements for accuracy and reliability. One of the most critical problems is how to improve the prediction performance by jointly exploring the spatial and temporal information within the cellular traffic data. A promising solution to this problem is provided by graph neural networks (GNNs), which can jointly leverage the cellular traffic in the temporal domain and the physical or logical topology of cellular networks in the spatial domain to make accurate predictions. In this article, we present the spatial-temporal analysis of a real-world cellular network traffic dataset and review the state-of-the-art research works in this field. Based on this, we further propose a time-series similarity-based graph attention network, TSGAN, for the spatial-temporal cellular traffic prediction. The simulation results show that our proposed TSGAN outperforms three classic prediction models based on GNNs or GRU on a real-world cellular network dataset in short-term, mid-term, and long-term prediction scenarios.

The convergence of Maritime Transportation Systems (MTS) and Internet of Things (IoT) has led to the promising IoT-empowered MTS (IoT-MTS). However, abnormal trajectories of maritime transportation ships can have highly negative impacts on the management of IoT-MTS. Therefore, anomaly detection of trajectories is important for the successful deployment of IoT-MTS. In this paper, we propose a Transfer Learning based Trajectory Anomaly Detection strategy, named TLTAD, for IoT-MTS. Specifically, a variational autoencoder is used to discover the potential connections between each dimension of the normal trajectory, while a graph variational autoencoder is used to explore the spatial similarity between normal trajectories. Based on internal connection of trajectories, a deep reinforcement learning algorithm, Twin Delayed Deep Deterministic policy gradient (TD3), is employed to train the trajectory anomaly detection model. To reduce the model training time, transfer learning is used to migrate the trained anomaly detection model between different regions of an ocean area or between similar ocean areas. Moreover, an efficient data transformation module is designed to improve the efficiency of model transfer. The experiments were conducted on a real-world automatic identification system (AIS) dataset. The results indicate that the proposed TLTAD can provide accurate anomaly detection on ships’ trajectories in IoT-MTS with reduced model training times.

The fifth-generation (5G) wireless communication technology enables high-reliability and low-latency communications for the Intelligent Transportation System (ITS). However, the growingly sophisticated attacks against 5G-enabled ITS (5G-ITS) might cause serious damages to the valuable data generated by various ITS applications. Therefore, establishing a secure 5G-ITS through trust evaluation against potential threats has become a key objective. Furthermore, as a distributed shared ledger and database, Blockchain has the characteristics of non-tampering, traceability, openness and transparency, can support both trust storage and trust verification for trust evaluation. In this paper, we propose a heterogeneous Blockchain based Hierarchical Trust Evaluation strategy, named BHTE, utilizing the federated deep learning technology for 5G-ITS. Specifically, the trusts of ITS users and task distributers are evaluated using the federated deep learning and hierarchical incentive mechanisms are designed for reasonable and fair rewards and punishments. Moreover, the trusts of ITS users and task distributers are stored on heterogeneous and hierarchical blockchains for trust verification. The extensive experiment results show that: (i) the proposed BHTE can achieve reasonable and fair trust evaluations on both ITS users and task distributers; (ii) the BHTE performs excellently with high system throughput and low latency.

The vigorous development of positioning technology and ubiquitous computing has spawned trajectory big data. By analyzing and processing the trajectory big data in the form of data streams in a timely and effective manner, anomalies hidden in the trajectory data can be found, thus serving urban planning, traffic management, safety control and other applications. Limited by the inherent uncertainty, infinity, time-varying evolution, sparsity and skewed distribution of trajectory big data, traditional anomaly detection techniques cannot be directly applied to anomaly detection in trajectory big data. To solve this problem, we propose a hierarchical trajectory anomaly detection scheme for Intelligent Transportation Systems (ITS) using both machine learning and blockchain technologies. To be specific, a hierarchical federated learning strategy is proposed to improve the generalization ability of the global trajectory anomaly detection model by secondary fusion of the multi-area trajectory anomaly detection model. Then, by integrating blockchain and federated learning, the iterative exchange and fusion of the global trajectory anomaly detection model can be realized by means of on-chain and off-chain coordinated data access. Experiments show that the proposed scheme can improve the generalization ability of the trajectory anomaly detection model in different areas, while ensuring its reliability.

The quantitative performance analysis plays a critical role in assessing the capability of vehicular edge computing (VEC) systems to meet the requirements of vehicular applications. However, developing accurate analytical models for VEC systems is extremely challenging due to the unique features of intelligent vehicular applications. Specifically, recent work revealed that the tasks generated by intelligent vehicular applications exhibit a high degree of burstiness, rendering the existing models that were designed based on the assumption of the non-bursty Poisson process unsuitable for VEC systems. To fill this gap, we developed an original analytical model to investigate the performance of VEC systems with bursty task arrivals. To facilitate vehicle cooperation, a new priority-based resource allocation scheme is exploited to schedule the tasks of vehicular applications, which are modelled by a Markov Modulated Poisson Process (MMPP). Next, a multi-state Markov chain is established to investigate the impact of load sharing strategy on the performance of VEC systems. Then, the end-to-end transmission latency is derived based on the proposed model. Comprehensive experiments are conducted to validate the accuracy of this analytical model under various system configurations. Furthermore, the developed model is used as a cost-effective tool to investigate the performance bottleneck of VEC systems.

Multi-access Edge Computing (MEC) is an emerging computing paradigm that extends cloud computing to the network edge to support resource-intensive applications on mobile devices. As a crucial problem in MEC, service migration needs to decide how to migrate user services for maintaining the Quality-of-Service when users roam between MEC servers with limited coverage and capacity. However, finding an optimal migration policy is intractable due to the dynamic MEC environment and user mobility. Many existing studies make centralized migration decisions based on complete system-level information, which is time-consuming and also lacks desirable scalability. To address these challenges, we propose a novel learning-driven method, which is user-centric and can make effective online migration decisions by utilizing incomplete system-level information. Specifically, the service migration problem is modeled as a Partially Observable Markov Decision Process (POMDP). To solve the POMDP, we design a new encoder network that combines a Long Short-Term Memory (LSTM) and an embedding matrix for effective extraction of hidden information, and further propose a tailored off-policy actor-critic algorithm for efficient training. The extensive experimental results based on real-world mobility traces demonstrate that this new method consistently outperforms both the heuristic and state-of-the-art learning-driven algorithms and can achieve near-optimal results on various MEC scenarios.

In Federated Learning (FL) client devices connected over the internet collaboratively train a machine learning model without sharing their private data with a central server or with other clients. The seminal Federated Averaging (FedAvg) algorithm trains a single global model by performing rounds of local training on clients followed by model averaging. FedAvg can improve the communication-efficiency of training by performing more steps of Stochastic Gradient Descent (SGD) on clients in each round. However, client data in real-world FL is highly heterogeneous, which has been extensively shown to slow model convergence and harm final performance when$K > 1$steps of SGD are performed on clients per round. In this article we propose decaying$K$as training progresses, which can jointly improve the final performance of the FL model whilst reducing the wall-clock time and the total computational cost of training compared to using a fixed$K$. We analyse the convergence of FedAvg with decaying$K$for strongly-convex objectives, providing novel insights into the convergence properties, and derive three theoretically-motivated decay schedules for$K$. We then perform thorough experiments on four benchmark FL datasets (FEMNIST, CIFAR100, Sentiment140, Shakespeare) to show the real-world benefit of our approaches in terms of real-world convergence time, computational cost, and generalisation performance.

Federated learning (FL) is a privacy-preserving distributed machine learning paradigm that enables collaborative training among geographically distributed and heterogeneous devices without gathering their data. Extending FL beyond the supervised learning models, federated reinforcement learning (FRL) was proposed to handle sequential decision-making problems in edge computing systems. However, the existing FRL algorithms directly combine model-free RL with FL, thus often leading to high sample complexity and lacking theoretical guarantees. To address the challenges, we propose a novel FRL algorithm that effectively incorporates model-based RL and ensemble knowledge distillation into FL for the first time. Specifically, we utilise FL and knowledge distillation to create an ensemble of dynamics models for clients, and then train the policy by solely using the ensemble model without interacting with the environment. Furthermore, we theoretically prove that the monotonic improvement of the proposed algorithm is guaranteed. The extensive experimental results demonstrate that our algorithm obtains much higher sample efficiency compared to classic model-free FRL algorithms in the challenging continuous control benchmark environments under edge computing settings. The results also highlight the significant impact of heterogeneous client data and local model update steps on the performance of FRL, validating the insights obtained from our theoretical analysis.

The Quality of Service (QoS) requirements of vehicular services have become more and more stringent in intelligent connected vehicles. Hence, the Enhanced Distributed Channel Access (EDCA) mechanism has been utilized in IEEE 802.11p to achieve multi-class QoS for the Internet of Vehicles. Recently, some analytical models have been developed to evaluate the performance of the IEEE 802.11p. Nevertheless, most works are under the assumption of ideal wireless channels and infinite buffer sizes that are not realistic for vehicular networks’ operating environments. In this paper, we propose an analytical model for IEEE 802.11p with bursty error transmission based on the Queuing Theory. Especially, the transmission queue is modelled as an M/G/1/N queueing system. The accuracy of this model has been validated by a set of simulation experiments based on ns-3 and SUMO. The model can be used as a cost-effective tool to investigate the performance of 802.11p under various network conditions.

The Industrial Internet of Things (IIoT) is an emerging technology that can promote the development of industrial intelligence, improve production efficiency, and reduce manufacturing costs. However, anomalies of IIoT devices might expose sensitive data about users of high authenticity and validity, resulting in security and privacy threats to the IIoT applications. That suggests the significance of anomaly detection executed by proper authorities. To address these problems, in this paper, we propose a reliable anomaly detection strategy for IIoT using federated learning. Specifically, we apply the federated learning technique to build a universal anomaly detection model with each local model trained by the deep reinforcement learning (DRL) algorithm. Since local data sets are not required during the federated learning, the chance of privacy leakage is reduced. In addition, by introducing privacy leakage degree and action relation to anomaly detection design, we can greatly improve the detection accuracy. The validation experiments indicate that the proposed strategy achieves high throughput, low latency, and high anomaly detection accuracy for privacy preservation in various IIoT scenarios.

With the rapid development of the Internet of Things (IoT), more and more data are generated by smart devices to support various edge services. Since these data may contain sensitive information, security and privacy of data aggregation has become a key challenge in IoT. To tackle this problem, a blockchain-based secure data aggregation strategy, namely (BSDA), is proposed for edge computing empowered IoT. Specifically, in order to restrict task receivers [i.e., mobile data collectors (MDCs)] to search and accept tasks, the block header is intergraded with a security label including task security level (SL) and task completion requirement. Accordingly, new block generation rules are developed to improve system performance in throughput and transaction latency. Furthermore, BSDA decomposes both sensitive tasks and task receivers into groups against privacy disclosure. On the other hand, a deep reinforcement learning method, the improved self-adaptive double bootstrapped deep deterministic policy gradient (IDDPG), is developed to design energy-efficient MDC routes under the constrains that the SLs of MDCs should be higher than the SLs of data aggregation tasks. Simulation results indicate that 1) as a privacy-preserving strategy, BSDA obtains high throughput and low transaction latency and 2) BSDA outperforms certain contemporary strategies in aggregation ratio and energy cost.

Over the past few years, fog radio access networks (F-RANs) have become a promising paradigm to support the tremendously increasing demands of multimedia services, by pushing computation and storage functionalities toward the edge of networks, closer to users. In F-RANs, distributed edge caching among fog access points (F-APs) can effectively reduce network traffic and service latency as it places popular contents at local caches of F-APs rather than the remote cloud. Due to the limited caching resources of F-APs and spatiotemporally fluctuant content demands from users, many cooperative caching schemes were designed to decide which contents are popular and how to cache them. However, these approaches often collect and analyze the data from Internet-of-Things (IoT) devices at a central server to predict the content popularity for caching, which raises serious privacy issues. To tackle this challenge, we propose a federated learning-based cooperative hierarchical caching scheme (FLCH), which keeps data locally and employs IoT devices to train a shared learning model for content popularity prediction. FLCH exploits horizontal cooperation between neighbor F-APs and vertical cooperation between the baseband unit (BBU) pool and F-APs to cache contents with different degrees of popularity. Moreover, FLCH integrates a differential privacy mechanism to achieve a strict privacy guarantee. Experimental results demonstrate that FLCH outperforms five important baseline schemes in terms of the cache hit ratio, while preserving data privacy. Moreover, the results show the effectiveness of the proposed cooperative hierarchical caching mechanism for FLCH.

Edge computing is an emerging promising computing paradigm that brings computation and storage resources to the network edge, hence significantly reducing the service latency and network traffic. In edge computing, many applications are composed of dependent tasks where the outputs of some are the inputs of others. How to offload these tasks to the network edge is a vital and challenging problem which aims to determine the placement of each running task in order to maximize the Quality-of-Service (QoS). Most of the existing studies either design heuristic algorithms that lack strong adaptivity or learning-based methods but without considering the intrinsic task dependency. Different from the existing work, we propose an intelligent task offloading scheme leveraging off-policy reinforcement learning empowered by a Sequence-to-Sequence (S2S) neural network, where the dependent tasks are represented by a Directed Acyclic Graph (DAG). To improve the training efficiency, we combine a specific off-policy policy gradient algorithm with a clipped surrogate objective. We then conduct extensive simulation experiments using heterogeneous applications modelled by synthetic DAGs. The results demonstrate that: 1) our method converges fast and steadily in training; 2) it outperforms the existing methods and approximates the optimal solution in latency and energy consumption under various scenarios.

The development and maturity of the fifth-generation (5G) wireless communication technology provides the industrial Internet of Things (IIoT) with ultra-reliable and low-latency communications and massive machine-type communications, and forms a novel IIoT architecture, 5G-IIoT. However, massive data transfer between interconnecting industrial devices also brings new challenges for the 5G-IIoT routing process in terms of latency, load balancing, and data privacy, which affect the development of 5G-IIoT applications. Moreover, the existing research works on IIoT routing mostly focus on the latency and the reliability of the routing, disregarding the privacy security in the routing process. To solve these problems, in this article, we propose a quality of service (QoS) and data privacy-aware routing protocol, named QoSPR, for 5G-IIoT. Specifically, we improve the community detection algorithm info-map to divide the routing area into optimal subdomains, based on which the deep reinforcement learning algorithm is applied to build the gateway deployment model for latency reduction and load-balancing improvement. To eliminate areal differences, while considering the privacy preservation of the routing data, the federated reinforcement learning is applied to obtain the universal gateway deployment model. Then, based on the gateway deployment, the QoS and data privacy-aware routing is accomplished by establishing communications along the load-balancing routes of the minimum latencies. The validation experiment is conducted on real datasets. The experiment results show that as a data privacy-aware routing protocol, the QoSPR can significantly reduce both average latency and maximum latency, while maintaining excellent load balancing in 5G-IIoT.

The ever-expanding scale of cloud datacenters necessitates automated resource provisioning to best meet the requirements of low latency and high energy-efficiency. However, due to the dynamic system states and various user demands, efficient resource allocation in cloud faces huge challenges. Most of the existing solutions for cloud resource allocation cannot effectively handle the dynamic cloud environments because they depend on the prior knowledge of a cloud system, which may lead to excessive energy consumption and degraded Quality-of-Service (QoS). To address this problem, we propose an adaptive and efficient cloud resource allocation scheme based on Actor-Critic Deep Reinforcement Learning (DRL). First, the actor parameterizes the policy (allocating resources) and chooses actions (scheduling jobs) based on the scores assessed by the critic (evaluating actions). Next, the resource allocation policy is updated by using gradient ascent while the variance of policy gradient is reduced with an advantage function, which improves the training efficiency of the proposed method. We conduct extensive simulation experiments using real-world data from Google cloud datacenters. The results show that our method can obtain the superior QoS in terms of latency and job dismissing rate with enhanced energy-efficiency, compared to two advanced DRL-based and five classic cloud resource allocation methods.

Federated Learning (FL) is an emerging approach for collaboratively training Deep Neural Networks (DNNs) on mobile devices, without private user data leaving the devices. Previous works have shown that non-Independent and Identically Distributed (non-IID) user data harms the convergence speed of the FL algorithms. Furthermore, most existing work on FL measures global-model accuracy, but in many cases, such as user content-recommendation, improving individual User model Accuracy (UA) is the real objective. To address these issues, we propose a Multi-Task FL (MTFL) algorithm that introduces non-federated Batch-Normalization (BN) layers into the federated DNN. MTFL benefits UA and convergence speed by allowing users to train models personalised to their own data. MTFL is compatible with popular iterative FL optimisation algorithms such as Federated Averaging (FedAvg), and we show empirically that a distributed form of Adam optimisation (FedAvg-Adam) benefits convergence speed even further when used as the optimisation strategy within MTFL. Experiments using MNIST and CIFAR10 demonstrate that MTFL is able to significantly reduce the number of rounds required to reach a target UA, by up to$5\times$when using existing FL optimisation strategies, and with a further$3\times$improvement when using FedAvg-Adam. We compare MTFL to competing personalised FL algorithms, showing that it is able to achieve the best UA for MNIST and CIFAR10 in all considered scenarios. Finally, we evaluate MTFL with FedAvg-Adam on an edge-computing testbed, showing that its convergence and UA benefits outweigh its overhead.

With the development of smart mobile terminals and mobile communication technologies, Mobile Edge Computing (MEC) has been applied to a variety of fields. However, MEC also brings new data security threats including the data access threat. To solve the cross-domain access control problem in MEC, this paper proposes a cross-domain access control protocol, named CDAC. In CDAC, a new user reputation evaluation strategy is proposed, which dynamically evaluates the comprehensive reputation of users based on different access behaviors of users, so that gateway nodes can evaluate user cross-domain requests. Meanwhile, different priorities are assigned according to user security levels to encourage users to regulate access behaviors to improve their reputations. Then, different gateway nodes implement cross-domain access control for users. The experiment results show that the proposed CDAC can provide efficient cross-domain access controls and achieve excellent system performances.

In the process of sharing students’ credit information across schools and departments, there are some problems such as tampering and leaking of students’ credit information.In this paper, combined with the characteristics of blockchain traceability and difficult to tamper, a credit information access control method based on blockchain is proposed, which not only protects students’ privacy, but also realizes the cross school access control of students’ credit information.This paper designs a multi blockchain architecture that combines consortium blockchain and private blockchain of colleges and universities. It stores credit information summary on the blockchain and original records off the blockchain to relieve the storage pressure of blockchain; Then, the multi authorization attribute encryption technology is used to set the access policy for fine-grained access control.Finally, the simulation results show that the scheme can achieve fine-grained access control of students’ credit information while protecting students’ privacy.

With the development of internet technology, the proliferation of network-based applications leads to large number of multi-source multi-sink traffic transmission. Such as wireless sensor network (WSN), to deal with actuator nodes or support high-level programming abstractions, it naturally calls for a many-to-many communication. But the existing algorithms or solutions are not able to solve the scenarios effectively, they face many difficulties and challenges when dealing with multi-source multi-sink network problems. In this paper, we develop a new traffic scheduling algorithm suitable for multi-source and multi-sink networks. According to traffic transmission rate and network structure information, it selects the optimal path to transmit traffic and achieve load balance. When the traffic or source nodes change in the network, the paths and traffic are adjusted as needed to ensure the overall optimum. To evaluate the performance on efficiency, we perform a series of simulations and the results indicate the advantages of the proposed algorithm.

The emergence of the Internet of Medical Things (IoMT) brings a huge impact on current medical system in the detection and prevention of medical diseases, as well as the sharing and analysis of medical data. To efficiently collect medical data for disease prevention, the mobile crowdsensing (MCS) is employed. However, the exposure of sensitive information about users and crowdsensing tasks might cause serious privacy leakage in MCS. To solve this problem, in this paper, a Privacy-enhanced Mobile Crowdsensing strategy utilizing Blockchain technology, named PMCB, is proposed. Specifically, we propose to classify the users by spectral clustering based on the social network generated by the social attributes of users. In this way, both crowdsensing tasks and participating users are classified such that task receivers are restricted to receive specific crowdsensing tasks. Furthermore, the blockchain is used to store crowdsensing tasks and smart contract is used for access control. Experiment results show that PMCB can achieve efficient privacy protection in mobile crowdsensing with high system throughput and low transaction latency.

Summary Mobile edge computing (MEC) necessitates cost‐effective deployment for executing scientific workflows with different tasks and datasets, which provides computing, storage and network control at the network edge. However, the execution of scientific workflows in MEC results in heavy costs of data placement including data transmission and data storage. Although there are solutions for data placement in traditional cloud computing, they cannot effectively respond to the latency‐sensitive property of scientific workflows, which leads to the excessive costs of data placement. To cope with this problem, we combine the advantages of MEC and cloud computing and propose a genetic algorithm particle swarm optimization (GAPSO) based method to explore the optimal strategy of data placement for scientific workflows in MEC. First, a unified model of data placement is designed to explore a cost‐effective strategy, which considers the different characteristics between MEC and cloud computing as well as the impact of latency constraint on transmission costs. Next, the advantages of genetic algorithm (GA) and particle swarm optimization (PSO) are integrated to optimize the proposed model, which utilities the fast convergence of PSO and the crossover and mutation operations of GA. Simulations using real‐world scientific workflows show the effectiveness of the proposed method for reducing data placement costs in MEC.

As an interdisciplinary area, Data Science draws scientific inquiry from a broad range of subject areas such as statistics, mathematics, computer science, machine learning, optimisation, signal processing, information retrieval, databases, cloud computing, computer vision, natural language processing, and so forth. Data Science aims to deliver valuable insights from data, and to meet the challenges of processing very large datasets, that is, Big Data, with new data continuously generated from various channels, such as smart devices, web, mobile and social media. Data volumes of applications in the fields of sciences and engineering, finance, media, online information resources, and so forth, are expected to double every two years over the next decade and beyond. The importance of data intensive systems has been raising and will continue to be one of the foremost fields of research. This brings up many research issues concerning capturing and accessing data effectively and fast, processing it whilst still achieving high performance and throughput, and storing it efficiently for future use. As such, data intensive systems pose many challenges in exploiting parallelism of current and upcoming computer architectures. This special issue focuses on recent advances in Data Science (e.g., Knowledge Discovery, Data Mining, Machine Learning, Big Data Analytics, Deep Learning, etc.) and data systems, and innovative real-world applications of such technologies to deliver effective and efficient solutions for current and future challenges. This special issue has attracted more than 20 submissions and 6 manuscripts were selected based on review reports. Each paper was reviewed by at least two reviewers and went through at least two rounds of reviews. The contributions of these papers are summarized below. The first contribution by Li et al. reports a novel weighted probabilistic frequent itemset mining algorithm in uncertain databases (i.e., w-PFI), which is implemented by an efficient candidate generation and validation paradigm similar to the working principle of Apriori. This work additionally presents a new probability model to support w-PFI candidate, and three pruning techniques to effectively remove the unpromising candidates immediately to improve system efficiency. The experimental results show that the proposed algorithm w-PFI yields the best performance amongst the referenced competitors in terms of running time and scalability. The second paper by Sadhukham and Palit presents a novel neighbourhood-based multi-label classifier based on the principles of reverse k-nearest neighbourhood. That is, the neighbourhood was estimated using the reverse k-nearest neighbourhood. This adaptive neighbourhood estimation with the support of implicit handling of the local imbalance works particularly well for multiple-label datasets with imbalanced labels. The proposed approach improves the efficacy of the compared methods based on the experimentation as evidenced by its competitive performance. The third publication by Tsinaslanidis and Guijarro considers chart pattern recognition for trading purposes. In particular, this work proposes the design of a trading system using generic pattern recognition technique which takes proven generic profitable patterns based on historical data as system inputs rather than restricting the search to specific technical patterns. The effectiveness of the proposed system was validated and evaluated by applying the approach to 560 NYSE stocks with generally promising results demonstrated. The article produced by Hu et al. documents an adaptive network with a stacked hourglass network and SSD for video pose estimation especially for videos with joint occlusion. The proposed network is supported by the optimisation of time series motion data using an outlier detection and a Kalman filter. The work was evaluated by applying the proposed adaptive network on two well-known benchmark human pose estimation datasets. The results show higher accuracy and good practicality. The next article by Naik et al. proposes a cognizant honeypot for active fingerprinting attack detection using dynamic fuzzy rule interpolation. This project firstly actively collected data using simulated attacks on honeypots and extracted the most influential attributes from the collected data as the signatures of active fingerprinting attacks. Then, the selected attributes were utilized to devise the dynamic fuzzy rule interpolation system and subsequently to implement the cognizant honeypot. The proposed system is featured by its dynamic rule base for more accurate and efficient detection. The final contribution by Gao et al. reports a hand gesture recognition approach using multimodal data fusion and a multiscale parallel convolutional neural network for human robot interaction. Ten hand gestures were considered in this project and the multiscale parallel convolutional neural network was trained using a dataset generated by this project. The proposed method was implemented on a seven-degree-of-freedom bionic manipulator and promising results were demonstrated based on the experiments using this manipulator. We would like to express our sincere thanks to Dr. Jon G. Hall (Editor-in-Chief of the Wiley-Blackwell Journal Expert Systems: The Journal of Knowledge Engineering) for providing the opportunity to edit this special issue. Additional thanks to the editorial staff for their excellent support. Finally, the guest editors would also like to thank all the referees for their thorough and constructive comments. The authors declare no conflicts of interest.

Localization techniques are becoming key to add location context to the Internet-of-Things (IoT) data without human perception and intervention. Meanwhile, the newly emerged low-power wide-area network (LPWAN) and 5G technologies have become strong candidates for mass-market localization applications. However, various error sources have limited localization performance by using such IoT signals. This article reviews the IoT localization system through the following sequence: IoT localization system review, localization data sources, localization algorithms, localization error sources and mitigation, and localization performance evaluation. Compared to the related surveys, this article has a more comprehensive and state-of-the-art review on IoT localization methods, an original review on IoT localization error sources and mitigation, an original review on IoT localization performance evaluation, and a more comprehensive review of IoT localization applications, opportunities, and challenges. Thus, this survey provides comprehensive guidance for peers who are interested in enabling localization ability in the existing IoT systems, using IoT systems for localization, or integrating IoT signals with the existing localization sensors.

With the worldwide large-scale outbreak of COVID-19, the Internet of Medical Things (IoMT), as a new type of Internet of Things (IoT)-based intelligent medical system, is being used for COVID-19 prevention and detection. However, since the widespread use of IoMT will generate a large amount of sensitive information related to patients, it is becoming more and more important yet challenging to ensure data security and privacy of COVID-19 applications in IoMT. The leakage of private information during IoMT data fusion process will cause serious problems and affect people's willingness to contribute data in IoMT. To address these challenges, this article proposes a new privacy-enhanced data fusion strategy (PDFS). The proposed PDFS consists of four important components, i.e., sensitive task classification, task completion assessment, incentive mechanism-based task contract design, and homomorphic encryption-based data fusion. The extensive simulation experiments demonstrate that PDFS can achieve high task classification accuracy, task completion rate, task data reliability and task participation rate, and low average error rate, while improving the privacy protection for data fusion under COVID-19 application environments based on IoMT.

The epoch of the Internet of Things (IoT) has come by enabling almost everything to gather and share electronic information. Considering the unreliable factors of public IoT, how to outsource huge amounts of indispensable stream data generated by the nodes to the remote storage (RS) efficiently and securely is one of the most challenging issues. In this article, we propose a secure lightweight stream data outsourcing framework for IoT based on identity and blockchain. Taking advantage of identity-based cryptography and blockchain, for public IoT containing untrusted communication channels, nodes, RS, and even verifiers, we introduce a private mobile network and multiple verifiers to ensure that the stream data are stored intact and updated correctly, without the costs and risks brought by the public-key infrastructures (PKI). Meanwhile, the framework can also achieve privacy-preserving checking, by revealing no data to the other entities besides the RS, even in the blockchains. Our comprehensive analysis and experiments demonstrate that the proposed framework is suitable for lightweight devices and practical for IoT.

Mobile-edge crowdsensing is capable of providing a large amount of data via pervasive mobile terminals for Industrial Internet of Things (IIoT). However, the generated data often contain users' sensitive information, which suggests the significance of privacy preserving in data aggregation and analysis for IIoT. Privacy preserving in mobile-edge crowdsensing have conflicting objectives, i.e., the edge fusion center (FC) requires data of better quality for data fusion with higher accuracy whereas participatory users (PUs) desire better privacy preserving by larger noise injection. Therefore, how to select proper noises to achieve the tradeoff between accuracy and privacy is a challenging problem. In addition, FC is subject to data tempering due to the lack of data reliability validations and incentive mechanisms. To tackle these problems, we propose a novel privacy-preserving mobile-edge crowdsensing strategy (PPCS) for IIoT. Specifically, PPCS provides a Kullback-Leibler privacy-preserving data aggregation using a reputation-based incentive mechanism. On the other hand, PPCS offers hypothesis test-based data reliability validation and PU's reputation update, which collaborate to ease the impact of tampered data. Meanwhile, a reinforcement learning algorithm, the expected Sarsa, is applied to obtain the optimal test threshold. Theoretical analysis and experimental results show that PPCS is an energy-efficient strategy and the data provided by PPCS has a better aggregation accuracy than certain baseline strategies.

Network function virtualization (NFV) is critical to the scalability and flexibility of various network services in the form of service function chains (SFCs), which refer to a set of Virtual Network Functions (VNFs) chained in a specific order. However, the NFV performance is hard to fulfill the ever-increasing requirements of network services mainly due to the static orchestrations of SFCs. To tackle this issue, a novel Scalable SFC Orchestration (SSCO) scheme is proposed in this paper for NFV-enabled networks via federated reinforcement learning. SSCO has three remarkable characteristics distinguishing from the previous work: (1) A federated-learning-based framework is designed to train a global learning model, with time-variant local model explorations, for scalable SFC orchestration, while avoiding data sharing among stakeholders; (2) SSCO allows for parameter update among local clients and the cloud server just at the first and last epochs of each episode to ensure that distributed clients can make model optimization at a low communication cost; (3) SSCO introduces an efficient deep reinforcement learning (DRL) approach, with the local learning knowledge of available resources and instantiation cost, to map VNFs into networks flexibly. Furthermore, a loss-weight-based mechanism is proposed to generate and exploit reference samples in replay buffers for future training, avoiding the strong relevance of samples. Simulation results obtained from different working scenarios demonstrate that SSCO can significantly reduce placement errors and improve resource utilization ratio to place time-variant VNFs compared with the state-of-the-art mechanisms. Furthermore, the results show that the proposed approach can achieve desirable scalability.

Guaranteeing network transmission is one of the most challenging issues in industrial informatization. In the industrial sites without proper networking infrastructure, by deploying unmanned aerial vehicles (UAV), transmission-oriented cyber-physical system (CPS) is an excellent candidate to exploit to provide transmission. In this article, we focus on establishing deterministic network transmission (DNT) using UAV-based CPS, complying with the principles in time sensitive network/deterministic networking in industrial internet. The software-defined networking (SDN) paradigm is adopted for UAVs-based CPS to achieve global optimization. First, we build the coordinate-based global topology view in the SDN controller to manage and control UAVs by integrating UAVs into the view and applying the network positioning method. Then, we introduce a hop-limited time synchronization approach to improve accuracy by reducing synchronization deviation. Last, based on the view, a geometric multipath generating method is proposed to enhance reliability by reducing the joint degree of multiple paths and facilitating convergence. The extensive simulation experiments show that our proposed UAV-CPS allows DNT to provide better reliability with reduced latency.

Sixth generation (6G) network is a revolutionary technology to satisfy the ever-growing demands from the sustainable development of emerging industrial applications and services. Due to its high flexibility, convenient and rapid deployment, self-organization capability, and outstanding expansibility, network-in-box (NIB) represents a promising approach for future networks. The integration of NIB with 6G can lead to many new applications in geoscience, robotics, and industrial automation. For 6G-enabled NIB, services are deployed directly on the NIB, which increases the fault tolerance and reduces the traffic volume on the backhaul link. As more and more data are processed and shared in industrial applications and services, the security of data aggregation becomes a key challenge for 6G-enabled NIB. To address this challenge, in this article, we propose a blockchain based privacy-aware distributed collection (BPDC) oriented strategy for data aggregation. In BPDC, an improved blockchain with a new block header structure and two different block generation rules are designed and introduced, which restricts the task receivers to search and receive the tasks beyond their levels of security permission. While guaranteeing the data aggregation performance, BPDC can also achieve privacy protection by decomposing sensitive tasks and task receivers into multiple groups. Validation experiments show that the BPDC accomplishes low overhead, high throughput, and privacy preservation in various industrial applications.

As an emerging technology, the industrial Internet of Things (IIoT) can promote the development of industrial intelligence, improve production efficiency, and reduce manufacturing costs. In IIoT, the improvement and progress of industrial production and applications are inseparable from data fusion, a process that realizes the collection, analysis, and processing of the massive IoT data generated by industrial equipment and applications. IIot demands a real-time, effective, and privacy-preserving data fusion process. However, the existing works need to train different learning models for data analysis, which cannot meet real-time requirements in IIoT. Meanwhile, the lack of defense against internal attacks and the difficulty to balance system performance and privacy protection hinder the effectiveness and privacy protection in the data fusion process. To solve the abovementioned problems, in this article, we propose a new transfer learning-based secure data fusion strategy (TSDF) for IIoT. The proposed TSDF consists of three parts, guidance based deep deterministic policy gradient (GDDPG) algorithm for task classification, transfer learning based GDDPG for grouping of task receivers, and a multiblockchain mechanism for privacy preservation. The experiment results show that TSDF can achieve high system throughput and low latency, providing privacy preservation in data fusion under various IIoT application environments.

With the massive deployment of 5G cellular infrastructures, traffic prediction has become an indispensable part of the cellular resource management system in order to provide reliable and fast communication services that can meet the increasing quality-of-service requirements of smart city. A promising approach for handling this problem is to introduce intelligent methods to implement a highly effective and efficient cellular traffic prediction model. Meanwhile, integrating the multiaccess edge computing framework in 5G cellular networks facilitates the application of intelligent traffic prediction models by enabling their implementation at the network edge. However, the data shortage and privacy issues may still be obstacles for training a robust and accurate prediction model at the edge. To address these issues, we propose a data-augmentation-based cellular traffic prediction model (ctGAN-S2S), where an effective data augmentation submodel based on generative adversarial networks is proposed to improve the prediction performance while protecting data privacy, and a long-short-term-memory-based sequence-to-sequence submodel is used to achieve the flexible multistep cellular traffic prediction. The experimental results on a real-world city-scale cellular traffic dataset reveal that our ctGAN-S2S model achieves up to 48.49% improvement of the prediction accuracy compared to four typical reference models.

Industrial Internet of Things (IIoT) is ushering in huge development opportunities in the era of Industry 4.0. However, there are significant data security and privacy challenges during automatic and real-time data collection, monitoring for industrial applications in IIoT. Data security and privacy in IIoT applications are closely related to the reliability of users, which is determined by user authentication that have been widely used as an effective approach. However, the existing user authentication mechanisms in IIoT suffer from single factor authentication and poor adaptability with the rapid growth of the number of users and the diversity of user categories. To solve the aforementioned issues, this article proposes a novel Authentication mechanism based on Transfer Learning empowered Blockchain, coined ATLB. In ATLB, blockchains are applied to achieve the privacy preservation for industrial applications. In addition, by introducing the transfer learning based authentication mechanism, trustworthy blockchains are built such that the privacy preservation for industrial applications is further enhanced. Specifically, ATLB first employs a guiding deep deterministic policy gradient algorithm to train the user authentication model of a specific region, which is then transferred locally for foreign user authentication or cross-regionally for another region's user authentication such that the model training time is significantly reduced. Experimental results show that the proposed ATLB not only provides accurate authentications for IIoT applications but also achieves high throughput and low latency.

Owing to its benefits such as flexibility, scalability, and interoperability, Software-Defined Networking (SDN) has been incorporated into Internet of Vehicles (IoV) to cope with the increasing demands of vehicular applications. The integration of SDN and IoV, namely SDN-IoV, can enrich many new applications for intelligent transportation such as traffic monitoring, smart navigation, and self-driving. The spatial crowdsourcing technology has been adopted as an effective data collection and processing method that is the premise of various SDN-IoV applications. However, as huge amounts of data are generated in spatial crowdsourcing services, the data privacy and security has become a key challenge for SDN-IoV. To overcome abovementioned challenge, a Deep Reinforcement Learning (DRL) and Blockchain empowered Spatial Crowdsourcing System (DB-SCS) is proposed. In DB-SCS, we design an improved multi-blockchain structure and a blockchain-based hierarchical task management method, which divide the spatial tasks into different categories according to the privacy requirements and the areas of the task and then decompose different categories of tasks and task receivers into sub-blockchains. While guaranteeing the data privacy, DB-SCS can also enhance the spatial crowdsourcing performance by using the proposed DRL-based management strategy to dynamically select the consensus algorithm, block size, and block generation rule. Extensive simulation experiments demonstrate that the DB-SCS can obtain high throughput, low overhead, and data privacy under various SDN-IoV scenarios.

Content Caching at the edge of vehicular networks has been considered as a promising technology to satisfy the increasing demands of computation-intensive and latency-sensitive vehicular applications for intelligent transportation. The existing content caching schemes, when used in vehicular networks, face two distinct challenges: 1) Vehicles connected to an edge server keep moving, making the content popularity varying and hard to predict. 2) Cached content is easily out-of-date since each connected vehicle stays in the area of an edge server for a short duration. To address these challenges, we propose a Mobility-aware Proactive edge Caching scheme based on Federated learning (MPCF). This new scheme enables multiple vehicles to collaboratively learn a global model for predicting content popularity with the private training data distributed on local vehicles. MPCF also employs a Context-aware Adversarial AutoEncoder to predict the highly dynamic content popularity. Besides, MPCF integrates a mobility-aware cache replacement policy, which allows the network edges to add/evict contents in response to the mobility patterns and preferences of vehicles. MPCF can greatly improve cache performance, effectively protect users' privacy and significantly reduce communication costs. Experimental results demonstrate that MPCF outperforms other baseline caching schemes in terms of the cache hit ratio in vehicular edge networks.

Multi-access edge computing (MEC) aims to extend cloud service to the network edge to reduce network traffic and service latency. A fundamental problem in MEC is how to efficiently offload heterogeneous tasks of mobile applications from user equipment (UE) to MEC hosts. Recently, many deep reinforcement learning (DRL)-based methods have been proposed to learn offloading policies through interacting with the MEC environment that consists of UE, wireless channels, and MEC hosts. However, these methods have weak adaptability to new environments because they have low sample efficiency and need full retraining to learn updated policies for new environments. To overcome this weakness, we propose a task offloading method based on meta reinforcement learning, which can adapt fast to new environments with a small number of gradient updates and samples. We model mobile applications as Directed Acyclic Graphs (DAGs) and the offloading policy by a custom sequence-to-sequence (seq2seq) neural network. To efficiently train the seq2seq network, we propose a method that synergizes the first order approximation and clipped surrogate objective. The experimental results demonstrate that this new offloading method can reduce the latency by up to 25 percent compared to three baselines while being able to adapt fast to new environments.

To cope with the increasing content requests from emerging vehicular applications, caching contents at edge nodes is imperative to reduce service latency and network traffic on the Internet-of-Vehicles (IoV). However, the inherent characteristics of IoV, including the high mobility of vehicles and restricted storage capability of edge nodes, cause many difficulties in the design of caching schemes. Driven by the recent advancements in machine learning, learning-based proactive caching schemes are able to accurately predict content popularity and improve cache efficiency, but they need gather and analyse users' content retrieval history and personal data, leading to privacy concerns. To address the above challenge, we propose a new proactive caching scheme based on peer-to-peer federated deep learning, where the global prediction model is trained from data scattered at vehicles to mitigate the privacy risks. In our proposed scheme, a vehicle acts as a parameter server to aggregate the updated global model from peers, instead of an edge node. A dual-weighted aggregation scheme is designed to achieve high global model accuracy. Moreover, to enhance the caching performance, a Collaborative Filtering based Variational AutoEncoder model is developed to predict the content popularity. The experimental results demonstrate that our proposed caching scheme largely outperforms typical baselines, such as Greedy and Most Recently Used caching.

Nowadays we are witnessing the formation of a massive Internet-of-Things (IoT) ecosystem that integrates a variety of wireless-enabled devices ranging from smartphones, wearables, and virtual reality facilities to sensors, drones, and connected vehicles. As IoT is penetrating every aspect of people’s life, work, and entertainment, an increasing number of IoT devices and the emerging IoT applications are driving exponential growth in wireless traffic in the foreseeable future. As a result, current IoT system architectures are facing significant challenges to handle millions of devices; thousands of servers; the transmission and processing of large volume of data, etc.

The rapidly expanding number of Internet of Things (IoT) devices is generating huge quantities of data, but public concern over data privacy means users are apprehensive to send data to a central server for machine learning (ML) purposes. The easily changed behaviors of edge infrastructure that software-defined networking (SDN) provides makes it possible to collate IoT data at edge servers and gateways, where federated learning (FL) can be performed: building a central model without uploading data to the server. FedAvg is an FL algorithm which has been the subject of much study, however, it suffers from a large number of rounds to convergence with non-independent identically distributed (non-IID) client data sets and high communication costs per round. We propose adapting FedAvg to use a distributed form of Adam optimization, greatly reducing the number of rounds to convergence, along with the novel compression techniques, to produce communication-efficient FedAvg (CE-FedAvg). We perform extensive experiments with the MNIST/CIFAR-10 data sets, IID/non-IID client data, varying numbers of clients, client participation rates, and compression rates. These show that CE-FedAvg can converge to a target accuracy in up to 6× less rounds than similarly compressed FedAvg, while uploading up to 3× less data, and is more robust to aggressive compression. Experiments on an edge-computing-like testbed using Raspberry Pi clients also show that CE-FedAvg is able to reach a target accuracy in up to 1.7× less real time than FedAvg.

Edge computing is a promising technology to empower the Internet of Things (IoT) by providing additional processing ability, where the tasks can be offloaded to the edge servers for efficient computing. To enable easy management and improve the resource utilization of edge computing, network function virtualization (NFV) is often employed to quickly deploy the requested network functions (NFs) for serving front-end devices. Considering that the edge servers are close to the front-end users, the time-varying geographical distribution of users has a significant influence on the NF deployment in the network of edge servers. Based on this observation, we propose a deep-reinforcement-learning (DRL)-based approach for the NF deployment, which has the following two salient features. First, we employ DRL to estimate the underlying wireless features affected by user mobility, which has a direct impact on the task performance in the edge-IoT systems. Second, we implicitly utilize the multiaccess opportunity to deploy the NFs, considering the estimated features and user requests. Compared to the existing works, the proposed work can significantly improve the resource utilization of edge servers as well as the computational efficiency of IoT tasks. The evaluation results obtained from extensive simulation experiments show that our approach can be well adapted to the time-varying user geodistributions and achieve improved performance in terms of both resource utilization of edge servers and task executions of the IoT devices.

Resource provisioning for cloud computing necessitates the adaptive and accurate prediction of cloud workloads. However, the existing methods cannot effectively predict the high-dimensional and highly-variable cloud workloads. This results in resource wasting and inability to satisfy service level agreements (SLAs). Since recurrent neural network (RNN) is naturally suitable for sequential data analysis, it has been recently used to tackle the problem of workload prediction. However, RNN often performs poorly on learning long-term memory dependencies, and thus cannot make the accurate prediction of workloads. To address these important challenges, we propose a deep Learning based Prediction Algorithm for cloud Workloads (L-PAW). First, a top-sparse auto-encoder (TSA) is designed to effectively extract the essential representations of workloads from the original high-dimensional workload data. Next, we integrate TSA and gated recurrent unit (GRU) block into RNN to achieve the adaptive and accurate prediction for highly-variable workloads. Using real-world workload traces from Google and Alibaba cloud data centers and the DUX-based cluster, extensive experiments are conducted to demonstrate the effectiveness and adaptability of the L-PAW for different types of workloads with various prediction lengths. Moreover, the performance results show that the L-PAW achieves superior prediction accuracy compared to the classic RNN-based and other workload prediction methods for high-dimensional and highly-variable real-world cloud workloads.

Due to the ever-changing system states and various user demands, resource allocation in cloud data center is faced with great challenges in dynamics and complexity. Although there are solutions that focus on addressing this problem, they cannot effectively respond to the dynamic changes of system states and user demands since they depend on the prior knowledge of the system. Therefore, it is still an open challenge to realize automatic and adaptive resource allocation in order to satisfy diverse system requirements in cloud data center. To cope with this challenge, we propose an advantage actor-critic based reinforcement learning (RL) framework for resource allocation in cloud data center. First, the actor parameterizes the policy (allocating resources) and chooses continuous actions (scheduling jobs) based on the scores (evaluating actions) from the critic. Next, the policy is updated by gradient ascent and the variance of policy gradient can be significantly reduced with the advantage function. Simulations using Google cluster-usage traces show the effectiveness of the proposed method in cloud resource allocation. Moreover, the proposed method outperforms classic resource allocation algorithms in terms of job latency and achieves faster convergence speed than the traditional policy gradient method.

In order to provide high-quality services, wireless network providers deploy a large number of base stations per unit area and maintain these base stations operating over a long period of time invariably. This situation resulted in tremendous energy waste and economic cost to service providers. Owing to the conflict between energy consumption and economic benefits, simply reducing energy consumption may cut the profits of network providers. In order to effectively balance the Quality-of-Service (QoS), energy consumption, and profits of wireless networks, we propose a new sleeping scheme for base stations by using Tullock Contest. In the proposed game-theoretical framework, each player is a base station which competes for service revenue by providing services while consuming energy. The stations are classified into two categories, running mode and sleeping mode. The eventual sleeping strategy can be obtained by applying Nash equilibrium. The proposed scheme adjusts the number of sleeping stations to balance the energy consumption and profits of wireless network providers with the premise of ensuring user QoS. The performance of the proposed scheme is evaluated and compared under different system configurations and user traffic patterns.

Content caching is a promising approach in edge computing to cope with the explosive growth of mobile data on 5G networks, where contents are typically placed on local caches for fast and repetitive data access. Due to the capacity limit of caches, it is essential to predict the popularity of files and cache those popular ones. However, the fluctuated popularity of files makes the prediction a highly challenging task. To tackle this challenge, many recent works propose learning based approaches which gather the users' data centrally for training, but they bring a significant issue: users may not trust the central server and thus hesitate to upload their private data. In order to address this issue, we propose a Federated learning based Proactive Content Caching (FPCC) scheme, which does not require to gather users' data centrally for training. The FPCC is based on a hierarchical architecture in which the server aggregates the users' updates using federated averaging, and each user performs training on its local data using hybrid filtering on stacked autoencoders. The experimental results demonstrate that, without gathering user's private data, our scheme still outperforms other learning-based caching algorithms such as m-epsilon-greedy and Thompson sampling in terms of cache efficiency.

Cloud computing and the mobile Internet have been the two most influential information technology revolutions, which intersect in mobile cloud computing (MCC). The burgeoning MCC enables the large-scale collection and processing of big data, which demand trusted, authentic, and accurate data to ensure an important but often overlooked aspect of big data — data veracity. Troublesome internal attacks launched by internal malicious users is one key problem that reduces data veracity and remains difficult to handle. To enhance data veracity and thus improve the performance of big data computing in MCC, this paper proposes a Data Trustworthiness enhanced Reputation Mechanism (DTRM) which can be used to defend against internal attacks. In the DTRM, the sensitivity-level based data category, Metagraph theory based user group division, and reputation transferring methods are integrated into the reputation query and evaluation process. The extensive simulation results based on real datasets show that the DTRM outperforms existing classic reputation mechanisms under bad mouthing attacks and mobile attacks.

Mobile crowdsourcing systems (MCSs) are important sources of information for the positioning services in Internet-of-Things such as gathering location information through employing citizens to participate in data collection. Although MCSs have attracted significant research and development efforts, there are salient open issues and challenges in security and privacy for MCS, which is an essential factor for its success. This paper proposes an integrated strategy named data trustworthiness enhanced crowdsourcing strategy (DTCS) to enhance data trustworthiness and defend against the internal threats for mobile crowdsourcing. The DTCS integrates effective methods including an evaluation scheme for the attribute relevancy and familiarity of participants, a trust relationship establishment method, a group division strategy based on attributes and metagraph, and a core-selecting-based incentive mechanism. The simulation results show that the DTCS improves the performance of the crowdsourcing strategy compared to the state-of-the-art including the TSCM and PPPCM. The DTCS can effectively defend against internal conflicting behavior attacks and collusion attacks to enhance data trustworthiness for mobile crowdsourcing.

The cities in the world are in the process of quick transition toward more smart, automatic, responsive, and flexible societies. The Internet-of-Things (IoT) are expected to improve the intelligence of the cities, promote the interaction between the human and the environment, enhance the reliability, resilience, operational efficiency, and energy efficiency, as well as reduce costs and resource consumption. The development, adoption, and application of IoT technology into smart cities is of huge interest. Local authorities have partnered with startups, technology companies, research institutions, and universities to test and deploy IoT across all dimensions of urban life such as smart grid (SG), smart buildings, water management, connected healthcare and patient monitoring, environment/climate monitoring, connected cars, and smart transportation.

With high variability and correlation in arrival rates and packet sizes, multimedia traffic places a great strain on Wireless Local Area Networks (WLANs) towards provision of satisfactory Quality- of-Service (QoS). Most existing performance models for wireless networks are restricted to unrealistic assumptions where specific traffic characteristics of burstiness, correlation and self-similarity are ignored. This paper proposes an original analytical model as a cost-effective tool to evaluate the performance of WLANs in the presence of heterogeneous multimedia traffic, capturing the burstiness, correlation and self- similarity characteristics using Batch Markovian Arrival Process (BMAP). The model derives important QoS metrics in terms of throughput, end- to-end delay and frame loss probability. Analytical results validated through extensive simulations reveal the degrading effect of burstiness, correlation and heterogeneity of traffic sources on the QoS performance of WLANs.

Information-centric networking (ICN) is an emerging paradigm that decouples content from the host to achieve fast and cost-efficient communication and content distribution in the future Internet. A key feature of ICN is the deployment of ubiquitous in-network caching to speed up service delivery and improve network resource utilisation. ICN caching has been widely studied in terms of caching strategies and caching performance. However, the economic aspect of ICN has received marginal consideration so far, although it is vital to understand the potential cost- efficiency of ICN before its wide deployment in service provider network. To address this issue, we propose a cost-aware caching scheme to study the Quality-of-Service (QoS) and cost of ICN and investigate the inner association between them. Two new models are designed to characterise the cost and QoS of ICN with arbitrary topology under heterogeneous bursty content requests. A multi- objective evolution algorithm is adopted to find the optimal cache resource allocation. Numerical results show the effectiveness of the proposed scheme in achieving cost- efficiency and QoS guarantee in ICN caching.

Summary Monitoring video of city surveillance camera plays an important role in public security and disaster relief, which is often used by first responder teams, such as firefighters and police officers. The first responders in emergency situations require consistent connection with one another and request the remote real‐time monitoring video for effective cooperation and coordination. However, the capacity and privacy of public wireless networks fail to satisfy the requirements in many emergency scenarios, which often leads to exceptionally high traffic loads and insecurity. Device‐to‐device (D2D) communications have been deemed a key solution for this problem, as responders can use D2D links for traffic offloading and secure communications. To investigate the D2D‐based solution for public safety video sharing, this paper focuses on the Focus Geographical Area (FGA) video consisting of multiple camera streams requiring higher bandwidth consumption than that of the traditional single‐camera stream, which attracts a large number of contents delivery requests in emergency situations. This paper develops a new Traffic Burden Switching Markovian (TBSM) model to evaluate the performance of transmitting real‐time FGA video in wireless networks with D2D communications. First, a novel D2D area model is introduced to characterize link‐switching in wireless D2D communication networks. Based on the proposed D2D area model, the state and transition matrix of TBSM model are then derived by jointly considering user mobility, link‐switching, and FGA video view‐switching. Thereafter, some key performance metrics including system offloading ratio, D2D link‐switching ratio, and view‐switching ratio are derived on the basis of coverage probability and ergodic rate. The performance results show the significant varying performance among D2D areas with different geographical locations in D2D enabled wireless networks, which is referred to as multi‐D2D‐area diversity. The excellent match between simulation and model results validates the accuracy of the TBSM model, which can be used to provide guidelines for the deployment and optimization of future wireless video networks with D2D communications.

Embedded multicore computing and applications

Software-Defined Networking (SDN) is an emerging architecture for the next-generation Internet, providing unprecedented network programmability to handle the explosive growth of big data driven by the popularisation of smart mobile devices and the pervasiveness of content-rich multimedia applications. In order to quantitatively investigate the performance characteristics of SDN networks, several research efforts from both simulation experiments and analytical modelling have been reported in the current literature. Among those studies, analytical modelling has demonstrated its superiority in terms of cost-effectiveness in the evaluation of large-scale networks. However, for analytical tractability and simplification, existing analytical models are derived based on the unrealistic assumptions that the network traffic follows the Poisson process, which is suitable to model nonbursty text data, and the data plane of SDN is modelled by one simplified Single-Server Single-Queue (SSSQ) system. Recent measurement studies have shown that, due to the features of heavy volume and high velocity, the multimedia big data generated by real-world multimedia applications reveals the bursty and correlated nature in the network transmission. With the aim of capturing such features of realistic traffic patterns and obtaining a comprehensive and deeper understanding of the performance behaviour of SDN networks, this article presents a new analytical model to investigate the performance of SDN in the presence of the bursty and correlated arrivals modelled by the Markov Modulated Poisson Process (MMPP). The Quality-of-Service performance metrics in terms of the average latency and average network throughput of the SDN networks are derived based on the developed analytical model. To consider a realistic multiqueue system of forwarding elements, a Priority-Queue (PQ) system is adopted to model the SDN data plane. To address the challenging problem of obtaining the key performance metrics, for example, queue-length distribution of a PQ system with a given service capacity, a versatile methodology extending the Empty Buffer Approximation (EBA) method is proposed to facilitate the decomposition of such a PQ system to two SSSQ systems. The validity of the proposed model is demonstrated through extensive simulation experiments. To illustrate its application, the developed model is then utilised to study the strategy of the network configuration and resource allocation in SDN networks.

Multi-hop wireless networks (MWNs) have been widely accepted as an indispensable component of next-generation communication systems due to their broad applications and easy deployment without relying on any infrastructure. Although showing huge benefits, MWNs face many security problems, particularly the internal multi-layer security threats being one of the most challenging issues. Since most security mechanisms require the cooperation of nodes, characterizing and learning actions of neighboring nodes and the evolution of these actions over time is vital to constructing an efficient and robust solution for security-sensitive applications such as social networking, mobile banking and teleconferencing. In this paper, we propose a new dynamic Cross-layer Reputation computation Model (CRM) to dynamically characterize and quantify actions of nodes. CRM couples an uncertainty-based conventional layered reputation computation model (RCM) with cross-layer design and multi-level security technology to identify malicious nodes and preservation of security against internal multi-layer threats. Simulation results and performance analyses demonstrate that CRM can provide rapid and accurate malicious node identification and management, and implement the preservation of security against the internal multi-layer and bad-mouthing attacks more effectively and efficiently than existing models.

The rapid development in wireless technologies and multimedia services has given rise to new requirements for the Internet, such as supporting billions of mobile devices and transmitting huge amount of multimedia content in real time. Content-Centric Networking (CCN), a future Internet architecture for efficient content dissemination, has been attracting ever-increasing attention from both academia and industry. In this paper, a new analytical model is developed as a cost-effective tool to investigate the performance of caching in CCN under bursty content requests. The accuracy of the model is validated through comparing the analytical results with those obtained from the extensive simulation experiments. As an example of its applications, the analytical model is used to investigate the effects of the cache size, content size, and bursty content requests on the cache hit ratio in CCN.

SUMMARY Supported by the IEEE 802.15.4 standard, embedded sensor networks have become popular and been widely deployed in recent years. The IEEE 802.15.4 medium access control (MAC) protocol is uniquely designed to meet the desirable requirements of the low end‐to‐end delay, low packet loss, and low power consumption in the low rate wireless personal areas networks (LR‐WPANs). This paper develops an analytical model to quantify the key performance metrics of the MAC protocol in LR‐WPANs with bursty ON–OFF traffic. This study fills the gap in the literature by removing the assumptions of saturated traffic or nonbursty unsaturated traffic conditions, which are unable to capture the characteristics of bursty multimedia traffic in sensor networks. This analytical model can be used to derive the QoS performance metrics in terms of throughput and total delay. The accuracy of the model is verified through NS‐2 ( http://www.isi.edu/nsnam/ns/ ) simulation experiments. This model is adopted to investigate the performance of the MAC protocol in LR‐WPANs under various traffic patterns, different loads, and various numbers of stations. Numerical results show that the traffic patterns and traffic burstiness have a significant impact on the delay performance of LR‐WPANs. Copyright © 2012 John Wiley & Sons, Ltd.

Wireless Mesh Networks (WMNs) have drawn much attention for emerging as a promising technology to meet the challenges in next generation networks. Security and privacy protection have been the primary concerns in pushing the success of WMNs. However, the solutions proposed to ensure the security of the routing protocol and the privacy information in WMNs are still not robust. In this paper, we propose a role based privacy-aware secure routing protocol (RPASRP), which combines a new dynamic reputation mechanism with the role based multi-level security technology and a novel hierarchical key management protocol to defend against the internal attacks and to achieve better security and privacy protection. Simulation results show that RPASRP implements the security and privacy protection against the inside attacks more effectively and efficiently and performs better than the classical hybrid wireless mesh protocol (HWMP) in terms of packet delivery ratio.

Abstract Contention free bursting (CFB) and block acknowledgement (BACK) are two innovative burst transmission schemes specified in the IEEE 802.11e standard for reducing the contention overheads and further improving the channel utilization of wireless local area networks (WLANs). Existing studies on performance analysis of the CFB and BACK schemes have been primarily focused on the system throughput and have not taken into account the realistic factors, such as unsaturated traffic loads and finite buffer capacity. To fill this gap, this paper proposes a new and comprehensive analytical model for evaluating the Quality‐of‐Service (QoS) metrics including throughput, end‐to‐end delay, and frame loss probability of both burst transmission schemes under unsaturated traffic conditions. The proposed model is validated through extensive simulation experiments and then is used to conduct performance analysis and comparison of the burst transmission schemes under various working conditions. The analytical results reveal that (1) both CFB and BACK schemes can substantially improve the QoS performance; (2) BACK scheme outperforms the CFB scheme when the transmission opportunity (TXOP) limit exceeds a threshold; (3) the analytical model can be used to identify the optimal configuration of system parameters for the burst transmission schemes subject to QoS constraints. Copyright © 2010 John Wiley & Sons, Ltd.

The explosive growth in advanced multimedia applications poses great challenges for design and deployment of wireless communication networks. Transmission Opportunity (TXOP) is a promising MAC protocol extension for provisioning of differentiated Quality-of-Service (QoS) in multimedia WLANs. However, for analytical tractability and simplicity, most existing performance models of TXOP have been restricted to unrealistic working scenarios where the traffic is saturated or follows a Poisson process, which is unable to capture the heterogeneous characteristics of multimedia traffic. To fill this gap, this paper proposes an original analytical model for TXOP in WLANs with heterogeneous stations in the presence of multimedia applications. Specifically, the traffic generated by heterogeneous stations with background, voice and video applications is modelled by the non-bursty Poisson, bursty Markov-Modulated Poisson Process, and fractal self-similar process, respectively. QoS measures including throughput, end-to-end delay, and frame loss probability are derived. The extensive comparison between the analytical results and those obtained from simulation experiments subject to the traffic parameters of real-world voice and video sources validates the accuracy of the developed model for WLANs with practical multimedia applications. The performance results reveal the importance of taking into account the heterogeneous stations for the accurate evaluation of TXOP in wireless multimedia networks.

The growing proliferation of wireless devices in contemporary wireless networks requires more spectrum usage. As a consequence, spectrum bands are pressingly getting congested. However, a number of frequency bands licensed to operators are under utilized for transmission. Cognitive Radio (CR), as a promising technique for improving spectrum utilization, can dynamically allocate spectrum. In this paper, we investigate the performance of a CR network composed of a primary/licensed user and a number of secondary/unlicensed users, which are subject to self-similar traffic flows and contend for a unique channel. An analytical model is developed to isolate the primary and secondary users from the original networks. Further, we address the queueing performance of individual secondary users by employing a decomposition approach. The comparison between analytical and simulation results validates the accuracy of the developed model.

Admission control is an important mechanism for the provisioning of the user-perceived Quality-of-Service (QoS) in the IEEE 802.11e Wireless Local Area Networks (WLANs). In this paper, we present an efficient admission control scheme based on analytical modelling and non-cooperative game theory where the Access Point (AP) and new users are the players. The decision of admission control is made by virtue of the strategies to maximize the utilities of the players, which are determined by the QoS performance metrics in terms of the end-to-end delay and frame loss probability. To obtain these required performance metrics, we develop a new analytical model incorporating the Contention Window (CW) and Transmission Opportunity (TXOP) differentiation schemes in the IEEE 802.11e protocol under unsaturated working conditions. The efficiency of the proposed admission control scheme is validated via NS-2 simulation experiments. The numerical results demonstrate that the proposed admission control scheme can maintain the system operation at an optimal point where the utility of the AP is maximized subject to the QoS constraints of both the real-time and non-real-time users.

The IEEE 802.15.4 standard defines physical layer and Medium Access Control (MAC) layer protocols for the Low Rate Wireless Personal Areas Network (LR-WPAN). The analytical models of 802.15.4 MAC have been primarily developed under the assumptions of the ideal channels or uniform error channels which fail to capture the characteristics of bursty and correlated channel errors in the practical wireless network environment. In this paper, we propose an analytical model for 802.15.4 MAC in LR-WPAN in the presence of bursty error channels. This model can be adopted to obtain the Quality-of-Service (QoS) performance metrics in terms of throughput, service time, and total delay. Utilizing the analytical model, we investigate the QoS performance of 802.15.4 MAC under various traffic loads, backoff parameters, numbers of stations, and channel conditions.

To support the differentiated Quality-of-Service (QoS) and improve the utilization of the scarce wireless bandwidth, the IEEE 802.11e standard specifies an efficient burst transmission scheme referred to as the transmission opportunity (TXOP). Recently, analytical models have been reported to evaluate the performance of the TXOP scheme. However, most of these models were developed under the assumptions of the ideal channels or uniform error channels which fail to capture the characteristics of bursty and correlated channel errors in the practical wireless environment. In this paper, we propose an analytical model for the TXOP scheme in WLANs in the presence of bursty error channels. To this end, the transmission queue of each station is modelled by a two-state continuous time Markov chain. This model can be adopted to obtain the performance metrics including the throughput and buffer overflow probability. The accuracy of the analytical model is validated via NS-2 simulation experiments. Utilizing the proposed model, we investigate the impact of traffic loads, TXOP limit, and the number of stations on the performance of the TXOP scheme under various channel conditions.

The enhanced distributed channel access (EDCA) protocol has been proposed to support differentiated quality-of-service (QoS) of wireless local area networks (WLANs). edca introduces a promising scheme, transmission opportunity (TXOP), which enables a station to transmit multiple frames consecutively in a burst upon winning the contention of the channel. The analytical models of the TXOP scheme have been mainly developed under the assumptions that the traffic generated by the stations is saturated or follows a non-bursty Poisson arrival process. These assumptions are unable to capture the characteristics of heterogeneous multimedia traffic. This paper proposes a new analytical model for the TXOP scheme in WLANs comprising heterogeneous classes of stations with multimedia applications. The traffic of such applications is modelled by the non-bursty Poisson, bursty Markov-modulated Poisson process (MMPP), and fractal self-similar traffic. The accuracy of the proposed model is validated through extensive NS-2 simulation experiments.

Arbitrary inter-frame space (AIFS), contention window (CW) and transmission opportunity (TXOP) are three important quality-of-service (QoS) differentiation schemes specified in the IEEE 802.11e enhanced distributed channel access (EDCA) protocol for wireless local area networks (WLANs). Analytical models of EDCA in the current literature have been mainly developed for the AIFS, CW, and TXOP schemes, separately. This study proposes a comprehensive analytical model to accommodate the combination of these three QoS schemes in WLANs under unsaturated traffic loads. We derive the performance metrics in terms of throughput, end-to- end delay, and frame loss probability. Extensive simulation experiments are conducted to validate the accuracy of the model.

Transmission opportunity (TXOP) is a new scheme specified in the IEEE 802.11e standard which enables a station to transmit multiple frames consecutively within a burst after it gains the channel. Realistic traffic loads in wireless local area networks (WLANs) with multimedia applications often exhibit the bursty and self-similar properties which imply the frequent occurrence of the large bursts of frame arrivals and thus require the TXOP scheme to be dynamically adapted to the traffic characteristics. This paper presents a dynamic TXOP scheme which adjusts the TXOP limits of mobile stations according to the current status of their transmission queues. We further develop an analytical model to evaluate the performance of this scheme under self-similar traffic. QoS performance metrics in terms of throughput, end-to-end delay, and frame loss probability are derived and validated via NS2 simulation experiments. The numerical results reveal that the dynamic TXOP scheme achieves the better QoS than the original one under self-similar traffic.

Contention free bursting (CFB) and block acknowledgement (BACK) are two efficient burst transmission schemes specified in the IEEE 802.11e standard for improving the utilization of scarce wireless bandwidth. Most existing performance models of the CFB and BACK schemes have focused on the analysis of system throughput and have not taken the realistic factors, such as unsaturated traffic loads and finite buffer capacity, into account. In this paper, we propose a comprehensive analytical model for evaluating the throughput, end-to-end delay, and loss probability of burst transmission schemes in wireless local area networks (WLANs) under unsaturated traffic conditions. The accuracy of the proposed model is validated through extensive ns2 simulation experiments. Performance results obtained from the model demonstrate that both schemes can substantially improve network performance. Moreover, the BACK scheme outperforms the CFB scheme when the transmission opportunity (TXOP) limit exceeds a certain threshold.

As the access point (AP) is responsible for forwarding all the frames to and from the infrastructure-based WLANs, the network performance is significantly degraded by the unbalanced traffic loads. A potential solution is to assign different transmission opportunities (TXOPs) to AP and other mobile stations, respectively. This study develops an analytical model to investigate the performance of infrastructure-based WLANs with the TXOP differentiation under the unbalanced traffic loads. The analytical model is validated through extensive ns2 simulation experiments.

Contention free bursting (CFB) is an innovative quality-of-service (QoS) scheme specified in the IEEE 802.11e standard. To reduce the contention overheads, this scheme enables the stations that gain the channel to transmit multiple frames back-to-back in a burst. Most existing analytical models of the CFB scheme have been developed under the assumption of identical stations with saturated traffic loads. In this paper, we present an analytical model for investigating the performance metrics of throughput, end-to-end delay, loss probability, and energy consumption of the CFB scheme in the presence of nonidentical stations with different traffic generation rates. The model is validated against extensive ns2 simulation experiments. Numerical performance results demonstrate the efficiency of the CFB scheme for improving the network performance.