Point cloud completion aims to reconstruct complete 3D shapes from partial observations, which is a challenging problem due to severe occlusions and missing geometry. Despite recent advances in multimodal techniques that leverage complementary RGB images to compensate for missing geometry, most methods still follow a Completion-by-Inpainting paradigm, synthesizing missing structures from fused latent features. We empirically show that this paradigm often results in structural inconsistencies and topological artifacts due to limited geometric and semantic constraints. To address this, we rethink the task and propose a more robust paradigm, termed Completion-by-Correction, which begins with a topologically complete shape prior generated by a pretrained image-to-3D model and performs feature-space correction to align it with the partial observation. This paradigm shifts completion from unconstrained synthesis to guided refinement, enabling structurally consistent and observation-aligned reconstruction. Building upon this paradigm, we introduce PGNet, a multi-stage framework that conducts dual-feature encoding to ground the generative prior, synthesizes a coarse yet structurally aligned scaffold, and progressively refines geometric details via hierarchical correction. Experiments on the ShapeNetViPC dataset demonstrate the superiority of PGNet over state-of-the-art baselines in terms of average Chamfer Distance (-23.5%) and F-score (+7.1%).

Federated learning (FL) is revolutionizing machine learning by enabling multiple decentralized clients to collaboratively train a shared model. In mobile scenarios, client devices exchange model parameters with a central server via wireless channels. However, designing efficient wireless FL (WFL) is challenging due to limited energy and channel capacity. To fully utilize communication resources, over-the-air (OTA) computation has been introduced, allowing direct aggregation of analog parameter signals. However, it conceals clients’ information from the server, making advanced client selection strategies, e.g., cluster-based client selection, and sparsification compression algorithms like TopK inapplicable. To address these limitations, we propose the WFL with Voting-based Clustering (WFL-VC) algorithm, which can integrate advanced client selection and the TopK model sparsification algorithm with OTA. WFL-VC consists of two phases: 1) Phase 1: clients vote on significant parameters based on local models, allowing the server to select clients and identify the global Topk parameters; and 2) Phase 2: the selected clients upload model update parameters with globally aligned indices for over-the-air computation at the server. By combining OTA computation with cluster-based client selection and TopK sparsification, WFL-VC substantially reduces the energy consumption of OTA-based WFL. Extensive experiments on real-world datasets show that WFL-VC outperforms competitive baselines while consuming considerably less energy.

Accurate anomaly recognition in video surveillance is critical to ensuring public safety, infrastructure protection, and intelligent security operations. However, existing methods often fail to generalize across diverse and dynamic environments due to their limited capacity to model complex spatio-temporal patterns. In this paper, we propose a novel Graph-Based Temporal Attention Memory Network (G-TAMNet) that significantly advances video anomaly detection by capturing intricate temporal dependencies and spatial relationships. By integrating temporal self-attention into a graph convolutional network (GCN) framework, our model enhances the learning of salient and contextually relevant features that traditional approaches tend to overlook. Furthermore, to enable deployment in resource-constrained settings, such as IoTbased surveillance systems, we incorporate model quantization strategies that reduce computational overhead without compromising detection accuracy. Extensive evaluations of three widely used benchmarks, UCFCrime, LAD-2000, and RWF-2000 the effectiveness of the proposed G-TAMNet model, achieving accuracy, precision, recall, and F1-scores of 54.3% / 61.1% / 59.01% / 61.1%,79.3% / 69.1% / 70.0% / 69.1%,and 94.0% / 94.0% / 94.2% / 94.1%, respectively. These results reflect consistent performance gains of 3.3%, 9.9%, and 0.74% in accuracy over existing state-ofthe-art methods on the corresponding datasets. Such improvements underscore the robustness, scalability, and practical viability of GTAMNet for real-time anomaly detection in resource-constrained IoT surveillance systems. In addition, its reliable generalization across diverse environments highlights the potential of the model to advance intelligent security analytics and transform real-world applications in the domain of information forensics.

To underscore the significance of the interactive frequency among diverse vertices in each snapshot, prior research has extended the$k$-core of general graphs to the$(k,h)$-core of temporal graphs, in which each vertex has at least$k$neighbors and is connected by at least$h$edges to each of these neighbors. Due to the numerous combinations of$k$and$h$, the quantity of$(k,h)$-cores is substantial, which necessitates considerable time and space for querying and decomposition. As a temporal graph evolves, for instance, with edges being inserted or removed from the previous snapshot, the affected$(k,h)$-cores must also be updated to reflect the latest structure. To address these challenges, we initially develop a novel$(k,h)$-core storage index that exhibits excellent query performance while consuming linear space regarding the graph size. Subsequently, we design an efficient decomposition algorithm to extract$(k,h)$-cores from a snapshot. Following this, we offer two maintenance algorithms to manage temporal graph evolution. Finally, we validate the effectiveness of our proposed methods on actual temporal graphs. Experimental results indicate that our methods surpass existing techniques by two orders of magnitude.

Online video streaming has evolved into an integral component of the contemporary Internet landscape. Yet, the disclosure of user requests presents formidable privacy challenges. As users stream their preferred online videos, their requests are automatically seized by video content providers, potentially leaking users’ privacy. Unfortunately, current protection methods are not well-suited to preserving user request privacy from content providers while maintaining high-quality online video services. To tackle this challenge, we introduce a novel Privacy-Preserving Video Fetching (PPVF) framework, which utilizes trusted edge devices to pre-fetch and cache videos, ensuring the privacy of users’ requests while optimizing the efficiency of edge caching. More specifically, we design PPVF with three core components: 1)Online privacy budget scheduler, which employs a theoretically guaranteed online algorithm to select non-requested videos as candidates with assigned privacy budgets. Alternative videos are chosen by an online algorithm that is theoretically guaranteed to consider both video utilities and available privacy budgets. 2)Noisy video request generator, which generates redundant video requests (in addition to original ones) utilizing correlated differential privacy to obfuscate request privacy. 3)Online video utility predictor, which leverages federated learning to collaboratively evaluate video utility in an online fashion, aiding in video selection in 1) and noise generation in 2). Finally, we conduct extensive experiments using real-world video request traces from Tencent Video and Netflix. The results demonstrate that PPVF effectively safeguards user request privacy while upholding high video caching performance.

To mitigate the rising concern on privacy infringement in recommenders, federated recommender (FRec) boosted with local differential privacy (LDP) has been proposed, in which each user privately retains his (or her) dataset, and only exposes model parameters distorted by LDP to a parameter server (PS). Although such kind of solution can largely preserve data privacy, it overlooks the potential unfairness issue. For example, a user can become a free-rider by setting an extremely small privacy budget to completely distort his (or her) model such that the model training is mainly contributed by other users. To guarantee fairness, we design a fairness-aware federated recommender framework called FFRec when users adopt heterogeneous privacy budgets. In FFRec, fairness implies that clients with higher utilities will have more opportunities to participate in training. We integrate fairness into FFRec by taking both sample size and privacy requirements into account. Specifically, a user is selected by the PS to participate in model training based on his (or her) sample size and potential noise influence by LDP and cumulative participation counts. We formulate the fairness-aware client selection problem as an integer programming problem and then reduce it into a submodular problem which has been proven to be NP-hard. To resolve this problem, we employ an approximation algorithm with an approximation ratio of 1 − e−12. Extensive experiments with popular field-measured datasets (i.e., Movielens and Netflix) demonstrate that FFRec can improve fairness by 10.3%-38.5% while guaranteeing high recommendation accuracy

As users request their preferred metaversal media, e.g., 360-degree video, user requests tracked by metaverse content providers (MCPs) pose significant privacy leakage risks. Unfortunately, existing privacy-enhancing techniques are largely ineffective in protecting user privacy for metaversal content requests since these requests cannot be easily altered or concealed by users and must remain visible to MCPs to ensure accurate content delivery. To safeguard user privacy in metaverse multimedia services (MMS), one practical approach is pre-fetching multimedia content (e.g., short videos, video patches in 360$^\circ$videos) that is not directly related to users' interests, thereby preventing MCPs from accurately inferring user preferences. However, plain pre-fetching strategies encounter a critical trade-off between privacy protection and edge caching performance given that MCPs often rely on edges for distributing metaverse content. In this paper, we propose acache-friendly and privacy-awarecontent pre-fetching(CRACE) algorithm for user devices (UDs) along with a complementary caching algorithm for edge caches (ECs). CRACE effectively mitigates privacy leakage in metaverse content requests while minimally impacting caching performance. Specifically, we introduce a novel privacy model to guide pre-fetching decisions and formulate a Stackelberg game to analyze strategic interactions between UDs and ECs. We derive optimal strategies that maximize their respective utilities and demonstrate the existence and uniqueness of the Stackelberg equilibrium. Extensive experiments conducted with real-world data demonstrate that CRACE significantly enhances privacy protection, reducing privacy disclosure by up to 59.03% compared to baseline algorithms, with negligible impact on the edge caching performance.

Managing evolving graph data presents substantial challenges in storage and privacy, and training graph neural networks (GNNs) on such data often leads to catastrophic forgetting, impairing performance on earlier tasks.Despite existing continual graph learning (CGL) methods mitigating this to some extent, they rely on centralized architectures and ignore the potential of distributed graph databases to leverage collective intelligence.To this end, we propose Federated Continual Graph Learning (FCGL) to adapt GNNs across multiple evolving graphs under storage and privacy constraints.Our empirical study highlights two core challenges: local graph forgetting (LGF), where clients lose prior knowledge when adapting to new tasks, and global expertise conflict (GEC), where the global GNN exhibits sub-optimal performance in both adapting to new tasks and retaining old ones, arising from inconsistent client expertise during server-side parameter aggregation.To address these, we introduce POWER, a framework that preserves experience nodes with maximum local-global coverage locally to mitigate LGF, and leverages pseudo-prototype reconstruction with trajectory-aware knowledge transfer to resolve GEC.Experiments on various graph datasets demonstrate POWER's superiority over federated adaptations of CGL baselines and vision-centric federated continual learning approaches.

Recent advances in graph machine learning have shifted to data-centric paradigms, driven by two emerging research fields: (1) Federated graph learning (FGL) facilitates multi-client collaboration but struggles with data and task heterogeneity, resulting in limited practicality; (2) Graph foundation model (GFM) enables desirable domain generalization but is typically confined to single-machine training, neglecting the potential of cross-silo data and computational resources. It is evident that these two paradigms are complementary, and their integration offers substantial advantages. Motivated by this, we present a pioneering study about the federated graph foundation model (FedGFM), a novel decentralized GFM training paradigm. Despite the promising vision of FedGFM, knowledge entanglement has emerged as a critical challenge, where multi-domain knowledge is encoded into indistinguishable representations, thereby limiting downstream adaptation. To this end, we propose FedGFM+, an effective FedGFM framework with two key modules to mitigate knowledge entanglement in a dual-pronged manner. (1) AncDAI: From a global perspective, we introduce a novel anchor-based domain-aware initialization strategy. Before pre-training, each client encodes its local graph into a domain-specific prototypes, which serve as semantic anchors in the representation space. Around each anchor, we construct synthetic embeddings to initialize the global model. We theoretically show that these prototypes are distinguishable across domains, and the initialization provides a strong inductive bias that facilitates disentanglement of domain-specific knowledge. (2) AdaDPP: From a local perspective, during pre-training, each client independently learns a lightweight graph prompt that captures domain semantic preferences. During fine-tuning, prompts from all clients are aggregated into an adaptive domain-sensitive prompt pool, from which the GFM selects relevant prompts to augment the target graph’s attributes, thereby improving the downstream adaptation. FedGFM+ is extensively evaluated on 8 diverse benchmarks spanning multiple domains and tasks, outperforming 20 baselines from isolated supervised learning, FGL, and federated variants of centralized GFM paradigms.

The data stream generated by users on web applications is often collected using a local differential privacy (LDP) approach to ensure privacy. This approach offers rigorous theoretical guarantees and low computational overhead, albeit at the expense of data utility. Data utility encompasses both the value of individual data points and the temporal relevance that exists between them, but existing studies primarily focus on enhancing the former utility while neglecting the latter. Furthermore, the collected data often requires cleaning, and we have demonstrated through a case study that data stream lacking time relevance poses a significant risk to users' privacy during the cleaning process. In this paper, for the first time we present an online LDP publishing mechanism while preserving the inherent temporal relevance for the infinite stream, called the Sampling Period Perturbation Algorithm (SPPA). Specifically, we model the temporal relevance between data points as the Fourier interpolation function, resulting in a computational complexity reduction from O(n2) to O(n log n) when compared with the conventional Markov approach in the offline setting. To strike a better balance between privacy and utility, we add noise to the sampling period due to its minimal impact on sensitivity, which is analyzed by our novel concepts of (ε,τ)-temporal indistinguishability and (ε,w,τ)-event LDP. Through extensive experiments, SPPA exhibits superior performance in terms of both data utility and privacy preservation compared to the state-of-the-art baselines. In particular, when ε=1, compared with the state-of-the-art baseline, SPPA diminishes the MSE by up to 64.2%, and raises the event monitoring efficiency by up to 21.4%.

Federated learning (FL) gained importance in sensitive Internet of Things (IoT) environments by creating a privacy-preserving ecosystem where participants share machine-learning models instead of raw data. However, FL shifts data control away from the server, exposing it to non-independent and identically distributed (non-IID) problems caused by biased clients (IoT devices). This hinders the learning process by increasing execution time and cost. Current solutions alter the FL structure or compromise privacy by offloading clients’ raw data to an external server. To mitigate these limitations, this article proposes a solution to the non-IID problem by introducing an initialization phase, orchestrated by the server, that constructs high-quality initial models. These models can boost FL accuracy and convergence, regardless of whether IoT participants exhibit non-IID properties. Our proposed initialization scheme involves clients training over the same model sequentially, lessening the impact of aggregation, a primary cause of model degradation in federated approaches. Furthermore, a regulator algorithm deployed on the server maintains model integrity and mitigates catastrophic forgetting, enhanced by a client selection process that emphasizes the compatibility of IoT clients to cooperate effectively. Moreover, we devise an optimization scheme based on clustering and genetic algorithms to reduce the selection time while ensuring optimal performance in IoT networks. Experiments on MNIST, KDD, and CIFAR10 data sets show promising results in terms of initial model resiliency against catastrophic forgetting and non-IID settings. Additionally, our findings suggest that our approach can significantly enhance FL training in IoT applications by achieving 40% higher initialization accuracy and a 20% average improvement in end results compared to conventional methods, all while reducing computation time by 80% compared to similar approaches.

Federated learning (FL) has attracted tremendous attention due to its capability to preserve data privacy. In FL, a parameter server (PS) without accessing clients' raw data can assist decentralized clients in completing model training by aggregating and distributing model parameters for multiple iterations. From the clients' perspective, exposing model parameters to the PS can still result in privacy leakage. To further enhance privacy protection, differentially private federated learning (DPFL) is invented, in which clients add differentially private (DP) noises to distort their parameters to be exposed. However, the main challenge of DPFL lies in inferior model accuracy due to DP noises. To overcome this challenge, in this paper we propose a novel algorithmic framework for DPFL, which is called CODP, by cascading and offsetting DP noises between iterations. In existing works, each DPFL client only considers how to protect its model parameters based on the number of iterations to expose parameters overlooking the underlying relation of model parameters in consecutive iterations. The novelty of CODP lies in cascading DP noises from each iteration to its subsequent iteration so that DP noises can be offset in the subsequent iteration, and hence model accuracy can be improved. Additionally, we theoretically prove that CODP can substantially improve the convergence rate of DPFL without compromising privacy preservation by leveraging the most widely used Laplace and Gaussian mechanisms, respectively. We conduct comprehensive experiments using MNIST, Fashion-MNIST, and Lending Club datasets to demonstrate that the model accuracy of DPFL can be remarkably improved by CODP with a fixed privacy budget.

The demand for mobile video streaming has seen a substantial surge in recent years. However, current platforms heavily depend on network capacity to ensure the delivery of high-quality video streams. The emergence of neural-enhanced video streaming presents a promising solution to address this challenge by leveraging client-side computation, thereby reducing bandwidth consumption. Nonetheless, deploying advanced super-resolution (SR) models on mobile devices is hindered by the computational demands of existing SR models. In this paper, we propose REM, a novel neural-enhanced mobile video streaming framework. REM utilizes a customized lookup table to facilitate real-time neural-enhanced video streaming on mobile devices. Initially, we conduct a series of measurements to identify abundant macroblock redundancies across frames in a video stream. Subsequently, we introduce a dynamic macroblock selection algorithm that prioritizes important macroblocks for neural enhancement. The SR-enhanced results are stored in the lookup table and efficiently reused to meet real-time requirements and minimize resource overhead. By considering macroblock-level characteristics of the video frames, the lookup table enables efficient and fast processing. Additionally, we design a lightweight macroblock-aware SR module to expedite inference. Finally, we perform extensive experiments on various mobile devices. The results demonstrate that REM enhances overall processing throughput by up to 10.2 times and reduces power consumption by up to 58.6% compared to state-of-the-art methods. Consequently, this leads to a 38.06% improvement in the quality of experience for mobile users.

Currently, beamforming antenna array technologies are of utmost importance in 5G communication systems. These technologies are essential for optimizing the coverage and signal quality of the cellular network. However, the optimization of broadcast beams presents significant challenges due to the complex strategy profile space. Each beam can be configured with different widths and heights, making it difficult for conventional algorithms to handle. To address this issue, we propose a novel approach called Multi-Agent Moth-Flame Reinforcement Learning (MAMF-RL) algorithm for broadcast beam optimization. MAMF-RL combines reinforcement learning and moth-flame optimization algorithms to interactively search for the optimal broadcast beams. By decomposing the problem into multiple single-sector antenna configuration problems, MAMF-RL effectively reduces the algorithm complexity. We conducted experiments utilizing real data in an 18-sector wireless coverage area. To evaluate the performance of our proposed method, we compared it with traditional methods such as the particle swarm algorithm. The results demonstrate that our MAMF-RL model achieves an average coverage rate of 1.82% higher and a 13.74% lower overlapping coverage rate compared to traditional methods.

The traditional recommendation system provides web services by modeling user behavior characteristics, which also faces the risk of leaking user privacy. To mitigate the rising concern on privacy leakage in recommender systems, federated learning (FL) based recommendation has received tremendous attention, which can preserve data privacy by conducting local model training on clients. However, devices (e.g., mobile phones) used by clients in a recommender system may have limited capacity for computation and communication, which can severely deteriorate FL training efficiency. Besides, offloading local training tasks to the cloud can lead to privacy leakage and excessive pressure to the cloud. To overcome this deficiency, we propose a novel federated cloud-edge recommendation framework, which is called FCER, by offloading local training tasks to powerful and trusted edge servers. The challenge of FCER lies in the heterogeneity of edge servers, which makes the parameter server (PS) deployed in the cloud face difficulty in judiciously selecting edge servers for model training. To address this challenge, we divide the FCER framework into two stages. In the first pre-training stage, edge servers expose their data statistical features protected by local differential privacy (LDP) to the PS so that edge servers can be grouped into clusters. In the second training stage, FCER activates a single cluster in each communication round, ensuring that edge servers with statistical homogenization are not repeatedly involved in FL. The PS only selects a certain number of edge servers with the highest data quality in each cluster for FL. Effective metrics are proposed to dynamically evaluate the data quality of each edge server. Convergence rate analysis is conducted to show the convergence of recommendation algorithms in FCER. We also perform extensive experiments to demonstrate that FCER remarkably outperforms competitive baselines by$3.85\%-9.14\%$on HR@10 and$1.46\%-11.77\%$on NDCG@10.

Deep learning (DL) has found extensive application in supporting various mobile applications. The efficient execution of DL tasks is paramount for ensuring the effectiveness of AI-driven mobile applications. While previous research has predominantly focused on minimizing the completion time of DL tasks, the associated cost of execution has often been overlooked. Nonetheless, cost becomes a critical factor, particularly when utilizing DL infrastructure rented from third-party cloud service providers. In this paper, we propose a cost-aware resource scheduling framework named CRS for orchestrating DL task execution in mobile cloud systems. Our aim is to minimize server rental costs by strategically orchestrating DL jobs with diverse deadlines and workload scales across rented cloud servers. We formally define the problem and prove its NP-hardness by reducing it to a multiple knapsack problem (MKP). To solve this problem, we devise an approximation algorithm with a guaranteed upper bound performance ratio of$1+\frac{1}{e-1}$. We evaluate CRS against state-of-the-art baselines through simulations of various job arrival scenarios in a real elastic mobile cloud system. The results demonstrate that CRS, on average, reduces rental costs by 45.1% compared to other baselines, while simultaneously achieving a shorter average job completion time (JCT) and maximum job completion time (i.e., makespan).

Existing Unsupervised Domain Adaptation (UDA) methods often fall short in fully leveraging contextual information from the target domain, leading to suboptimal decision boundary separation during source and target domain alignment. To address this, we introduce GrabDAE, an innovative UDA framework designed to tackle domain shift in visual classification tasks. GrabDAE incorporates two key innovations: the Grab-Mask module, which blurs background information in target domain images, enabling the model to focus on essential, domain-relevant features through contrastive learning; and the Denoising Auto-Encoder (DAE), which enhances feature alignment by reconstructing features and filtering noise, ensuring a more robust adaptation to the target domain. These components empower GrabDAE to effectively handle unlabeled target domain data, significantly improving both classification accuracy and robustness. Extensive experiments on benchmark datasets, including VisDA-2017, Office-Home, and Office31, demonstrate that GrabDAE consistently surpasses state-of-the-art UDA methods, setting new performance benchmarks. By tackling UDA's critical challenges with its novel feature masking and denoising approach, GrabDAE offers both significant theoretical and practical advancements in domain adaptation.

Hierarchical federated learning (HFL) improves the scalability and efficiency of traditional federated learning (FL) by incorporating a hierarchical topology into the FL framework. In a typical HFL system, clients are divided into multiple tiers, and the training process involves both local and global model aggregation. However, existing HFL approaches have several significant drawbacks. Firstly, the root parameter server (PS) is vulnerable to single-point failure and also acts as a bottleneck for global aggregation. Additionally, frequent global aggregation over the wide area network (WAN) incurs substantial communication costs, which negatively affect training efficiency. In this paper, we propose a novel HFL algorithm called CPFedAvg to address the aforementioned challenges. CPFedAvg introduces a root-free hierarchical topology, where the top tier consists of multiple PSes, effectively resolving the issues associated with the root PS. Additionally, we substitute the expensive global aggregation with parameter mixing operations between the PSes in the top tier. We analyze the convergence rate of CPFedAvg under non-convex loss. Based on this analysis, we formulate a convex optimization problem to optimize the frequency of executing local aggregations between consecutive parameter mixing operations. To simulate real-world communication networks, we develop FedNetSimulator to simulate a diverse range of FL communication processes. Finally, we conduct extensive experiments using real datasets (i.e., CIFAR-10 and CIFAR-100). The experimental results demonstrate that CPFedAvg can improve model accuracy by up to 18% and the speedup can be as high as 6 compared with the state-of-the-art baselines.

In recent years, the integration of mobile edge computing (MEC) and non-orthogonal multiple access (NOMA) has gained significant attention for its potential to reduce energy consumption and offloading latency in future wireless networks. While NOMA can enhance system capacity, accommodating multiple users on the same channel may lead to decoding inaccuracies and reduced offloading accuracy. To tackle these problems, this paper proposes a multi-user offloading model that combines NOMA and orthogonal multiple access (NOMA-OMA) to optimize resource allocation. Users are divided into groups based on their geographical locations, with each group further divided into subgroups. OMA is used within each subgroup, while NOMA is employed between different subgroups to achieve joint multi-user offloading. We divide the optimization problem into two sub-problems, namely power and time allocation between different subgroups and delay allocation within the same subgroup. Closed-form expressions for the two sub-problems are derived. The proposed method achieves optimal system energy consumption while increasing the number of users and maintaining low system complexity. Simulation results demonstrate the effectiveness of the proposed method.

To mitigate the rising concern of privacy leakage, the federated recommender (FR) paradigm emerges as a potential solution, in which decentralized clients co-train the recommendation model without exposing their raw user-item rating data. The differentially private federated recommender (DPFR) further enhances the FR by injecting differentially private (DP) noises into clients' data. Yet, current DPFRs, suffering from noise distortion, cannot achieve the desired satisfactory accuracy. Various efforts have been dedicated to improving DPFRs by adaptively allocating the privacy budget over the learning process. However, due to the intricate relation between privacy budget allocation and model accuracy, existing attempts are still far from maximizing the DPFR accuracy. To address this challenge, we develop a BGTplanner (Budget Planner) to strategically allocate the privacy budget for each round of the DPFR training, improving overall training performance. Specifically, we leverage the Gaussian process regression and historical information to predict the change in the recommendation accuracy with a certain allocated privacy budget. Additionally, Contextual Multi-Armed Bandit (CMAB) is harnessed to make privacy budget allocation decisions by reconciling the current improvement and long-term privacy constraints. Our extensive experimental results on real datasets demonstrate that theBGTplannerachieves an average improvement of 6.76% in training performance compared to the state-of-the-art baselines.

With the ongoing advancement of information and communication technologies, the communication technologies for UAV swarm networks have undergone rapid development, especially in the context of large-scale UAV network deployments. In recent years, UAVs have found wide-ranging applications in both military and civilian domains. However, the inherent complexity and high dynamic nature of UAV swarm activities present substantial challenges to traditional routing algorithms, prompting the need for the design and implementation of efficient and sustainable routing solutions. To address these challenges, this paper introduces a UAV swarm routing algorithm based on evolutionary game theory, with a particular focus on energy efficiency and resource optimization. We leverage evolutionary game theory to enhance cooperation among nodes and adopt a strategy update rule that imitates the best-performing agents. In the proposed algorithm, nodes engage in continuous packet forwarding and participate in game interactions with neighboring nodes, adjusting their strategies based on accumulated gains. This strategy not only significantly enhances network lifetime and improves the packet delivery rate but also optimizes energy consumption and resource utilization, aligning with sustainable computing principles. To validate the effectiveness of the proposed routing method, we conduct extensive simulation experiments within a designed and implemented system model under different environmental contexts. The analysis confirmed the accuracy and effectiveness of the proposed routing method, highlighting its exceptional performance in terms of the network survival time, the number of successfully transmitted packets, and the adaptability in dynamic scenarios.

Over the past decade, the Unmanned Aerial Vehicle (UAV) swarm has emerged as a disruptive force reshaping our lives and work. Benefiting from its fast and flexible deployment capabilities, UAV swarms have been widely applied to emergency communications. In the event of damaged ground communication base stations, UAV swarms can quickly reconstruct an emer-gency communication network. However, considering the limited coverage power of a single UAV node, it underscores the need for effective coordination among swarm units as well as diligent planning of a coverage trajectory. In this paper, we propose a cooperative intelligence-based UAV swarm approach for establishing emergency communications. We model a multi-UAV base station-assisted emergency communication scenario as a team Markov game model. To achieve cooperative collaboration among multiple UAVs, we propose a Q-function mixing network based coverage trajectory planning algorithm. Our experimental results demonstrate the superior convergence speed and throughput of the proposed algorithm.

Metaverse has gained rapid interest from the research community due to its various promising features. These features include proactive learning and self-sustainability. These features enable wireless systems with analysis prior to deployment, efficient resource management with strict latency, and operation with the least possible intervention from the operators. Therefore, deploying the metaverse for wireless systems will offer many benefits. However, metaverse signaling itself requires novel design. Therefore, in this work, a new framework using network virtualization for the metaverse is proposed. Such virtualization will provide more flexibility in terms of management by using the shared physical network resources to support different services. The proposed framework takes into account three key stakeholders, namely, the network operators, a metaverse operator, and the end-users. Resources will be purchased by a metaverse operator from network operators and allocated to users in the proposed framework. To carry out this interaction, a cost function is defined that considers both communication resources and computing resources. By optimizing communication resource management, computing resource management, association, communication resources cost, and computing resource management costs, the cost function is minimized. To achieve this, we propose a strategy based on matching theory and convex optimization. In order to demonstrate the effectiveness of the proposed scheme, numerical results are provided in the final section.

Federated graph learning (FGL) has risen as a promising paradigm for collaboratively training graph neural networks while safeguarding data privacy. Nevertheless, the distributed nature of FGL also renders it susceptible to backdoor attacks. Although backdoor attacks are recognized as a significant threat to both centralized graph learning and federated learning (FL), the study of such attacks in FGL remains very limited. Current research on FGL backdoor attacks often merely adapts centralized graph backdoor attacks or FL backdoor attacks designed for image classification tasks to the FGL context, leaving key issues such as the effectiveness of triggers and the stealthiness of malicious models largely unexplored. To bridge this research gap, in this paper, we propose a novel backdoor attack, named FGLBA, targeting the FGL paradigm. Specifically, we design an input-aware trigger generator that generates a customized trigger for each target node based on its feature vector and neighborhood information, making that poisoned nodes injected with triggers are more likely misclassified into the category specified by the attacker. Additionally, we develop a stealthy federated backdoor training strategy that leverages collaborative optimization among multiple malicious clients to circumvent existing server-side defenses. The trigger generator and malicious clients' local models are iteratively optimized through a bilevel optimization framework, enabling the malicious models to achieve optimal attack performance under the optimal trigger generator. Extensive experiments on 4 real-world datasets demonstrate the effectiveness and superiority of our attack, outperforming all baseline attacks and successfully bypass 6 state-of-the-art and classical FL backdoor defenses.

Federated learning (FL) is an emerging machine learning paradigm for preserving data privacy. However, diverse client hardware often has varying computation resources. Such system heterogeneity limits the participation of resource-constrained clients in FL, and hence degrades the global model accuracy. To enable heterogeneous clients to participate in and contribute to FL training, previous works tackle this problem by assigning customized sub-models to individual clients with model pruning, distillation, or low-rank based techniques. Unfortunately, the global model trained by these methods still encounters performance degradation due to heterogeneous sub-model aggregation. Besides, most methods are heuristic-based and lack convergence analysis. In this work, we propose the FedLMT framework to bridge the performance gap, by assigning clients with a homogeneous pre-factorized low-rank model to substantially reduce resource consumption without conducting heterogeneous aggregation. We theoretically prove that the convergence of the low-rank model can guarantee the convergence of the original full model. To further meet clients’ personalized resource needs, we extend FedLMT to pFedLMT, by separating model parameters into common and custom ones. Finally, extensive experiments are conducted to verify our theoretical analysis and show that FedLMT and pFedLMT outperform other baselines with much less communication and computation costs.

Neural-enhanced video streaming systems have successfully addressed the challenge of limited network bandwidth by utilizing super-resolution (SR) techniques to enhance video quality. However, mobile users often face constraints in terms of computational resources required for SR operations. To overcome this, the integration of mobile edge computing becomes crucial. The main challenge lies in efficiently allocating GPU resources on the edge server to multiple users as the available GPU resources are typically insufficient to process all video chunks. In this paper, we formulate the problem of an edge server assisting multiple users in selecting bitrate levels and performing SR inference, and prove its NP-hardness. Subsequently, we propose an edge-assisted video streaming framework named Edge-Assisted SR (EASR) for high-definition neural-enhanced video streaming. This framework is built upon the theory of model predictive control (MPC). EASR addresses the variable reward of SR enhancement across different video chunks by making joint decisions on bitrate, SR, and GPU allocation for each chunk to maximize the average quality of experience (QoE) for all users. We evaluate the performance of EASR on four videos and real network traces. Extensive experiments reveal that EASR outperforms other baselines by $18.76 \%$ to $58.37 \%$ in terms of average QoE and 0.005 to 0.017 in terms of structural similarity index (SSIM).

Variable bitrate (VBR) encoding has gained considerable interest due to its capacity to enhance video quality and mitigate transmission congestion in contrast to constant bitrate (CBR) encoding. However, adaptive bitrate (ABR) streaming faces challenges when dealing with VBR-encoded videos, primarily stemming from the significant variability in chunk size and the consequent bitrate fluctuations. This paper proposes CoarseUCB, a context-aware online learning algorithm for bitrate adaptation in VBR-encoded videos. CoarseUCB considers important aspects of VBR-encoded video streaming and uses the upper confidence bound (UCB) method for bitrate selection. The UCB method does not require precise bandwidth estimation and balances the exploration and exploitation of each action effectively. Additionally, CoarseUCB accounts for the impact of multiple future video chunks when making the bitrate decision for the current chunk. To evaluate the effectiveness of CoarseUCB, we conduct experiments to assess its efficiency. The results show that CoarseUCB delivers a higher average user quality of experience (QoE) compared to state-of-the-art ABR algorithms, resulting in an improvement of up to 9.81%.

Gaze prediction is essential for enhancing user experiences of virtual reality (VR) applications. However, existing methods seldom considered the privacy nature of gaze data, which may reveal both psychological and physiological characteristics of VR users. Moreover, the commonly adopted one-sizefits-all prediction model cannot well capture behavioral patterns of different VR users. In this paper, we propose a privacyaware personalized gaze prediction framework called GazeFed, which can train a personalized gaze prediction model for each user in a collaborative manner. In GazeFed, only intermediate computations are exchanged between users and the server. The raw gaze data samples are locally preserved to protect user privacy. The global model is shared among all users, which can be further trained with local gaze data to generate a personalized prediction model for each individual user. We also propose a deep neural network tailored for VR gaze prediction called GazeNet, which can effectively extract features from VR contents, gaze data and other user behaviors, and improve the accuracy of gaze prediction. Moreover, the technique of differential privacy (DP) is also integrated to provide more privacy protection, and we theoretically prove that GazeFed can well converge and satisfy the requirement of differential privacy in the meanwhile. Last, we conduct extensive experiments to evaluate the effectiveness of our proposed GazeFed on real datasets and various VR scenarios. The experimental results demonstrate that GazeFed outperforms the state-of-the-art approaches.

As VR devices become increasingly prevalent, live 360-degree video has surged in popularity. However, current live 360-degree video systems heavily rely on uplink bandwidth to deliver high-quality live videos. Recent advancements in neural-enhanced streaming offer a promising solution to this limitation by leveraging server-side computation to conserve bandwidth. Nevertheless, these methods have primarily concentrated on neural enhancement within a single domain (either spatial or temporal), which may not adeptly adapt to diverse video scenarios and fluctuating bandwidth conditions. In this paper, we propose Lumos, a novel spatial-temporal integrated neural-enhanced live 360-degree video streaming system. To accommodate varied video scenarios, we devise a real-time Neural-enhanced Quality Prediction (NQP) model to predict the neural-enhanced quality for different video contents. To cope with varying bandwidth conditions, we design a Content-aware Bitrate Allocator, which dynamically allocates bitrates and selects an appropriate neural enhancement configuration based on the current bandwidth. Moreover, Lumos employs online learning to improve prediction performance and adjust resource utilization to optimize user quality of experience (QoE). Experimental results demonstrate that Lumos surpasses state-of-the-art neural-enhanced systems with an improvement of up to 0.022 in terms of SSIM, translating to an 8.2%-8.5% enhancement in QoE for live stream viewers.

With the increasing demand for artificial intelligence (AI), cluster jobs require high-performance GPU instances and often face stringent deadline constraints. Previous studies have proposed various scheduling strategies to minimize job completion time and instance costs, assuming accurate prediction of job execution time across different instances. However, such assumptions are often unrealistic due to the inherent unpredictability of job execution time. Additionally, jobs typically involve large data sets and incur substantial cold-start time, leading to increased job completion latency and degradation of user quality of service. To tackle these challenges, we introduce an algorithm named Exponential Weighting Scheduling (EWS) for GPU clusters, which employs an online learning approach based on the combinatorial multi-armed bandit (CMAB) framework. EWS dynamically updates the probability distribution of decision spaces using real-time information on job performance across different instances and employs randomized decision-making for scheduling. Furthermore, we provide theoretical proof that this online strategy guarantees sublinear regret in terms of performance. Extensive experiments validate that our algorithm significantly enhances user quality of service and reduces instance utilization costs compared to other state-of-the-art baselines.

Federated learning (FL) emerges as an attractive collaborative machine learning framework that enables training of models across decentralized devices by merely exposing model parameters. However, malicious attackers can still hijack communicated parameters to expose clients’ raw samples resulting in privacy leakage. To defend against such attacks, differentially private FL (DPFL) is devised, which incurs negligible computation overhead in protecting privacy by adding noises. Nevertheless, the low model utility and communication efficiency makes DPFL hard to be deployed in the real environment. To overcome these deficiencies, we propose a novel DPFL algorithm called FedDP-SA (namely, federated learning with differential privacy by splitting Local data sets and averaging parameters). Specifically, FedDP-SA splits a local data set into multiple subsets for parameter updating. Then, parameters averaged over all subsets plus differential privacy (DP) noises are returned to the parameter server. FedDP-SA offers dual benefits: 1) enhancing model accuracy by efficiently lowering sensitivity, thereby reducing noise to ensure DP and 2) improving communication efficiency by communicating model parameters with a lower frequency. These advantages are validated through sensitivity analysis and convergence rate analysis. Finally, we conduct comprehensive experiments to verify the performance of FedDP-SA compared with other state-of-the-art baseline algorithms.

With the significant increase in the number of motor vehicles, road-related issues such as traffic congestion and accidents have also escalated. The development of an accurate and efficient traffic flow forecasting model is essential for helping car owners plan their journeys. Despite advancements in forecasting models, there are three remaining issues: (i) failing to effectively use cyclical data; (ii) failing to adequately capture spatial dependencies; and (iii) high time complexity and memory usage. To tackle the aforementioned challenges, we present a novel Spatial-Temporal Graph Attention Gated Recurrent Transformer Network (STGAGRTN) for traffic flow forecasting. Specifically, the use of a Spatial Transformer module allows for the extraction of dynamic spatial dependencies among individual nodes, going beyond the limitation of only considering neighboring nodes. Subsequently, we propose a Temporal Transformer to extract periodic information from traffic data and capture long-term dependencies. Additionally, we utilize two additional classical techniques to complement the aforementioned modules for extracting characteristics. By incorporating comprehensive spatial-temporal characteristics into our model, we can accurately predict multiple nodes simultaneously. Finally, we have successfully optimized the computational complexity of the Transformer module from O(n2) to O(nlogn). Our model has undergone extensive testing on four authentic datasets, providing compelling evidence of its superior predictive capabilities.

Metaverse (especially 360-degree) video streaming allows broadcasting virtual events in the metaverse to a broad audience. To reduce the huge bandwidth consumption, quite a few super-resolution (SR)-enhanced 360-degree video streaming systems have been proposed. However, there is very limited work to investigate how the granularity of SR model affects the system performance, and how to choose a proper SR model for different video contents under diverse environmental conditions. In this paper, we first conduct a dedicated measurement study to unveil the impact of different granularities of SR models. It is found that the scene of a video largely determines the effectiveness of SR models in different granularities. Based on our observations, we propose a novel 360-degree video streaming framework with saliency-driven dynamic super-resolution, called SDSR. To maximize user QoE, we formally formulate an optimization problem and adopt the model predictive control (MPC) theory for bitrate adaptation and SR model selection. To improve the effectiveness of SR model, we leverage the saliency information, which well reflects users’ view interests, for model training. In addition, we reuse an SR model for similar chunks based on temporal redundancy of a video. Finally, we conduct extensive experiments on real traces and the results show that SDSR outperforms the state-of-the-art algorithms with an improvement up to 32.78% in terms of the average QoE.

Mobile edge computing (MEC) and millimeter-wave (mmWave) communication are promising techniques for future cellular networks. MEC enables latency-critical tasks offloading at the network edge, while mmWave provides an abundant spectrum for gigabit-per-second data transmission. Dense deployment of remote radio units (RRUs) is necessary due to high mmWave signal path loss, and hence limiting the deployment cost becomes a prime network design factor. Our work considers that RRUs are deployed to provide mmWave access and to offload computation requests to edge servers (ESs) via fronthaul links. We propose an edge network (EN) deployment problem by jointly optimizing the mmWave access and fronthaul networks. Converged fiber and in-band mmWave techniques are utilized for flexible fronthaul links deployment and cost reduction. The deployed EN is expected to fulfill coverage, reliability and latency requirements of ultra-reliable low-latency (uRLLC) services. We formulate the optimization problem as an integer linear program (ILP) and propose a multi-objective evolutionary algorithm to solve the problem. The numerical results demonstrate that our proposed algorithm can achieve close-to-optimal solutions compared with the ILP formulation. We also comparatively evaluate the deployment costs under different EN settings and show that our algorithm provides up to 20.3% cost savings compared to non-converged solutions.

Although Federated Learning (FL) prevents the exposure of original data samples when collaboratively training machine learning models among decentralized clients, it has been revealed that vanilla FL is still susceptible to adversarial attacks if model parameters are leaked to malicious attackers. To enhance the protection level of FL, Differential Private Federated Learning (DPFL) has been proposed in recent years. DPFL injects zero-mean noises randomly generated by differential private (DP) mechanisms on local model parameters before they are disclosed. Nevertheless, DP noises can significantly deteriorate model utility jeopardizing the practicality of DPFL. In this paper, we are among the first to explore how to improve the model utility of DPFL by tuning the number of local iterations (LIs) on DPFL clients. Our work shows that such a local iteration tuning approach can well mitigate the adverse influence of DP noises on the final model utility. Formally, we derive the sensitivity (a measure of the maximum change of the output given two adjacent inputs) with respect to the number of LIs conducted on DPFL clients for the Laplace mechanism, and the aggregated variances of Laplace noises at the server side. We further conduct convergence rate analysis to quantify the influence of the Laplace noises on the final model accuracy and determine how to optimally set the number of LIs. Finally, to verify our theoretical findings, we perform extensive experiments using three real-world datasets, namely, Lending Club, MNIST and Fashion-MNIST. The results not only corroborate our analysis, but also demonstrate that our approach significantly improves the practicality of DPFL.

The differentially private federated learning (DPFL) paradigm emerges to firmly preserve data privacy from two perspectives. First, decentralized clients merely exchange model updates rather than raw data with a parameter server (PS) over multiple communication rounds for model training. Secondly, model updates to be exposed to the PS will be distorted by clients with differentially private (DP) noises. To incentivize clients to participate in DPFL, various incentive mechanisms have been proposed by existing works which reward participating clients based on their data quality and DP noise scales assuming that all clients are honest and genuinely report their DP noise scales. However, the PS cannot directly measure or observe DP noise scales leaving the vulnerability that clients can boost their rewards and lower DPFL utility by dishonestly reporting their DP noise scales. Through a quantitative study, we validate the adverse influence of dishonest clients in DPFL. To overcome this deficiency, we propose a robust incentive mechanism called client selection with reverse auction (CSRA) for DPFL. We prove that CSRA satisfies the properties of truthfulness, individual rationality, budget feasibility and computational efficiency. Besides, CSRA can prevent dishonest clients with two steps in each communication round. First, CSRA compares the variance of exposed model updates and claimed DP noise scale for each individual to identify suspicious clients. Second, suspicious clients will be further clustered based on their model updates to finally identify dishonest clients. Once dishonest clients are identified, CSRA will not only remove them from the current round but also lower their probability of being selected in subsequent rounds. Extensive experimental results demonstrate that CSRA can provide robust incentive against dishonest clients in DPFL and significantly outperform other baselines on three real public datasets.

Given that devices (i.e., clients) participating in federated edge learning (FEL) are autonomous and resource-constrained in nature, it is critical to design effective incentive mechanisms to encourage client participation so as to improve the performance of FEL. In this article, we aim to boost the FEL training efficiency by answering how much compute resource should clients autonomously contribute to maximize their utilities. To this end, we develop AutoFL, an autonomous client participation decision framework for federated learning at the network edge without assuming that each client possesses complete information. We first model the problem of autonomous client participation as a Bayesian game with incomplete information, where each player in the game is associated with a set of types according to network conditions. We optimize an individual client's decision based on the dynamics of the population estimated following the Bayes rule. We prove that AutoFL can converge to a unique Bayesian Nash equilibrium point. Empirical results on three real datasets show that AutoFL achieves a higher model accuracy with only 15.5-24.5% model aggregation time per global training round, and its energy cost saving on mobile devices is 82.2-86.8% compared to the state-of-the-art algorithms. Moreover, we can achieve a 2.75-3.2x long-term fairness compared to classical solutions.

In recent years, the rapid growth of Internet of Things (IoT) devices and applications has posed significant challenges for existing Mobile Edge Computing (MEC) architectures. The inherent latency uncertainties in MEC architectures make it difficult to support latency-sensitive applications such as autonomous vehicles. Additionally, the increasing number of connected devices has led to substantial challenges in terms of limited throughput for MEC servers. With the recent advancements in programmable network hardware, such as SmartNICs and programmable switches, the Network-based Computing (NBC) paradigm has gained widespread attention. Leveraging line-rate processing capabilities, NBC offers a promising solution for high throughput and low latency processing. This paper aims to explore the potential benefits and challenges of incorporating NBC into existing MEC architectures. The feasibility of our proposed architecture is evaluated using two use cases, Linear Quadratic Regulator (LQR) control and Complex Event Processing (CEP), demonstrating significant improvements in latency performance.

The publicly released machine learning (ML) models are susceptible to malicious attacks (e.g., gradient leakage attacks), which may expose sensitive training data of data-sharing platforms to untrusted third-parties. To preserve the privacy of training data, differential privacy (DP) is exploited to limit the amount of leaked privacy with a predefined budget, which in fact is a non-recoverable resource. Considering DP, allocating privacy budgets to ML queries is a non-trivial but crucial problem because a certain amount of non-recoverable privacy budget will be consumed if a datablock is assigned to a query once. Meanwhile, both datablocks and ML queries are continuously generated, which further complicates the problem. Most existing works simply relied on greedy-based algorithms to make myopic allocation decisions, far away from the optimal decision. In this paper, we propose a novelHistory-awarePrivacyBudgetAllocation (HPBA) algorithm for data-sharing platforms to address the above challenges. Different from existing works, HPBA leverages historical query records to approximate global ML query patterns so as to overcome the drawback of shortsighted greedy-based algorithms. Moreover, the performance of HPBA is theoretically guaranteed by competitive analysis. A lightweight version called S-HPBA is proposed to further reduce computation overhead by using fewer historical records. Experimental results demonstrate that, compared to the state-of-the-art baselines, HPBA and S-HPBA improve the average performance by 32.8% and 16.2% in terms of model accuracy, respectively.

The flying ad hoc networks (FANETs) have attracted a large amount of attention from both academia and industry. Benefiting from the flexibility, the FANETs have been widely deployed in various scenarios, ranging from agricultural production to emergency rescue. However, in FANETs, the mobility of unmanned aerial vehicles (UAVs) has led to critical challenges for the stability of communications. Especially, the routing flooding mechanism extremely limits the scalability of FANET. To overcome these technical challenges, constructing a hierarchy and clustering structure in FANETs is considered a promising solution. In this paper, we propose the fission spectral clustering (FSC) strategy for UAV swarm networks. We model the UAV clustering problem as a graph cut problem. The time-sequential attributes weight of nodes and edges will be input to the FSC algorithm. Then, it will construct the Laplace matrix and calculate the first k-th eigenvectors of it. We apply the K-Means algorithm into this feature space to cut the graph by clustering the eigenvectors. Each cluster will constantly fission with this strategy until it satisfies the size and structure constraints in the UAV clusters. Some simulations are implemented to evaluate our proposed algorithm in comparison to the other state-of-the-art solutions.

Volumetric video is fully three-dimensional and provides users with highly immersive and interactive experience. However, it is difficult to stream volumetric video over the Internet due to sheer video size and limited network bandwidth. Existing solutions suffered from poor perceptual quality and low coding efficiency. In this paper, we first conduct a comprehensive user study to understand the effectiveness of popular perceptual quality metrics for volumetric video. It is observed that those metrics cannot well capture the impact of user viewing behaviors. Considering the findings that users are more sensitive to the distortion of 2D image rendered from 3D point cloud, a new metric called Volu-FMAF is proposed to better represent perceptual quality of volumetric video. Next, we propose a novel neural-based volumetric video streaming framework RenderVolu and design a distortion-aware rendered image super-resolution network, called RenDA-Net, to further improve user perceptual quality. Last, we conduct extensive experiments with real datasets to validate our proposed method, and the results show that our method can boost the perceptual quality of volumetric video by 171% to 190%, and achieves a speedup of 108x in terms of decoding efficiency compared to the state-of-the-art approaches.

Different from conventional federated learning, personalized federated learning (PFL) is able to train a customized model for each individual client according to its unique requirement. The mainstream approach is to adopt a kind of weighted aggregation method to generate personalized models, in which weights are determined by the loss value or model parameters among different clients. However, such kinds of methods require clients to download others' models. It not only sheer increases communication traffic but also potentially infringes data privacy. In this paper, we propose a new PFL algorithm called FedDWA (Federated Learning with Dynamic Weight Adjustment) to address the above problem, which leverages the parameter server (PS) to compute personalized aggregation weights based on collected models from clients. In this way, FedDWA can capture similarities between clients with much less communication overhead. More specifically, we formulate the PFL problem as an optimization problem by minimizing the distance between personalized models and guidance models, so as to customize aggregation weights for each client. Guidance models are obtained by the local one-step ahead adaptation on individual clients. Finally, we conduct extensive experiments using five real datasets and the results demonstrate that FedDWA can significantly reduce the communication traffic and achieve much higher model accuracy than the state-of-the-art approaches.

Federated learning (FL) is a prospective distributed machine learning framework that can preserve data privacy. In particular, cross-silo FL can complete model training by making isolated data islands of different organizations collaborate with a parameter server (PS) via exchanging model parameters for multiple communication rounds. In cross-silo FL, an incentive mechanism is indispensable for motivating data owners to contribute their models to FL training. However, how to allocate the reward budget among different rounds is an essential but complicated problem largely overlooked by existing works. The challenge of this problem lies in the opaque feedback between reward budget allocation and model utility improvement of FL, making the optimal reward budget allocation complicated. To address this problem, we design an online reward budget allocation algorithm using Bayesian optimization named BARA (Budget Allocation for Reverse Auction). Specifically, BARA can model the complicated relationship between reward budget allocation and final model accuracy in FL based on historical training records so that the reward budget allocated to each communication round is dynamically optimized so as to maximize the final model utility. We further incorporate the BARA algorithm into reverse auction-based incentive mechanisms to illustrate its effectiveness. Extensive experiments are conducted on real datasets to demonstrate that BARA significantly outperforms competitive baselines by improving model utility with the same amount of reward budget.

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

Federated learning (FL) empowers distributed clients to collaboratively train a shared machine learning model through exchanging parameter information. Despite the fact that FL can protect clients’ raw data, malicious users can still crack original data with disclosed parameters. To amend this flaw, differential privacy (DP) is incorporated into FL clients to disturb original parameters, which however can significantly impair the accuracy of the trained model. In this work, we study an imperative question which has been vastly overlooked by existing works: what are the optimal numbers of queries and replies in FL with DP so that the final model accuracy is maximized. In FL, the parameter server (PS) needs to query participating clients for multiple global iterations to complete training. Each client responds a query from the PS by conducting a local iteration. We consider FL that will uniformly and randomly select participating clients to conduct local iterations with the FedSGD algorithm. Our work investigates how many times the PS should query clients and how many times each client should reply the PS by incorporating two most extensively used DP mechanisms (i.e., the Laplace mechanism and Gaussian mechanisms). Through conducting convergence rate analysis, we can determine the optimal numbers of queries and replies in FL with DP so that the final model accuracy can be maximized. Finally, extensive experiments are conducted with publicly available datasets: MNIST and FEMNIST, to verify our analysis and the results demonstrate that properly setting the numbers of queries and replies can significantly improve the final model accuracy in FL with DP.

Drone-swarm-assisted mobile edge computing (MEC) provides extra computation and storage capacity for smart city applications and the Industrial Internet of Things. To solve the problems of traditional fixed base stations in a complex terrain, including cost of deployment, transmission loss of telecommunication, and limited coverage, this article brings forward the unmanned aerial vehicles (UAVs) as MEC nodes in the air. For the purpose of matching the dynamic mobile devices and UAV trajectory, this article raises a multi-UAVs-assisted MEC offloading algorithm based on global and local path planning controlled by ground station and onboard computer. Firstly, this article considers a drone swarm scheduling and allocation strategy based on the priority of monitoring areas, UAVs residual energy and distance to target points, so as to minimize the global flight length and energy consumption. Secondly, based on user mobility, this article calculates the optimal communication coverage of a UAV, and jointly optimizes the local path planning and computing offloading, so as to maximize the number of offloading services and minimize the total latency in completing the computation task. Finally, based on the total latency and energy consumption of path planning and computation offloading, a UAV cluster computation offloading strategy with optimized energy efficiency is realized. Experimental results prove that the proposed algorithm can provide more offloading services while obtaining shorter path length and greater energy efficiency.

With the large-scale commercialization of 5G, the global industry has started the exploration of the next generation mobile communication technology (6G). From mobile Internet, to IoT, and then to the smart connection of everything, 6G will transform from 5G’s service objects of people and things to the intelligent networking of agent that supports human–machine–object. 6G networks should have the characteristics of ubiquitous intelligence and ubiquitous perception, which poses challenges for 6G network construction. Therefore, we propose a 6G Semantic Communication Scheme based on Intelligent Fabrics for transportation in-cabin scenarios (6GSCS-IF), which can provide senseless intelligent interaction in transportation in-cabin environment through widely and flexibly deployed intelligent fabrics, demonstrating the superiority of intelligent fabrics in realizing human–machine–object intelligent sensory interaction. Then, we propose a Deep Learning-based Semantic Communication Model for Time-series data (DL-SCMT), and use deep learning for semantic sensing and information extraction to build an end-to-end semantic communication system. The experimental results show that the semantic communication services provided by this model can achieve better signal reconstruction and higher-order intelligent services compared with traditional communication methods.

The accelerating convergence of artificial intelligence and edge computing has sparked a recent wave of interest in edge intelligence. While pilot efforts focused on edge DNN inference serving for a single user or DNN application, scaling edge DNN inference serving to multiple users and applications is however nontrivial. In this paper, we propose an online optimization framework EdgeAdaptor for multi-user and multi-application edge DNN inference serving at scale, which aims to navigate the three-way trade-off between inference accuracy, latency, and resource cost via jointly optimizing the application configuration adaption, DNN model selection and edge resource provisioning on-the-fly. The underlying long-term optimization problem is difficult since it is NP-hard and involves future uncertain information. To address these dual challenges, we fuse the power of online optimization and approximate optimization into a joint optimization framework, via i) decomposing the long-term problem into a series of single-shot fractional problems with a regularization technique, and ii) rounding the fractional solution to a near-optimal integral solution with a randomized dependent scheme. Rigorous theoretical analysis derives a parameterized competition ratio of our online algorithms, and extensive trace-driven simulations verify that its empirical value is no larger than 1.4 in typical scenarios.

The high-definition (HD) live video streaming has gained significant popularity due to the rapid growth of 4 G/5 G and social media. However, for devices with constrained bandwidth, they still have no sufficient bandwidth to support HD live video streaming. In this paper, we propose a neural-enhanced HD live video streaming framework calledLiveSRto provide universal HD live video streaming for both bandwidth-constrained and bandwidth-rich devices. For bandwidth-constrained devices, LiveSR delivers low-quality video streams and then boosts video quality at the device side with super-resolution (SR) techniques. The difficulty lies in how to train the SR model with low cost and conduct quality enhancement in real time. To address these challenges, we design a crowdsourced online training method by exploiting computation resources and HD video data on bandwidth-rich devices in the same video channel. We also propose an imitation learning-based decision making algorithm to make downloading decisions for video chunks and SR models under limited bandwidth. We implement and evaluate our proposed LiveSR framework using real network traces, and the experiment results show that LiveSR outperforms all the other baseline approaches, with 65.5% improvement in terms of the average QoE and 5.7% in terms of video quality (i.e., PSNR), and the achieved frame rate can be as high as 30 frames per second.

Due to the expensive and laborious annotations of labeled data required by fully-supervised learning in the crowd counting task, it is desirable to explore a method to reduce the labeling burden. There exists a large number of unlabeled images in the wild that can be easily obtained compared to labeled datasets. Based on the characteristics of consistent spatial transformation with the annotations of heads and image, this paper proposes a self-supervised learning framework with unlabeled and limited labeled data for pre-training and fine-tuning crowd counting model (SSL-FT). It includes an online network and a target network that receive the same images but are randomly processed by two defined augmentation transformations. We leverage unlabeled data to pre-train the online network based on a self-supervised loss and small-scale labeled data to transfer the model to a specific domain based on a fully-supervised loss. We demonstrate the effectiveness of the SSL-FT on four public datasets including ShanghaiTech PartA, PartB, UCF-QNRF and WorldExpo'10 utilizing a classical counting model. Experimental results show that our approach performs better than state-of-art semi-supervised methods.

In vanilla Federated Learning (FL) systems, a centralized parameter server (PS) is responsible for collecting, aggregating and distributing model parameters with decentralized clients. However, the communication link of a single PS can be easily overloaded by concurrent communications with a massive number of clients. To overcome this drawback, multiple PSes can be deployed to form a parallel FL (PFL) system, in which each PS only communicates with a subset of clients and its neighbor PSes. On one hand, each PS conducts iterations with clients in its subset. On the other hand, PSes communicate with each other periodically to mix their parameters so that they can finally reach a consensus. In this paper, we propose a novel parallel federated learning algorithm called Fed-PMA, which optimizes such parallel FL under constrained communications by conducting parallel parameter mixing and averaging with theoretic guarantees. We formally analyze the convergence rate of Fed-PMA with convex loss, and further derive the optimal number of times each PS should mix with its neighbor PSes so as to maximize the final model accuracy within a fixed span of training time. Theoretical study manifests that PSes should mix their parameters more frequently if the connection between PSes is sparse or the time cost of mixing is low. Inspired by our analysis, we propose the Fed-APMA algorithm that can adaptively determine the near-optimal number of mixing times with non-convex loss under dynamic communication conditions. Extensive experiments with realistic datasets are carried out to demonstrate that both Fed-PMA and its adaptive version Fed-APMA significantly outperform the state-of-the-art baselines.

Due to the high cost of cellular networks, vehicle users would like to offload elastic traffic through vehicular networks as much as possible. This demand prompts researchers to consider how to make the vehicular network system achieve better performance for requests coming online, such as maximizing throughput. The traffic in vehicular networks is transferred through opportunistic contacts between vehicles and infrastructures. When making scheduling decisions, the scheduler must be aware of vehicles’ future trajectories. Vehicles’ future trajectories are usually predicted by trajectory prediction algorithms when users are unwilling to report their future trips. Unfortunately, no trajectory prediction algorithm can be completely accurate, and these inaccurate prediction results will degrade the throughput achieved by scheduling algorithms. In this paper, we focus on reducing the negative impact of inaccurate predictions. Specifically, we measure two data-driven trajectory prediction algorithms that have been widely used for trajectory predictions and understand the characteristics of the accuracy of predicted contacts. Based on the enlightenment from the measurement, we design a system, i.e., i-Offload, to offload elastic traffic under imperfect trajectory predictions. The experimental results show that our system has good throughput and high scheduling efficiency even under imperfect trajectory predictions. Compared with existing scheduling algorithms, our method improves the throughput by about one time.

Machine learning (ML) tasks are one of the major workloads in today's edge computing networks. Existing edge-cloud schedulers allocate the requested amounts of resources to each task, falling short of best utilizing the limited edge resources for ML tasks. This paper proposesTapFinger, a distributed scheduler for edge clusters that minimizes the total completion time of ML tasks through co-optimizing task placement and fine-grained multi-resource allocation. To learn the tasks’ uncertain resource sensitivity and enable distributed scheduling, we adopt multi-agent reinforcement learning (MARL) and propose several techniques to make it efficient, including a heterogeneous graph attention network as the MARL backbone, a tailored task selection phase in the actor network, and the integration of Bayes’ theorem and masking schemes. We first implement asingle-task schedulingversion, which schedules at most one task each time. Then we generalize to themulti-task schedulingcase, in which a sequence of tasks is scheduled simultaneously. Our design can mitigate the expanded decision space and yield fast convergence to optimal scheduling solutions. Extensive experiments using synthetic and test-bed ML task traces show thatTapFingercan achieve up to 54.9% reduction in the average task completion time and improve resource efficiency as compared to state-of-the-art schedulers.

LEO satellite networks have become a necessary supplement to terrestrial networks aiming to provide worldwide, ubiquitous connectivity, especially in complicated areas (e.g., mountains, oceans, and disaster areas) where terrestrial network infrastructures are typically sparingly distributed or unavailable. However, the increasing computation-intensive Internet-of-Things (IoT) applications (e.g., real-time remote monitoring, intelligent transportation) require not only efficient and reliable communication but also massive computing capabilities. Constrained by the battery and computing resources, the computing tasks and data of applications have to be transmitted to remote cloud servers. This bandwidth limitation and high transmission delay in LEO networks will reduce the quality-of-service (QoS) of IoT applications. Recently, the combination of LEO networks and edge computing (i.e., Satellite Mobile Edge Computing, SMEC) offers significant opportunities to address these problems. The IoT devices can directly get the computing resources directly from satellites rather than remote servers, thus avoiding long-distance transmission. Considering the resource constraints on satellites, offloading policy plays a crucial role in whole system performance. In this paper, we design a hybrid offloading architecture, which applies a centralized training and distributed execution framework. Also, we propose a multi-agent actor-critic reinforcement learning algorithm, where a centralized “critic” is augmented with the global network state to ease the training procedure of distributed user equipments (UE) by evaluating the benefits of their decisions, while the UEs can adjust their policies according to the critic’s evaluation and choose their own decisions relying on their observations.

360-degree video streaming has gained tremendous growth over the past years. However, the delivery of 360-degree videos over the Internet still suffers from the scarcity of network bandwidth and adverse network conditions (e.g., packet loss, delay). In this paper, we propose a practical neural-enhanced 360-degree video streaming framework called Masked360, which can significantly reduce bandwidth consumption and achieve robustness against packet loss. In Masked360, instead of transmitting the complete video frame, the video server only transmits a masked low-resolution version of each video frame to reduce bandwidth significantly. When delivering masked video frames, the video server also sends a lightweight neural network model called MaskedEncoder to clients. Upon receiving masked frames, the client can reconstruct the original 360-degree video frames and start playback. To further improve the quality of video streaming, we also propose a set of optimization techniques, such as complexity-based patch selection, quarter masking strategy, redundant patch transmission and enhanced model training methods. In addition to bandwidth savings, Masked360 is also robust to packet loss during the transmission, because packet losses can be concealed by the reconstruction operation performed by the MaskedEncoder. Finally, we implement the whole Masked360 framework and evaluate its performance using real datasets. The experimental results show that Masked360 can achieve 4K 360-degree video streaming with bandwidth as low as 2.4 Mbps. Besides, video quality of Masked360 is also improved significantly, with an improvement of 5.24-16.61% in terms of PSNR and 4.74-16.15% in terms of SSIM compared to other baselines.

Eye tracking techniques have been widely adopted by a wide range of devices (e.g., AR/VR headsets, smartphones) to enhance user experiences. However, eye gaze data is private in nature, which can reveal users’ psychological and physiological features. Privacy protection techniques can be incorporated to preserve privacy of eye tracking information. Yet, most existing solutions based on Differential Privacy (DP) mechanisms cannot well protect privacy for individual users without sacrificing user experience. In this paper, we are among the first to propose a novel gaze model-based privacy control framework called Otus for eye tracking applications, which incorporates local DP (LDP) mechanisms to preserve user privacy and improves user experience in the meanwhile. First, we conduct a measurement study on real traces to illustrate that direct noise injection on raw gaze trajectories can significantly lower the utility of gaze data. To preserve utility and privacy simultaneously, Otus injects noises in two steps: (1) Extracting model features from raw data to depict gaze trajectories on individual users; (2) Adding LDP noises into model features so as to protect privacy. On one hand, established models can be used to recover user gaze data in order to improve service quality of eye tracking applications. On the other hand, we only need to add LDP noises to distort a small number of model parameters rather than every point on a trajectory to preserve privacy, which has less impact on the utility of gaze data given the same privacy budget. By applying the tile view graph model in step (1), we illustrate the entire workflow of Otus and prove its privacy protection level. For evaluation, we conduct extensive experiments using real gaze traces and the results show that Otus can effectively protect privacy for individual users without significantly compromising gaze data utility.

Instead of training a single global model to fit the needs of all clients, personalized federated learning aims to train multiple client-specific models to better account for data disparities across participating clients. However, existing solutions suffer from serious unfairness among clients in terms of model accuracy and slow convergence under non-lID data. In this paper, we propose a novel personalized federated learning framework, called D PFed, which employs deep reinforcement learning (D RL) to identify relationship between clients and enable closer collaboration among similar clients. By exploiting such relationships, DPFed can personalize model aggregation for each client and achieve fast convergence. Moreover, by regularizing the reward function of DRL, we can reduce the variance of model accuracy across clients and achieve a higher level of fairness. Finally, we conduct extensive experiments to evaluate the effectiveness of our proposed framework under a variety of datasets and degrees of non-lID data distribution. The results demonstrate that DPFed outperforms other alternatives in terms of convergence speed, model accuracy, and fairness.

Recent advancements of neural-enhanced techniques, especially super-resolution (SR), show great potential in revolutionizing the landscape of Internet video delivery. However, there are still quite a few key questions (e.g., how to choose a proper resolution configuration for training samples, how to set the training patch size, how to perform the best patch selection, how to set the update frequency of SR model) that have not been well investigated and understood. In this paper, we perform a dedicated measurement study to revisit super-resolution techniques for Internet video streaming. Our measurements are based on real-world video datasets, and the results provide a number of important insights: (1) It is possible that the SR model trained with low-resolution patches (e.g., (540p, 1080p) pairs) can achieve almost the same performance as that trained with high-resolution patches (e.g., (1080p, 2160p) pairs); (2) Compared to the saliency of training patches, the size of training patches has little impact on the performance of trained SR model; (3) The improvement of video quality brought by more frequent SR model update is not very significant. We also discuss the implications of our findings for system design, and we believe that our work is essential for paving the way for the success of future neural-enhanced video streaming systems.

Federated learning (FL) is an emerging paradigm through which decentralized devices can collaboratively train a common model. However, a serious concern is the leakage of privacy from exchanged gradient information between clients and the parameter server (PS) in FL. To protect gradient information, clients can adopt differential privacy (DP) to add additional noises and distort original gradients before they are uploaded to the PS. Nevertheless, the model accuracy will be significantly impaired by DP noises, making DP impracticable in real systems. In this work, we propose a novel noise information secretly sharing (NISS) algorithm to alleviate the disturbance of DP noises by sharing negated noises among clients. We theoretically prove that: 1) if clients are trustworthy, DP noises can be perfectly offset on the PS and 2) clients can easily distort negated DP noises to protect themselves in case that other clients are not totally trustworthy, though the cost lowers model accuracy. NISS is particularly applicable for FL across multiple Internet of Things (IoT) systems, in which all IoT devices need to collaboratively train a model. To verify the effectiveness and the superiority of the NISS algorithm, we conduct experiments with the MNIST and CIFAR-10 data sets. The experimental results verify our analysis and demonstrate that NISS can improve model accuracy by 19% on average and obtain better privacy protection if clients are trustworthy.

Mobile edge computing (MEC) is a key technology that enables the deployment of applications (or services) at the proximity of mobile users. However, the performance of mobile edge computing is sensitive to the quality and availability of underlying connection links. It is still unclear to what extent intermittent connectivity affects the performance of mobile edge computing. In this paper, we make the first attempt to quantify the influence of intermittent connectivity on mobile edge computing from a theoretical perspective. Specifically, we propose an analytical framework based on discrete-time Markov chain and derive a closed-form expression of the task processing time under different network conditions. Our model can be further extended to account for the case with group task arrivals. We also conduct extensive simulations to examine the accuracy of our proposed analytical models with both synthetic and real-world user mobility traces. The results show that our model can well capture the influence of intermittent connectivity on MEC. Our model sheds important insights into the impact of intermittent connectivity on task processing in MEC, which we believe should be taken into account when designing future MEC systems.

With the widespread application of artificial intelligence and the Internet of Things, the intellectualization of the industrial Internet of Things (IIoT) has received more and more attention. However, in the application scenario with numerous sensors, the contradiction between massive requests of computing tasks and high requirements of inference quality affects the operation efficiency and service reliability. Moreover, due to the heterogeneity of computing resources and the randomness of communication environments of the cloud-edge system, how to compute and deploy deep learning models in a cloud-edge collaborative environment has also become a challenging problem. Therefore, this article presents a collaborative cloud-edge service cognitive framework for deep neural network (DNN) model service configuration to provide dynamic and flexible computing services. In order to adapt to different service requirements, we explored the tradeoffs between accuracy, latency, and energy consumption indicators, and a revenue target is established, which considers the quality of service experience and the system energy consumption to improve resource utilization efficiency. By transforming the optimization of the revenue target into a partially observable DNN configuration reinforcement learning problem, a dueling deep Q-learning network-based self-adaptive DNN configuration algorithm is proposed. Experimental results show that the proposed mechanism can effectively learn from external experience, adapt to the dynamic network environment, and reduce delay and energy consumption while meeting the service requirements.

The significant achievements have been made in crowd detection and tracking due to the advancement of artificial intelligence in the autonomous driving. However, the image-based methods have strict requirements for the collection conditions of video, and the development of the new generation of flexible fabrics has become potential sensors to perceive context. In this paper, an intelligent fabric space enabled by multi-sensing sensors is established to track the motion objects. We propose a behavior analysis pipeline including the modules of data preparation, trajectory coupling, motion scenario segmentation, and motion pattern measurement to capture the crowd information from micro-level and macro-level over the intelligent fabric space. After making preprocess for the multi-sensing data, a coupling mechanism is formulated to fuse the video-based trajectory and fabric-based trajectory. And an automatic motion scenario segmentation model divides the surrounding scenario into main-crowd, sub-crowd, and background according to the motion behavior. Further, we define measurement metrics to analyze the motion pattern for the different crowds. Extensive experiments prove that our proposed methods effectively fuse multiple trajectories and realize the crowd segmentation and the motion description. This will greatly help autonomous vehicles and control system perceive the surrounding pedestrians and the environment to make precise driving decisions.

Image-based three-dimensional (3D) reconstruction utilizes a set of photos to build 3D model and can be widely used in many emerging applications such as augmented reality (AR) and disaster recovery. Most of existing 3D reconstruction methods require a mobile user to walk around the target area and reconstruct objectives with a hand-held camera, which is inefficient and time-consuming. To meet the requirements of delay intensive and resource hungry applications in 5G, we propose an edge computing-based photo crowdsourcing (EC-PCS) framework in this paper. The main objective is to collect a set of representative photos from ubiquitous mobile and Internet of Things (IoT) devices at the network edge for real-time 3D model reconstruction, with network resource and monetary cost considerations. Specifically, we first propose a photo pricing mechanism by jointly considering their freshness, resolution and data size. Then, we design a novel photo selection scheme to dynamically select a set of photos with the required target coverage and the minimum monetary cost. We prove the NP-hardness of such problem, and develop an efficient greedy-based approximation algorithm to obtain a near-optimal solution. Moreover, an optimal network resource allocation scheme is presented, in order to minimize the maximum uploading delay of the selected photos to the edge server. Finally, a 3D reconstruction algorithm and a 3D model caching scheme are performed by the edge server in real time. Extensive experimental results based on real-world datasets demonstrate the superior performance of our EC-PCS system over the existing mechanisms.

With the growth of participating clients, the centralized parameter server (PS) will seriously limit the scale and efficiency of Federated Learning (FL). A straightforward approach to scale up the FL system is to construct a Parallel FL (PFL) system with multiple parallel PSes. However, it is unclear whether PFL can really accelerate FL or reduce the training time of FL. Even if the answer is yes, it is non-trivial to design a highly efficient parameter average algorithm for a PFL system. In this paper, we propose a completely parallelizable FL algorithm called P-FedAvg under the PFL architecture. P-FedAvg extends the well-known FedAvg algorithm by allowing multiple PSes to cooperate and train a learning model together. In P-FedAvg, each PS is only responsible for a fraction of total clients, but PSes can mix model parameters in a dedicatedly designed way so that the FL model can well converge. Different from heuristic-based algorithms, P-FedAvg is with theoretical guarantees. To be rigorous, we theoretically analyze the convergence rate of P-FedAvg in terms of the number of conducted iterations, the communication cost of each global iteration and the optimal weights for each PS to mix parameters with its neighbors. Based on theoretical analysis, we conduct a case study on five typical overlay topolgoies formed by PSes to further examine the communication efficiency under different topologies, and investigate how the overlay topology affects the convergence rate, communication cost and robustness of a PFL system. Lastly, we perform extensive experiments with real datasets to verify our analysis and demonstrate that P-FedAvg can significantly speed up FL than traditional FedAvg and other competitive baselines. We believe that our work can help to lay a theoretical foundation for building more efficient PFL systems.

Today’s Internet traffic has been dominated by video contents. To efficiently serve online videos for millions of users, it is essential to cache frequently requested videos on various devices such as edge servers, personal computers, etc. Existing caching algorithms are mainly designed by leveraging the information of past request records. However, it is insufficient to only use simple statistics of past request records,e.g., video popularity which ignores the occurrence time of past video request events and the discrepancies among individual devices. In this paper, we propose a radically different learning-based video caching algorithm for Internet devices, calledPPVC (Point Process based Video Cache)which can take exact video request patterns into account. By utilizing Hawkes Process (HP), we are able to link the future video request rates of a device with three kinds of historical records, namely, historical requests for the same video launched by the device itself, historical requests for the same video from other devices with a similar request pattern, and historical requests for other similar videos from the same device. The video request patterns can be efficiently computed via Singular Value Decomposition (SVD). Parameters linking these historical events can be determined by maximizing the likelihood of historical events. To further reduce the computation load, we also propose an online version of PPVC, which can timely update cached videos with the incremental arrival of events. One nice property of PPVC is that it can adapt to the change of video popularity very fast and is also applicable to Internet devices at different levels, ranging from the high-level servers that serve a large population of users to the low-level user devices (e.g., personal computers). Finally, we conduct extensive simulations with real traces and the results show that PPVC can always achieve the best video caching performance in terms of the hit rate on all levels of Internet devices, and quickly adapt to the dynamics of video requests.

Federated learning (FL) emerges as a promising paradigm to enable a federation of clients to train a machine learning model in a privacy-preserving manner. Most existing works assumed that the central parameter server (PS) determines the participation of clients implying that clients cannot make autonomous participation decisions. The above assumption is unrealistic because the participation in FL training may incur various cost and clients also have strong desire to be rewarded for participation. To address this problem, we design a novel autonomous client participation scheme to incentivize clients. Specifically, the PS provides a certain reward shared among participating clients for each training round. Clients decide whether to participate each FL training round or not based on their own utilities (i.e., reward minus cost). The process can be modeled as a minority game (MG) with incomplete information and clients end up in the minority side win after each training round because the reward of each participating client may not cover its cost if too many clients participate and vice verse. The challenge of autonomous participation schemes lies in lowering thevolatilityof participating clients in each round due to the lack of coordination among clients. Through solid analysis, we prove that: 1) The volatility of participating clients in each round is very high under the standard MG scheme. 2) The volatility of participating clients can be reduced significantly under the stochastic MG scheme. 3) A coalition based MG is proposed, which can further reduce the volatility in each round. By conducting extensive experiments in real settings, we demonstrate that the stochastic MG-based scheme outperforms other state-of-the-art algorithms in terms of utility and volatility, and the coalition MG-based client participation scheme can further boost the utility by 39%-48% and reduce the volatility by 51%–100%. Moreover, our algorithms can achieve almost the same model accuracy as that obtained by centralized client participation algorithms.

It is always a challenging problem to deliver a huge volume of videos over the Internet. To meet the high bandwidth and stringent playback demand, one feasible solution is to cache video contents on edge servers based on predicted video popularity. Traditional caching algorithms (e.g., LRU, LFU) are too simple to capture the dynamics of video popularity, especially long-tailed videos. Recent learning-driven caching algorithms (e.g., DeepCache) show promising performance, however, such black-box approaches are lack of explainability and interpretability. Moreover, the parameter tuning requires a large number of historical records, which are difficult to obtain for videos with low popularity. In this paper, we optimize video caching at the edge using a white-box approach, which is highly efficient and also completely explainable. To accurately capture the evolution of video popularity, we develop a mathematical model calledHRSmodel, which is the combination of multiple point processes, including Hawkes’ self-exciting, reactive and self-correcting processes. The key advantage of the HRS model is its explainability, and much less number of model parameters. In addition, all its model parameters can be learned automatically through maximizing the Log-likelihood function constructed by past video request events. Next, we further design an online HRS-based video caching algorithm. To verify its effectiveness, we conduct a series of experiments using real video traces collected from Tencent Video, one of the largest online video providers in China. Experiment results demonstrate that our proposed algorithm outperforms the state-of-the-art algorithms, with 15.5% improvement on average in terms of cache hit rate under realistic settings.

In today's Internet, recommender systems play an indispensable role in helping users discover items of interests, such as products, books, movies and so on. However, a higher recommendation accuracy is commonly at the cost of more disclosure of user privacy. Thus, a wider adoption of recommender systems poses significant security and privacy concerns to users. In this article, we propose a light-weight privacy-preserving framework calledRAPfor recommender systems, which can protect user privacy while still ensuring a high recommendation accuracy. Instead of directly sending users’ private ratings to the recommender, users first conduct a local perturbation operation on private ratings, and then send the perturbed ratings to the recommender. The recommender can run recommendation algorithms directly over the perturbed ratings and return the results to users. Different from crypto-based methods, our perturbation and de-perturbation methods are linear operations. Thus,RAPis light-weight and highly efficient in privacy protection. To be more rigorous, we formally prove that the order of recommendation accuracy will not decrease when ourRAPframework is applied to any MF (Matrix Factorization)-based recommender systems. We also derive the closed-form expression for the degree of privacy preservation of our framework. Finally, we conduct extensive evaluations using large-scale real-world datasets to verify the effectiveness of ourRAPframework and compare with other baseline algorithms. The results show that ourRAPframework can improve the degree of privacy preservation from zero to over 0.5 for theMovielensdataset and 4 for theJesterdataset, and still maintain the approaching level of recommendation accuracy.

With the growth of participating clients, the centralized parameter server (PS) will seriously limit the scale and efficiency of Federated Learning (FL). A straightforward approach to scale up the FL system is to construct a Parallel FL (PFL) system with multiple PSes. However, it is unclear whether PFL can really achieve a faster convergence rate or not. Even if the answer is yes, it is non-trivial to design a highly efficient parameter average algorithm for a PFL system. In this paper, we propose a completely parallelizable FL algorithm called P-FedAvg under the PFL architecture. P-FedAvg extends the well-known FedAvg algorithm by allowing multiple PSes to cooperate and train a learning model together. In P-FedAvg, each PS is only responsible for a fraction of total clients, but PSes can mix model parameters in a dedicatedly designed way so that the FL model can well converge. Different from heuristic-based algorithms, P-FedAvg is with theoretical guarantees. To be rigorous, we conduct theoretical analysis on the convergence rate of P-FedAvg, and derive the optimal weights for each PS to mix parameters with its neighbors. We also examine how the overlay topology formed by PSes affects the convergence rate and robustness of a PFL system. Lastly, we perform extensive experiments with real datasets to verify our analysis and demonstrate that P-FedAvg can significantly improve convergence rates than traditional FedAvg and other competitive baselines. We believe that our work can help to lay a theoretical foundation for building more efficient PFL systems.

The rapidly evolving technology of edge computing shows great potential in revolutionizing the market of cloud gaming. Edge computing can significantly lower the latency for better gaming experiences by performing computation at the proximity of game players. However, the acceleration of latency-sensitive cloud gaming services at the edge is challenging due to the heterogeneity of edge servers, different requirements among game players, and so on. In this paper, we propose an efficient latency-sensitive scheduling algorithm called EGSA to satisfy latency constraints for cloud gaming services at the edge. We first formulate the problem as a weighted congestion game, which takes a number of key factors (e.g., game genres, user strategies, latency constraint and device heterogeneity) into account. Based on the weighted congestion game model, we further design an efficient latency-sensitive scheduling algorithm, which can approximate the pure Nash equilibrium under Shapley cost-sharing method. We also perform theoretic analysis to prove that our proposed algorithm converges in polynomial steps. Finally, we conduct a set of experiments and the results show that our algorithm outperforms alternative strategies with up to 46% performance improvement.

The prevalence of personal devices motivates the rapid development of crowdsourced livecast in recent years. However, there exists huge diversity of upstream bandwidth among amateur broadcasters. Moreover, the highest video quality that can be streamed is limited by the hardware configuration of broadcaster devices (e.g., 540p for low-end mobile devices). The above factors pose significant challenges to the ingestion of high-resolution live video streams, and result in poor quality-of-experience (QoE) for viewers. In this paper, we propose a novel live video ingest approach called CrowdSR for crowdsourced livecast. CrowdSR can transform a low-resolution video stream uploaded by weak devices into a high-resolution video stream via super-resolution, and then deliver the stream to viewers. CrowdSR can exploit crowdsourced high-resolution video patches from similar broadcasters to speedup model training. Different from previous work, our approach does not require any modification at the client side, and thus is more practical and easy to implement. Finally, we implement and evaluate CrowdSR by conducting a series of real-world experiments. The results show that CrowdSR significantly outperforms the baseline approaches by 0.42-1.09 dB in terms of PSNR and 0.006-0.014 in terms of SSIM.

Variable Bitrate (VBR) video encoding can provide much high quality-to-bits ratio compared to the widely adopted Constant Bitrate (CBR) encoding, and thus receives significant attentions by content providers in recent years. However, it is challenging to design efficient adaptive bitrate algorithms for VBR-encoded videos due to the sharply fluctuating chunk size and the resulting bitrate burstiness. In this paper, we propose a neural adaptive streaming framework called Vibra for VBR-encoded videos, which can well accommodate the high fluctuation of video chunk sizes and improve the quality-of-experience (QoE) of end users significantly. Our framework takes the characteristics of VBR-encoded videos into account, and adopts the technique of deep reinforcement learning to train a model for bitrate adaptation. We also conduct extensive trace-driven experiments, and the results show that Vibra outperforms the state-of-the-art ABR algorithms with an improvement of 8.17% -- 29.21% in terms of the average QoE.

Recently, smart cities, healthcare system, and smart vehicles have raised challenges on the capability and connectivity of state-of-the-art Internet-of-Things (IoT) devices, especially for the devices in hotspots area. Multiaccess edge computing (MEC) can enhance the ability of emerging resource-intensive IoT applications and has attracted much attention. However, due to the time-varying network environments, as well as the heterogeneous resources of network devices, it is hard to achieve stable, reliable, and real-time interactions between edge devices and their serving edge servers, especially in the 5G ultradense network (UDN) scenarios. Ultradense edge computing (UDEC) has the potential to fill this gap, especially in the 5G era, but it still faces challenges in its current solutions, such as the lack of: 1) efficient utilization of multiple 5G resources (e.g., computation, communication, storage, and service resources); 2) low overhead offloading decision making and resource allocation strategies; and 3) privacy and security protection schemes. Thus, we first propose an intelligent UDEC (I-UDEC) framework, which integrates blockchain and artificial intelligence (AI) into 5G UDEC networks. Then, in order to achieve real-time and low overhead computation offloading decisions and resource allocation strategies, we design a novel two-timescale deep reinforcement learning (2Ts-DRL) approach, consisting of a fast-timescale and a slow-timescale learning process, respectively. The primary objective is to minimize the total offloading delay and network resource usage by jointly optimizing computation offloading, resource allocation, and service caching placement. We also leverage federated learning (FL) to train the 2Ts-DRL model in a distributed manner, aiming to protect the edge devices' data privacy. Simulation results corroborate the effectiveness of both the 2Ts-DRL and FL in the I-UDEC framework and prove that our proposed algorithm can reduce task execution time up to 31.87%.

At present, computed tomography (CT) is widely used to assist disease diagnosis. Especially, computer aided diagnosis (CAD) based on artificial intelligence (AI) recently exhibits its importance in intelligent healthcare. However, it is a great challenge to establish an adequate labeled dataset for CT analysis assistance, due to the privacy and security issues. Therefore, this paper proposes a convolutional autoencoder deep learning framework to support unsupervised image features learning for lung nodule through unlabeled data, which only needs a small amount of labeled data for efficient feature learning. Through comprehensive experiments, it shows that the proposed scheme is superior to other approaches, which effectively solves the intrinsic labor-intensive problem during artificial image labeling. Moreover, it verifies that the proposed convolutional autoencoder approach can be extended for similarity measurement of lung nodules images. Especially, the features extracted through unsupervised learning are also applicable in other related scenarios.

Video accounts for a large proportion of traffic on the Internet. Understanding its geographical viewing patterns is extremely valuable for the design of Internet ecosystems for content delivery, recommendation and ads. While previous works have addressed this problem at coarse-grain scales (e.g., national), the urban-scale geographical patterns of video access have never been revealed. To this end, this article aims to investigate the problem that whether there exists distinct viewing patterns among the neighborhoods of a large-scale city. To achieve this, we need to address several challenges including unknown of patterns profiles, complicate urban neighborhoods, and comprehensive viewing features. The contributions of this article include two aspects. First, we design a framework to automatically identify geographical video viewing patterns in urban neighborhoods. Second, by using a dataset of two months real video requests in Shanghai collected from one major ISP of China, we make a rigorous analysis of video viewing patterns in Shanghai. Our study reveals the following important observations. First, there exists four prevalent and distinct patterns of video access behavior in urban neighborhoods, which are corresponding to four different geographical contexts: downtown residential, office, suburb residential and hybrid regions. Second, there exists significant features that distinguish different patterns, e.g., the probabilities of viewing TV plays at midnight, and viewing cartoons at weekends can distinguish the two viewing patterns corresponding to downtown and suburb regions.

360-degree video streaming shows great potential to revolutionize the streaming market, by providing much better immersive experience than standard video streams. However, its wide adoption is hindered by the surging demand of network bandwidth due to multi-screen video transmission. To reduce the bandwidth cost, one promising approach is to predict a user’s field of view (FoV), and then prefetch video tiles that a user will view a few seconds ahead. The challenge lies in that user behaviors cannot be properly captured with very limited information, especially the viewing time spent on each tile and the FoV switching behavior are hard to predict. In this paper, we propose a novel 360-degree video streaming algorithm calledTVG-Streamingto optimize user experiences by learning user view behaviors. Different from previous approaches, our idea is to exploit tile-view graphs (TVGs) generated by real user behaviors and accurately estimate the probability that each tile falls in the FoV. With the tile view probability, we can determine the bitrate of each tile for delivery and buffering with limited bandwidth budget so as to maximize users’ quality of experience (QoE). For evaluation, we conduct extensive experiments using real traces and the results show that our proposedTVG-Streamingalgorithm significantly outperforms other algorithms by at least 20% improvement in terms of users’ QoE.

With increasing popularity of related applications of mobile crowdsensing, especially in the field of Internet of Vehicles (IoV), task allocation has attracted wide attention. How to select appropriate participants is a key problem in vehicle-based crowdsensing networks. Some traditional methods choose participants based on minimizing distance, which requires participants to submit their current locations. In this case, participants' location privacy is violated, which influences disclosure of participants' sensitive information. Many privacy preserving task allocation mechanisms have been proposed to encourage users to participate in mobile crowdsensing. However, most of them assume that different participants' task completion quality is the same, which is not reasonable in reality. In this paper, we propose an optimal location privacy preserving and service quality guaranteed task allocation in vehicle-based crowdsensing networks. Specifically, we utilize differential privacy to preserve participants' location privacy, where every participant can submit the obfuscated location to the platform instead of the real one. Based on the obfuscated locations, we design an optimal problem to minimize the moving distance and maximize the task completion quality simultaneously. In order to solve this problem, we decompose it into two linear optimization problems. We conduct extensive experiments to demonstrate the effectiveness of our proposed mechanism.

With the development of smart cities, Internet services will be pervasively accessible for moving vehicles. It is envisioned that the video content demand of vehicles will explode in the near future. However, the strategy to efficiently distribute video content in large-scale vehicular networks is still absent due to challenges arising from the huge video population, heavy bandwidth consumption, heterogeneous user devices, and vehicles’ mobility. In this work, we propose to collaboratively replicate video content on Roadside Units (RSUs) to enhance video distribution services based on the fact that the contact period between moving vehicles and a single RSU is not long enough to complete video downloading. In our design, a video file is split into multiple chunks. Each RSU replicates a small number of original chunks and chunks encoded by network coding. Replicating encoded chunks can reduce redundancy of chunks on different RSUs so that RSUs can complement each other better, whereas original chunks can be transrated to chunks with lower bitrates flexibly to fit in users’ devices. Therefore, we replicate both original and encoded chunks on RSUs to take advantages of both sides. Stochastic models are employed to analyze chunk download processes and a convex optimization problem is formulated to determine the optimal partition of space allocated to each kind of chunks. Furthermore, we extend our strategy to support video streaming services and empirically prove that the influence caused by limitations of network coding is moderate. In the end, we conduct extensive simulations which not only validate the accuracy of our models but also demonstrate that our strategy can effectively boost video distribution services.

In 360-degree video streaming, users commonly watch a video scene within aField of View (FoV). Such observation provides an opportunity to save bandwidth consumption by predicting and then prefetching video tiles within the FoV. However, existing FoV prediction methods seldom consider the diversity among user behaviors and the impact of different video genres. Thus, previous one-size-fits-all models cannot make accurate prediction for users with different behavior patterns. In this paper, we propose a user-aware viewport prediction algorithm calledSparkle, which is a practical whitebox approach for FoV prediction. Instead of training a single learning model to predict the behaviors for all users, our proposed algorithm is tailored to fit each individual user. In particular, unlike other learning models, our prediction model is completely explainable and all the parameters have their physical meanings. We first conduct a measurement study to analyze real user behaviors and observe that there exists sharp fluctuation of view orientation and user posture has significant impact on the viewport movement of users. Moreover, cross-user similarity is diverse across different video genres. Inspired by these insights, we further design a user-aware viewport prediction algorithm by mimicking a user's viewport movement on the tile map, and determine how a user will change the viewport angle based on his (or her) trajectory and other similar users’ behaviors in the past time window. Extensive evaluations with real datasets demonstrate that, our proposed algorithm significantly outperforms the state-of-the-art benchmark methods (e.g., LSTM-based methods) by over$\text{5}\%$, and the prediction accuracy is much more stable on various types of 360-degree videos than previous methods.

With the advent of the Internet era, the trend of highly informed society has been becoming more and more obvious, and the requirement of society on communication is also increasing. flexible satellite communication mode has many advantages such as large communication load and no geographic restriction, which cannot be replaced by other communication modes. In the satellite communication system, the most important is the satellite earth station (SES). When receiving signals from the target satellite, the SES terminal must accurately point to the satellite and track it to obtain the maximum receiving signal and reduce the interference with other signals simultaneously. However, the motion of either satellite or terminal can cause a change in signal intensity, so it is necessary to adjust the pointing of the SES antenna in time to maintain optimal signal receiving conditions. In order to satisfy different satellite communication scenarios, in this paper, Artificial intelligent (AI) technology is applied to the satellite communication process, mainly to optimize the optimal antenna angle and time consumption reduction. Firstly, the process of antenna pointing is introduced, and the traditional antenna search algorithm Auto-Acqire algorithm (AA algorithm) is analyzed in detail. Considering that the satellite system needs to adapt to the communication requirements of different terminals, based on AI antenna pointing algorithms are proposed. In order to verify this research, we build an experimental platform and compare the traditional AA algorithm as a benchmark algorithm with FI-GRU and II-DRL algorithms. According to the experimental results, the two algorithms proposed in this paper can improve the efficiency of satellite pointing and tracking tasks.

The following topics are dealt with: cloud computing; Internet of Things; learning (artificial intelligence); virtual machines; mobile computing; security of data; resource allocation; scheduling; software engineering; regression analysis.

360-degree videos have gained increasing popularity due to its capability to provide users with immersive viewing experience. Given the limited network bandwidth, it is a common approach to only stream video tiles in the user's Field-of-View (FoV) with high quality. However, it is difficult to perform accurate FoV prediction due to diverse user behaviors and time-varying network conditions. In this paper, we re-design the 360-degree video streaming systems by leveraging the technique of super-resolution (SR). The basic idea of our proposed SR360 framework is to utilize abundant computation resources on the user devices to trade off a reduction of network bandwidth. In the SR360 framework, a video tile with low resolution can be boosted to a video tile with high resolution using SR techniques at the client side. We adopt the theory of deep reinforcement learning (DRL) to make a set of decisions jointly, including user FoV prediction, bitrate allocation and SR enhancement. By conducting extensive trace-driven evaluations, we compare the performance of our proposed SR360 with other state-of-the-art methods and the results show that SR360 significantly outperforms other methods by at least 30% on average under different QoE metrics.

Recent years have witnessed great success of mobile short-form video apps. However, most current video streaming strategies are designed for long-form videos, which cannot be directly applied to short-form videos. Especially, short-form videos differ in many aspects, such as shorter video length, mobile friendliness, sharp popularity dynamics, and so on. Facing these challenges, in this paper, we perform an in-depth measurement study on Douyin, one of the most popular mobile short-form video platforms in China. The measurement study reveals that Douyin adopts a rather simple strategy (called Next-One strategy) based on HTTP progressive download, which uses a sliding window with stop-and-wait protocol. Such a strategy performs poorly when network connection is slow and user scrolling is fast. The results motivate us to design an intelligent adaptive streaming scheme for mobile short-form videos. We formulate the short-form video streaming problem and propose an adaptive short-form video streaming strategy called LiveClip using a deep reinforcement learning (DRL) approach. Trace-driven experimental results prove that LiveClip outperforms existing state-of-the-art approaches by around 10%-40% under various scenarios.

Federated collaborative filtering (Fed-CF) is a variant of federated learning (FL) models, which can protect user privacy in recommender systems. In Fed-CF, the recommendation model is collectively trained across multiple decentralized clients by exchanging gradients only. However, the decentralized nature of Fed-CF makes it vulnerable to shilling attacks, which can be realized by inserting fake ratings of target items to distort recommendation results. Unfortunately, previous detection algorithms cannot work well in the FL framework, as all original data samples are not disclosed at all. In this paper, we are the first to systematically study the problem of shilling attacks in the context of federated learning, and propose an effective detection method called Federated Shilling Attack Detector (FSAD) to detect shilling attackers in Fed-CF. We first show the feasibility of shilling attacks in Fed-CF. Next, we dedicatedly design four novel features based on exchanged gradients among clients. By incorporating these gradient-based features, we train a semi-supervised Bayes classifier to identify shilling attackers effectively. Finally, we conduct extensive experiments based on real-world datasets to evaluate the performance of our proposed FSAD method. The experimental results show that FSAD can detect shilling attackers in Fed-CF with high accuracy, with the F1value as high as 0.90 on the Netflix dataset, which approaches the performance of the optimal detector that utilizes complete private user information for detection.

With the development of Internet of Things (IoT) and communication technology, the number of next-generation IoT devices has increased explosively, and the delay requirement for content requests is becoming progressively higher. Fortunately, the edge-caching scheme can satisfy users' demands for low latency of content. However, the existing caching schemes are not smart enough. To address these challenges, we propose a human-like hybrid caching architecture based on the software-defined edge cloud, which simultaneously considers the content popularity and the fine-grained user characteristics. Then, an optimization problem with a caching hit ratio as an optimization objective is formulated. To solve this problem, using reinforcement learning, we design a human-like hybrid caching algorithm. The extensive experiments show that compared with popular caching schemes, human-like hybrid caching schemes can improve the cache hit ratio by 20%.

Task offloading is one of key operations in edge computing, which is essential for reducing the latency of task processing and boosting the capacity of end devices. However, the heterogeneity among tasks generated by various users makes it challenging to design efficient task offloading algorithms. In addition, the assumption of complete information for offloading decision-making does not always hold in a distributed edge computing environment. In this article, we formulate the problem of heterogeneous task offloading in a distributed environment as a minority game (MG), in which each player must make decisions independently in each turn and the players who end up on the minority side win. The multi-player MG incentivizes players to cooperate with each other in the scenarios with incomplete information, where players don't have full information about other players (e.g., the number of tasks, the required resources). To address the challenges incurred by task heterogeneity and the divergence of naive MG approaches, we propose an MG based scheme, in which tasks are divided into subtasks and instructed to form into a set of groups as possible, and the left ones are scheduled to perform decision adjustment in a probabilistic manner. We prove that our proposed algorithm can converge to a near-optimal point, and also investigate its stability and price of anarchy in terms of task processing time. Finally, we conduct a series of simulations to evaluate the effectiveness of our proposed scheme and the results indicate that our scheme can achieve around 30% reduction of task processing time compared with other approaches. Moreover, our proposed scheme can converge to a near-optimal point, which cannot be guaranteed by naive MG approaches.

Edge computing is envisioned to be the de-facto paradigm of hosting emerging low latency Internet-of-Things (IoT) data streaming services.For IoT data streaming in edge computing, cost management is of strategic significance, due to the low cost-efficiency of edge servers. While existing literature adopts a reactive approach to dynamically provisioning edge servers to reduce cost, the delay of server activation and instantiation has been mostly ignored. In this paper, we target a proactive approach to dynamic edge server provisioning for real-time IoT data streaming across edge nodes, which adjusts server provisioning ahead of time, based on prediction of the upcoming workload. To effectively predict upcoming workload, a learning-based method online gradient descent is applied. We further combine the online learning method with an online optimization algorithm for server provisioning in a joint online optimization framework, through (1) minimizing of the regret incurred by inaccurate workload prediction, and (2) minimizing the cost incurred by near-optimal online decisions. The resulting predictive online algorithm can well leverage the power of prediction and achieve a good performance guarantee, as verified by both rigorous theoretical analysis and extensive trace-driven evaluations.

Confronting with the sheer amount of Over-the-Top (OTT) videos, personalized recommendation is especially important for users to locate videos of interest. However, previous approaches seldom considered the influence of watching time when designing video recommendation algorithms. In this paper, we first conduct a detailed measurement study on a leading OTT video service provider in China and our results show that user view preferences are substantially influenced by watching time. Based on the above results, we further propose a personalized time-aware video recommendation algorithm called TAMF for OTT videos. The basic idea of our proposed TAMF algorithm is to utilize matrix factorization to unveil how watching time affects user view interests and cluster time slots with similar influence. In this way, we can collaboratively learn users' personal interests if their views belong to the same cluster, and precisely capture user view preferences with watching time. Finally, we also conduct extensive experiments using real traces to evaluate the performance of our algorithm, and the experimental results show that our proposed algorithm can improve video recommendation performance by 4.83% and 4.42% in terms of WMRR and WMAP respectively and significantly boost user engagement.

Mobile edge computing helps healthcare Internet of Things (IoT) devices with energy harvesting provide satisfactory quality of experiences for computation intensive applications. We propose a reinforcement learning (RL)-based privacy-aware offloading scheme to help healthcare IoT devices protect both the user location privacy and the usage pattern privacy. More specifically, this scheme enables a healthcare IoT device to choose the offloading rate that improves the computation performance, protects user privacy, and saves the energy of the IoT device without being aware of the privacy leakage, IoT energy consumption, and edge computation model. This scheme uses transfer learning to reduce the random exploration at the initial learning process and applies a Dyna architecture that provides simulated offloading experiences to accelerate the learning process. A post-decision state learning method uses the known channel state model to further improve the offloading performance. We provide the performance bound of this scheme regarding the privacy level, the energy consumption, and the computation latency for three typical healthcare IoT offloading scenarios. Simulation results show that this scheme can reduce the computation latency, save the energy consumption, and improve the privacy level of the healthcare IoT device compared with the benchmark scheme.

The interactive robot is expected to support emotion analysis and utilize the deep learning and machine learning to provide users with continuous emotional care. However, it is a great challenge to securely acquire sufficient data for emotion analysis such that the privacy of emotional data is adequately protected. To address the security issue, this paper proposes a security policy based on identity authentication and access control to ensure the security certificate through an interactive robot or edge devices while the access control of private data stored in the edge cloud is adequately protected. Specifically, this paper adopts a polynomial-based access control policy and designs a secure and effective access control scheme. At the same time, this paper puts forward an identity authentication mechanism in view of edge cloud systems, which can reduce the computational overhead and authentication delay in a collaborative authentication of multiple edge clouds. The effectiveness of the proposed access control policy and identity authentication mechanism is verified by an actual testbed platform.

Edge computing emerges as a promising paradigm to decentralize computation power to the edge of the network and thus improve user experience by task offloading. A user can perfectly schedule his tasks to be executed on edge servers if the execution time of all tasks can be known beforehand. However, it is difficult to know the task execution time (TET) before performing actual offloading, which normally varies on edge servers with different software and hardware configurations. Moreover, such configuration information is not always available to end users due to security concerns. In this paper, we first propose a learning-driven algorithm to accurately predict TETs of all tasks in such an asymmetrically informed edge computing environment. The basic idea is to predict unknown TETs using only a small sampled set of TETs by exploiting the underlying correlation between TETs and edge server configurations. Next, we formulate the problem of task offloading into a constrained optimization problem, which is unfortunately proved to be NP-hard. To address the above challenge, we design a task offloading algorithm, called Maximum Efficiency First Ordered (MEFO), to achieve near-optimal efficiency. Field measurements and experiments have been conducted to demonstrate that our proposed learning-driven algorithm can predict TETs more accurately than other algorithms as long as the fraction of sampled TETs is larger than a small predefined threshold, and our proposed MEFO algorithm achieves a much higher success rate of task offloading and a shorter processing delay with very limited information of edge servers.

With the advance of cloud computing and 4G/5G technology, video contents recorded by in-car cameras (i.e., vehicular digital video recorders) can be uploaded to the cloud to facilitate accident analysis, online surveillance, video sharing, etc. However, the cost of uploading such huge volume of video contents via unstable vehicular access networks (including cellular base stations and road-side units) can be considerable by considering the increasing video quality requirement, time constraint, and limited local buffer space. In this paper, we propose an adaptive video recording and uploading scheme to maximize the overall utility of cloud-based in-car video uploading over vehicular access networks. Specifically, the utility function is defined as the weighted sum of bandwidth cost and video quality and we formulate the problem into a constrained Markov decision process (MDP). Based on the theoretic foundation of MDP, we design and implement an algorithm to obtain an adaptive chunk uploading policy for video contents over vehicular access networks. Extensive simulations have been conducted to demonstrate that our policy can achieve the best performance compared with other alternative strategies.

Recent proliferation of mobile networks and smart devices drives the rapid growth of mobile video traffic. Caching popular video content at any possible place of the network near to users could significantly increase their delivery efficiency. However, fundamental problems of how cache behaves and what is the principle for cache deployment in a mobile network under large-scale video views are still unknown, which include three closely relevant problems: 1) what is the best scale of regions to deploy cache appliances; 2) how many contents should be cached; and 3) which contents should be cached. In this paper, we synthetically study these problems by analyzing 10 million video view requests of six most popular content providers, in the city of Shanghai, China. We first aggregate videos from different providers by topics to measure user interests, and divide the city into nonoverlapping regions of different sizes to investigate the influence of scale. Then, we define metrics of view concentration, popular topic number, cache revenue, and popular topic similarity to quantitatively characterize cache behaviors and consequently answer the three problems. Our studies reveal that: 1) it is effective to deploy cache in regions of a wide range of different scales; 2) the larger scale region and the regions with more views should cache more contents; and 3) different regions, especially small scale ones, should cache different contents. Furthermore, based on trace-driven evaluation, we show that the overall cache hit ratio can increase by up to 30% when we apply above guidelines for cache deployment.

Recently, crowdsourcing-based content delivery networks (CDN) emerge as a promising technology that can distribute massive video content to a vast number of Internet users by crawling bandwidth and storage resources from Internet end devices. Any ordinary Internet users with excessive resources can be recruited into such systems as mini-servers. Different from edge servers equipped with dedicated resources in traditional CDNs, the resource of a single mini-server is scarce and volatile that can vary severely with time, since its bandwidth is shared by many different applications. How to build a robust high performance crowdsourcing-based CDN system has attracted contributions from both academia and industry, but how to solve the drawback caused by unstable uploading bandwidth is still a challenging problem. So far, a prevalent methodology is to migrate the strategies implemented by traditional CDNs into crowdsourcing-based CDN systems based on the fact that these two kinds of systems share many similarities. In this paper, our argument is that the content delivery time can be reduced by replicating coded content on mini-servers (which is almost useless for edge servers in traditional CDNs) to enable downloading users to automatically adapt their downloading progress with oscillating bandwidth capacity from different mini-servers. Theoretical model is created to derive the performance improvement (evaluated in term of average file downloading time) achieved by our strategy, which is further validated via simulation. This paper not only provides system designers a more efficient content replication solution, but also can push forward the development of the crowdsourcing-based CDNs.

The knowledge of view preferences of users is crucial for online video providers to improve their system operations and video recommendations. However, it is challenging to accurately acquire this knowledge by merely relying on a single online video system. In this paper, we conduct a joint statistical study using the cross-platform information obtained from Douban, the largest online video database with video rating functionality in China, and Youku, one of the largest online video streaming systems in China. The Douban dataset includes feedbacks (e.g., movie ratings, comments, and reviews) from all users of different online video systems, and movie metadata (e.g., release date, actors, and directors), based on which we can statistically explore effective and significant factors attributing to video view counts. Meanwhile, our study unveils user behaviors that are latent when only observing a single video system. Finally, a multiple correlation analysis reveals that factors extracted from Douban can significantly increase our ability to predict video view counts. Our study can benefit video caching, video procurement, and advertisement campaign for online video providers.

All large-scale online video systems, for example, Netflix and Youku, make a significant investment on video recommendations that can dramatically affect video information diffusion processes among users. However, there is a lack of efficient methodology to interpret how various recommendation mechanisms affect information diffusion processes resulting in the difficulty to evaluate video recommendation efficiency. In this paper, we propose to quantify and explain video recommendation mechanisms by using epidemic models to mine video view count traces. It is well known that an epidemic model is an efficient approach to model information diffusion processes; while view count traces can be viewed as the results of video information diffusion driven by video recommendations. Thus, we propose a framework based on extended epidemic models to quantify and interpret two recommendation mechanisms, that is, direct and word-of-mouth (WOM) recommendations, by fitting video view count traces collected from Tencent Video, a large-scale online video system in China. Our approach is a novel methodology to evaluate video recommendation mechanisms, and a new perspective to interpret how recommendation mechanisms drive view count evolution.

With the growing popularity of mobile devices, a new type of peer-to-peer communication mode for mobile cloud computing has been introduced. By applying a variety of short-range wireless communication technologies to establish connections with nearby mobile devices, we can construct a mobile cloudlet in which each mobile device can either works as a computing service provider or a service requester. Although the paradigm of mobile cloudlet is cost-efficient in handling computation-intensive tasks, the understanding of its corresponding service mode from a theoretic perspective is still in its infancy. In this paper, we first propose a new mobile cloudlet-assisted service mode named Opportunistic task Scheduling over Co-located Clouds (OSCC), which achieves flexible cost-delay tradeoffs between conventional remote cloud service mode and mobile cloudlets service mode. Then, we perform detailed analytic studies for OSCC mode, and solve the energy minimization problem by compromising among remote cloud mode, mobile cloudlets mode and OSCC mode. We also conduct extensive simulations to verify the effectiveness of the proposed OSCC mode, and analyze its applicability. Moreover, experimental results show that when the ratio of data size after task execution over original data size associated with the task is smaller than 1 (i.e.,r<; 1) and the average meeting rate of two mobile devices λ is larger than 0:00014, our proposed OSCC mode outperforms existing service modes.

The online video streaming service is of huge market values with billions of worldwide users. For online video providers, e.g., Netflix, Youku, the crucial question is how to understand users' view behaviors and preferences because this knowledge is important for their business operation. Existing solutions mainly rely on analyzing users' historical view records, which however are not always available, especially for new videos and unprovided videos. Different from existing solutions, we propose to infer user behaviors and preferences by jointly analyzing data collected from multiple platforms (e.g., video streaming systems, video databases, etc.). In particular, we use the movie data crawled from a leading video streaming system (i.e., Youku), and a well-known video database in China (i.e., Douban) for this study. Our investigation points out that movie quality (evaluated in terms of Douban scores) and release date jointly influence viewers' preferences. In addition, we reveal a series of user behaviors, e.g., users are reluctant to post comments or ratings for movies they do not like, and user eyeballs are heavily captured by new movies. Understanding of these user behaviors covered by this study is essential for video recommendation and video popularity prediction which can benefit video procurement and advertisement campaign.

With the astronomical growth of online video population, the video recommendation system is crucial for users to locate videos fitting their interests. The collaborative filtering (CF) realizing personalized recommendation by analyzing users' historical view records is currently the most prevalent algorithm adopted by existing systems. Nevertheless, video recommendation performance can be improved for most cases, particularly the one with cold-start problem, if additional information is involved. In this article, we propose an AP-based Context-Aware (APCA) recommendation scheme on top of the traditional factor-based CF algorithm by utilizing the information of access points which has not been explored yet by existing works. The underlying principle is that users' view preferences are expected to be different with different contexts, e.g., hotel, home, public areas, which can be inferred by mining the information of access points via which users launch video requests. With the data collected from Tencent Video, a leading online video provider in China, we present a measurement study to show user view preferences in different contexts before our APCA algorithm is introduced. Experiments are executed driven by the trace data collected from Tencent Video to validate the effectiveness of our scheme in improving recommendation performance.

Recent advances in mobile devices (e.g., smartphones and wearables) and wireless technologies are fueling a new wave of user demands for an improved user experience. Indeed, users are not only expecting ubiquitous network connections for traditional services (e.g., messaging and calling), but also demanding extensive access to a wealth of video contents and services. However, this growing demand is seriously hindered by the fact that the onboard resources with mobile devices are inherently limited and their growth rate falls behind that of their desktop counterparts. It follows that new solutions should be in order to resolve this fundamental tussle. Fortunately, the emerging cloud computing offers a natural solution to extend the desktop visual experience to mobile devices. It actually provides both computational and storage support for media-rich applications with both front-end and back-end functionalities.

In recent years, empowered by rich media generation devices and convenient Internet access, Crowdsourced Live Game Video Streaming (CLGVS) has become one of the most popular Internet services. Twitch.tv, the most well-known CLGVS platform in the world, allows gamers to broadcast their gaming videos over the Internet. With the prevalence of mobile devices, viewers can watch gamers playing video games anywhere, anytime, on any devices (e.g., smartphones, tablets, or personal computers). However, the heterogeneity of user devices makes conventional solutions hard to ensure user-perceived quality. In this paper, we address the problem of cost-effective adaptive live game video streaming from the perspective of CLGVS service providers. Our purpose is to minimize the operational cost for CLGVS service providers by making live transcoding decisions, bit-rate adaptation decisions, and datacenter assignment decisions dynamically. Meanwhile, our algorithm also ensures good-enough service quality for viewers. Due to the diversity of game genres, we also consider game genres when designing our algorithm. To achieve the above purpose, we formulate the problem into a constrained stochastic optimization problem. By leveraging the Lyapunov optimization framework, we derive the online strategy with provable performance bound. To evaluate the effectiveness of our proposed algorithm, we further conduct a series of trace-driven simulations. The experimental results demonstrate the effectiveness of our algorithm in terms of operational cost and service quality. Our proposed algorithm can reduce operational cost by up to 50% while achieving good-enough viewer QoE compared with other alternatives.

With the ever-growing number of users enjoying online video service in mobile environments, video streaming services have been dominating the mobile traffic. It can be predicted that a small improvement in the user's watching experience will cause a substantial leap in profitability in terms of content providers and distributors, network operators and service providers for mobile videos. Though recent years have witnessed effective efforts to improve a user's video quality of experience (QoE) by the use of big data for analyzing users' viewing behaviors based on large-scale, video- viewing history datasets, it is very challenging to precisely analyze users' hidden intents and feelings when they are watching online videos. In addition to obtain a better video QoE, we propose to introduce user's emotional reactions into QoE assessment. In this scheme, first, the user's mood is detected in a real time fashion via emotion detection networking. Then, a mood matching process is performed to gain the similarity of the user's intent and the video content property in terms of emotion design. Finally, a novel, decision tree-based adjustment model is proposed to characterize the relationship between QoE and various factors, including buffer ratio, average bitrate, and the user's emotions. Our study opens a road for improving video QoE based on emotion detection networking.

Multimedia transmissions for IoT (Internet-of-Things) sensing has a high demand of route capacity and tight requirements of end-to-end delay. In this paper, we address the problems on how to guarantee delay-related QoS requirements and to balance the energy consumption, while using multipath routing to offer high transmission capability for IoT multimedia sensing. This motivates us to design a Multipath Planning for Single-Source based transmissions routing scheme, namely MPSS, which establishes desirable multiple route paths following B-spline trajectories based on geographical information of source and sink node, sending and receiving angles, and inter-path distance. We further utilize a factor of hop distance to reduce the cumulated error of each hop due to the density of nodes, and to guarantee the delay-related QoS requirements. A Multipath Planning for Multi-Source routing scheme is also designed, namely MPMS, to assign the angle scope according to the source node's priority and traffic. Experimental results show that MPSS can effectively generate well-patterned multiple spline-based routes, and the end-to-end delay is under control according to the delay QoS requirement, while the total energy consumption is minimized.

The upsurge of cloud video recording (CVR) has gained increasing attention from the general public and entrepreneurs. With live video records archived in the cloud, the CVR paradigm enables various smart services by keeping track of activities in the monitored region from anywhere at any time. However, the limited upstream bandwidth affects the quality of surveillance when multiple distributed cameras share the same upstream link. To solve the problem, this paper proposes an efficient upstream bandwidth multiplexing algorithm to intelligently allocate upstream bandwidth for each live video stream while maximizing the overall utility from the perspective of a CVR user. Specifically, we formulate the upstream bandwidth multiplexing problem as a constrained stochastic optimization problem, and apply the technique of hierarchical approximation to solve it efficiently. Our algorithm can be extended to take the priority of video streams into account and allocate more upstream bandwidth to video streams with higher priorities. We explicitly prove the approximation ratio of the proposed algorithm. In addition, we also conduct extensive trace-driven simulations to verify the effectiveness of our algorithm. The simulation results show that our algorithm improves the overall CVR user utility by over 20% compared with other alternatives, and the average utility per bandwidth unit is guaranteed to be stable even when the number of video streams increases.

In the era of mobile Internet, mobile game apps (i.e., applications) enable users to play games on mobile devices anywhere at any time. Such a change has brought a dramatic revolution to the traditional gaming industry. In this paper, we aim at having a comprehensive understanding of the ecosystem of mobile game apps. To this purpose, we conduct a large-scale measurement study over all game apps hosted by four leading app stores in China, which cover both Android and iOS platforms. We collect information of over 75000 mobile game apps in a period of three months (October 2014-January 2015). With obtained datasets, we study the scale, evolution, and overlap of game apps in different app stores from a macroscopic level. We find that none of major app stores can provide a complete set of all game apps. We also investigate download patterns of mobile game apps and the impacts brought by user comments and ratings. We observe clear Pareto effect and power-law effect for game app downloads, and there is no strong positive correlation between app score and the number of its downloads. Last, we characterize the features of popular and unpopular game apps and confirm the negative impacts of embedded ads and paid items. We believe our measurement results can provide useful insights and advice for users, developers, and app store operators.

Performance of multihop cooperative sensor networks depends on relaying candidate selection, optimal relay assignment, and cooperative communication. In this paper, we first propose a novel relaying candidate selection scheme (KCN-selection) to choose k-cooperative nodes (KCN) at each hop based on geographic information, while the certain number of k is initially determined based on an on-demand end-to-end (ETE) reliability in the presence of unreliable communication links. However, the pre-assigned KCN cannot ensure an optimal performance due to wireless channel dynamics. To prolong the lifetime of wireless sensor network (WSN), we schedule some part of KCN to sleep while the on-demand ETE reliability still can be guaranteed with wireless channel variations. A probabilistic ETE reliability model is built to compute optimal duty cycle for KCN in an online manner. Furthermore, a KCN based optimal relay assignment and cooperative data delivery (KCN-delivery) scheme is presented, which can provide fully stateless, energy-efficient sensor-to-sink data delivery at a low communication overhead without the help of prior neighborhood knowledge. Simulation results show that our scheme significantly outperforms existing protocols in wireless sensor networks with highly dynamic wireless channel.

In order to improve the accuracy and efficiency of emotion recognition, we design a novel system called Learning through Interactive Video and Emotion-aware System (LIVES). LIVES includes data collection, emotion recognition, and result validation, as well as emotion feedback. We adopt transfer learning to label and validate moods in LIVES, while the emotion can be classified into six types of mood in a reasonable accuracy. Through transfer learning, the time-consuming and labor-intensive processing cost on data collection and labeling can also be greatly reduced. In our prototype system, LIVES is used to enhance an emotion-aware robot's intelligence provided by cloud. LIVES-based emotion recognition is executed in the remote cloud while corresponding result is sent to the robot for emotion feedback. The experimental results demonstrate LIVES significantly improves the accuracy and effective of emotion classification.

Privacy leakage has become a growing concern for microblogging social networks. While the use of social networks facilitates information sharing and collaboration, many users are disclosing their sensitive information in the meanwhile. In this paper, we aim to better understand privacy leakage in the microblogging social networks. Towards this, we conducted a comprehensive measurement study to investigate the privacy problem in the largest microblogging social network in China from macroscopic, medium-scopic, and microscopic perspectives. For the macroscopic analysis, we analyzed the profile pages of 1.57 million users and obtained a broad picture on the openness of users and the leakage of user-sensitive information via their profile pages. We find that verified users prefer to disclose more information on their profile pages than unverified users, and the youth and singles normally have a higher open degree. For the medium-scopic analysis, we investigated the social links among Weibo users and show the feasibility to identify the closest friends of a user. For the microscopic analysis, we explored in-depth a small set of users by textual analysis and manual analysis. We observe that unverified users leak slightly more privacy than verified users, and males are only a bit more open than females. We can further identify the location, age, and daily activities of a user by manually analyzing their public information on the Weibo. In addition to providing insight into the severity of privacy leakage, we also discuss a few possible solutions to protect user privacy in the microblogging social networks. Copyright © 2015John Wiley & Sons, Ltd.

Cloud gaming has become a new trend for gamers to access high-end video games. By rendering games in the remote cloud and streaming video scenes to the users, games can be played anywhere, anytime, on any device (e.g., smartphones, tablets, or personal computers). In this paper, we address the problem of achieving cost-effective adaptive cloud gaming in geo-distributed data centers from the perspective of cloud gaming service providers (CGSPs). Unlike previous work, we consider a cloud gaming system supported with the adaptive streaming technology. Our purpose is to minimize the overall service cost for CGSPs, by adaptively adjusting the selection of data centers, virtual machine allocation and video bitrate configuration for each user. Meanwhile, we also need to ensure good-enough quality of experience (QoE) for gamers. To this objective, we formulate the problem into a constrained stochastic optimization problem, and apply the Lyapunov optimization theory to drive the corresponding online strategy with provable upper bounds. Due to the diverse QoE requirements of video games, we also take the difference among game genres into account during the algorithm design. Finally, we conduct extensive trace-driven simulations to evaluate the effectiveness of our algorithm and our results show that our proposed algorithm can achieve significant gain over other alternative approaches.

Cloud gaming has emerged as a promising approach to more affordable and accessible games. By rendering high-end video games in the cloud and streaming encoded game scenes to players via the broadband networks, users are relieved from downloading or installing game software. With cloud gaming, users can easily play high-end 3-D video games on any devices anytime and anywhere. In this paper, we conducted a comprehensive measurement study of a leading cloud gaming system in China, namely, CloudUnion. Unlike the previous work, our measurement study was based on an in-depth understanding of the internal mechanisms of CloudUnion, and thus we were able to reveal problems that cannot be observed in a black-box approach. We built a dedicated measurement platform, which enables us to study CloudUnion from different views, including the global view, local view, and user view. We also conducted a comparison study with another cloud gaming system, namely, GamingAnywhere. Our measurement results unveil the pros and cons of the current cloud gaming system design, and bring forth important insights about the cloud infrastructure, user behaviors, traffic patterns, user-perceived quality, and so on. Our work will be valuable for the design of future cloud gaming systems.

The increasing popularity of online social networks (OSNs) has been transforming the dissemination pattern of social video contents. Considering the unique features of social videos, e.g., huge volume, long-tailed, and short length, how to utilize the information propagation pattern to improve the efficiency of content distribution for social videos attracts more and more attention. In this paper, we first conduct a large scale measurement to explore the social video viewing behavior under the community classification. Based on the measurement, we investigate the community driven sharing video distribution problem under the cloud-centric content delivery network (CDN) architecture. In particular, we formulate it as a constrained optimization problem with the objective to minimize the operational cost. The constraint is the averaged transmission delay. Following that, we propose a dynamic algorithm to seek the optimal solution. Our trace-driven experiments further demonstrate our algorithm can make a better tradeoff between monetary cost and QoS, and outperforms the traditional method with less operational cost while satisfying the QoS requirement.

The emergence of cloud computing provides a cost-effective approach to deliver video streams to a large number of end users with the desired user quality of experience (QoE). Under such a paradigm, a video service provider (VSP) can launch its own video streaming services virtually by renting the distribution infrastructure from one or more cloud service providers (CSPs). However, CSPs such as Amazon EC2 normally offer multiple pricing options for virtual machine (VM) instances that they can provide, such as on-demand instances, reserved instances, and spot instances. Such diverse pricing models make it challenging for a VSP to determine how to optimally procure the required number of VM instances in different types to satisfy dynamic user demands. Given the limited budget, a VSP needs to carefully balance the procurement cost and the achieved QoE for end users. In this paper, we investigate the tradeoff between the cost incurred by VM instance procurement and the achieved QoE of end users under Amazon EC2's pricing models, and formulate the VM instance provisioning and procurement problem into a constrained stochastic optimization problem. By applying the Lyapunov optimization framework, we design an online procurement algorithm, which approaches the optimal solution with explicitly provable upper bounds. We also conduct extensive trace-driven simulations and our results show that our proposed algorithm (OPT-ORS) achieves a good balance between the procurement cost and the user QoE for cloud-based VSPs. In the achieved near-optimal situation, our algorithm guarantees that reserved VM instances are fully utilized to satisfy the baseline user demand, on-demand VM instances are only rented to handle flash crowds, while more spot VM instances are rented than on-demand VM instances to serve user demand over the baseline due to their low prices.

As a new paradigm, cloud gaming allows users to play high-end video games instantly without downloading or installing the original game software. In this paper, we first conduct a series of well-designed active and passive measurements on a large-scale cloud gaming platform and identify the significant diversity in the queueing delay and response delay among users. We note that the latency problem largely results from user-specified request routing and inelastic server provisioning. To address latency problem of the cloud gaming platform, we further propose an online control algorithm called iCloudAccess to perform intelligent request dispatching and server provisioning. Our main objective is to cut down the provisioning cost of cloud gaming service providers while still ensuring the user quality-of-experience requirements. We formulate the problem as a constrained stochastic optimization problem and apply the Lyapunov optimization theory to derive the online control algorithm with provable upper bounds. We also conduct extensive trace-driven simulations to evaluate the effectiveness of our algorithm, and our results show that our proposed algorithm achieves significant gain over other alternative approaches.

Mobile video traffic, owing to the rapid adoption of smartphones and tablets, has been growing exponentially in recent years and started to dominate the mobile Internet. In reality, mobile video applications commonly adopt buffering techniques to handle bandwidth fluctuation and minimize the impact of stochastic wireless channels on user experiences. However, recent measurement work reveals that mobile users tend to abort more frequently than PC users during viewing videos. Such a high abortion rate results in a significant wastage of buffered video data, which is directly translated into monetary and energy cost for mobile users. In this paper, we propose an intelligent buffer management strategy called CBM (Cost-aware Buffer Management), for mobile video streaming applications. Our purpose is to minimize cost induced by un-consumed video data while respecting certain user experience requirements. To this objective, we formulate the problem into a constrained stochastic optimization problem, and apply the Lyapunov optimization theory to derive the corresponding online strategy for cost minimization. Different from conventional heuristic-based strategies, our proposed CBM strategy can provide provably performance guarantee with explicit bounds. We also conduct extensive simulations to validate the effectiveness of our proposed strategy and our experimental results show that CBM achieves significant gains over existing schemes.

The prevalence of social networking services dramatically changes the landscape of video distribution, in which social video contents spread much faster than traditional video-sharing portals. The pervasive wireless connectivity further enables users to view and generate videos from anywhere at any time. In this paper, we focus on the problem of collaborative distribution of social videos in a wireless community cloud. We aim to minimize the total power consumption of all participants in the community. To this purpose, we first analyze the distribution problem using a Markovian model and study how the soft deadline threshold impacts the total power consumption. We derive the closed-form expression to reveal the relationship between the optimal power allocation strategy and the soft deadline threshold. Our numerical results show that the minimum power consumption increases convexly as the soft deadline threshold approaches one. Moreover, we also observe that when more paths are used for parallel transmission, the total power consumption increases in spite that the power consumption of each individual path is reduced.

For Internet video services, the high fluctuation of user demands in geographically distributed regions results in low resource utilizations of traditional content distribution network systems. Due to the capability of rapid and elastic resource provisioning, cloud computing emerges as a new paradigm to reshape the model of video distribution over the Internet, in which resources (such as bandwidth, storage) can be rented on demand from cloud data centers to meet volatile user demands. However, it is challenging for a video service provider (VSP) to optimally deploy its distribution infrastructure over multiple geo-distributed cloud data centers. A VSP needs to minimize the operational cost induced by the rentals of cloud resources without sacrificing user experience in all regions. The geographical diversity of cloud resource prices further makes the problem complicated. In this paper, we investigate the optimal deployment problem of cloud-assisted video distribution services and explore the best tradeoff between the operational cost and the user experience. We aim to pave the way for building the next-generation video cloud. Toward this objective, we first formulate the deployment problem into a min-cost network flow problem, which takes both the operational cost and the user experience into account. Then, we apply the Nash bargaining solution to solve the joint optimization problem efficiently and derive the optimal bandwidth provisioning strategy and optimal video placement strategy. In addition, we extend the algorithms to the online case and consider the scenario when peers participate into video distribution. Finally, we conduct extensive simulations to evaluate our algorithms in the realistic settings. Our results show that our proposed algorithms can achieve a good balance among multiple objectives and effectively optimize both operational cost and user experience.

Measurement studies of popular peer-to-peer (P2P) live video systems reveal that there exists extreme unfairness among peers in the swarm. Such kind of unfairness will provide disincentives to altruistic super peers and encourage free riding behavior in the system. It is essential for video service providers to take fairness into consideration when designing their systems. In this paper, we develop a simple model of P2P live video systems to understand the fairness problem from a theoretic perspective. We identify the fundamental tradeoff between fairness and performance, and propose a semidistributed algorithm based on the subgradient method to tune the P2P live video system toward optimal fairness while still maintaining the targeted universal streaming rate. We also conduct extensive trace-driven simulations to validate the effectiveness of our proposed algorithm. The simulation results show that our algorithm can guide the system toward optimal fairness quickly without degrading streaming performance at the same time.

To provide elastic cloud services with QoS guarantee, it is essential for cloud data centers to provision virtual machines rapidly according to user requests. Due to bandwidth bottleneck of centralized model, P2P model is recently adopted in data centers to relieve server workload by enabling sharing among VM instances. In this paper, we develop a simple theoretic model to analyze two typical P2P models for VM image distribution, namely, isolated-image P2P distribution model and cross-image P2P distribution model. We compare their efficiency under different parameter settings and derive their corresponding optimal server bandwidth allocation strategies. In addition, we also propose a practical optimal server bandwidth provisioning algorithm for chunk-level cross-image P2P distribution mechanism to further improve its efficiency. Extensive simulations are conducted to validate the effectiveness of our proposed algorithm.

We study a natural and potentially devastating attack against BitTorrent, namely, attacking the initial seed in a torrent's early stages. The goal of this attack is to diminish the seed's ability to upload blocks. If the attacker can discover and react quickly enough to the new torrent, it can possibly "nip the torrent in its bud," preventing all of the leechers from obtaining the entire file. We consider two natural seed attacks: the bandwidth attack and the connection attack. We take a three-prong approach to analyze these attacks. First, we actually launch and measure the attacks using popular BitTorrent seeds (Azureus, uTorrent, and BitTornado). To this end, because we do not want to interfere with torrents in the wild, we have created our own private torrents within PlanetLab. Second, to gain insight into our empirical results, we carefully analyze the connection management and seeding algorithms in open-source BitTorrent seeds. Third, we construct a simple fluid model which provides additional insights into the empirical results. We have discovered that the three BitTorrent seeds investigated are quite resilient to such an attack. The observations and conclusions in this paper can help P2P developers design highly-resilient P2P systems.

Deep packet inspection (DPI), based on regular expressions, is expressive, compact, and efficient in specifying attack signatures. We focus on their implementations based on general-purpose processors that are cost-effective and flexible to update. In this paper, we propose a novel solution, called deterministic finite automata with extended character-set (DFA/EC), which can significantly decrease the number of states through slightly extending the character-set. Different from existing state reduction algorithms, our solution requires only a single memory access for each byte in the traffic payload, which is the minimum. We perform experiments with the Snort rule-sets. Results show that, compared to DFA, a DFA/EC can be over four orders of magnitude smaller, has smaller memory bandwidth, and runs faster. We believe that DFA/EC will lay a groundwork for a new type of state compression technique in fast packet inspection.

BitTorrent is the most successful open Internet application for content distribution. Despite its importance, both in terms of its footprint in the Internet and the influence it has on emerging P2P applications, the BitTorrent Ecosystem is only partially understood. We seek to provide a nearly complete picture of the entire public BitTorrent Ecosystem. To this end, we crawl five of the most popular torrent-discovery sites over a ine-month period, identifying all of 4.6 million and 38,996 trackers that the sites reference. We also develop a high-performance tracker crawler, and over a narrow window of 12 hours, crawl essentially all of the public Ecosystem's trackers, obtaining peer lists for all referenced torrents. Complementing the torrent-discovery site and tracker crawling, we further crawl Azureus and Mainline DHTs for a random sample of torrents. Our resulting measurement data are more than an order of magnitude larger (in terms of number of torrents, trackers, or peers) than any earlier study. Using this extensive data set, we study in-depth the Ecosystem's torrent-discovery, tracker, peer, user behavior, and content landscapes. For peer statistics, the analysis is based on one typical snapshot obtained over 12 hours. We further analyze the fragility of the Ecosystem upon the removal of its most important tracker service.

Incentive mechanisms play a critical role in P2P systems. Private BitTorrent sites use a novel incentive paradigm, where the sites record upload and download amounts of users and require each user to maintain its upload-to-download ratio above a specified threshold. This paper explores in-depth incentives in private P2P file-sharing systems. Our contributions are threefold. We first conduct a measurement study on a representative private BitTorrent site, examining how incentives influence user behavior. Our measurement study shows that, as compared with public torrents, a private BitTorrent site provides more incentive for users to contribute and seed. Second, we develop a game theoretic model and analytically show that the ratio mechanism indeed provides effective incentives. But existing ratio incentives in private BitTorrent sites are vulnerable to collusions. Third, to prevent collusion, we propose an upload entropy scheme, and show through analysis and experiment that the entropy scheme successfully limits colluding, while rarely affecting normal users who do not collude.

A private BitTorrent site (also known as a "Bit Torrent darknet") is a collection of torrents that can only be accessed by members of the darknet community. The private BitTorrent sites also have incentive policies which encourage users to continue to seed files after completing downloading. Although there are at least 800 independent BitTorrent darknets in the Internet, they have received little attention in the research community to date. We examine BitTorrent darknets from macroscopic, medium-scopic and microscopic perspectives. For the macroscopic analysis, we consider 800+ private sites to obtain a broad picture of the darknet landscape, and obtain a rough estimate of the total number of files, accounts, and simultaneous peers within the entire darknet landscape. Although the size of each private site is relatively small, we find the aggregate size of the darknet landscape to be surprisingly large. For the medium-scopic analysis, we investigate content overlap between four private sites and the public BitTorrent ecosystem. For the microscopic analysis, we explore in-depth one private site and examine its user behavior. We observe that the seed-to-leecher ratios and upload-to-download ratios are much higher than in the public ecosystem. The macroscopic, medium-scopic and microscopic analyses when combined provide a vivid picture of the darknet landscape, and provide insight into how the darknet landscape differs from the public BitTorrent ecosystem.

Peer Exchange (PEX), in which peers directly exchange with each other lists of active peers in the torrent, has been widely implemented in modern BitTorrent clients for decentralized peer discovery. However, there is little knowledge about the behavior of PEX in operational systems. In this paper, we perform both passive measurements and Planetlab experiments to study the impact and properties of BitTorrent PEX. We first study the impact of PEX on the download efficiency of BitTorrent. We observe that PEX can significantly reduce the download time for some torrents. We then analyze the freshness, redundancy and spread speed of PEX messages. Finally, we also conduct large- scale Planetlab experiments to understand the impact of PEX on the overlay properties of BitTorrent.

When a host discovers that it has a software vulnerability that is susceptible to an attack, the host needs to obtain and install a patch. Because centralized distribution of patches may not scale well, peer-to-peer (P2P) approaches have recently been suggested. There is, however, a serious privacy problem with peer-assisted patch distribution: when a peer A requests a patch from another peer B, it announces to B its vulnerability, which B can exploit instead of providing the patch. Through analytical modeling and simulation, we show that a large majority of vulnerable hosts will typically become compromised with a basic design for peer- assisted patch distribution. We then study the effectiveness of two different approaches in countering this privacy problem. The first approach utilizes special-purpose peer nodes, referred to as honeypots, that discover and blacklist malicious peers listening for patch requests from susceptible hosts. In the second approach, the patches are requested through an anonymizing network, hiding the identities of susceptible hosts from malicious peers. Using analytical models and simulation, we show that, honeypots do not completely solve the privacy problem; in contrast, an anonymizing network turns out to be more suitable for security patch distribution.

In recent years, there have been several large-scale deployments of P2P live video systems. Existing and future P2P live video systems will offer a large number of channels, with users switching frequently among the channels. In this paper, we develop infinite-server queueing network models to analytically study the performance of multichannel P2P live video systems. Our models capture essential aspects of multichannel video systems, including peer channel switching, peer churn, peer bandwidth heterogeneity, and Zipf-like channel popularity. We apply the queueing network models to two P2P streaming designs: the isolated channel design (ISO) and the View-Upload Decoupling (VUD) design. For both of these designs, we develop efficient algorithms to calculate critical performance measures, develop an asymptotic theory to provide closed-form results when the number of peers approaches infinity, and derive near-optimal provisioning rules for assigning peers to groups in VUD. We use the analytical results to compare VUD with ISO. We show that VUD design generally performs significantly better, particularly for systems with heterogeneous channel popularities and streaming rates.

In current multi-channel live P2P video systems, there are several fundamental performance problems including exceedingly-large channel switching delays, long playback lags, and poor performance for less popular channels. These performance problems primarily stem from two intrinsic characteristics of multi-channel P2P video systems: channel churn and channel- resource imbalance. In this paper, we propose a radically different cross-channel P2P streaming framework, called view-upload decoupling (VUD). VUD strictly decouples peer downloading from uploading, bringing stability to multichannel systems and enabling cross-channel resource sharing. We propose a set of peer assignment and bandwidth allocation algorithms to properly provision bandwidth among channels, and introduce substream swarming to reduce the bandwidth overhead. We evaluate the performance of VUD via extensive simulations as well with a PlanetLab implementation. Our simulation and PlanetLab results show that VUD is resilient to channel churn, and achieves lower switching delay and better streaming quality. In particular, the streaming quality of small channels is greatly improved.

In recent years there have been several large-scale deployments of P2P live video systems. Existing and future P2P live video systems will offer a large number of channels, with users switching frequently among the channels. In this paper, we develop infinite-server queueing network models to analytically study the performance of multi-channel P2P streaming systems. Our models capture essential aspects of multi-channel video systems, including peer channel switching, peer churn, peer bandwidth heterogeneity, and Zipf-like channel popularity. We apply the queueing network models to two P2P streaming designs: the isolated channel design (ISO) and the View-Upload Decoupling (VUD) design. For both of these designs, we develop efficient algorithms to calculate critical performance measures, develop an asymptotic theory to provide closed-form results when the number of peers approaches infinity, and derive near- optimal provisioning rules for assigning peers to groups in VUD. We use the analytical results to compare VUD with ISO. We show that VUD design generally performs significantly better, particularly for systems with heterogeneous channel popularities and streaming rates.

In recent years, many distributed rating systems have been proposed against the increasing misbehaviors of peers in peer-to-peer (P2P) networks. However, the low accuracy, long-response time and vulnerabilities under the adversary attacks of P2P rating systems have long been criticized and hindering the practical deployment of such a mechanism. There is also a lack of systematic analysis and evaluation for understanding the systems. In this paper, we first present a framework of stochastic analytical model for evaluating P2P rating systems. The performances of two representative designs, namely the unstructured self-managing rating (UMR) system and the structured supervising rating (SSR) system, are then studied with our model. We identify the positive features as well as the negative ones of the two designs with different design choices and under various network environments and adversary attacks. We also propose a configurable loosely supervising rating system, and show that this system works inexpensively, and could make trade-off between the false rating attack resistance of the UMR system and the accuracy, responsiveness, whitewashing attack resistance as well as a failure resilience of the SSR system, thus providing a better overall performance according to the application context.

Abstract In this paper, we present a simple mathematical model for studying the performance of the BitTorrent ( http://www.bittorrent.com ) file sharing system. We are especially interested in the distribution of peers in different states of the download job progress. With the model we find that the distribution of the download peers follows an asymmetric U‐shaped curve under the stable state, due to BitTorrent's unchoking strategies. In addition, we find that the seeds' departure rate and the download peers' abort rate will influence the peer distribution in different ways notably. We also analyze the content availability under the dying process of the BitTorrent file sharing system. We find that the system's stability deteriorates with decreasing and unevenly distributed online peers, and BitTorrent's built‐in ‘tit‐for‐tat’ unchoking strategy could not help to preserve the integrity of the file among the download peers. We propose an innovative ‘tit‐for‐tat’ unchoking strategy which enables more peers to finish the download job and prolongs the system's lifetime. By playing our innovative strategy, download peers could cooperate to improve the stability of the system by making a trade‐off between the current downloading rate and the future service availability. Finally, experimental results are presented to validate our analytical results and support our proposals. Copyright © 2007 John Wiley & Sons, Ltd.

Abstract The phenomenon of system churn degrades the lookup performance of distributed hash table (DHT) systems greatly. To handle the churn, a number of approaches have been proposed to date. However, there is a lack of theoretical analysis to direct how to make design choices under different churn rates and how to configure their parameters optimally. In this paper, we analytically study three important aspects on optimizing DHT lookup performance under churn, i.e. lookup strategy, lookup parallelism and lookup key replication. Our objective is to build a theoretical basis for designers to make better design choices in the future. We first compare the performance of two representative lookup strategies—recursive routing and iterative routing—and explore the existence of better alternatives. Then we study the effectiveness of lookup parallelism in systems with different churn rates and show how to select the optimal degree of parallelism. Owing to the importance of key replication on lookup performance, we also analyze the reliability of the replicated key under two different replication policies, and show how to perform proper configuration. Besides the analytical study, our results are also validated by simulation, and Kad is taken as a case to show the meaningfulness of our analysis. Copyright © 2007 John Wiley & Sons, Ltd.

As a fundamental problem in DHT-based P2P systems, load balancing is important to avoid performance degradation and guarantee system fairness. In this paper, to get a better understanding about the effectiveness of migration-based load balancing approaches in DHT systems, we analytically study two representative migration-based load balancing strategies: rendezvous directory strategy (RDS) and independent searching strategy (ISS). They differ in load information management and decision making in the process of load balancing. We analyze their performance in terms of efficiency, scalability and robustness, and explore the impact of their parameter settings. Based on the analysis results, we also propose a gossip-based strategy (GBS) for load balancing in DHT systems, which attempts to achieve the benefits of both RDS and ISS. Later, the effectiveness of GBS is evaluated by simulation under different workload and churn.

Previous studies show that more than 85% of the peers have joined multiple torrents in BitTorrent, but theoretical work on multiple files BitTorrent downloading is rare. In this paper, we first consider the scenario of multi-torrent downloading. We present a fluid-model based analysis on the multi-torrent concurrent downloading scheme, which is implicitly adopted in practical applications, and quantitatively compare its performance with an alternative scheme of multi-torrent sequential downloading. We also consider the scenario of multi-file torrent downloading (e.g. multiple files shared within a single torrent), and find that the scheme of multi-file torrent concurrent downloading, which is explicitly engaged in practical applications, is inefficient. A new scheme named collaborative multi-file torrent sequential downloading is proposed, and we show via numerical analysis that the download performance could be improved by collaboration among the peers in different subtorrents. Finally, we propose a self-adaptive mechanism for practically deploying our multi-file torrent downloading scheme in a distributed fashion under situations when correlation among the files and majority peers' behaviors are unknown

Abstract — In this paper, a simple mathematical model is presented for studying the performance of the BitTorrent [1] file sharing system. We are especially interested in the distribution of the peers with different states of the download job completedness. With the model we find that in the stable state the distribution of the download peers follows a U-shaped curve, and the parameters such as the departure rate of the seeds and the abort rate of the download peers will influence the peer distribution in different ways notably. We also analyze the file availability and the dying process of the BitTorrent file sharing system. We find that the system’s stability deteriorates with the clustering of the peers, and BitTorrent’s built-in “tit-for-tat ” unchoking strategy could not help to preserve the integrity of the file among the download peers when the size of the community is small. An innovative peer selection strategy which enables more peers to finish the download job and prolongs the system’s lifetime is proposed, in which the peers cooperate to improve the stability of the system by making a tradeoff between the current download rate and the future service availability. Finally, experimental results are presented to validate our analysis and findings. I.

In DHT-based P2P systems, the technique of "virtual server" is widely used to achieve load balance. To efficiently handle the workload skewness , "virtual servers" are allowed to migrate between nodes. Among existing migration-based load balancing strategies, there are two main categories: (I) rendezvous directory strategy (RDS) and (2) independent searching strategy (ISS). However, none of them can achieve resilience and efficiency at the same time. In this paper, we propose a gossip dissemination strategy (GDS) for load balancing in DHT systems, which attempts to achieve the benefits of both RDS and ISS. GDS doesn't rely on a few static rendezvous directories to perform load balancing. Instead, load information is disseminated within the formed groups via a gossip protocol, and each peer has enough information to act as the rendezvous directory and perform load balancing within its group. Besides intra-group balancing, inter-group balancing and emergent balancing are also supported by GDS. To further improve system resilience, the position of the rendezvous directory is randomized in each round. For a better understanding, we also perform analytical studies on GDS in terms of its scalability and efficiency under churn. Finally, the effectiveness of GDS is evaluated by extensive simulation under different workload and churn levels

The phenomenon of churn degrades the lookup performance of DHT-based P2P systems greatly. To date, a number of approaches have been proposed to handle it from both the system side and the client side. However, there lacks theoretical analysis to direct how to make design choices under different churn levels and how to configure their parameters optimally. In this paper, we analytically study three important aspects on improving DHT lookup performance under churn, i.e., lookup strategy, lookup parallelism and lookup key replication. Our objective is to build a theoretical basis for DHT designers to make better design choices in the future. We first compare the performance of two representative lookup strategies - recursive routing and iterative routing, and explore the existence of better alternatives. Then we show the effectiveness of parallel lookup in systems with different churn levels and how to select the optimal degree of parallelism. Due to the importance of key replication on lookup performance, we also analyze the reliability of replicated keys under two different replication policies, and discuss how to make configuration in different environments. Besides analytical study, our results are also validated by simulation, and Kad is taken as a case to show the meaningfulness of our analysis