With the rapid advancement of ubiquitous connectivity, the Internet of Unmanned Agents (IUA) has emerged as a promising paradigm for distributed intelligent perception and decision-making. In such systems, numerous unmanned agents collaboratively collect environmental data to support coordinated tasks. To preserve data privacy, Federated Learning (FL), as a decentralized machine learning framework, enables collaborative training of a global model across agents without directly exchanging raw data. However, FL faces several critical challenges in IUA environments, including high communication overhead under constrained wireless bandwidth, potential privacy leakage from shared model parameters, and agent dropouts caused by unstable connectivity. To address these challenges, we propose PPE-FL, a privacy-preserving and communication-efficient federated learning scheme designed for IUA scenarios. PPE-FL replaces conventional high-dimensional gradient uploads with lightweight ranking-based votes, substantially reducing communication overhead. Then, we design an obfuscation mechanism to protect the privacy of locally generated ranking-based votes, safeguarding both raw data and intermediate parameters. Furthermore, PPE-FL supports mask reconstruction through partial interactions among online unmanned agents, enabling robust aggregation under dynamic network conditions. Experimental results demonstrate that the proposed PPE-FL reduces communication costs by 89.5% compared to VCD-FL and by 87.7% compared to PPML, while maintaining model accuracy and privacy protection.

Video analytics (VA) has become essential in applications, yet it poses significant challenges related to privacy preservation, network bandwidth, and computational resources. With the increasing deployment of high-definition cameras, privacy concerns and resource constraints are becoming critical barriers to the widespread adoption of VA systems. Existing privacy-preserving techniques are often static, inefficient, and fail to adapt to dynamic, real-time scenarios. In this paper, we propose Parachute, a dynamic, resource-aware and privacy-preserving video analytics system that adaptively switches between a local mode and a collaborative mode in response to traffic conditions. The system uses local reinforcement learning to enable each individual camera to operate independently, and switches to multi-agent reinforcement learning for coordinated optimization when local resources become limited. Experiments on real-world datasets demonstrate that Parachute effectively balances detection accuracy and privacy protection, outperforming baseline methods under bandwidth constraints.

Nowadays IoT devices in Mobile Edge Computing (MEC) networks have been deployed in large-scale quantities to guarantee sensing data collection for anomalous event detection as full as possible even if some devices are in fault. Some techniques, such as clustering and dimensionality reduction, are adopted to eliminate redundant sensing data collection in this large-scale deployment. However, they not only have high computational complexity and easily cause the loss of information on the primary sensing attributes for detection, but also bring certain errors to the detection because of their low sensitivity to data processed. In addition, insufficient collection of primary attribute data samples often results from physical or human factors, and blind imputation of large-scale data gaps without basis may lead to greater irreparable losses. To address the above challenges, we first complete the selection of optimal primary attribute device collection and aggregation (PADCA) path based on minimum spanning tree, reducing data communication cost for redundant primary attributes collection. Then, we propose an anomalous impact correlation search strategy to quickly locate all MEC servers whose management regions have cascading anomalous event and help determine the transferable source MEC servers. Leveraging this, we use transfer learning to help detect anomalous events in the management regions of the MEC servers with insufficient primary attribute data samples, where a particle swarm optimization based back-propagation (PSO-BP) neural network model is used to infer the fusion weight of each primary attribute. Experimental results show that our method achieves higher detection performance in terms of detection time, energy consumption, accuracy, and receiver operating characteristic (ROC) curve compared to the benchmarks by at least 24%, 34%, 0.5 and 0.05.

The unprecedented advancements in quantum technology have opened new prospects for the widespread adoption of quantum applications, placing new demands on the information transmission capabilities of large-scale quantum networks. Long-distance and stable entanglements are deemed as the lifeline in quantum network communication. However, some weaknesses, e.g., quantum decoherence, scarce quantum memory, and uneven-quality entanglement, of the quantum entanglement hinder the development. In this paper, we proposeSophon, an online transmission framework for quantum networks, which utilizes high-dimensional entanglements to concurrently transmit multi-qubit data to satisfy the transmission requirements of the real-time request set. We first model the quantum network with multi-qubit entanglement represented by$W$quantum state and then formulate the Entanglement Routing and Qubit Provisioning (ERQP) problem as a global-local optimization process. To solve theERQPproblem, we distributedly regard each network node as an RL agent for resource provisioning and extend the step-updating of the Markov Decision Process by introducing a centralized controller for entanglement route selection to optimize local and global objectives, respectively. Extensive simulations demonstrate, on the self-made simulation platform,Sophonachieves a$21.89\%-66.52\%$decrease in the communication cost, and is more robust on different scales of the network topology and the request set than the baselines.

In recent years, volumetric videos have gradually prospered as an intriguing video paradigm, offering users a fully immersive viewing experience with six Degrees of Freedom (DoF). However, most current live volumetric video streaming methods struggle to facilitate the real-time performance requirements due to the nature of frequent user interactions and the complexity of network environments during video playback. Inspired by the correlation between the human visual effects and adjacent frame motion features, we proposeCetus, a context-aware cross-layer coordination system for live volumetric videos. First, we present an application-layer Neural Radiance Fields (NeRF)-based codec framework that leverages spatio-temporal semantic information for optimizing the compression quality of each video frame. Second, we exploit a flexible cross-layer coordination framework that seamlessly integrates frame drop strategy with partially reliable transmission, orchestrating transport protocols and application-informed rates to enhance the Quality of Experience (QoE) for multiple users. Furthermore, we develop a lightweight branching decision tree algorithm that adaptively makes fine-grained frame drop decisions. Experimental evaluations of our implemented system prototype demonstrate that Cetus significantly outperforms existing baseline approaches. Compared to the state-of-the-art baselines, Cetus effectively improves video frame rate by at least 24.7% and video quality by an average of 32.6%.

Serverless computing promises fine-grained resource elasticity and billing, making it an attractive way to build complex applications as multi-stage workflows. Nonetheless, existing workflow orchestration ignores the heterogeneous demands of the computation and communication parts within a stage, potentially resulting in resource inefficiency on either side. In this paper, we advocate forcomputation-communication-separated orchestrationto unleash hybrid resource (i.e., compute and network) elasticity. We present HyFaaS, a serverless workflow orchestrator that improves performance while ensuring cost efficiency. It seamlessly decouples computation and communication as a series of hybrid stages re-expressed within HyDAG, a novel workflow abstraction. HyFaaS uses a gray-box profiling model to identify their Pareto-optimal saturated configurations, and then deploys the saturated workflow to juggle communication and scaling overheads through two-level HyDAG partitioning. Along with event-driven runtime fine-tuning, HyFaaS further scales down the non-critical stages to reduce cost via branch-aware coordination. Experimental results show that HyFaaS surpasses existing solutions by 32.7%–50.4% on end-to-end latency, while lowering cost by up to 1.37×.

With the rapid development of 6 G communication technology and the Internet of Things (IoT), mobile edge computing (MEC) is regarded as an effective paradigm of providing low-delay, high-quality services to mobile users. In the IoT device-edge-cloud network, the optimal deployment of MEC servers is a prerequisite for a better task offloading, while the improved performance of mobile users task offloading also indicates the deployment scheme is optimal. Most of current MEC servers deployment studies focus on reducing delay and deployment costs, but ignore the offloading requirements of mobile users with similar task type and cooperative relationship arriving at the same community. In this paper, we study the MEC servers deployment driven by the task offloading requirements of community mobile users in current period by utilizing the stability of their social cooperative relationships to maximize the service satisfaction of all community mobile users in the future task offloading. First, the cooperative relationship strength between mobile users is measured to form a group of resource requesters based on interaction probability, movement trajectory and credit strength. Then, we implement the optimal search of base stations (BSs) using spatial index, followed by the one-to-many matching theory between BSs and community group resource requesters, to balance the load of BSs and reduce the communication delay between them. Finally, we use TD($\lambda$) algorithm and task similarity between cooperative users to deploy MEC servers with suitable resources around BSs so that the deployment scheme can significantly improve the future task offloading performance of all community mobile users. Based on the real data set provided by Shanghai Telecom, it is confirmed that the proposed scheme has significant advantages in improving all community mobile users service satisfaction, with an average improvement of 18.49% compared with the baselines.

Federated Learning (FL) has become a powerful technique for collaborative model training across decentralized entities while preserving data privacy. Despite its potential, FL faces significant challenges, including communication overhead, resource heterogeneity, and data heterogeneity. Existing solutions fall short in addressing disparities in client resources and the errors introduced by direct model aggregation across heterogeneous clients. To tackle these issues, we propose DynFed, a novel federated learning framework that incorporates dynamic quantization bit-width allocation and multi-teacher knowledge distillation for model aggregation. DynFed dynamically adjusts quantization bit-widths to clients based on their resource heterogeneity, adapting these allocations according to variations in the local loss function during training. This adaptive quantization strategy optimizes resource utilization while preserving model performance. For model aggregation, DynFed utilizes a dynamic multi-teacher knowledge distillation approach, assigning the most suitable teacher model to each data sample based on a comprehensive evaluation score, thereby ensuring effective knowledge transfer even in the presence of quantization-induced errors. This method not only mitigates the negative effects of heterogeneous bit-widths but also leverages client model diversity to enhance the robustness of the global model. Extensive experimental results demonstrate the superiority of DynFed over state-of-the-art methods.

As a killer app of edge computing, real-time video analytics has found its wide usage in diverse applications, such as security surveillance and manufacturing automation. Unlike state-of-the-art efforts in edge video analytics, which primarily focus on single-task scenarios, we address multi-task video analytics, enabling concurrent execution of multiple tasks on a single video stream. Specifically, our approach aims to minimize monetary costs for the edge service provider through efficient query and resource scheduling, while meeting accuracy and latency requirements of diverse video analytics tasks. A crucial prerequisite for this is to determine the relationship between video analytics accuracy and system configuration parameters. We design a Transformer-aided configuration-accuracy predictor to capture both the current video content and inter-frame temporal dependencies, generating precise configuration-accuracy profiles in real-time. To better exploit the scarce communication and computing resources, a query merging technique is employed, which allows queries from the same camera to share the network bandwidth and neural network models, leading to reduced resource consumption. A heuristic algorithm is then readily proposed to schedule video queries and resources, which dynamically adapts video configurations, query merging, video analytics model selection, task placement, and GPU provisioning. Experimental results show that our system achieves near-optimal performance and outperforms state-of-the-art methods, demonstrating the superiority of our collaboration scheme.

Free weight training (FWT) is of utmost importance for physical well-being. The success of FWT depends largely on choosing the suitable workload, as improper selections can lead to suboptimal outcomes or injury. Current workload estimation approaches rely on manual recording and specialized equipment with limited feedback. Therefore, we introducePPGSpotter, a wearable PPG-based FWT monitoring system in a convenient, low-cost, and fine-grained manner. By characterizing the arterial geometry compressions caused by the deformation of distinct muscle groups,PPGSpottercan infer essential FWT factors such as current workload, repetitions, and exercise type and provide recommendations for workload adjustment. To remove pulse-related interference, we develop an arterial interference elimination approach based on adaptive filtering, effectively extracting the pure motion-derived signal (MDS). Furthermore, we explore 2D representations of MDS within the phase space to extract spatiotemporal information, enablingPPGSpotterto address the challenge of resisting sensor shifts. Finally, we leverage a multi-task CNN-based network and workload adjustment guidance to achieve personalized FWT monitoring. Extensive experiments with 15 participants confirm thatPPGSpottercan achieve promising workload estimation (0.59 kg RMSE), repetitions estimation (0.96 reps RMSE), and exercise type recognition (91.57% F1-score) while providing valid workload adjustment recommendations (0.22 kg RMSE).

Federated learning (FL)has achieved state-of-the-art performance in distributed machine learning with privacy preservation, which promotes AIoT. However, FL is restricted by the expensive communication cost due to exchanging a large number of model parameters and model updates (e.g., gradients) between the aggregator and participants in multiple rounds. This could be challenging in resource-constrained networks where devices are often resource-constrained in terms of computation and communication. Existing works mainly focus on improving communication efficiency from local training and model/gradient compression; nevertheless, studying communication efficiency for FL from the perspective of gradient estimation remains unexplored. In this paper, we bridge this gap by conducting a systematic study on gradient estimation for the communication-efficient FL. We propose a bandit-based gradient estimation-aware FL ($\mathtt{BGEFL }$) framework that can directly estimate participants’ gradients with limited bandit feedback (i.e., their local function values). We prove that$\mathtt{BGEFL }$enjoys an$\mathcal {O}(1)$communication complexity, that is a constant-size uplink communication in which each client uploads only one point’s feedback in the uplink. Moreover, our bandit-based gradient estimator is communication-efficient, unbiased, and stable. We prove theconvergenceperformance of$\mathtt{BGEFL }$for training strongly convex, general convex, and non-convex models. Finally, we evaluate our$\mathtt{BGEFL }$over several datasets and the experimental results demonstrate the effectiveness of$\mathtt{BGEFL }$.

With the flourishing of global services, low-latency analytics on large-volume geo-distributed data has been a regular requirement for application decision-making. Serverless computing, with its rapid function start-up and lightweight deployment, provides a compelling way for geo-distributed analytics. However, existing research focuses on elastic resource scaling at the stage granularity, struggling to heterogeneous resource demands across component functions in wide-area settings. The neglect potentially results in the cost inefficiency and Service Level Objective (SLO) violations. In this paper, we advocate for fine-grained function orchestration to exploit wide-area resource elasticity. We thereby present Demeter, a fine-grained function orchestrator that saves job execution costs for geo-distributed serverless analytics while ensuring SLO compliance. By learning from volatile and bursty environments, Demeter jointly makes per-function placement and resource allocation decisions using a well-optimized multi-agent reinforcement learning algorithm with a pruning mechanism. It prevent the irreparable performance loss by function congestion control. Ultimately, we implement Demeter and evaluate it with the realistic workloads. Experimental results reveal that Demeter outperforms the baselines by up to 46.6% on cost, while reducing SLO violation by over 23.7% and bringing it to below 15%.

Free weight training (FWT) is of utmost importance for physical well-being. However, the success of FWT depends on choosing the suitable workload, as improper selections can lead to suboptimal outcomes or injury. Current workload estimation approaches rely on manual recording and specialized equipment with limited feedback. Therefore, we introduce PPGSpotter, a novel PPG-based system for FWT monitoring in a convenient, low-cost, and fine-grained manner. By characterizing the arterial geometry compressions caused by the deformation of distinct muscle groups during various exercises and workloads in PPG signals, PPGSpotter can infer essential FWT factors such as workload, repetitions, and exercise type. To remove pulse-related interference that heavily contaminates PPG signals, we develop an arterial interference elimination approach based on adaptive filtering, effectively extracting the pure motion-derived signal (MDS). Furthermore, we explore 2D representations within the phase space of MDS to extract spatiotemporal information, enabling PPGSpotter to address the challenge of resisting sensor shifts. Finally, we leverage a multi-task CNN-based model with workload adjustment guidance to achieve personalized FWT monitoring. Extensive experiments with 15 participants confirm that PPGSpotter can achieve workload estimation (0.59 kg RMSE), repetitions estimation (0.96 reps RMSE), and exercise type recognition (91.57% F1-score) while providing valid workload adjustment recommendations.

In the era of global services, low-latency analytics on large-volume geo-distributed data has been a regular demand for application decision-making. Serverless computing facilitates fast function start-up and deployment, making it an attractive way for geo-distributed analytics. We argue that the serverless paradigm holds the potential to breach current performance bottlenecks via fine-grained function orchestration. However, how to configure it for geo-distributed analytics remains ambiguous. To fill this gap, we present Demeter, a scalable fine-grained function orchestrator for geo-distributed serverless analytics systems. Demeter aims to minimize the composite cost of co-existing jobs while meeting the user-specific Service Level Objectives (SLO). To handle the volatile environments and learn the diverse function demands, a Multi-Agent Reinforcement Learning (MARL) solution is used to co-optimize the per-function placement and resource allocation. The MARL extracts holistic and compact states via hierarchical graph neural networks, and then designs a novel actor network to shrink the huge decision space and model complexity. Finally, we implement Demeter and evaluate it using realistic workloads. The experimental results reveal that Demeter significantly saves costs by 23.3%∼32.7%, while reducing SLO violations by over 27.4%, surpassing state-of-the-art solutions.

Recent literature advances motion sensors mounted on smartphones and AR/VR headsets to speech eavesdropping due to their sensitivity to subtle vibrations. The popularity of motion sensors in earphones has fueled a rise in their sampling rate, which enables various enhanced features. This paper investigates a new threat of eavesdropping via motion sensors of earphones by developing EarSpy, which builds on our observation that the earphone's accelerometer can capture bone conduction vibrations (BCVs) and ear canal dynamic motions (ECDMs) associated with speaking; they enable EarSpy to derive unique information about the wearer's speech. Leveraging a study on the motion sensor measurements captured from earphones, EarSpy gains abilities to disentangle the wearer's live speech from interference caused by body motions and vibrations generated when the earphone's speaker plays audio. To enable user-independent attacks, EarSpy involves novel efforts, including a trajectory instability reduction method to calibrate the waveform of ECDMs and a data augmentation method to enrich the diversity of BCVs. Moreover, EarSpy explores effective representations from BCVs and ECDMs, and develops a neural network model with character-level and word-level speech recognition models to realize speech recognition. Extensive experiments involving 14 participants demonstrate that EarSpy reaches a promising recognition for the wearer's speech.

Federated Learning (FL)has achieved state-of-the-art performance in training a global model in a decentralized and privacy-preserving manner. Many recent works have demonstrated that incentive mechanism is of paramount importance for the success of FL. Existing incentives to FL either neglect communication efficiency, or consider communication efficiency but design the incentive mechanisms using non-cooperative games under complete information assumption, or study incentive mechanism under incomplete information but only apply to the sequential interaction setting. We shed light on this problem from the cooperative perspective and propose an incentive mechanism for communication-efficient FL based on the Nash bargaining theory. Specially, we formulate our incentive mechanism as a one-to-manyconcurrent bargaininggame among the aggregator and clients, and systematically analyze the Nash bargaining solution (NBS, game equilibrium) to design the incentive mechanism. It should be noted that the existingsequential bargainingis not suitable for incentivizing FL due to high (exponential) time complexity, which deteriorates the straggler problem in FL. Our formulated bargaining game is challenging due to the NP-hardness. We propose a probabilistic greedy-based client selection algorithm and derive an analytical payment solution as an approximate NBS. We prove the convergence guarantee of our incentive mechanism for communication-efficient FL. Finally, we conduct experiments over real-world datasets to evaluate the performance of our incentive mechanism.

Mobile edge computing provides relatively rich computation resources for Internet-of-Things (IoT) task offloading at the edge of networks. As time goes on, user tasks present diverse requirements in function, type, dependency, urgency, etc., which makes edge servers take on dynamically diversified service features to adapt to the requirements of user tasks. Moreover, cache has been studied a lot in recent years for reducing the execution cost of related or dependent tasks. However, jointly considering which result data required to be cached and where to cache is still an intractable problem in task offloading due to dynamically diversified and sensitive features of task and edge servers for prediction. To provide more comprehensive consideration, we propose a multiple features matching scheme, coupled with federated learning-assisted collaborative caching, to enhance the efficiency of task offloading. Specifically, we first build a common features of historical tasks based FI-tree to help search for an edge server that best matches the requested task features. This helps to obtain optimal task allocation and improve offloading performance. Further, the results of tasks related to or dependent on cached results can be obtained directly through the collaborative edge cache prediction model trained by two-stage federated learning. In this way, the amount of data executed for offloaded tasks is reduced, thereby speeding up the return of final results as well as reducing the delay and energy of task execution. Meanwhile, it avoids massive transmission of task results correlated data and also protects the privacy of these data when training the prediction model. Experimental results show that our proposed method outperforms the benchmark approaches through reducing the time delay and energy consumption by at least 15.6% and 18.2%.

Applying the serverless paradigm to edge computing improves edge resource utilization while bringing the benefits of flexible scaling and pay-as-you-go to latency-sensitive applications. This extends the boundaries of serverless computing and improves the quality of service for Function-as-a-Service users. However, as an emerging cloud computing paradigm, serverless edge computing faces pressing challenges, with one of the biggest obstacles being delay caused by excessively long container cold starts. Cold start delay is defined as the time between when a serverless function is triggered and when it begins to execute, and its existence seriously impacts resource utilization and Quality of Service (QoS). In this paper, we study how to minimize the total system cost by caching function containers and selecting routes for neighboring functions via edge or public clouds. We prove that the proposed problem is NP-hard even in the special case where the user request contains only one function, and that the unpredictability of user requests and the impact between adjacent time decisions require that the problem to be solved in an online fashion. We then design the Online Lazy Caching algorithm, an online algorithm with a worst-case competitive ratio using a randomized dependent rounding algorithm to solve the problem. Extensive simulation results show that the proposed online algorithm can achieve close-to-optimal performance in terms of both total cost and cold start cost compared to other existing algorithms, with average improvements of 31.6% and 51.7%.

Nowadays, the emerging short video streaming applications have gained substantial attention. With the rapidly burgeoning demand for short video streaming services, maximizing their Quality of Experience (QoE) is an onerous challenge. Current video preloading algorithms cannot determine video preloading sequence decisions appropriately due to the impact of users’ swipes and bandwidth fluctuations. As a result, it is still ambiguous how to improve the overall QoE while mitigating bandwidth wastage to optimize short video streaming services. In this article, we devise Gamora, a buffer-aware short video streaming system to provide a high QoE of users. In Gamora, we first propose an unordered preloading algorithm that utilizes a Deep Reinforcement Learning (DRL) algorithm to make video preloading decisions. Then, we further devise an Asymmetric Imitation Learning (AIL) algorithm to guide the DRL-based preloading algorithm, which enables the agent to learn from expert demonstrations for fast convergence. Finally, we implement our proposed short video streaming system prototype and evaluate the performance of Gamora on various real-world network datasets. Our results demonstrate that Gamora significantly achieves QoE improvement by 28.7%–51.4% compared to state-of-the-art algorithms, while mitigating bandwidth wastage by 40.7%–83.2% without sacrificing video quality.

Video analytics play a pivotal role in enhancing the safety of intelligent surveillance and autonomous driving. However, the transmission of vast video data and the computational demands of video analytics present challenges within traditional cloud computing paradigms. To address latency concerns, dynamic video analytics often leverage edge deployments. Nevertheless, the efficient allocation of resources at the edge, balancing cost-effectiveness and accuracy, becomes crucial, especially when multiple video analytics services concurrently operate within the system. This paper introduces an edge-centric incentive mechanism designed to encourage greater participation from edge nodes in offloading tasks. The key focus is on addressing the dynamic nature of edge resources and optimizing system returns through a rational pricing mechanism. We propose a decentralized Soft Actor-Critic algorithm grounded in game theory (DSACG) to autonomously learn the optimal pricing strategy. A comprehensive theoretical analysis, supported by extensive simulations, substantiates the effectiveness of our proposed solution.

The 360-degree video streaming service provides a unique immersive viewing experience for users, who can freely change their Field-of-View (FoV) to view different portions of the videos. However, the demands for high throughput and low latency for 360-degree video pose substantial challenges to the current network infrastructure. Super Resolution (SR) is the procedure for reconstructing high-resolution images from low-resolution ones. Hence, caching video content on the network edge in advance, which is near end users, and applying the SR technique can significantly alleviate the transmission latency. In this article, we describeNOVA, an efficientNeural-OptimizedViewportAdaptive 360-degree video streaming system to improve the Quality of Experience (QoE) of users. In NOVA, we first design a foveated rendering SR approach to super-resolve video tiles utilizing computational resources at the edge. Subsequently, we present a meta-learning-based Multi-Agent Reinforcement Learning (MARL) algorithm to select SR depths and video tiles inside users’ viewports for agile video tile adaptation to optimize overall QoE under frequent network fluctuations. Finally, we implement the holistic prototype of NOVA and evaluate its performance on various real-world network datasets. Extensive experiments illustrate that compared to the state-of-the-art algorithms, NOVA improves average user-perceived QoE by up to 27%.

Recent years have witnessed video streaming gradually evolve into one of the most popular Internet applications. With the rapidly growing personalized demand for real-time video streaming services, maximizing their Quality of Experience (QoE) is a long-standing challenge. The emergence of the serverless computing paradigm has potential to meet this challenge through its fine-grained management and highly parallel computing structures. However, it is still ambiguous how to implement and configure serverless components to optimize video streaming services. In this paper, we propose EAVS, an Edge-assisted Adaptive Video streaming system with Serverless pipelines, which facilitates fine-grained management for multiple concurrent video transmission pipelines. Then, we design a chunk-level optimization scheme to address video bitrate adaptation. We propose a Deep Reinforcement Learning (DRL) algorithm based on Proximal Policy Optimization (PPO) with a trinal-clip mechanism to make bitrate decisions efficiently for better QoE. Finally, we implement the serverless video streaming system prototype and evaluate the performance of EAVS on various real-world network traces. Our results show that EAVS significantly improves QoE and reduces the video stall rate, achieving over 9.1% QoE improvement and 60.2% latency reduction compared to state-of-the-art solutions.

Proper handwashing, having a crucial effect on reducing bacteria, serves as the cornerstone of hand hygiene. For elders with dementia, they suffer from a gradual loss of memory and difficulty coordinating handwashing steps. Proper assistance should be provided to them to ensure their hand hygiene adherence. Toward this end, we propose AWash, leveraging inertial measurement unit (IMU) readily available in most wrist-worn devices (e.g., smartwatches) to characterize handwashing actions and provide assistance. To monitor handwashing scenarios round-the-clock while achieving energy efficiency, we design methods that distinguish handwashing from other daily activities and dynamically adjust the sampling duty cycle. Upon detecting handwashing actions, we design several novel techniques to segment different handwashing actions and extract sensor-body inclination angles that handle particular interference of senile dementia patients. Moreover, a user-independent network model is built to recognize the handwashing actions of senile dementia patients without requiring their training data. Furthermore, we propose a transfer learning method that improves system performance. To meet users’ diverse needs, we use a state machine to make prompt decisions, supporting customized assistance. Extensive experiments on a prototype with eight older participants demonstrate that AWash can increase the user’s independence in the execution of handwashing.

Mobile devices are promising to apply two-factor authentication to improve system security. Existing solutions have certain limits of requiring extra user effort, which might seriously affect user experience and delay authentication time. In this paper, we propose PPGPass, a novel mobile two-factor authentication system, which leverages Photoplethysmography (PPG) sensors available in most wrist-worn wearables. PPGPass simultaneously performs a password/pattern/signature authentication and a physiological-based authentication. To realize both nonintrusive and secure, we design a two-stage algorithm to separate clean heartbeat signals from PPG signals contaminated by motion artifacts so that users do not have to deliberately keep their bodies still. In addition, to deal with noncancelable issues when biometrics are compromised, we design a repeatable and non-invertible method to generate cancelable feature templates as alternative credentials. We leverage the great power ofRandom ForestandSupport Vector Data Descriptionto detect adversaries and verify a user's identity. To the best of our knowledge, PPGPass is the first nonintrusive and secure mobile two-factor authentication based on PPG sensors. Extensive experiments demonstrate that PPGPass can achieve the false acceptance rate of 3.11% and the false recognition rate of 3.71%, which confirms its high effectiveness, security, and usability.

In the traditional video streaming service provisioning paradigm, viewers typically request video content through a central Content Delivery Network (CDN) server. However, because of the uncertain wide area network delays, the (remote) viewers usually suffer from long video streaming delay, which affects the quality of experience. Multi-Access Edge Computing (MEC) offers a way to shorten the video streaming delay by building small-scale cloud infrastructures at the network edge, which are in close proximity to the viewers. In this paper, we present novel centralized and distributed algorithms for the video content placement problem in MEC. In the proposed centralized video content placement algorithm, we leverage the Lyapunov optimization technique to formulate the video content placement problem as a series of one-time-slot optimization problems and apply an Alternating Direction Method of Multipliers (ADMM)-based method to solve each of them. We further devise a distributed Multi-Agent Reinforcement Learning (MARL)-based method with value decomposition mechanism and parallelization policy update method to solve the video content placement problem. The value Decomposition mechanism deals with the credit assignment among multiple agents, which promotes the cooperative optimization of the global target and reduces the frequency of information exchange. The parallelization of policy network can speed up the convergence process. Simulation results verify the effectiveness and superiority of our proposed centralized and distributed algorithms in terms of performance.

Network Function Virtualization (NFV) provides the possibility to implement complex network functions from dedicated hardware to software instances called Virtual Network Functions (VNF) by leveraging the virtualization technology. Service Function Chaining (SFC) is therefore defined as a chain-ordered set of placed VNFs that handles the traffic of the delivery and control of a specific application. Due to the advantages of flexibility, efficiency, scalability, and short deployment cycles, NFV has been widely recognized as the next-generation network service provisioning paradigm. In this paper, we study the problem of online SFC control across geo-distributed datacenters, which is to dynamically place required VNFs on datacenter nodes and find routing paths between each adjacent VNF pair for each NFV service flow that varies over time. To that end, we first formulate this problem as an offline optimization problem whose goal is to minimize the average delay such that each datacenter's average cost does not exceed a given expense value. Considering that the offline optimization requires complete offline network information which is difficult to obtain or predict in practice, we present an online SFC control framework without requiring any future information about the traffic demands. More specifically, we leverage the Lyapunov optimization technique to formulate the problem as a series of one-time slot offline optimization problems and then apply a primal-decomposition method to solve each one-time slot problem. Simulation results reveal that our proposed online SFC control framework can efficiently reduce long-term average delay while keeping datacenter's long-term average cost consumption low.

Driver drowsiness is a significant factor in road crashes. However, existing solutions for driver drowsiness detection have major drawbacks of requiring special hardware, constrained recording conditions, and cannot handle the asynchronous and contradictory nature of multiple indicators. In view of this, we propose FDWatch, a novel drowsiness detection system that exploits the low-cost Photoplethysmogram (PPG) sensor and motion sensor integrated into wrist-worn devices. We design a set of novel algorithms to extract multiple drowsiness-related indicators covering major categories of human factors. In particular, we demonstrate that commodity PPG sensors can be utilized to detect yawning behavior; it contributes as an important indicator for drowsiness detection. The core of FDWatch is based on the Dempster-Shafer evidence theory. It considers different indicators as evidence describing the state of the driver from different angles. To make the extracted indicators applicable to Dempster-Shafer evidence theory, we employ backpropagation neural networks to obtain the basic probability assignment. Moreover, we propose a similarity-distance-based method to handle evidence conflicts. Extensive experiments with real-road driving data show that FDWatch can accurately detect driver drowsiness with a missing alarm rate of 3.57% and a false alarm rate of 3.68%.

The efficacy of Network Function Virtualization (NFV) depends critically on (1) where the virtual network functions (VNFs) are placed and (2) how the traffic is routed. Unfortunately, these aspects are not easily optimized, especially under time-varying network states with different QoS requirements. Given the importance of NFV, many approaches have been proposed to solve the VNF placement and Service Function Chaining (SFC) routing problem. However, those prior approaches mainly assume that the network state is static and known, disregarding dynamic network variations. To bridge that gap, we leverage Markov Decision Process (MDP) to model the dynamic network state transitions. To jointly minimize the delay and cost of NFV providers and maximize the revenue, we first devise a customized Deep Reinforcement Learning (DRL) algorithm for the VNF placement problem. The algorithm uses the attention mechanism to ascertain smooth network behavior within the general framework of network utility maximization (NUM). We then propose attention mechanism-based DRL algorithm for the SFC routing problem, which is to find the path to deliver traffic for the VNFs placed on different nodes. The simulation results show that our proposed algorithms outperform the state-of-the-art algorithms in terms of network utility, delay, cost, and acceptance ratio.

The ever-growing security issues in various scenarios create an urgent demand for a reliable and convenient identification system. Traditional identification systems request users to provide passwords, fingerprints, or other easily stolen information. Existing works show that everyone’s gait and respiration have unique characteristics and are difficult to imitate. But these works only use gait or respiration information to achieve identification, which leads to low accuracy or long identification time. And they have no strong anti-interference ability, which leads to the limitation in practical application. Toward this end, we propose a new system which uses both gait and respiratory biometric characteristics to achieve user identification using Wi-Fi (GRi-Fi) in the presence of interferences. In our system, we design a segmentation algorithm to segment gait and respiration data. And we design a weighted subcarrier screening method to improve the anti-interference ability. In order to shorten the identification time, we propose a feature integration method based on the weighted average. Finally, we use a deep learning method to identify users accurately. Experimental results show that GRi-Fi can identify the users identity with an average accuracy of 98.3% in noninterference environments. Even in the presence of multiple interferences, the average identification accuracy also reaches 91.2%. In future applications, our system can be applied to many fields of Internet of Things, such as smart home systems and clocking in at companies.

With the rapid development of the Internet, more and more computing-intensive applications with high requirements on computing delay and energy consumption have emerged. Recently, the use of mobile-edge computing servers for auxiliary computing is considered as an effective way to reduce latency and energy consumption. In addition, applications such as autonomous driving will generate a large number of repetitive tasks. Using a cache to store the computational results of popular tasks can avoid the overhead caused by repetitive processing. In this article, we study the problem of computation offloading for users in multiple regions. The optimization goal is expressed as choosing offloading strategies and caching strategies to minimize the total delay and energy consumption of all regions. We first use the deep reinforcement learning (DRL) deep deterministic policy gradient (DDPG) framework to solve the problem of computational offloading in a single region. We also show the inefficiency of existing collaborative caching approaches in multiple regions, and propose a new collaborative caching algorithm (CCA) to improve the overall cache hit rate of the system. Finally, we integrate the DDPG and CCA algorithms to form a holistic efficient caching and offloading strategy for all regions. The simulation results show that the proposed algorithm can significantly improve the cache hit rate, and has an excellent performance in reducing the total system overhead.

Bike Sharing Systems (BSSs) have emerged as an economical and eco-friendly solution to alleviate the last-mile problem in intelligent transport systems. As an exclusive route selection problem in BSSs, Bike Trip Planning (BTP) has a clear goal: to select the available routes with minimum time cost for bike users, while satisfying their basic needs, e.g., the bounded longest walking distance. In this paper, we propose a real-time Lyapunov-based Bike Trip Planning (LBTP) policy that considers the users’ waiting at stations, which has not been sufficiently studied in the literature. Both the total time cost and the service rate of all users are the core criteria of a BSS, so we make use of the Lyapunov optimization theory to make a tradeoff between them. Our policy can achieve self-organizing bike redistribution without extra redistribution budget required. The evaluation results show the superiority of our policy on the both system utility and user service rate compared with the existing BTP policies, and reveal the extra travel time fairness degree among different types of users under our policy.

Speeding is one of the biggest threatens to road safety. However, facilities like radar detector and speed camera are not deployed everywhere, as roads in some areas like campus and residential areas often lack these facilities. Several solutions either depend on pre-deployed infrastructures, or require additional devices, which motivate us to explore the practicability of using smartphones’ acoustic sensors to detect vehicle speed. In this paper, we propose a Hybrid Detection system for vehicle Speed (HDSpeed). We first investigate the relationship between acoustic pattern and vehicle speed. According to our findings on typical patterns of both electric vehicles (EVs) and gasoline vehicles (GVs), we separately extract different features from the acoustic signals of EVs and GVs. A CNN and an LSTMN are designed for training EV and GV models, respectively. Considering that applying neural networks obtains coarse-grained information like a speed section, we propose a detection method based on active acoustic sensing, in which method HDSpeed calculates the fine-grained speed by detecting the distance change between the smartphone and the passing vehicle. In addition, the previously detected speed section can eliminate interferences of surrounding moving objects. Through extensive experiments in real driving environments, HDSpeed achieves an average error of$2.17km/h$.

Driving safety has drawn much public attention in recent years due to the fast-growing number of cars. Smoking is one of the threats to driving safety but is often ignored by drivers. Existing works on smoking detection either work in contact manner or need additional devices. This motivates us to explore the practicability of using smartphones to detect smoking events in driving environment. In this paper, we propose a cigarette smoking detection system, named HearSmoking, which only uses acoustic sensors on smartphones to improve driving safety. After investigating typical smoking habits of drivers, including hand movement and chest fluctuation, we design an acoustic signal to be emitted by the speaker and received by the microphone. We calculate Relative Correlation Coefficient of received signals to obtain movement patterns of hands and chest. The processed data is sent into a trained Convolutional Neural Network for classification of hand movement. We also design a method to detect respiration at the same time. To improve system performance, we further analyse the periodicity of the composite smoking motion. Through extensive experiments in real driving environments, HearSmoking detects smoking events with an average total accuracy of 93.44 percent in real-time.

In the traditional video streaming service provisioning paradigm, users typically request video contents through nearby Content Delivery Network (CDN) server(s). However, because of the uncertain wide area networks delays, the (remote) users usually suffer from long video streaming delay, which affects the quality of experience. Multi-Access Edge Computing (MEC) offers caching infrastructures in closer proximity to end users than conventional Content Delivery Networks (CDNs). Yet, for video caching, MEC's potential has not been fully unleashed as it overlooks the opportunities of collaborative caching and multi-bitrate video transcoding. In this paper, we model and formulate an Integer Linear Program (ILP) to capture the long-term cost minimization problem for caching videos at MEC, allowing joint exploitation of MEC with CDN and real-time video transcoding to satisfy arbitrary user demands. While this problem is intractable and couples the caching decisions for adjacent time slots, we design a polynomial-time online orchestration framework which first relaxes and carefully decomposes the problem into a series of subproblems solvable in each individual time slot and then converts the fractional solutions into integers without violating constraints. We have formally proved a parameterized-constant competitive ratio as the performance guarantee for our approach, and also conducted extensive evaluations to confirm its superior practical performance. Simulation results demonstrate that our proposed algorithm outperforms the state-of-the-art algorithms, with 13.6% improvement on average in terms of total cost.

Network Function Virtualization (NFV) has been emerging as an appealing solution that transforms from dedicated hardware implementations to software instances running in a virtualized environment. In NFV, the requested service is implemented by a sequence of Virtual Network Functions (VNF) that can run on generic servers by leveraging the virtualization technology. These VNFs are pitched with a predefined order, and it is also known as the Service Function Chaining (SFC). Considering that the delay and resiliency are two important Service Level Agreements (SLA) in a NFV service, in this paper, we first investigate how to quantitatively model the traversing delay of a flow in both totally ordered and partially ordered SFCs. Subsequently, we study how to calculate the VNF placement availability mathematically for both unprotected and protected SFCs. After that, we study the delay-sensitive Virtual Network Function placement and routing problem with and without resiliency concerns. We prove that this problem is NP-hard under two cases. We subsequently propose an exact Integer Nonlinear Programming (INLP) formulation and an efficient heuristic for this problem in each case. Finally, we evaluate the proposed algorithms in terms of acceptance ratio, average number of used nodes and total running time via extensive simulations.

Hand hygiene has a significant impact on human health. Proper handwashing, having a crucial effect on reducing bacteria, serves as the cornerstone of hand hygiene. For the elder with dementia, they suffer from a gradual loss of memory and difficulty in coordinating steps in the execution of handwashing. Proper assistance should be provided to them to ensure their hand hygiene adherence. Toward this end, we propose AWash, leveraging only commodity IMU sensor mounted on most wrist-worn devices (e.g., smartwatches) to characterize hand motions and provide assistance accordingly. To handle particular interference of senile dementia patients in IMU sensor readings, we design a number of effective techniques to segment handwashing actions, transform sensory input to body coordinate system, and extract sensor-body inclination angles. A hybrid neural network model is used to enable AWash to generalize to new users without retraining or adaptation, avoiding the trouble of collecting behavior information of every user. To meet the diverse needs of users with various executive functioning, we use a state machine to make prompt decisions, which supports customized assistance. Extensive experiments on a prototype with eight older participants demonstrate that AWash can increase the user's independence in the execution of handwashing.

The efficacy of Network Function Virtualization (NFV) depends critically on (1) where the virtual network functions (VNFs) are placed and (2) how the traffic is routed. Unfortunately, these aspects are not easily optimized, especially under time-varying network states with different quality of service (QoS) requirements. Given the importance of NFV, many approaches have been proposed to solve the VNF placement and traffic routing problem. However, those prior approaches mainly assume that the state of the network is static and known, disregarding real-time network variations. To bridge that gap, in this paper, we formulate the VNF placement and traffic routing problem as a Markov Decision Process model to capture the dynamic network state transitions. In order to jointly minimize the delay and cost of NFV providers and maximize the revenue, we devise a customized Deep Reinforcement Learning (DRL) algorithm, called A-DDPG, for VNF placement and traffic routing in a real-time network. A-DDPG uses the attention mechanism to ascertain smooth network behavior within the general framework of network utility maximization (NUM). The simulation results show that A-DDPG outperforms the state-of-the-art in terms of network utility, delay, and cost.

The safety of the elderly has attracted much attention nowadays. Among various daily activities, fall is one of the most dangerous events for the elderly, especially those who live alone. Most existing works on fall detection are based on wearable devices, which are inconvenient in using. Several solutions only use coarse-grained Wi-Fi signal information that contains many biases, and lack considerations on environmental changes. These situations motivate us to design a fine-grained and robust fall detection approach. In this article, we propose a fall detection system, called FallViewer, based on analyzing the channel state information (CSI) of Wi-Fi signals. To get fine-grained information, we propose phase and amplitude calibration methods for deviation correction. Then, an adjustment approach for antenna power is designed to eliminate the multipath interference. Furthermore, we apply a double sliding window to get a flexible threshold, which improves the robustness of FallViewer to various environments. Finally, FallViewer extracts features of the processed Wi-Fi signal and sends the features to a LibSVM for classification. Through experiments in different environments, FallViewer can detect fall events with an average accuracy of 95.8%, which indicates that FallViewer can work reliably and effectively.

Cloud radio access network (C-RAN) is a promising 5G network architecture by establishing baseband units (BBU) pools to perform baseband processing functionalities and deploying remote radio heads (RRHs) for wireless signal transmission and reception. Mobile-edge computing (MEC) offers a way to shorten the service delay by building small-scale cloud infrastructures at the network edge. By co-locating the BBU pool with edge cloud at the so-called BBU node, we can take full advantages of C-RAN and MEC for better spectrum utilization and delay-guaranteed services. In this article, we first study how to allocate each user's task to the BBU node and find the path from his/her accessing RRH node to the BBU node such that the maximum service delay among all the requests is minimized. We then consider this problem with survivability concerns, which is to use both primary and backup BBU nodes to issue the request such that the primary path and backup path are link disjoint. We analyze the complexities of these two problems and prove they are NP-hard in general. Subsequently, we devise a randomized approximation algorithm and an efficient heuristic to solve the considered problems, respectively. The simulation results show that the proposed algorithms outperform two benchmark heuristics in terms of acceptance ratio and maximum service delay.

Drowsy driving is one of the biggest threats to driving safety, which has drawn much public attention in recent years. Thus, a simple but robust system that can remind drivers of drowsiness levels with off-the-shelf devices (e.g., smartphones) is very necessary. With this motivation, we explore the feasibility of using acoustic sensors on smartphones to detect drowsy driving. Through analyzing real driving data to study characteristics of drowsy driving, we find some unique patterns of Doppler shift caused by three typical drowsy behaviours (i.e., nodding, yawning and operating steering wheel), among which operating steering wheels is also related to drowsiness levels. Then, a real-time Drowsy Driving Detection system named D3-Guard is proposed based on the acoustic sensing abilities of smartphones. We adopt several effective feature extraction methods, and carefully design a high-accuracy detector based on LSTM networks for the early detection of drowsy driving. Besides, measures to distinguish drowsiness levels are also introduced in the system by analyzing the data of operating steering wheel. Through extensive experiments with five drivers in real driving environments, D3-Guard detects drowsy driving actions with an average accuracy of 93.31%, as well as classifies drowsiness levels with an average accuracy of 86%.

Mobile Edge Computing (MEC) offers a way to shorten the cloud servicing delay by building the small-scale cloud infrastructures at the network edge, which are in close proximity to the end users. Moreover, Network Function Virtualization (NFV) has been an emerging technology that transforms from traditional dedicated hardware implementations to software instances running in a virtualized environment. In NFV, the requested service is implemented by a sequence of Virtual Network Functions (VNF) that can run on generic servers by leveraging the virtualization technology. Service Function Chaining (SFC) is defined as a chain-ordered set of placed VNFs that handles the traffic of the delivery and control of a specific application. NFV therefore allows to allocate network resources in a more scalable and elastic manner, offer a more efficient and agile management and operation mechanism for network functions and hence can largely reduce the overall costs in MEC. In this paper, we study the problem of how to place VNFs on edge and public clouds and route the traffic among adjacent VNF pairs, such that the maximum link load ratio is minimized and each user's requested delay is satisfied. We consider this problem for both totally ordered SFCs and partially ordered SFCs. We prove that this problem is NP-hard, even for the special case when only one VNF is requested. We subsequently propose an efficient randomized rounding approximation algorithm to solve this problem. Extensive simulation results show that the proposed approximation algorithm can achieve close-to-optimal performance in terms of acceptance ratio and maximum link load ratio.

Network Function Virtualization (NFV) has been emerging as an appealing solution that transforms complex network functions from dedicated hardware implementations to software instances running in a virtualized environment. Due to the numerous advantages such as flexibility, efficiency, scalability, short deployment cycles, and service upgrade, NFV has been widely recognized as the next-generation network service provisioning paradigm. In NFV, the requested service is implemented by a sequence of Virtual Network Functions (VNF) that can run on generic servers by leveraging the virtualization technology. These VNFs are pitched with a predefined order through which data flows traverse, and it is also known as the Service Function Chaining (SFC). In this article, we provide an overview of recent advances of resource allocation in NFV. We generalize and analyze four representative resource allocation problems, namely, (1) the VNF Placement and Traffic Routing problem, (2) VNF Placement problem, (3) Traffic Routing problem in NFV, and (4) the VNF Redeployment and Consolidation problem. After that, we study the delay calculation models and VNF protection (availability) models in NFV resource allocation, which are two important Quality of Service (QoS) parameters. Subsequently, we classify and summarize the representative work for solving the generalized problems by considering various QoS parameters (e.g., cost, delay, reliability, and energy) and different scenarios (e.g., edge cloud, online provisioning, and distributed provisioning). Finally, we conclude our article with a short discussion on the state-of-the-art and emerging topics in the related fields, and highlight areas where we expect high potential for future research.

Mobile Crowd Sensing (MCS) enables the platform to offer data-based service by incentivizing mobile users to perform sensing task and collecting sensing data from them. Most of the existing works on MCS only consider designing incentive mechanisms for a single MCS platform. In this paper, we study the incentive mechanism in MCS with multiple platforms under two scenarios: competitive platform and cooperative platform. We correspondingly propose new competitive and cooperative mechanisms for each scenario. In the competitive platform scenario, platforms decide their prices on rewards to attract more participants, while the users choose which platform to work for. We model such a competitive platform scenario as a two-stage Stackelberg game. In the cooperative platform scenario, platforms cooperate to share sensing data with each other. We model it as many-to-many bargaining. Moreover, we first prove the NP-hardness of exact bargaining and then propose heuristic bargaining. Finally, numerical results show that (1) platforms in the competitive platform scenario can guarantee their payoff by optimally pricing on rewards and participants can select the best platform to contribute; (2) platforms in the cooperative platform scenario can further improve their payoff by bargaining with other platforms for cooperatively sharing collected sensing data.

Micro finger gesture recognition is an emerging approach to realize more friendly interaction between human and smart devices, especially for small wearable devices, such as smartwatches and virtual reality glasses. This paper proposes airFinger, a novel solution utilizing NIR light sensing to realize both real-time gesture recognition and finger tracking aiming at micro finger gestures. Using a custom NIR-based sensor with novel algorithms to capture subtle finger movements, airFinger enables to detect a rich set of micro finger gestures and track finger movements in terms of scrolling direction, velocity, and displacement. Besides, airFinger is capable of effective noise mitigation, gesture segmentation, and reducing false recognition due to the unintentional actions of users. Extensive experimental results demonstrate that airFinger has robustness against individual diversity, gesture inconsistency, and many other impacts. The overall performance reaches an average accuracy as high as 98.72% over a set of 8 micro finger gestures among 10, 000 gesture samples collected from 10 volunteers.

Mobile devices are promising to apply two-factor authentication in order to improve system security and enhance user privacy-preserving. Existing solutions usually have certain limits of requiring some form of user effort, which might seriously affect user experience and delay authentication time. In this paper, we propose PPGPass, a novel mobile two-factor authentication system, which leverages Photoplethysmography (PPG) sensors in wrist-worn wearables to extract individual characteristics of PPG signals. In order to realize both nonintrusive and secure, we design a two-stage algorithm to separate clean heartbeat signals from PPG signals contaminated by motion artifacts, which allows verifying users without intentionally staying still during the process of authentication. In addition, to deal with non-cancelable issues when biometrics are compromised, we design a repeatable and non-invertible method to generate cancelable feature templates as alternative credentials, which enables to defense against man-in-the-middle attacks and replay attacks. To the best of our knowledge, PPGPass is the first nonintrusive and secure mobile two-factor authentication based on PPG sensors in wearables. We build a prototype of PPGPass and conduct the system with comprehensive experiments involving multiple participants. PPGPass can achieve an average F1 score of 95.3%, which confirms its high effectiveness, security, and usability.

With the proliferation of Internet of Things (IoT), zillions of bytes of data are generated at the network edge, incurring an urgent need to push the frontiers of artificial intelligence (AI) to network edge so as to fully unleash the potential of the IoT big data. To materialize such a vision which is known as edge intelligence, federated learning is emerging as a promising solution to enable edge nodes to collaboratively learn a shared model in a privacy-preserving and communication-efficient manner, by keeping the data at the edge nodes. While pilot efforts on federated learning have mostly focused on reducing the communication overhead, the computation efficiency of those resource-constrained edge nodes has been largely overlooked. To bridge this gap, in this article, we investigate how to coordinate the edge and the cloud to optimize the system-wide cost efficiency of federated learning. Leveraging the Lyapunov optimization theory, we design and analyze a cost-efficient optimization framework CEFL to make online yet near-optimal control decisions on admission control, load balancing, data scheduling, and accuracy tuning for the dynamically arrived training data samples, reducing both computation and communication cost. In particular, our control framework CEFL can be flexibly extended to incorporate various design choices and practical requirements of federated learning, such as exploiting the cheaper cloud resource for model training with better cost efficiency yet still facilitating on-demand privacy preservation. Via both rigorous theoretical analysis and extensive trace-driven evaluations, we verify the cost efficiency of our proposed CEFL framework.

In this article, we propose points-of-interest (POI)-tagging App-assisted incentive mechanism (PTASIM), an incentive mechanism that explores the cooperation with POI-tagging App for mobile edge crowdsensing (MEC). PTASIM requests App to tag some edges to be POI, which further guides App users to perform tasks at that location. We further model the interactions of users, platform, and App by a three-stage decision process. App first determines the POI-tagging price to maximize its payoff. Platform and users subsequently decide how to determine tasks reward and select edges to be tagged, and how to select the best task to perform, respectively. We analyze the optimal solution in those stages. Specifically, we prove that greedy algorithm could provide the optimal solution for platform's payoff maximization in polynomial time. The numerical results show that: 1) the cooperation with App brings long-term and sufficient participation; and 2) the optimal strategies reduce platform's tasks cost as well as improve App's revenues.

Since the number of cars has grown rapidly in recent years, driving safety draws more and more public attention. Drowsy driving is one of the biggest threatens to driving safety. Therefore, a simple but robust system that can detect drowsy driving with commercial off-the-shelf devices (such as smart-phones) is very necessary. With this motivation, we explore the feasibility of purely using acoustic sensors embedded in smart-phones to detect drowsy driving. We first study characteristics of drowsy driving, and find some unique patterns of Doppler shift caused by three typical drowsy behaviors, i.e., nodding, yawning and operating steering wheel. We then validate our important findings through empirical analysis of the driving data collected from real driving environments. We further propose a real-time Drowsy Driving Detection system (D3-Guard) based on audio devices embedded in smartphones. In order to improve the performance of our system, we adopt an effective feature extraction method based on undersampling technique and FFT, and carefully design a high-accuracy detector based on LSTM networks for the early detection of drowsy driving. Through extensive experiments with 5 volunteer drivers in real driving environments, our system can distinguish drowsy driving actions with an average total accuracy of 93.31% in real-time. Over 80% drowsy driving actions can be detected within first 70% of action duration.

Mobile edge computing (MEC) offers a way to shorten the cloud servicing delay by building the small-scale cloud infrastructures, such as cloudlets at the network edge, which are in close proximity to end users. On one hand, it is energy consuming and costly to place each cloudlet on each access point (AP) to process the requested tasks. On the other hand, the service provider should provide delay-guaranteed service to end users, otherwise they may get revenue loss. In this paper, we first model how to calculate the task completion delay in MEC and mathematically analyze the energy consumption of different equipments in MEC. Subsequently, we study how to place cloudlets on the network and allocate each requested task to cloudlets and public cloud with the minimum total energy consumption without violating each task's delay requirement. We prove that this problem is NP-hard and propose a Benders decomposition-based algorithm to solve it. We also present a software-defined network (SDN)-based framework to deploy the proposed algorithm. Extensive simulations reveal that the proposed algorithm can achieve an (close-to-)optimal performance in terms of energy consumption and acceptance ratio compared with two benchmark heuristics.

The usage of hybrid energy supplied sensors in the Internet of Things has enabled longer lifetime of sensors and expanded scope of applications. These sensors can combine advantages of environmental energy harvesting techniques and wireless energy harvesting techniques. However, how to coordinate them is still a challenge and has not been studied extensively. In this article, we present a system based on mobile crowd wireless charging to manage energy of hybrid energy supplied sensors. When environmental energy is insufficient, the system will utilize smart devices carried by mobile users as chargers to provide wireless energy. We construct and study a W3W problem in the system: when to leverage mobile crowd wireless charging to support rechargeable sensors, where to perform wireless energy transfer, and whom to allocate and incentivize as chargers to maximize useful energy value over all sensors subject to a budget. In order to control the actual quality of wireless energy charging, we propose a design principle named task completion trustfulness. We consider offline and online conditions and design corresponding algorithms with incentive allocations. Extensive simulations are conducted to demonstrate the effectiveness of our algorithms, which also validates our theoretical results.

With the rapid increasing of smart phones and their embedded sensing technologies, mobile crowd sensing (MCS) becomes an emerging sensing paradigm for performing large-scale sensing tasks. One of the key challenges of large-scale mobile crowd sensing systems is how to effectively select the minimum set of appropriate participants from the huge user pool to perform the tasks. However, the capabilities of individual participants are usually unknown by the selection mechanism, which leads to the most challenging issue of participant selection. While online learning techniques can be used to learn the participant's capability, the diverse expertise of each individual makes a single capability metric is not sufficient. To address the multi-expertise of participants, in this paper we introduce a new self-learning architecture which leverages the historical performing records of participants to learn the different capabilities (both sensing probability and time delay) of participants. Formulating the participant selection problem as a combinational multi-armed bandit problem, we present an online participant selection algorithm with both performance guarantee and bounded regret. Extensive simulations with a real-world mobile dataset demonstrate the efficiency of the proposed solution.

Customers often suffer from the variability of data access time in cloud storage service, caused by network congestion, load dynamics, etc. One solution to guarantee a reliable latency-sensitive service is to issue requests with multiple download/upload sessions, accessing the required data (replicas) stored in one or more servers. In order to minimize storage costs, how to optimally allocate data in a minimum number of servers without violating latency guarantees remains to be a crucial issue for the cloud provider to tackle. In this paper, we study the latency-sensitive data allocation problem for cloud storage. We model the data access time as a given distribution whose Cumulative Density Function (CDF) is known, and prove that this problem is NP-hard. To solve it, we propose both exact Integer Nonlinear Program (INLP) and Tabu Search-based heuristic. The proposed algorithms are evaluated in terms of the number of used servers, storage utilization and throughput utilization.

In current cloud computing systems, when leveraging virtualization technology, the customer’s requested data computing or storing service is accommodated by a set of communicated virtual machines (VM) in a scalable and elastic manner. These VMs are placed in one or more server nodes according to the node capacities or failure probabilities. The VM placement availability refers to the probability that at least one set of all customer’s requested VMs operates during the requested lifetime. In this paper, we first study the problem of placing at most$H$groups of$k$requested VMs on a minimum number of nodes, such that the VM placement availability is no less than$\delta$, and that the specified communication delay and connection availability for each VM pair under the same placement group are not violated. We consider this problem with and without Shared-Risk Node Group (SRNG) failures, and prove this problem is NP-hard in both cases. We subsequently propose an exact Integer Nonlinear Program (INLP) and an efficient heuristic to solve this problem. We conduct simulations to compare the proposed algorithms with two existing heuristics in terms of performance. Finally, we study the related reliable routing problem of establishing a connection over at most$w$link-disjoint paths from a source to a destination, such that the connection availability requirement is satisfied and each path delay is no more than a given value. We devise an exact algorithm and two heuristics to solve this NP-hard problem, and evaluate them via simulations.

In data‐communication networks, network reliability is of great concern to both network operators and customers. On the one hand, the customers care about receiving reliable services and, on the other hand, for the network operators it is vital to determine the most vulnerable parts of their network. In this article, we first study the problem of establishing a connection over at most (partially) link‐disjoint paths and for which the total availability is no less than ( ). We analyze the complexity of this problem in generic networks, shared‐risk link group networks and multilayer networks. We subsequently propose a polynomial‐time heuristic algorithm and an exact integer nonlinear program for availability‐based path selection. The proposed algorithms are evaluated in terms of acceptance ratio and running time. Subsequently, in the three aforementioned types of networks, we study the problem of finding a (set of) network cut(s) for which the failure probability of its links is largest. © 2015 Wiley Periodicals, Inc. NETWORKS, Vol. 66(4), 306–319 2015

Solving network flow problems is a fundamental component of traffic engineering and many communications applications, such as content delivery or multi-processor scheduling. While a rich body of work has addressed network flow problems in "deterministic networks" finding flows in "stochastic networks" where performance metrics like bandwidth and delay are uncertain and solely known by a probability distribution based on historical data, has received less attention. The work on stochastic networks has predominantly been directed to developing single-path routing algorithms, instead of addressing multi-path routing or flow problems. In this paper, we study constrained maximum flow problems in stochastic networks, where the delay and bandwidth of links are assumed to follow a log-concave probability distribution, which is the case for many distributions that could represent bandwidth and delay. We formulate the maximum-flow problem in such stochastic networks as a convex optimization problem, with a polynomial (in the input) number of variables. When an additional delay constraint is imposed, we show that the problem becomes NP-hard and we propose an approximation algorithm based on convex optimization. Furthermore, we develop a fast heuristic algorithm that, with a tuning parameter, is able to balance accuracy and speed. In a simulation-based evaluation of our algorithms in terms of success ratio, flow values, and running time, our heuristic is shown to give good results in a short running time.