Although Federated Learning (FL) can enable advanced autonomous driving via leveraging massive distributed data in vehicular networks, vehicle mobility causes frequent connection interruptions, hindering the FL process. In this paper, we propose a novelMobility-AwareVehicularFL(MAVFL) scheme, which can accelerate the training process in dynamic vehicular networks via adaptive vehicle selection and sparse training. Specifically, the MAVFL dynamically selects participating vehicles based on their locations and training loss. By incorporating adaptive model sparsification, the proposed scheme dynamically proceeds with sparse masks during vehicle local training, thereby reducing communication overhead while preserving model accuracy. We conduct a rigorous convergence analysis to uncover how vehicle mobility and model sparsification affect convergence rate. Furthermore, we formulate an optimization problem to accelerate the training process, which jointly optimizes vehicle selection, sparsification ratio, and bandwidth allocation to minimize training delay. To solve the problem, we employ the Lyapunov optimization method to decouple the long-term problem into a series of instantaneous subproblems. Next, a generalized Benders decomposition method structures the original problem into a master subproblem for vehicle selection and a primal subproblem for bandwidth allocation and sparsification ratio selection. The optimal solutions are derived via alternating iterations between these problems. Extensive simulation results based on the SUMO simulator demonstrate that the MAVFL accelerates model convergence by up to 14% and reduces communication overhead by up to 26% while preserving model accuracy, as compared to the state-of-the-art benchmarks.

As a popular distributed learning paradigm, federated learning (FL) over mobile devices fosters numerous applications, while their practical deployment is hindered by participating devices’ computing and communication heterogeneity. Some pioneering research efforts proposed to extract subnetworks from the global model, and assign as large a subnetwork as possible to the device for local training based on its full computing and communications capacity. Although such fixed size subnetwork assignment enables FL training over heterogeneous mobile devices, it is unaware of (i) the dynamic changes of devices’ communication and computing conditions and (ii) FL training progress and its dynamic requirements of local training contributions, both of which may cause very long FL training delay. Motivated by those dynamics, in this paper, we develop a wireless and heterogeneity aware latency efficient FL (WHALE-FL) approach to accelerate FL training through adaptive subnetwork scheduling. Instead of sticking to the fixed size subnetwork, WHALE-FL introduces a novel subnetwork selection utility function to capture device and FL training dynamics, and guides the mobile device to adaptively select the subnetwork size for local training based on (a) its computing and communication capacity, (b) its dynamic computing and/or communication conditions, and (c) FL training status and its corresponding requirements for local training contributions. We provide a theoretical convergence analysis for WHALE-FL with heterogeneous subnetwork assignment, based on which subnetwork structures can be dynamically optimized to reduce the resulting gap to standard full-model FL. Our evaluation shows that, compared with peer designs, WHALE-FL effectively accelerates FL training without sacrificing learning accuracy.

As a popular distributed learning paradigm, federated learning (FL) over mobile devices fosters numerous applications, while their practical deployment is hindered by participating devices' computing and communication heterogeneity. Some pioneering research efforts proposed to extract subnetworks from the global model, and assign as large a subnetwork as possible to the device for local training based on its full computing capacity. Although such fixed size subnetwork assignment enables FL training over heterogeneous mobile devices, it is unaware of (i) the dynamic changes of devices' communication and computing conditions and (ii) FL training progress and its dynamic requirements of local training contributions, both of which may cause very long FL training delay. Motivated by those dynamics, in this paper, we develop a wireless and heterogeneity aware latency efficient FL (WHALE-FL) approach to accelerate FL training through adaptive subnetwork scheduling. Instead of sticking to the fixed size subnetwork, WHALE-FL introduces a novel subnetwork selection utility function to capture device and FL training dynamics, and guides the mobile device to adaptively select the subnetwork size for local training based on (a) its computing and communication capacity, (b) its dynamic computing and/or communication conditions, and (c) FL training status and its corresponding requirements for local training contributions. Our evaluation shows that, compared with peer designs, WHALE-FL effectively accelerates FL training without sacrificing learning accuracy.

To enable large model (LM) based edge intelligent service provisioning, on-device fine-tuning with locally personalized data allows for continuous and privacy-preserving LM customization. In this paper, we propose RingAda, a collaborative training framework designed for fine-tuning transformer-based LMs on edge devices. Particularly, RingAda performs parameterefficient adapter fine-tuning across a set of interconnected edge devices, forming a ring topology for per-batch training by sequentially placing frozen transformer blocks and their trainable adapter modules on the devices. RingAda follows a novel pipeline-parallel training mechanism with top-down adapter unfreezing, allowing for early-stopping of backpropagation at the lowest unfrozen adapter layer, thereby accelerating the finetuning process. Extensive experimental results demonstrate that RingAda significantly reduces fine-tuning time and memory costs while maintaining competitive model performance compared to its peer designs.

The proliferation of Internet of Things (IoT)-generated distributed personal data enables user-specific large language model (LLM) adaptation at the edge. The split federated learning (SFL) facilitates collaborative learning and reduces memory footprint by model splitting, which necessitates the transmission of intermediate activations, rendering it susceptible to reconstruction attacks and privacy breaches. In this paper, we present a privacy-aware SFL scheme addressing the accuracy-efficiency-privacy trilemma in LLM fine-tuning over heterogeneous IoT devices. Particularly, we develop a privacy quantification metric based on Fisher information to assess layer-wise privacy risks in smashed data transmission. Guided by this metric, we establish an analytical model that captures the intricate relationships between privacy leakage, fine-tuning convergence time, and device energy consumption. To optimize these three aspects, we formulate a multi-objective mixed-integer programming problem. Then, an -constraint-based block coordinate descent (BCD) algorithm is proposed to jointly determine the optimal LLM split layer, transmit power, and bandwidth allocation for IoT devices under their memory and network constraints. Extensive simulation results demonstrate the proposed scheme’s effectiveness in achieving 24% faster convergence, 40% lower energy consumption, and 7% reduced privacy leakage compared to baseline approaches, while maintaining competitive model accuracy.

Training latency is critical for the success of numerous intrigued applications ignited by federated learning (FL) over heterogeneous mobile devices. By revolutionarily overlapping local gradient transmission with continuous local computing, FL can remarkably reduce its training latency over homogeneous clients, yet encounter severe model staleness, model drifts, memory cost and straggler issues in heterogeneous environments. To unleash the full potential of overlapping, we propose, FedEx, a novelfederated learning approach toexpedite FL training over mobile devices under data, computing and wireless heterogeneity. FedEx redefines the overlapping procedure with staleness ceilings to constrain memory consumption and make overlapping compatible with participation selection (PS) designs. Then, FedEx characterizes the PS utility function by considering the latency reduced by overlapping, and provides a holistic PS solution to address the straggler issue. FedEx also introduces a simple but effective metric to trigger overlapping, in order to avoid model drifts. Experimental results show that compared with its peer designs, FedEx demonstrates substantial reductions in FL training latency over heterogeneous mobile devices with limited memory cost.

Many rescue missions demand effective perception and real-time decision making, which highly rely on effective data collection and processing. In this study, we propose a three-layer architecture of emergency caching networks focusing on data collection and reliable transmission, by leveraging efficient perception and edge caching technologies. Based on this architecture, we propose a disaster map collection framework that integrates coded caching technologies. Our framework strategically caches coded fragments of maps across unmanned aerial vehicles (UAVs), fostering collaborative uploading for augmented transmission reliability. Additionally, we establish a comprehensive probability model to assess the effective recovery area of disaster maps. Towards the goal of utility maximization, we propose a deep reinforcement learning (DRL) based algorithm that jointly makes decisions about cooperative UAVs selection, bandwidth allocation and coded caching parameter adjustment, accommodating the real-time map updates in a dynamic disaster situation. Our proposed scheme is more effective than the non-coding caching scheme, as validated by simulation.

In emergency scenarios, strong mobility and serious interference cause unstable transmission of on-site information such as close-up photos and high resolution videos, which requires a robust temporary communication network. In this paper, we focus on a UAV-assisted wireless cooperative communication and coded caching network, where emergency command vehicles and a UAV serve as content providers (CPs) to cache and transmit coded fragments or complete files for rescuers regarded as content requesters (CRs). The delivery success probability and content hit ratio are theoretically derived by incorporating the physical connectivity and social relationship between CPs and CRs. Aiming at maximizing the overall content hit ratio, we propose a multiagent two-timescale deep reinforcement learning (MA2T-DRL) algorithm to jointly optimize the transmission power and caching strategies for CPs. Specifically, we develop a two tier deep-Q networks (DQNs) framework integrating a slow-timescale DQN (ST-DQN) and a fast-timescale DQN (FT-DQN) for caching decision-making and power decision-making respectively, and then the QMIX framework is leveraged to aggregate all the outputs from local ST-DQNs. Considering the cooperative characteristics of coded caching, we further propose a novel clustering method for CPs such that CPs in the same cluster have the same willingness to serve CRs, and each cluster is regarded as the agent for training which further reduces the aggregation scale of the mixing network. Simulation results show that the proposed MA2T-DRL algorithm is efficient in model training, and presents the advantages in performance and complexity compared with the single-agent centralized training and the multiagent independent distributed training.

The distributed inference paradigm enables the computation workload to be distributed across multiple devices, facilitating the implementation of deep learning based intelligent services on extremely resource-constrained Internet of Things (IoT) scenarios. Yet it raises great challenges to perform complicated inference tasks relying on a cluster of IoT devices that are heterogeneous in their computing/communication capacity and prone to crash or timeout failures. In this paper, we present RoCoIn, a robust cooperative inference mechanism for locally distributed execution of deep neural network-based inference tasks over heterogeneous edge devices. It creates a set of independent and compact student models that are learned from a large model using knowledge distillation for distributed deployment. In particular, the devices are strategically grouped to redundantly deploy and execute the same student model such that the inference process is resilient to any local failures, while a joint knowledge partition and student model assignment scheme are designed to minimize the response latency of the distributed inference system in the presence of devices with diverse capacities. Extensive simulations are conducted to corroborate the superior performance of our RoCoIn for distributed inference compared to several baselines, and the results demonstrate its efficacy in timely inference and failure resilience.

Federated learning (FL) enables mobile devices to collaboratively learn a shared prediction model while keeping data locally. However, there are two major research challenges to practically deploy FL over mobile devices: (i) frequent wireless updates of huge size gradients v.s. limited spectrum resources, and (ii) energy-hungry FL communication and local computing during training v.s. battery-constrained mobile devices. To address those challenges, in this paper, we propose a novel multi-bit over-the-air computation (M-AirComp) approach for spectrum-efficient aggregation of local model updates in FL and further present an energy-efficient FL design for mobile devices. Specifically, a high-precision digital modulation scheme is designed and incorporated in the M-AirComp, allowing mobile devices to upload model updates at the selected positions simultaneously in the multi-access channel. Moreover, we theoretically analyze the convergence property of our FL algorithm. Guided by FL convergence analysis, we formulate a joint transmission probability and local computing control optimization, aiming to minimize the overall energy consumption (i.e., iterative local computing + multi-round communications) of mobile devices in FL. Extensive simulation results show that our proposed scheme outperforms existing ones in terms of spectrum utilization, energy efficiency, and learning accuracy.

The rapid growth of cloud computing has led to high energy consumption in data centers (DCs), significantly burdening the safe operation of the power grid. As DC loads are seen as emergency demand response (EDR) resources, they can be aggregated into virtual power plants (VPPs) for the energy market trading, enhancing the renewable energy consumption capacity and providing grid benefits. However, VPPs might opt to maintain the profits they gain from EDR as confidential, driven by self-interest. Additionally, the incompatibility between the EDR transactions and task scheduling can result in revenue loss for DCs. To address these challenges, we propose a joint energy trading and computation scheduling (JETCS) framework for geo-distributed DCs participating in the EDR of VPPs. We first formulate DCs' energy and revenue computation as a maxi-mization problem to balance task delay and energy consumption. Then, we employ contract theory to facilitate the energy trading between DCs and VPPs against the information asymmetry. Due to nonlinearity and the infeasibility of obtaining an analytical result, we propose the proximal Jacobian alternating direction method of multipliers (PJADMM) algorithm to find an optimal solution with low complexity. The simulation results demonstrate that our proposed framework successfully encourages VPPs to reveal their actual profits and enhances the benefits for both parties.

In this paper, we propose a UAV network adaptation scheme driven by joint communication and positioning service provisioning in an emergency scenario, where massive rescuers’ concurrent and time-varying service demands are guaranteed with a scarce spectrum. Particularly, we establish a utility function that integrates communication rate and positioning error by jointly considering the single coverage constraint for data communication and the triple coverage constraint for positioning. Based on it, we propose a genetic algorithm based multi-agent deep deterministic policy gradient (GA-MADDPG) approach that adapts the UAV deployment, role switching, and user association strategies in a hierarchical manner to accommodate the rescuers’ demands for communication and positioning services in real-time. Specifically, the MADDPG module is applied for communication and positioning UAV network deployment based on the rescuers’ spatial distribution and their service demands, while the reward-based fitness is calculated and fed in the GA module periodically to optimize the UAV roles. Extensive simulation results show that our approach improves communication-positioning utility by up to 38% among comparison schemes.

The advances of communication technology and edge intelligence are deriving new computation offloading modes in the energy Internet by integrating computing capabilities of cloud servers, edge gateways (EGs), and terminal nodes into forecasting the renewable energy generation. However, the largely dispersed data generated by abundant photovoltaic (PV) stations and limited transmission capacity will degrade the collaboration of clouds, edges, and end nodes and, as a result, fail to satisfy the delay requirements of tasks. Owing to the similarity of power data generated by PV stations with akin geographical positions and weather conditions, we can reuse and offload the selected and representative power data so as to reduce transmission costs and overloads. In this article, we propose a similarity-aware stable matching approach (SASMA) to efficiently offload prediction tasks to EGs or cloud platforms with reusing the computing results. Specifically, we analyze task similarity and build the reuse strategy for the power data, and propose a similarity graph algorithm (SGA) to select representative PV stations and derive reuse relations. We also propose a similarity-based Gale–Shapley algorithm to match reused PV stations, computing nodes with prediction models. The objective is to maximize the prediction accuracy with a stable match. Simulation results show the effectiveness of the proposed approach while examining the tradeoff between the prediction accuracy and the system delay.

Federated learning (FL) is a popular collaborative distributed machine learning paradigm across mobile devices. However, practical FL over resource constrained mobile devices confronts multiple challenges, e.g., the local on-device training and model updates in FL are power hungry and radio resource intensive for mobile devices. To address these challenges, in this paper, we attempt to take FL into the design of future wireless networks and develop a novel joint design of wireless transmission and weight quantization for energy efficient FL over mobile devices. Specifically, we develop flexible weight quantization schemes to facilitate on-device local training over heterogeneous mobile devices. Based on the observation that the energy consumption of local computing is comparable to that of model updates, we formulate the energy efficient FL problem into a mixed-integer programming problem where the quantization and spectrum resource allocation strategies are jointly determined for heterogeneous mobile devices to minimize the overall FL energy consumption (computation + transmissions) while guaranteeing model performance and training latency. Since the optimization variables of the problem are strongly coupled, an efficient iterative algorithm is proposed, where the bandwidth allocation and weight quantization levels are derived. Extensive simulations are conducted to verify the effectiveness of the proposed scheme.

Preventing COVID-19 disease from spreading in communities will require proactive and effective healthcare resource allocations, such as vaccinations. A fine-grained COVID-19 vulnerability map will be essential to detect the high-risk communities and guild the effective vaccine policy. A mobile-crowdsourcing-based self-reporting approach is a promising solution. However, an accurate mobile-crowdsourcing-based map construction requests participants to report their actual locations, raising serious privacy concerns. To address this issue, we propose a novel approach to effectively construct a reliable community-level COVID-19 vulnerability map based on mobile crowdsourced COVID-19 self-reports without compromising participants’ location privacy. We design a geo-perturbation scheme where participants can locally obfuscate their locations with the geo-indistinguishability guarantee to protect their location privacy against any adversaries’ prior knowledge. To minimize the data utility loss caused by location perturbation, we first design an unbiased vulnerability estimator and formulate the location perturbation probability generation into a convex optimization. Its objective is to minimize the estimation error of the direct vulnerability estimator under the constraints of geo-indistinguishability. Given the perturbed locations, we integrate the perturbation probabilities with the spatial smoothing method to obtain reliable community-level vulnerability estimations that are robust to a small-sampling-size problem incurred by location perturbation. Considering the fast-spreading nature of coronavirus, we integrate the vulnerability estimates into the modified susceptible-infected-removed (SIR) model with vaccination for building a future trend map. It helps to provide a guideline for vaccine allocation when supply is limited. Extensive simulations based on real-world data demonstrate the proposed scheme superiority over the peer designs satisfying geo-indistinguishability in terms of estimation accuracy and reliability.

Mobile crowdsensing has emerged as a promising paradigm where location-based sensing tasks are outsourced to mobile participants carrying sensor-equipped devices. A critical issue of crowdsensing is to guarantee the sensing coverage by appropriately recruiting participants, which requires participants’ precise locations and thus raises privacy concerns. In this paper, we are motivated to develop a privacy preserving participant recruitment scheme for mobile crowdsensing, which maximizes the spatial coverage of the sensing range while protecting participants’ location privacy against an untrusted crowdsensing platform. Briefly, we propose a utility-assured location obfuscation mechanism operated in a hexagonal grid system, which the participants can follow to locally perturb their locations with personalized privacy demands. Given the obfuscated locations, we efficiently solve a coverage-maximized participant recruitment problem with the budget constraint by using a deterministic rounding algorithm. Considering the existence of biased sensing data incurred by location obfuscation, we further develop a fault-aware crowdsensing framework to improve the robustness of the recruitment strategy, where a constant-approximation algorithm is applied to select participants against any number of unqualified sensing results. Extensive simulations on real-world location datasets and Uber’s geospatial indexing system validate the efficacy of our location obfuscation mechanism and participant recruitment schemes in mobile crowdsensing systems.

Device-to-Device (D2D) communication enabling direct data transmission between two mobile users has emerged as a vital component for 5G cellular networks to improve spectrum utilization and enhance system capacity. A critical issue for realizing these benefits in D2D-enabled networks is to properly allocate radio resources while coordinating the co-channel interference in a time-varying communication environment. In this paper, we propose a Stackelberg game (SG) guided multi-agent deep reinforcement learning (MADRL) approach, which allows D2D users to make smart power control and channel allocation decisions in a distributed manner. In particular, we define a crucial Stackelberg Q-value (ST-Q) to guide the learning direction, which can be calculated based on the equilibrium achieved in the Stackelberg game. With the guidance of the Stackelberg equilibrium, our approach converges faster with fewer iterations than the general MADRL method and thereby exhibits better performance in handling the network dynamics. After the initial training, each agent can infer timely D2D resource allocation strategies with distributed execution. Extensive simulations are conducted to validate the efficacy of our proposed scheme in developing timely resource allocation strategies. The results also show that our method outperforms the general MADRL based approach in terms of the average utility, channel capacity, and training time.

The coupling of federated learning (FL) and multi-access edge computing (MEC) has the potential to foster numerous applications. However, it poses great challenges to train FL fast enough with limited communication and computing resources of mobile edge devices. Motivated by recent development in ultra fast wireless transmissions and promising advances in artificial intelligence (AI) computing hardware of mobile devices, in this paper, we propose a time efficient FL over future mobile edge devices, called dynamic batch sizes assisted federated learning (DBFL) with convergence guarantee. The DBFL allows batch sizes to increase dynamically during training, which can unleash the computing potential of GPU’s parallelism for on- device training and effectively leverage the fast wireless transmissions (WiFi-6, 5G, 6G, etc.) of mobile edge devices. Furthermore, based on the derived DBFL’s convergence bound, we develop a batch size control scheme to minimize the total time consumption of FL over mobile edge devices, which trade-offs the “talking”, i.e., communication time, and “working”, i.e., computing time, by adjusting the incremental factor appropriately. Extensive simulations are conducted to validate the effectiveness of our proposed DBFL algorithm and demonstrate that our scheme outperforms existing time efficient FL approaches in terms of the total time consumption in various settings.

Recent advances in machine learning, wireless communication, and mobile hardware technologies promisingly enable federated learning (FL) over massive mobile edge devices, which opens new horizons for numerous intelligent mobile applications. Despite the potential benefits, FL imposes huge communication and computation burdens on participating devices due to periodical global synchronization and continuous local training, raising great challenges to battery constrained mobile devices. In this work, we target at improving the energy efficiency of FL over mobile edge networks to accommodate heterogeneous participating devices without sacrificing the learning performance. To this end, we develop a convergence-guaranteed FL algorithm enabling flexible communication compression. Guided by the derived convergence bound, we design a compression control scheme to balance the energy consumption of local computing (i.e., "working") and wireless communication (i.e., "talking") from the long-term learning perspective. In particular, the compression parameters are elaborately chosen for FL participants adapting to their computing and communication environments. Extensive simulations are conducted using various datasets to validate our theoretical analysis, and the results also demonstrate the efficacy of the proposed scheme in energy saving.

As an emerging distributed learning paradigm, Federated Learning (FL) allows smart meters to collaboratively train a load forecasting model while keeping their private data on local devices. However, two critical issues hinder the deployment of ordinary FL algorithm in load forecasting: (i) one global model cannot fit all users well due to their heterogeneous load patterns; (ii) the training speed of FL severely depends on a few stragglers with scarce communication and computing resources. In this work, we propose a novel multi-center FL framework for load forecasting to learn multiple models simultaneously by grouping the users according to their model dissimilarity and training time. Specifically, a problem is formulated to jointly optimize the grouping strategy and forecasting model parameters, which is resolved by integrating the matching algorithm into the update process of model parameters in FL. Simulation results on real load data show that, compared with the existing load forecasting methods based on FL, the prediction error of our scheme is reduced by 8.11%, and the training time is reduced by 90.37%.

Multiaccess edge computing (MEC) empowers service providers (SPs) to run applications on the shared edge platforms in close proximity to mobile users, enabling ultralow latency access to a wide variety of cloud services. However, how to decide the amount of edge computing resources to rent for mobile service provisioning poses great challenges as the service demand is unknown to SPs a priori and may vary across the geographically distributed edge sites spatially and temporally. The resource rental decision also significantly affects SPs' deploying profits since it is critical for service deployment and workload assignment. This article investigates the service provisioning problem in a cooperative edge computing system under service demand uncertainty. We develop a holistic solution to make two-timescale decisions on edge resource rental and workload assignment to maximize SP's deploying profits. Briefly, we exploit historical service demand traces at the edge sites to characterize the uncertainty in a data-driven manner and formulate the edge service provisioning problem into a two-stage risk-averse optimization. To solve the formulated problem without compromising the data privacy, we propose an algorithm integrating Benders decomposition (BD) and alternating direction method of multipliers (ADMMs), which enables each edge site to keep the historical traces locally and participate in the optimization process. Based on real-world data sets, extensive simulations are conducted to validate the efficacy of our scheme.

The aim of this paper is to preserve location privacy of crowdsourced-based spectrum sensing agents using geo-indistinguishability. We considered database-driven dynamic spectrum access, where a radio environment map provides spectrum availability information for dynamic spectrum access management. Moreover, we assumed crowdsourced-based spectrum sensing, where a pool of allocated mobile users, called crowdsourced-based spectrum sensing agents, sense the spectrum and report their actual location and the received signal strength to the spectrum manager that constructs a radio environment map. This discloses location information of crowdsourced-based spectrum sensing agents and violates their location privacy. Consequently, crowdsourced-based spectrum sensing agents could be discouraged to participate in spectrum sensing. In our paper, to solve the problem of location disclosure, we adopted planar Laplacian mechanism, where each crowdsourced-based spectrum sensing agent reports an obfuscated location instead of its actual location, which achieves geo-indistinguishability. Our simulation results were based on real-world CRAWDAD dataset. Our results showed that with a moderate privacy level, location privacy of crowdsourced-based spectrum sensing agents was preserved while the effect of introduced location noise on the accuracy of radio environment map was insignificant.

The pandemic of the coronavirus (COVID-19) has caused an unprecedented global public health crisis, and most countries in the world are running out of the healthcare resources. A fine-grained COVID-19 vulnerability map will be essential to track the number of people with covid-like symptoms, so that the the potential outbreak communities can be identified and the valuable healthcare resources can proactively and dynamically be allocated. Mobile crowdsourcing based symptom reporting is a promising and convenient option to construct such a map, while it may compromise the location privacy of crowdsourcing participants. In this work, we propose a novel approach to establish the COVID-19 vulnerability map based on the crowdsourced reporting without disclosing the participants' location privacy to a semi-honest crowdsourcing aggregator. Briefly, based on the differentially private geo-indistinguishability, the mobile participants are able to locally perturb their geographic data. With the masked geographic information, we employ the best linear unbiased prediction estimator with spatial smoothing to obtain the reliable vulnerability estimates in the areas of interest and construct the map. Given the fast spreading nature of coronavirus, we integrate the vulnerability estimates with a susceptible-exposed-infected-removed (SEIR) model to build up a future trend map. Extensive simulations based on real-world data verify the effectiveness of the proposed method.

The advance of edge computing pushes computing functionalities to the network edge and brings lucrative opportunities for edge operators (EOs) to cater the users with low latency requirement. Unlike in cloud computing, edge servers have limited computing capacity and require a proper resource planning. To avoid loss of potential profit, a promising way is to outsource cloud resources from a public cloud with additional cost when the edge computing capacity is insufficient to meet the real-time demands. Besides, the uncertainty of future demands also affects EOs' profits. It's essential to consider the interaction among market participants with different risk attitudes. To this end, we study multiple risk-averse EOs with one risk-neutral Cloud Provider (CP) in an edge computing market, where each EO competes to serve the users by determining the optimal resource provision strategies given the demand and the outsource price charged by the CP, and the CP sets the price based on the best responses of the EOs. We model the interaction between EOs and CP as a two stage Stackelberg game, and employ a data-driven optimization approach to characterize the uncertainty. We explore the existence and uniqueness of subgame Nash equilibrium, and find the equilibrium based on the Sample Average Approximation (SAA) method. Extensive simulations using real-world cluster data traces verify the effectiveness of the proposed method.

Proactive caching in mobile-edge computing (MEC) networks is promising to handle the ever-increasing demand for wireless video services, and transcoding at MEC servers further improves the flexibility of video content delivery. However, how to effectively conduct caching for adaptive bitrate streaming poses great challenges due to the uncertainty of user preferences. The caching decisions also have a profound impact on the system energy efficiency since they may change the video delivery modes. In this article, by integrating caching, transcoding, and backhaul retrieving in a MEC-enabled adaptive streaming system, we propose a holistic solution to jointly determine the caching of bitrate-aware files and the scheduling of video requests in an energy-efficient manner. Specifically, we leverage a data-driven approach to characterize the uncertainty of real request arrivals. Based on the uncertainty model, we formulate a data-driven risk-averse optimization to derive a robust strategy for caching and delivery scheduling, which is a two-stage stochastic mixed-integer programming (SMIP) with the goal of minimizing the total expected energy consumption. We also develop feasible solutions and conduct extensive simulations on real-world data sets. The results validate the effectiveness of the proposed scheme in both the energy efficiency and the cache hit ratio.

Server and Network Assisted Dynamic adaptive streaming over HTTP (SAND) is a promising technology to cope with the dramatic increase in video streaming traffic. The new emerging Mobile Edge Computing (MEC) paradigm may further facilitate bitrate adaptation and video transcoding in a SAND system with the help of local edge servers. A critical issue in MEC-SAND framework is to guarantee Quality of Experience (QoE) for clients while achieving efficient utilization of edging network resources. In this paper, we aim to develop an adaptive video delivery scheme to minimize the delay in MEC assisted ultra-dense networks. In our scheme, each client is mapped to a server that better fits its requirements and transmission condition, and a bitrate selection mechanism is exploited to decide the best video version for the client. Besides, time-consuming transcoding tasks are carefully scheduled considering edge computing capacity. We formulate a Mix-Integer Non-Linear Programming (MINLP) problem to jointly determine cell association, bitrate adaption, and computing resource allocation. We exploit the generalized Benders decomposition method to reduce the solving complexity of the formulated problem. Numerical results validate the effectiveness and efficiency of the proposed scheme.

Mobile crowdsensing is recognized to be a promising paradigm wherein location-based sensing tasks are outsourced to participants carrying mobile devices. A prominent issue of crowdsensing is to guarantee the sensing coverage by appropriately recruiting participating devices, which requires the disclosure of participants' locations and leads to potential location privacy threats. In this paper, we aim to develop a privacy-preserving participant recruiting scheme for mobile crowdsensing, which guarantees the crowdsensing coverage while preserving participants' location differential privacy against a semi-honest crowdsensing aggregator. Briefly, based on the differential private geo-indistinguishability method, we enable candidate participants to locally perturb their location data. With the obfuscated location information, we formulate the crowdsensing coverage optimization as an Integer Program (IP), and develop a 1-(1 - 1/f)f-approximation algorithm, which yields a near-optimal participant recruiting solution. Through extensive simulations, we demonstrate the tradeoff between privacy preservation and crowdsensing utility, and show that satisfactory crowdsensing coverage can be achieved while preserving the participants' differential location privacy.