Mobile Edge Computing (MEC) pushes computing functionalities away from the centralized cloud to network edge, thereby meeting latency requirements of many emerging mobile applications and saving backhaul bandwidth. Although existing works have studied computation of-floading policies, service caching is an equally, if not more important, design topic MEC, yet receives much less attention. Service refers application services their related databases/libraries in edge server (e.g. MEC-enabled...

Mobile edge computing (also known as fog computing) has recently emerged to enable <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">in-situ</i> processing of delay-sensitive applications at the mobile networks. Providing grid power supply in support computing, however, is costly and even infeasible (in certain rugged or under-developed areas), thus mandating on-site renewable energy a major sole increasingly many scenarios. Nonetheless, high...

The (ultra-)dense deployment of small-cell base stations (SBSs) endowed with cloud-like computing functionalities paves the way for pervasive mobile edge computing, enabling ultra-low latency and location-awareness a variety emerging applications Internet Things. To handle spatially uneven computation workloads in network, cooperation among SBSs via workload peer offloading is essential to avoid large at overloaded provide high quality service end users. However, performing effective faces...

Mobile Edge Computing (MEC) pushes computing functionalities away from the centralized cloud to proximity of data sources, thereby reducing service provision latency and saving backhaul network bandwidth. Although computation offloading for MEC systems has been extensively studied in literature, placement is an equally, if not more, important design topic MEC, yet receives much less attention. Service refers configuring platform storing related libraries/databases at edge server, e.g.,...

Shared edge computing platforms deployed at the radio access network are expected to significantly improve quality-of-service delivered by application service providers (ASPs) in a flexible and economic way. However, placing every possible site an ASP is practically infeasible due ASP's prohibitive budget requirement. In this paper, we investigate placement problem of under limited budget, where dynamically rents computing/storage resources sites host its applications close proximity end...

Federated Learning (FL) has been considered as an appealing framework to tackle data privacy issues of mobile devices compared conventional Machine (ML). Using Edge Servers (ESs) intermediaries perform model aggregation in proximity can reduce the transmission overhead, and it enables great potential low-latency FL, where hierarchical architecture FL (HFL) attracted more attention. Designing a proper client selection policy significantly improve training performance, widely investigated...

Industrial Fog computing deploys various industrial services, such as automatic monitoring/control and imminent failure detection, at the Nodes (FNs) to improve performance of systems. Much effort has been made in literature on design fog network architecture computation offloading. This paper studies an equally important but much less investigated problem service hosting where FNs are adaptively configured host services for Sensor (SNs), thereby enabling corresponding tasks be executed by...

Small cell base stations (SBSs) endowed with cloud-like computing capabilities are considered as a key enabler of edge (EC), which provides ultra-low latency and location-awareness for variety emerging mobile applications the Internet Things. However, due to limited computation resources an individual SBS, providing services high quality its users faces significant challenges when it is overloaded excessive amount workload. In this paper, we propose collaborative among SBSs by forming SBS...

Vehicular Cloud Computing (VCC) is a new technological shift which exploits the computation and storage resources on vehicles for computational service provisioning. Spare onboard are pooled by VCC operator, e.g. roadside unit, to serve tasks using vehicle-as-a-resource framework. This paper investigates timely provisioning deadline-constrained in systems leveraging task replication technique (i.e., allowing one be executed vehicles). A learning-based algorithm, called DATEV (Deadline-Aware...

Recent breakthroughs in deep learning (DL) have led to the emergence of many intelligent mobile applications and services, but meanwhile also pose unprecedented computing challenges on resource-constrained devices. This paper builds a collaborative inference system between device powerful edge server, aiming at joining power both on-device processing computation offloading. The basic idea this is partition neural network (DNN) into front-end part running back-end with key challenge being how...

Merging Mobile Edge Computing (MEC), which is an emerging paradigm to meet the increasing computation demands from mobile devices, with dense deployment of Base Stations (BSs), foreseen as a key step towards next generation networks. However, new challenges arise for designing energy efficient networks since radio access resources and computing BSs have be jointly managed, yet they are complexly coupled traffic in both spatial temporal domains. In this paper, we address challenge...

Mobile Edge Computing (MEC) (a.k.a. fog computing) has recently emerged to enable low-latency and location-aware data processing at the edge of mobile networks. Providing grid power supply in support MEC, however, is costly even infeasible, thus mandating on-site renewable energy as a major or sole many scenarios. Nonetheless, high intermittency unpredictability harvesting creates new challenges performing effective MEC. In this paper, we develop an algorithm called GLOBE that performs joint...

Shared edge computing platforms, which enable Application Service Providers (ASPs) to deploy applications in close proximity mobile users are providing ultra-low latency and location-awareness a rich portfolio of services. Though ubiquitous service provisioning, i.e., deploying the application at all possible sites, is always preferable, it impractical due often limited operational budget ASPs. In this case, an ASP has cautiously decide where how much willing use. A central issue here that...

This paper studies a federated learning (FL) system, where <i>multiple</i> FL services co-exist in wireless network and share common resources. It fills the void of resource allocation for multiple simultaneous existing literature. Our method designs two-level framework comprising <i>intra-service</i> <i>inter-service</i> allocation. The intra-service problem aims to minimize length rounds by optimizing bandwidth among clients each service. Based on this, an inter-service is further...

Mobile Edge Computing (MEC) is delivering a rich portfolio of computation services to enable ultra-low latency and location-awareness for emerging mobile applications. However, the vulnerability this new paradigm potential security privacy issues prevents users from fully embracing its advantage. While various defensive strategies have been proposed secure connection between end devices edge servers, an equally important issue, server-side risk still under-investigated most computing...

Federated Adversarial Learning (FAL) is a robust framework for resisting adversarial attacks on federated learning. Although some FAL studies have developed efficient algorithms, they primarily focus convergence performance and overlook generalization. Generalization crucial evaluating algorithm unseen data. However, generalization analysis more challenging due to non-smooth loss functions. A common approach addressing this issue leverage smoothness approximation. In paper, we develop...

Computation offloading via device-to-device (D2D) communication, or D2D offloading, can enhance mobile computing performance by exploiting spare resources of nearby user devices. The success relies on participation in collaborative service provisioning, which incurs extra costs to users providing the service, thus mandating an incentive mechanism that compensate for these costs. Although design has been intensively studied literature, this paper considers a much more challenging yet less...

The dense deployment of small-cell base stations (SBSs) endowed with cloud-like computing capabilities paves the way for pervasive mobile edge (MEC), enabling ultra-low latency and location-awareness emerging applications. To handle spatially imbalanced computation workloads in network, cooperation among SBSs via peer offloading is essential to avoid large at overloaded provide high quality service end users. However, performing effective faces many challenges due uncertainties system...

Federated learning (FL) has reshaped the paradigm by overcoming privacy concerns and siloed data. In FL, an aggregator schedules a set of mobile users (MUs) to collectively train global model with their local datasets subsequently aggregates updates. However, have many uncertainties like unstable network connections volatile availability, which leads straggler problem deteriorates efficiency FL system. Besides, issue non-IID hinders convergence performance model. To hurdle user...