Empowered by computing resources at the network edge, data sensed from Internet of Things (IoT) devices can be processed and stored in their nearby cloudlets to reduce traffic load core network, while various IoT applications run response time between users (e.g., user equipment mobile networks) cloudlets. Considering spatial temporal dynamics each application's workloads among cloudlets, workload allocation for application affects requests. While assigning users' requests minimize delay,...

As latency is the key performance metric for IoT applications, fog nodes co-located with cellular base stations can move computing resources close to devices. Therefore, data flows of devices be offloaded in their proximity, instead remote cloud, processing. However, consist both communications and latency. Owing spatial temporal dynamics device distributions, some BSs are lightly loaded, while others, which may overloaded, incur congestion. Thus, traffic load allocation among (BSs) affect...

The vehicular edge computing (VEC) can cache contents in different RSUs at the network to support real-time applications. In VEC, owing high-mobility characteristics of vehicles, it is necessary user data advance and learn most popular interesting for users. Since usually contains privacy information, users are reluctant share their with others. To solve this problem, traditional federated learning (FL) needs update global model synchronously through aggregating all users' local models...

Vehicles on the road exchange data with base station frequently through vehicle to infrastructure (V2I) communications ensure normal use of vehicular applications, where IEEE 802.11 distributed coordination function is employed allocate a minimum contention window (MCW) for channel access. Each may change its MCW achieve more access opportunities at expense others, which results in unfair communication performance. Moreover, key parameter privacy information and each not willing share it...

Vehicular edge computing (VEC) is a promising technology to support real-time vehicular applications, where vehicles offload intensive computation tasks the nearby VEC server for processing. However, traditional that relies on single communication cannot well meet requirement task offloading, thus heterogeneous integrating advantages of dedicated short-range communications (DSRC), millimeter-wave (mmWave) and cellular-based vehicle infrastructure (C-V2I) introduced enhance capacity. The...

Edge caching is a promising solution for next-generation networks by empowering units in small-cell base stations (SBSs), which allows user equipments (UEs) to fetch users' requested contents that have been pre-cached SBSs. It crucial SBSs predict accurate popular through learning while protecting personal information. Traditional federated (FL) can protect privacy but the data discrepancies among UEs lead degradation model quality. Therefore, it necessary train personalized local models...

As accessing computing resources from the remote cloud for big data processing inherently incurs high end-to-end (E2E) delay mobile users, cloudlets, which are deployed at edge of networks, can potentially mitigate this problem. Although load offloading in cloudlet networks has been proposed, placing cloudlets to minimize deployment cost providers and E2E user requests not addressed so far. The locations number their servers have a crucial impact on both requests. Therefore, paper, we...

Vehicular edge computing (VEC) is envisioned as a promising approach to process the explosive computation tasks of vehicular user (VU). In VEC system, each VU allocates power partial through offloading and remaining local execution. During offloading, adopts multi-input multi-output non-orthogonal multiple access (MIMO-NOMA) channel improve spectrum efficiency capacity. However, condition uncertain due interference among VUs caused by MIMO-NOMA time-varying path loss mobility VU. addition,...

As accessing computing resources from the remote cloud inherently incurs high end-to-end (E2E) delay for mobile users, cloudlets, which are deployed at edge of a network, can potentially mitigate this problem. Although some research works focus on allocating workloads among cloudlet placement aiming to minimize deployment cost (i.e., consisting both and average E2E cost) has not been addressed effectively so far. The locations number cloudlets have crucial impact in network users. Therefore,...

Multi unmanned aerial vehicle (UAV) network is a promising solution to providing wireless coverage ground users in challenging rural areas (such as Internet of Things (IoT) devices farmlands), where the traditional cellular networks are sparse or unavailable. A key challenge such 3-D placement all UAV base stations (BSs) that formed multi-UAV network: 1) utilizes minimum number UAVs while ensuring—2) backhaul connectivity directly (or via other UAVs) nearby terrestrial BS; and 3) area...

Vehicles in platoons need to process many tasks support various real-time vehicular applications. When a task arrives at vehicle, the vehicle may not due its limited computation resource. In this case, it usually requests offload other vehicles platoon for processing. However, when resources of all are insufficient, cannot be processed time through offloading platoon. Vehicular fog computing (VFC)-assisted can solve problem VFC which is formed by driving near Offloading delay an important...

In vehicular edge computing (VEC), some tasks can be processed either locally or on the mobile (MEC) server at a base station (BS) nearby vehicle. fact, are offloaded not, based status of vehicle-to-infrastructure (V2I) and vehicle-to-vehicle (V2V) communication. this paper, device-to-device (D2D)-based V2V communication multiple-input multiple-output nonorthogonal multiple access (MIMO-NOMA)-based V2I considered. actual scenarios, channel conditions for MIMO-NOMA-based uncertain, task...

Edge cloudlets are promising to mitigate the high network delay incurred by remote cloud in executing workloads offloaded from a user equipment (UE). However, response time of task request consists both and computing delay. Considering spatial temporal dynamics among cloudlets, if workload an edge cloudlet is heavy, may be unbearable. In this letter, we design hierarchical propose allocation scheme minimize average UEs' requests deciding which UE assigned how much resource provisioned serve...

Drone base stations (DBSs) can potentially provision low-cost and flexible networking with high mobility while in-band full-duplex (IBFD) conceivably improve spectrum efficiency. Therefore, it is logical to employ DBSs IBFD in a cellular network the throughput. We decompose this problem into DBS placement joint bandwidth power allocation problem, propose two heuristic algorithms solve whole problem. Simulation results have demonstrated that total throughput of dynamic algorithm achieves up...

With the development of Internet Vehicles, platooning strategy has been widely studied as potential approach to ensure safety autonomous driving. Vehicles in form platoon adopt 802.11p exchange messages through vehicle-to-vehicle (V2V) communications. When multiple platoons arrive at an intersection, leader vehicle each adjusts its movement characteristics that it can cross and thus following vehicles have adjust their accordingly. In this case, time-varying connectivity among leads...

Edge computing enables data collected by Internet of Things (IoT) devices to be stored in and processed local fog nodes as well allows IoT users access applications via these at the same time. In this case, communications latency critically affects response time user requests. Owing dynamic distribution [i.e., equipments (UEs)], drone base station (DBS), which can flexibly deployed for hotspot areas, potentially improve wireless mitigating heavy traffic loads macro BSs. Drone-based poses two...

Fully utilizing green energy can remarkably decrease the operational cost of cloudlet providers in provisioning networks (GCNs), which are powered by both and brown energy. Owing to spatial temporal dynamics demands generation, migrating Avatars (i.e., virtual machines) from deprived cloudlets into over-provisioned reduce total on-grid consumption GCN. However, Avatar migration itself consumes non-negligible consumption. In this letter, we propose Energy driven AvataR (EARN) scheme GCN...

Vehicular fog and cloud computing (VFCC) system, which provides huge power for processing numerous computation-intensive delay sensitive tasks, is envisioned as an enabler intelligent connected vehicles (ICVs). Although previous works have studied the optimal offloading scheme in VFCC no existing work has considered departure of that are i.e., occupied vehicles. However, leaving system with uncompleted tasks will affect overall performance system. To solve problem, this paper, we study...

Platooning strategy is an important part of autonomous driving technology. Due to the limited resource vehicles in platoons, mobile-edge computing (MEC) usually used assist platoons obtain useful information, increasing its safety. Specifically, adopt IEEE 802.11 distributed coordination function (DCF) mechanism transmit large amount data base station (BS) through vehicle-to-infrastructure (V2I) communications, where information can be extracted by edge server connected BS and then sent back...

The performance of federated learning systems is bottlenecked by communication costs and training variance. overhead problem usually addressed three communication-reduction techniques, namely, model compression, partial device participation, periodic aggregation, at the cost increased Different from traditional distributed systems, suffers data heterogeneity (since devices sample their possibly different distributions), which induces additional variance among during training. Various...

The growing deployment and advanced development of high-speed train (HST) systems, coupled with the reliance on demand for constant Internet connectivity anytime anywhere, have necessitated imminent provisioning broadband services in HSTs. Ground-to-train free space optical (FSO) communications suffer from frequent handovers due to high mobility HSTs, thus shortening connection time between ground, greatly impacting passengers' user experience. To provision we propose rotating transceiver...

We propose a Green Cloudlet Network (GCN) architecture to provide seamless Mobile Cloud Computing (MCC) services User Equipments (UEs) with low latency in which each cloudlet is powered by both green and brown energy. Fully utilizing energy can significantly reduce the operational cost of providers. However, owing spatial dynamics demand generation, gap among different cloudlets network unbalanced, i.e., some cloudlets' demands be fully provided but others need utilize on-grid (i.e., energy)...