With the explosive increment of computation requirements, multiaccess edge computing (MEC) paradigm appears as an effective mechanism. Besides, for Internet Things (IoT) in disasters or remote areas requiring MEC services, unmanned aerial vehicles (UAVs) and high altitude platforms (HAPs) are available to provide services these IoT devices. In this article, we develop hierarchical framework composed HAPs UAVs, various applications. particular, problem is formulated maximize total data...

Unmanned aerial vehicle (UAV)-enabled mobile edge computing has been recognized as a promising technology to flexibly and efficiently handle computation-intensive latency-sensitive tasks in the era of fifth generation (5G) beyond. In this paper, we study problem Service Provisioning for UAV-enabled computiNg (SPUN). Specifically, under task latency requirements various resource constraints, jointly optimize service placement, UAV movement trajectory, scheduling, computation allocation,...

The air-ground integrated network is a key component of future sixth generation (6G) networks to support seamless and near-instant super-connectivity. There pressing need intelligently provision various services in 6G networks, which challenging. To meet this need, article, we propose novel architecture called UaalS, that is, unmanned aerial vehicles (UAVs) as intelligent service for the network, featuring UAV enabler boost edge intelligence with help machine learning (ML) techniques. We...

Nonorthogonal multiple access (NOMA) and cognitive integrated satellite terrestrial relay networks are the promising key part for next-generation wireless networks. This article researches joint effects of channel estimation errors (CEEs) hardware impairments on secrecy performance The noncolluding eavesdropping scheme is applied in eavesdroppers, where eavesdropper with highest capacity selected to overhear legitimate transmission signal. Moreover, detailed analysis outage probability (SOP)...

Unmanned aerial vehicle (UAV) swarm enabled edge computing is envisioned to be promising in the sixth generation wireless communication networks due their wide application sensories and flexible deployment. However, most of existing works focus on by a single or small scale UAVs, which are very different from UAV swarm-enabled computing. In order facilitate practical applications computing, state art research presented this article. The potential applications, architectures implementation...

Unmanned aerial vehicles (UAVs) have been widely used to perform search and tracking tasks in military civil fields. To these autonomously, a swarm of multiple UAVs need be endowed with intelligence through machine learning (ML). However, the traditional centralized ML cannot directly applied UAV networks, since it is challenging transmit raw data limited bandwidth energy budget. As distributed manner, federated (FL) more suitable for networks than schemes order boost edge UAVs. Considering...

With the vigorous development of artificial intelligence (AI), applications based on deep neural networks (DNNs) have changed people's lifestyles and production efficiency. However, large amount computation data generated from network edge becomes major bottleneck, traditional cloud-based computing mode has been unable to meet requirements realtime processing tasks. To solve above problems, by embedding AI model training inference capabilities into edge, (EI) a cutting-edge direction in...

Unmanned aerial vehicles (UAVs), or drones, are envisioned to support extensive applications in next-generation wireless networks both civil and military fields. Empowering UAV networks' intelligence with artificial intelligence, especially machine learning (ML), techniques, is inevitable appealing enable the aforementioned applications. To solve problems of traditional cloud-centric ML for such as privacy concerns, unacceptable latency, resource burden, a distributed technique, federated...

This paper establishes a new layered flying ad hoc networks (FANETs) system of mobile edge computing (MEC) supported by multiple UAVs, where the first layer user UAVs can perform tasks such as area coverage, and second MEC are deployed sever for with computing-intensive tasks. In this system, we divide into clusters, transmit cluster members (CMs) within to its head (CH). Then, need determine whether each CH' executed locally or offloaded one remote execution (i.e., task scheduling), how...

Adaptive routing and efficient packet delivery in Flying Ad Hoc Networks (FANETs) are significant challenges due to underlying environment constraints, such as dynamic nature, mobility, limited connectivity. With the increasing number of machine learning (ML) applications wireless networks, FANETs can benefit from these data-driven predictions. This letter proposes a Packet Arrival Prediction (PAP) protocol improve transmission link reliability. Primarily, we apply Long Short-Term Memory...

Recently, many exciting usage scenarios and groundbreaking technologies for sixth generation (6G) networks have drawn more attention. The revolution of 6G mainly lies in ubiquitous intelligence, which promotes the development edge intelligence (EI) by running artificial (AI) algorithms at network edge. By embedding training capabilities across nodes, federated learning (FL) can achieve high security alleviate traffic congestion, provides a promising way to realize EI. While traditional FL...

Area coverage is one of the most common and important tasks for flying ad hoc networks (FANETs). The increasingly large scale FANETs brings challenges in communication coverage. Clustering an effective technique networking management large-scale networks. Meanwhile, some applications, i.e., face recognition, need to perform intensive computation after unmanned aerial vehicles (UAVs) area Due long response delay transferring data cloud, it becomes a trend use mobile-edge computing (MEC)...

Ubiquitous intelligence has been widely recognized as a critical vision of the future sixth generation (6G) networks, which implies over whole network from core to edge, including end devices. Nevertheless, fulfilling this vision, particularly at is extremely challenging due limited resources edge devices well ubiquitous coverage envisioned by 6G. To empower intelligence, in article, we propose framework called air-ground integrated federated learning (AGIFL), organically integrates networks...

In recent years, with the growth in Unmanned Aerial Vehicles (UAVs), UAV-based systems have become popular both military and civil applications. these scenarios, lack of reliable communication infrastructure has motivated UAVs to establish a network as flying nodes, also known Flying Ad Hoc Networks (FANETs). However, FANETs, high mobility degree terrestrial users may be responsible for constant changes topology, making end-to-end connections FANETs challenging. Mobility estimation...

Satellite communication has become a popular study topic owing to its inherent advantages of high capacity, large coverage, and no terrain restrictions. Also, it can be combined with terrestrial overcome the shortcomings current wireless communication, such as limited coverage destructibility. In recent years, integrated satellite-unmanned aerial vehicle-terrestrial networks (IS-UAV-TNs) have aroused tremendous interests effectively reduce transmission latency enhance quality-of-service...

Unmanned Aerial Vehicles (UAVs) are widely used as mobile information collectors for sensors to prolong the network time in Wireless Sensor Networks (WSNs) due their flexible deployment, high mobility, and low cost. This paper focuses on scenario where rotary-wing UAVs complete collection mission cooperatively. For first time, we study problem of minimizing completion a multi-UAV system monitoring when considering quality. The includes flying hovering time. By optimizing trajectories all...

In this letter, we investigate the joint optimization of computation offloading, channel allocation and position deployment problem for coalition-based unmanned aerial vehicle (UAV) mobile edge computing networks. To characterize hierarchical offloading feature in UAV network, propose framework formulate a discrete multi-leader multi-follower energy minimization Stackelberg game. addition, prove that subgame are exact potential games with Nash equilibrium. Then existence equilibrium (SE) is...

One fundamental question in Wireless Rechargeable Sensor Networks (WRSNs) is the energy provisioning problem, i.e., how to deploy sources a network ensure that nodes can harvest sufficient for continuous operation. Though potential mobility of has been exploited reduce number necessary problem existing literature, non-negligible impacts constraints node speed and battery capacity on are completely overlooked, order simplify analysis. In this paper, we propose new metric - Quality Energy...

Crowdsensing has been well recognized as a promising approach to enable large scale urban data collection. In typical crowdsensing system, the task owner usually needs provide incentives users (say participants) encourage their participation. Among existing incentive mechanisms, posted pricing widely adopted because it is easy implement while ensuring truthfulness and fairness. One critical challenge set right price recruit crowd with small total payment reasonable sensing quality, i.e.,...

Vehicles can establish a collaborative environment cognition through sharing the original or processed sensor data from vehicular sensors and status map. Clustering in ad-hoc network (VANET) is crucial for enhancing stability of environment. In this paper, problem clustering innovatively transformed into cutting graph problem. A novel algorithm based on Spectral improved force-directed designed. It takes average lifetime all clusters as an optimization goal so that entire system be enhanced....

This paper considers the fundamental problem of Placement unmanned Aerial vehicles achieviNg 3D Directional coverAge (PANDA), that is, given a set objects with determined positions and orientations in space, deploy fixed number UAVs by adjusting their such overall directional coverage utility for all is maximized. First, we establish model both cameras objects. Then, propose Dominating Coverage Set (DCS) extraction method to reduce infinite solution space PANDA limited one without...

Unmanned aerial vehicles (UAVs) have been widely used in military and civilian fields by carrying out intelligent applications with deep learning technologies, such as battlefield search rescue; intelligence, surveillance, reconnaissance (ISR); smart city monitoring. Due to deeper more complex models of neural networks (DNNs) limited on-board resources UAVs, most existing works either rely on cloud-based intelligence transmitting original data remote powerful cloud servers running DNNs...

UAVs Ad-Hoc Networks has earned more and attentions recently. How to design a collision-free MAC protocol which allows access the networks rapidly reliably is crucial challenge. Many protocols proposed for VANETs or have some limitations, i.e., ones need full duplex technique not very practical now. This paper propose CF-MAC with half-duplex radio omnidirectional antenas utilizes region marking scheme reduce collision probability near zero. Compare VeMAC an outstanding VANETs, simulations...