The rapid proliferation of networked devices and emerging applications has driven the evolution of computing power networks (CPNs) as a key architecture to meet the demands of sixth-generation (6G) communication. However, terrestrial CPNs still face challenges such as limited coverage, vulnerability to wireless impairments, and slow responsiveness in emergency or disaster scenarios. To address these challenges, this paper proposes a UAV-enabled computing power network (UCPN) that leverages the flexible deployment and line-of-sight communication advantages of UAVs to enhance transmission reliability and service continuity. In particular, we design a 1+1 protection transmission mechanism tailored for UCPNs, in which duplicated task data are forwarded over node-disjoint multi-hop UAV paths and recovered through interval-aware packet scheduling, enabling reliable task delivery under UAV failures and dynamic wireless conditions. Building upon this protection mechanism, we further develop a multi-agent reinforcement learning (MARL)–based node assignment and routing optimization algorithm, referred to as MAPPO-NARO. Unlike existing MARL-based UAV routing or task offloading approaches that primarily focus on single-path transmission or isolated node selection, the proposed algorithm explicitly incorporates 1+1 protection decisions into the MARL formulation, jointly learning access UAV selection, computing UAV assignment, and fault-tolerant dual-path routing under resource and latency constraints. Simulation results demonstrate that the proposed algorithm achieves lower packet loss, better load balance, and higher reliability compared with the baseline methods. Moreover, when UAV failures occur due to adverse weather conditions, signal interference, or hardware malfunctions, the proposed scheme still maintains high service availability, which indicates that it is well suited for emergency scenarios.

Remote sensing images (RSIs) are widely used in the fields of geological resources monitoring, earthquake relief, and weather forecasting, but they are easily nullified due to haze cover. Transformer-based image dehazing model can better remove the haze in RSIs and improve the clarity of RSIs. However, due to the insufficient ability to extract detailed information, the model performs poorly in the case of thick haze. To solve this problem, this letter introduces an additional self-attention mechanism to help the model acquire more detailed information based on the existing Transformer-based image dehazing model and introduces an adapter module to improve the model’s fitting capacity with newly added content. Experimental results on benchmark RSIs indicate that the proposed method yields an average improvement of 0.95 in PSNR and 0.6% in SSIM for light haze removal. Notably, the method exhibits a significant enhancement of 1.34 in PSNR and 1.9% in SSIM for the removal of thick haze, underscoring its advantage in heavy haze conditions. The source code can be accessed via https://github.com/Eric3200C/ASTA.

This paper considers an unmanned aerial vehicle (UAV)-enabled multi-package delivery system, where a cargo UAV collects the parcels of ground users, and finally delivers them to the destination. One key aspect of this system is to ensure a stable and reliable connection between the UAV and the base station (BS) throughout the mission for the safety of the UAV flight. To this end, we minimize the communication outage time between the UAV and the BSs while maximizing the value of the packages picked up via optimizing the UAV path and pick-up design. Although the formulated problem is difficult to solve due to its non-convexity, we propose a connectivity-aware delivery (CAD) framework that divides the delivery mission into the path design phase and the pick-up design phase to address this challenging problem. Specifically, in the path design phase, we design the optimal flight path between any two package collection points of the UAV based on deep reinforcement learning to reduce the expected communication outage duration. In the pick-up design phase, we propose a genetic algorithm based pick-up algorithm which decides the selection and order of the packages to be picked by the UAV to maximize the value of the picked-up parcels under the constraints of the UAV’s load and energy. Extensive experiments and comparative studies demonstrate the superior performance of our framework in terms of both the outage rate and total value of the picked packages.

This paper investigates an aerial reconfigurable intelligent surface (RIS)-aided communication system under the probabilistic line-of-sight (LoS) channel, where an unmanned aerial vehicle (UAV) equipped with an RIS is deployed to assist two ground nodes in their information exchange. An optimization problem with the objective of maximizing the minimum average achievable rate is formulated to jointly design the communication scheduling, the RIS’s phase shift, and the three-dimensional (3D) UAV trajectory. To solve such a non-convex problem, we propose an efficient iterative algorithm to obtain its suboptimal solution. Simulation results show that our proposed design significantly outperforms the existing schemes and provides new insights into the elevation angle and distance trade-off for the UAV-borne RIS communication system.

The rapid development of unmanned aerial vehicle (UAV) technology provides flexible communication services to terrestrial nodes. Energy efficiency is crucial to the deployment of UAVs, especially rotary-wing UAVs whose propulsion power is sensitive to the wind effect. In this paper, we first derive a three-dimensional (3D) generalised propulsion energy consumption model (GPECM) for rotary-wing UAVs under the consideration of stochastic wind modeling and 3D force analysis. Based on the GPECM, we study a UAV-enabled downlink communication system, where a rotary-wing UAV flies subject to stochastic wind disturbance and provides communication services for ground users (GUs). We aim to maximize the energy efficiency (EE) of the UAV by jointly optimizing the 3D trajectory and user scheduling among the GUs based on the GPECM. We formulate the problem as a stochastic optimization, which is difficult to solve due to the lack of real-time wind information. To address this issue, we propose an offline-based online adaptive (OBOA) design that is comprised of two phases, namely, an offline phase and an online phase. In the offline phase, we average the wind effect on the UAV by leveraging stochastic programming (SP) based on wind statistics; then, in the online phase, we further optimize the instantaneous velocity to adapt to the real-time wind. Simulation results show that the optimized trajectories of the UAV in both phases can better adapt to changes of the speed and direction of the wind, resulting in a higher EE compared with the wind-unaware scheme. In particular, the proposed OBOA design can be applied in the scenario with dramatic wind changes, and allows the UAV to adjust its velocity dynamically to achieve better performance in terms of EE.

Reconfigurable intelligent surface (RIS), as an emerging technology, has recently been applied to expand the range of mobile-edge computing (MEC) networks and improve wireless environments. However, current terrestrial RIS-assisted MEC networks have some limitations, such as severe signal attenuation and inflexible equipment deployment. To take full advantage of the superiority of the RIS, this article considers an aerial RIS (ARIS)-assisted aerial computing scheme, where the ARIS and the other unmanned aerial vehicle (UAV) equipped with a MEC server are employed to facilitate offloading computing tasks from Internet of Things (IoT) user equipments (UEs) to the access point (AP). With the flexibility of the dual-UAV, we can mitigate the Non-Line-of-Sight (NLoS) air–ground paths caused by obstacles. In the proposed scenario, to improve the system energy efficiency while ensuring the UEs receive high-quality wireless services, we intend to jointly optimize the trajectories of the two UAVs, the phase shift of the ARIS, the computation offloading strategy, and computation resource allocation. The issue is formulated as a mixed nonconvex optimization problem, so it is difficult to solve it in time for adapting different environments by using conventional convex optimization methods. However, we develop a double deep$Q$-network (DDQN)-based algorithm to obtain the near-optimal online decision-making solution. Simulation findings indicate that the proposed DDQN-based algorithm can effectively increase the energy efficiency of the proposed dual-UAV cooperative MEC system in comparison to the benchmark schemes.

This paper considers a backscatter communication (BC) system, which is based on the non-orthogonal multiple access (NOMA) protocol and assisted by a full-duplex unmanned aerial vehicle (UAV). To improve the communication quality of this NOMA-based system, we increase the number of backscatter devices (BDs) and maximize the sum rate by optimizing the reflection coefficient (RC) of BDs and the location of the UAV. As the sum rate problem is a non-convex problem, we propose an iterative algorithm to solve the problem by using the block coordinated descent (BCD) technique and quadratic transform algorithm. The RC problem is solved by monotonicity. Then, the location problem is solved by the quadratic transform algorithm. Finally, simulation results demonstrate that the proposed algorithm achieves higher sum rate than the other schemes.

This paper investigates a reconfigurable intelligent surface (RIS)-assisted unmanned aerial vehicle (UAV)-enabled wireless sensor network (WSN) under the probabilistic line-of-sight (LoS) channel in urban areas, where a UAV is dispatched to collect data from spatially distributed sensor nodes (SNs) with the aid of an RIS to enhance the communication quality. With the objective of maximizing the minimum average data collection rate from all the SNs for the UAV, we jointly design the communication scheduling, the phase shift of the RIS, and the UAV trajectory. However, due to its non-convexity, the formulated problem is difficult to solve. Therefore, we propose an efficient algorithm to attain its suboptimal solution by leveraging alternating optimization (AO), successive convex approximation (SCA), and semidefinite relaxation (SDR). Simulation results reveal new insights on the elevation angle-distance trade-off for the RIS-assisted UAV-enabled WSN, and the data collection rate of our proposed algorithm is significantly improved compared with other benchmark schemes.

This paper proposes a mobile unmanned aerial vehicle (UAV) jamming scheme under the probabilistic line-ofsight channel model (PLCM) to improve the secrecy of ground wiretap channels, in which a friendly UAV is deployed to cooperatively transmit jamming signals to confuse the suspicious eavesdropper. Our goal is to maximize the average (expected) secrecy rate by jointly optimizing the source transmit power, UAV jamming power and trajectory for a given flight time. Since the expected secrecy rate is highly complicated with respect to the UAV trajectory, we derive a more tractable lower bound for it. Nevertheless, the resulting optimization problem remains a non-convex problem, which is difficult to solve optimally. Therefore, we propose an efficient iterative algorithm to obtain a suboptimal solution to it by applying the block coordinate descent (BCD) and successive convex approximation (SCA) techniques. Simulation results show that the joint power and trajectory optimization scheme under the PLCM significantly outperforms various benchmark schemes.

This paper investigates a novel unmanned aerial vehicles (UAVs) secure communication system with the assistance of reconfigurable intelligent surfaces (RISs), where a UAV and a ground user communicate with each other, while an eavesdropper tends to wiretap their information. Due to the limited capacity of UAVs, an RIS is applied to further improve the quality of the secure communication. The time division multiple access (TDMA) protocol is applied for the communications between the UAV and the ground user, namely, the downlink (DL) and the uplink (UL) communications. In particular, the channel state information (CSI) of the eavesdropping channels is assumed to be imperfect. We aim to maximize the average worst-case secrecy rate by the robust joint design of the UAV’s trajectory, RIS’s passive beamforming, and transmit power of the legitimate transmitters. However, it is challenging to solve the joint UL/DL optimization problem due to its non-convexity. Therefore, we develop an efficient algorithm based on the alternating optimization (AO) technique. Specifically, the formulated problem is divided into three sub-problems, and the successive convex approximation (SCA),$\mathcal {S}$-Procedure, and semidefinite relaxation (SDR) are applied to tackle these non-convex sub-problems. Numerical results demonstrate that the proposed algorithm can considerably improve the average secrecy rate compared with the benchmark algorithms, and also confirm the robustness of the proposed algorithm.

In this paper, we propose a practical transmission scheme using polar coding for the half-duplex degraded relay-eavesdropper channel. We prove that the proposed scheme can achieve the maximum perfect secrecy rate under the decode-and-forward (DF) strategy. Our proposed scheme provides an approach for ensuring both reliable and secure transmission over the relay-eavesdropper channel while enjoying practically feasible encoding/decoding complexity.