As edge applications demand real-time processing with limited bandwidth and energy, traditional communication systems face challenges to meet performance requirements due to the centralized architecture and redundant data transmission. To address these challenges, we propose a UAV-assisted semantic edge computing network that leverages UAV mobility and semantic communication. We formulate a joint optimization problem involving UAV trajectory, data allocation, and semantic extraction to maximize the semantic processing rate. To solve this problem, we develop a hybrid deep deterministic policy gradient (H-DDPG) algorithm that integrates deep reinforcement learning (DRL) with convex optimization via block coordinate descent (BCD), thereby enabling efficient joint decision-making across tightly coupled variables. Furthermore, we propose a hybrid diffusion deep deterministic policy gradient (H-D3PG) algorithm, which incorporates denoising diffusion models into the DRL framework. By addressing the limited adaptability of deterministic strategies, this design enhances policy expressiveness and stability. As a result, the algorithm enables adaptive trajectory control under time-varying semantic tasks and wireless channel conditions in UAV-assisted edge networks. Simulations show that H-D3PG improves the semantic processing rate by up to 38.8% while reducing energy consumption compared to Raw Data Transmission.

Federated learning (FL) has emerged as a promising solution to facilitate the deployment of artificial intelligence (AI) on wireless devices. However, heterogeneity of wireless devices, including disparities in computation capabilities, data sizes, and energy constraints, introduces delays in the FL completion time, particularly due to inefficient communication and slow updates from resource-constrained devices. To address this issue, we propose an unmanned aerial vehicle (UAV)-assisted FL framework that integrates UAV as a central server, collaborating with the devices to facilitate the model training process. Accordingly, we jointly consider computation and transmission strategies, as well as the task assignment and UAV trajectory to minimize the completion time of the FL process. Particularly, we consider the location uncertainties associated with the devices, along with the consequent chance-constrained aggregation process, to achieve a robust learning process. We employ the Bernstein-type inequalities to reformulate the probabilistic-form optimization into its deterministic counterpart. Then we solve the problem under a block coordinate descent framework. Simulation results demonstrate that the proposed approach significantly reduces the completion time of FL and achieves robust performance guarantee in the presence of location deviations.

Federated Learning (FL) offers promising solutions for deploying AI in wireless networks, allowing resourceconstrained devices to collaboratively train machine learning models, and reducing deployment costs. However, FL faces challenges due to device heterogeneity and unreliable communication links, which extend training time. Unmanned Aerial Vehicles (UAVs), with their flexibility and deployment advantages, have emerged as valuable assets in addressing these limitations by enhancing line-of-sight communication and providing proximal computational resources. This paper proposes a UAV-assisted FL framework that jointly optimizes resource allocation, task loads, and UAV trajectories to minimize FL completion time. Through a block coordinate descent (BCD) approach, our framework addresses the formulated joint optimization problem. Simulation results demonstrate that our proposed framework effectively balances resource allocation and significantly reduces FL completion time compared to benchmark schemes.

Federated Learning (FL) and Mobile Edge Computing (MEC) technologies alleviate the burden of deploying artificial intelligence (AI) on wireless devices with low computational capabilities. However, they also introduce energy consumption challenges in FL model training and data processing. In this paper, we employ Unmanned Aerial Vehicles (UAVs) to collect data from wireless devices and carry edge servers to assist the central server located at the base station in training FL model. We also consider the deviation of UAVs' locations to address its impact on network performance. Specifically, we formulate a robust joint optimization problem to minimize the energy consumption of UAVs, considering the computational resources, transmit power, transmission time, and FL model accuracy. Moreover, Gaussian-distributed uncertainties caused by deviation in UAV locations result in probabilistic constraints on data offloading. We initially employ the Bernstein-type inequality (BTI) to transform probabilistic constraints into deterministic forms. Subsequently, we adopt the Block Coordinate Descent (BCD) to separate the problem into three subproblems. Simulation results demonstrate a significant reduction in energy consumption and superiority in robustness.

With the rapid development of unmanned aerial vehicle (UAV) clusters, they will become the main means in urban transportation, traffic monitoring and other fields. The positioning accuracy of UAV clusters is the core basis of the application, this paper proposes a UAV cluster information geometry fusion positioning method based on low-orbit satellite system, which uses the geometric relationship between UAV clusters to transform the low-orbit constellation navigation information of each UAV into an information geometry probability model, reducing the influence of the low-orbit satellite system time asynchrony, and through Kullback-Leibler average fusion to achieve UAV cluster real-time high-precision positioning. The method effectively solves the problem caused by the easy loss of GNSS signals in the obscured environment, and significantly improves the reliability and stability of UAV cluster positioning in urban environments. Comparing the method of this paper with the existing UAV fusion navigation methods in terms of positioning accuracy stability, positioning real-time and error mutation under the occlusion scenario, the experimental results show that the method of this paper has obvious superiority in the above indexes. A cluster positioning method based on low orbit satellite systems has been proposed. Realized the positioning of unmanned aerial vehicle clusters based on low orbit satellite systems. Good improvement in positioning accuracy and stability. image

With the development of vehicle applications such as intelligent transportation and autonomous driving, the application fields based on location services have increasingly higher requirements for vehicle positioning reliability and real-time accuracy. However, the existing single navigation source of vehicles makes it difficult to realize real-time and high-precision positioning in different scenarios. The current multi-source information fusion methods have the problems of low generalization ability, poor expansibility, and high computational complexity, so it is challenging to apply in the field of vehicle positioning. To solve the above problems, this paper proposes a vehicle heterogeneous multi-source information fusion positioning method (MIFP) based on information probability, which converts the multiple heterogeneous navigation sources into information probability models to realize the unification of the time-frequency parameter format and designs an information fusion algorithm to realize the rapid fusion based on the theory of relative entropy. Through simulation tests and experimental verification by comparing with mainstream information fusion methods, such as the UKF method, the FGA method, and the NNA method, the MIFP method has high positioning accuracy and strong real-time performance. It can effectively solve the problems of weak expansion ability and large calculation amounts of current vehicle fusion positioning models. In the case of interference or mutation, the MIFP method can also suppress the influence of sudden errors on vehicle positioning.

Integrating the unmanned aerial vehicles (UAVs) assisted mobile edge computing (MEC) network with the blockchain technology emerges its superiority in the network utilization, differentiated service, and security, which has been regarded as a promising technique for time-critical applications. In this paper, we propose a UAV-assisted MEC network architecture and a comprehensive data processing flow, where the UAVs cooperate with the base station in computation as edge servers and act as blockchain nodes. We formulate an optimization problem that jointly considers UAVs’ position, data offloading, and resource allocation for minimizing the total time consumption of data processing. To address this problem, we decouple it as three tractable subproblems and propose a Block Coordinate Descent (BCD)-based iterative algorithm. In addition, we analyze the task migration and resource allocation problem in computation, and obtain analytical solutions by the Karush-Kuhn-Tucker (KKT) conditions. The simulated results indicate that the proposed algorithm leads to substantial performance gains.

The coordination and flexibility of drone swarm networks play a critical role in future combat scenarios. Since the operational tasks and functions become more complex, the time-sensitive services, including control commands, real-time audio and video streams, requires higher transmission performance. In this paper, we propose a joint routing and scheduling scheme to satisfy the deterministic transmission requirements in drone swarm networks. This scheme integrates segmented source routing and time-division multiplexing to construct a joint routing and scheduling mechanism, to control the service transmission delay within the required range. First, we analyze the architecture and service flow characteristics of swarm network, to establish a three-layer cross-layer model of service flow - forwarding link - time slot. Subsequently, an optimal link selection and time-slot allocation scheme is designed based on an integrated ant colony tabu search algorithm. Simulation results demonstrate that the proposed scheme outperforms traditional CSMA and TD-GPSR schemes in performance metrics such as end-to-end delay, packet loss rate, and scheduling success rate, particularly under high-load conditions.

The air and ground cooperative mobile edge computing (MEC) network provides a new paradigm for the development of the Internet of Things (IoT), which enhances the coverage of the terrestrial base station (TBS) and deploys computing resources near IoT devices. In this paper, we construct a UAV-assisted MEC system for IoT networks and design a data processing procedure. The UAV collects data from devices as a relay and makes decisions to offload some tasks to the central server connected with the TBS, while the onboard edge server in the UAV can perform local computing. Furthermore, we jointly optimize the device association, UAV's trajectories, task offloading, and resource allocation to reduce the energy consumption of the entire system. To solve this problem, we decompose it into three tractable sub-problems and use the block coordinate descent (BCD) method to iteratively optimize each set of control variables. Among them, device association is formulated as a linear programming problem, while UAV's trajectory optimization is transformed into a convex problem by introducing slack variables and using successive convex approximation (SCA). The offloading and resource assignment problem is proved to be convex via theoretical analysis and problem transformation. In addition, we derive the optimal relationship between computation duration and computing energy, which greatly reduces the complexity of problems. Simulation results show that the designed system and the algorithms can significantly reduce the total energy consumption, and the offloading strategies have a decisive impact on computation energy consumption.

Unmanned aerial vehicles (UAVs) combining with mobile edge computing (MEC) networks have promoted the application of Internet of Things (IoT) devices, providing enhanced coverage with flexible computing services. But the energy consumption of data processing is still a shortage in the UAV-assisted MEC architecture. Motivated by that, we propose a dynamic UAV-assisted MEC network and formulate a problem and jointly optimize association strategies, UAV trajectory, data offloading, and resource distribution for minimizing total energy consumption. To deal with this tricky problem, we devise a dichotomy-based joint iterative optimization algorithm. Specifically, we divide the problem into three sub-problems, solving by the integer programming, successive convex optimization, and dichotomy method. Finally, the simulation consequences prove that the devised network and algorithm significantly reduce total energy consuming.

As an important form of renewable energy utilization, microgrid (MG) is considered to be the main bearing form of distributed generation in the future. One of the most concerning issues in the operation of MG is how to realize its economic dispatch (ED). Nowadays, distributed algorithms have been increasingly used to solve the economic dispatch problem of MG. However, the MG based on the distributed optimization architecture must bear higher cyber-attack risks. To address this issue, this paper investigates the distributed robust ED problem of MG. Firstly, a multi-objective dispatch model of MG using a linear weighted sum (LWS) algorithm is developed, which considers the environmental and economic costs. On this basis, an event-triggered fully distributed algorithm is proposed, which can effectively reduce communication times. Furthermore, an attack resilient strategy against false data injection (FDI) attacks is implemented in the proposed fully distributed algorithm, which has strong robustness against various colluding attacks and non-colluding attacks, and can eliminate incorrect measurement of incremental cost and power generation data. Finally, the effectiveness of the proposed distributed control strategy is demonstrated through case studies in this paper.

As environmental protection greatly influences the social development, for the multi-energy systems (MES) equipped with a cluster of energy devices, the economic dispatch (ED) problem should not only be considered but also the environmental protection problem should be considered in energy utilization. To address this issue, a multi-objective dispatch model of MES using a linear weighted sum algorithm (LWS) is developed in this paper, which considers the environmental and economic costs. On this basis, a fully distributed algorithm with the coupled control mechanism of power and heat is presented to realize coordination optimization between the environmental and economic benefits. Furthermore, an event-triggered communication strategy is implemented in the fully distributed algorithm, which can be effectively applied to the multi-objective dispatch model, to reduce the communication burden. Finally, the simulation results verify the effectiveness of the proposed distributed control strategy.

In recent years, distributed algorithms have been increasingly used to solve the economic dispatch (ED) problem of multi-energy systems (MES) due to the advantages of high flexibility, strong robustness, and privacy. However, the MES based on the distributed optimization architecture must bear higher cyber-attack risks, so as to maintain the safe and stable operation of MES. To address this issue, an event-triggered fully distributed algorithm is proposed to solve the ED problem, which can effectively mitigate the communication burden. On this basis, an attack resilient strategy against false data injection (FDI) attacks is implemented in the proposed fully distributed algorithm, which can eliminate incorrect measurement of incremental cost and power generation data caused by cyber-attacks. In addition, a reputation value protocol embedded in the proposed attack resilient strategy is designed to effectively reduce the potential of direct isolation of the node. Finally, case studies are given in this paper to validate the effectiveness of the proposed distributed control scheme on a 9-bus MES.

With the assistance of the fifth generation (5G) and the internet of things (IoT), intelligent transportation systems (ITS) have great potential and capacity to make transportation systems efficient. To well assist the ITSs, advanced network architecture and reasonable offloading decision should be specially designed while ensuring data security. In this paper, we consider a blockchain-enabled intelligent transportation uplink scenario, which can collect and encrypt the aggregated data from smart vehicles (SVs) with blockchain. Considering the coupling of unmanned aerial vehicles (UAVs) position and offloading decision, we formulate a joint UAVs position optimization and data offloading decision problem in order to reduce the total time and energy consumption of data processing. We first divide UAVs into two categories and form neighborhood UAVs according to their data load. Then, we adapt the non-dominated sorting genetic algorithm II (NSGA-II) iteratively. Simulation results indicate that the algorithm can reduce energy consumption while ensuring the required time and achieving a good balance.

With the rapid development of large urban agglomerations and the increasing complexity of urban roads, the high-precision positioning of vehicles has become the cornerstone for the application of vehicle core technologies such as automatic driving. The real-time positioning accuracy of satellite navigation is easily affected by urban canyons, and its stability is poor; thus, how to use the information of the internet of vehicles to achieve satellite navigation fusion has become a difficult problem of multivehicle cooperative positioning. Aiming at this problem, this paper proposes a multivehicle 3D cooperative positioning algorithm based on information geometric probability fusion of GNSS/wireless station navigation (MVCP-GW), which creatively converts various navigation source information into an information geometric probability model, unifies navigation information time–frequency parameters, and reduces the impact of sudden error. Combined with the Kullback–Leibler algorithm (KLA) fusion method, it breaks off the shackles of the probabilistic two-dimensional model and achieves multivehicle three-dimensional cooperative positioning. Compared with the existing cooperative positioning algorithms in the performance of accuracy stability, applicability, obstruction scenarios, and physical verification, the simulation results and physical verification show that the MVCP-GW algorithm can effectively improve real-time vehicle positioning and the stability of vehicle positioning, as well as resist the impact of obstructed environments.

Combining unmanned aerial vehicles (UAVs) with multi-access edge computing (MEC) networks has been deemed as a potential approach for delay-sensitive applications. In this paper, we propose a UAV-assisted MEC network architecture and jointly optimize the UAVs' position, task offloading, bandwidth allocation, and computing resource allocation to minimize the time consumption of each terminal devices cluster. To solve this problem, we design a joint optimization algorithm based on the particle swarm optimization (PSO) and bisection searching (BSS) approach. The results of the simulation reveal that the devised algorithm can significantly reduce time consumption and guarantee the fairness of the whole network.

The Internet of Things (IoT) has gained rapid development, but due to the limited battery capacity and access capacity, there are many complex problems in the application. In this paper, we consider an air-and-ground cooperative wireless network, which can provide dynamic coverage for sensor equipments (SEs). Jointly considering the dynamic deployment of the aerial base stations (ABSs) and the admission-and-power control of the SEs, we formulate a two time-scale network control problem to minimize the long-term power consumption of all SEs under their individual rate requirement. On large time scales, we propose a particle swarm optimization algorithm (PSOA) to adjust the positions of the ABSs. On small time scales, we devise a joint admission-and-power control algorithm (JACA). Simulation results indicate that the air-and-ground network incorporated with the proposed algorithms can significantly reduce the total power consumption of the SEs compared with the other schemes.

In this letter, we consider an air-and-ground cooperative network, where several aerial base stations (ABS) help terrestrial base stations (TBS) for coverage enhancement. In this network, we first quantify the space-time coverage ratio (STCR) by fully considering the antenna models and the dynamic of the ABS, and then formulate a joint ABS deployment and TBS antenna downtilt optimization problem with the objective to maximize the STCR of the concerned area. The objective function involves many control variables and judgement operations, which make the problem very complex. To solve the problem effectively, we first adopt the genetic algorithm (GA). Using the solutions of the GA as training samples, we propose a deep neural network architecture to further reduce the computational time. Simulation results indicate that the proposed GA significantly improves the coverage ratio and the deep neural network (DNN) architecture achieves orders of magnitude acceleration in computational time with acceptable performance.

The intelligent warehouse logistics system (IWLS) is an essential component in the emerging industry 5.0. To well assist the IWLS, advanced network architecture and control policies with the adaptive capability to the variation of traffic should be specially designed. In this paper, we consider an air-and-ground cooperative wireless network that enables dynamic coverage to support the flexible scheduling of the automatic guided vehicles (AGVs) in the IWLS. Jointly considering the dynamic deployment of unmanned aerial vehicles (UAVs) as well as the adaptive power control of AGVs, we formulate a two time-scale network control problem to minimize the transmission power consumption of all AGVs under their individual rate requirement. On large time scales, we first propose a particle swarm optimization based algorithm (PSOA) to obtain the deployment position of the ABS. Then, using the results of the PSOA as training data, we design a deep neural network (DNN) framework aimed at reducing the computational time of the PSOA. On small time scales, we devise an online power control algorithm (OPCA) by using some of stochastic network optimization methods. With current channel conditions, the OPCA can generate the real-time power control policy and ensure the long-term rate requirement. Numerical simulations indicate that the DNN framework enhances the coverage performance of the network only consuming a few milliseconds of computation time. Incorporated with the OPCA, the total transmission power of the AGVs is significantly reduced.

Energy-saving techniques are vital for the battery-powered sensor devices (SDs), which affect their lifetime. In this paper, we propose an air-and-ground cooperative wireless sensor network (AGWSN), wherein several UAVs are deployed as aerial access points (AAPs) to assist the terrestrial access point (TAP) for data collecting. The positions of the AAPs can be modified to approach the cell-edge SDs, therefore reducing the energy of the SDs expended in uploading data. To fully exploit the potential of the AGWSN, we formulate a joint AAP position optimization, channel allocation, and power control problem to minimize the total power consumption of all SDs subject to their decoding threshold. To solve the formulated problem, we first analyze the optimal user pairing rule in each cell and based on the rule propose a maximum-weighted-independent-set inspired algorithm for the AAP position optimization. Then, we remodel the channel allocation problem as an interference minimization problem and devise a K-CUT based algorithm to solve it. We further propose a low-complex iterative algorithm to obtain the optimal transmission power for each SD. The performance of the proposed algorithms is evaluated via theoretical analysis and numerical simulation. Simulation results indicate that if the intracell and intercell interference are not well coordinated, the superiorities of the AGWSN cannot be developed, and its performance is even worse than the traditional terrestrial network (TTN). Cooperated with our algorithms, the AGWSN significantly outperforms the TTN in terms of total power consumption and probability of successful decoding.