Shichao Xia

With the widespread application of unmanned aerial vehicles (UAVs) in smart city scenarios under the Internet of Everything, multi-UAV collaborative trajectory planning faces multiple challenges including cost constraints, collision risks, and complex action spaces. To address these issues, a distributed multi-UAV 3D trajectory planning collaborative optimization method is proposed, which enhances system efficiency through joint optimization of UAVs energy consumption and Age of Information (AoI). Firstly, an improved genetic algorithm-based optimization mechanism is designed to determine the number of UAVs by introducing threat factors and composite reward factors. Then, a multi-agent deep reinforcement learning (MADRL)-enabled collaborative planning framework is established, modeling the trajectory planning problem as a multi-objective Markov decision process (MDP) to achieve autonomous trajectory optimization in complex urban environments through distributed policy networks. Finally, the system implements adaptive speed adjustment for UAVs using a greedy algorithm to improve resource utilization. Simulation results demonstrate that compared with baseline algorithms, the proposed method achieves superior performance in reducing energy consumption, enhancing AoI, and optimizing trajectory planning strategies, validating its effectiveness in intelligent urban air mobility systems.

With the increasing complexity and diversity of modern computing environments, the collaborative capabilities of heterogeneous edge computing networks have become essential in meeting diverse user needs and enhancing overall network performance. However, due to concerns over data privacy, security, and the technical standards and protocols unique to each network node, nodes are often reluctant to share their computational resources and information. This issue significantly restricts the collaborative capacity and system efficiency of edge computing networks. To address this challenge, we propose a Blockchain-Based Collaborative Task Offloading Algorithm in Heterogeneous Edge Computing Networks (BCTOH). By introducing blockchain technology, the algorithm ensures resource and data security among heterogeneous edge nodes. Additionally, it deploys a Collaborative Reinforcement Learning (CRL) algorithm across heterogeneous network nodes, facilitating resource information sharing, cooperation, and distributed task offloading training. This approach breaks down trust barriers between heterogeneous edge nodes, reducing latency and energy consumption in task offloading and improving service quality and system reliability. Simulation results demonstrate that the proposed BCTOH algorithm effectively coordinates task offloading among heterogeneous edge nodes, optimizing system latency and energy consumption and significantly enhancing overall network performance.

Unmanned aerial vehicles (UAVs), due to their inherent flexibility and autonomous operation, are widely used in Internet of things (IoT) networks for collecting data to facilitate real-time evaluation and monitoring applications. This paper investigates an UAV-assisted IoT network, in which the UAV sequentially accesses IoT devices (IoTDs). During hovering, the UAV works on a full-duplex mode while collecting data from target devices, taking into account actual propulsion power consumption. In order to quantify the freshness of devices data, we introduce the concept of age of information (AoI). A multi-objective optimization method is proposed to jointly optimize three objectives: maximization of the data rate, minization of AoI, and minization of the UAV energy consumption over a particular mission period. These three objectives partially conflict with each other and provide weight parameters to describe their importance. Since the data uploaded by IoTDs is dynamically changing, the trajectory planning of the UAV is required. Considering that the UAV has no prior knowledge of the network environment, the optimization problem is reformulated as a Markov decision process (MDP). Aiming at the learning problem of the UAV control strategies over multiple objectives, a deep reinforcement learning algorithm for multi-objective collaborative optimization is proposed. While training, the agent collects data in time according to the devices priority, and generates optimal strategies under the conditions of giving weights. Experimental results demonstrate that the proposed Multi-Objective Twin Delayed Deep Deterministic Policy Gradient algorithm jointly optimizes three objectives and can adjust the optimal policy based on the weight parameters of each objective.

This paper investigates the planning of Unmanned aerial vehicles (UAVs) trajectory in UAV-assisted Internet of Things (IoT) networks with a massive number of IoT devices (IoTDs). Existing UAV-assisted IoT network data collection schemes mostly focus on optimizing energy consumption and data collection throughput, while neglecting the temporal value of data collection. With the assistance of the age of information (AoI), the average AoI of data collected by the UAV from IoTDs is minimized to enhance information freshness. To strike a balance between trajectory planning and information freshness, a two-stage artificial intelligence (AI) algorithm is proposed in this paper. Firstly, to tackle the issue of prolonged flight time caused by the UAV sequentially collecting data from IoTDs, an improved clustering algorithm is introduced to determine the cluster centers of IoTDs. Secondly, considering that the UAV lacks prior knowledge of the IoT network environment, the AoI minimization problem is reformulated as a Markov decision process (MDP). A neural network algorithm based on twindelayed deep deterministic policy gradient (TD3) is employed to optimize UAV trajectory. Simulation results show that the proposed algorithm is superior to the benchmark algorithms, particularly in scenarios involving a massive number of IoTDs.

Mobile edge computing (MEC) enables various services to be cached in close proximity to the user equipments (UEs), thereby reducing the service delay of many emerging applications. However, the limitation of storage, computation, and radio resources, the dynamics of the decentralized MEC environment, and the complex spatial relationships of service request types and wireless network states between edge nodes make it difficult to realize efficient edge computing services. To address these challenges, this paper integrates the digital twin (DT) technology with a multi-cell MEC network to study an intelligent cooperative task offloading and service caching scheme, aiming at maximizing a quality of services (QoE)-based system utility. Specifically, we first construct a digital twin edge network (DITEN) to reflect the physical MEC system in real-time and provide data for training. With the help of DT technology, it is easy to access data resources in the DITEN to improve the simulation ability and reduce the communication cost. Then, we propose a graph attention-based multi-agent reinforcement learning (GatMARL) algorithm to learn the optimal task offloading and service caching strategies in the DITEN. The GatMARL employs a graph attention-based value decomposition network to capture the potential spatial relationships between edge nodes to learn better attentive cooperation policy. Simulation results demonstrate that the proposed GatMARL algorithm exhibits an effective performance improvement compared with state-of-the-art benchmarks.

The multi-access edge computing (MEC) and ultra-dense network (UDN) are regarded as essential and complementary technologies in the age of Internet of Things (IoT). Deploying MEC servers at the macro-cell and small-cell stations can significantly improve user experience as well as increase network capacity. Nevertheless, there still remain many obstacles in practical MEC-enabled UDNs. Among them, a unique challenge is how to coordinate computing and networking to fit the diverse offloading demands of IoT applications in dynamic network environments. To this end, this paper first investigates a distributed delay-constrained computation offloading methodology based on computing and networking coordination in the UDN. An extended game-theoretic approach based on the Lyapunov optimization theory is designed to achieve adaptive task offloading and computing power management in time-varying environments. Furthermore, considering the uncertainty in users’ mobility and limited edge resources, distributed two-stage and multi-stage stochastic programming algorithms under various uncertainties are proposed. The proposed algorithms take posterior recourse actions to compensate for inaccurate predicted network information. Extensive simulations validate the effectiveness and rationality of the proposed algorithms and their superior performance over several benchmark schemes.

Accurate spatial-temporal traffic modeling and prediction play an important role in intelligent transportation systems (ITS). Recently, various deep learning methods such as graph convolutional networks (GCNs) and recurrent neural networks (RNNs) have been widely adopted in traffic prediction tasks to extract spatial-temporal dependencies based on a large volume of high-quality training data. However, there exist data scarcity problems in some transportation networks, and in these cases, the performance of traditional GCNs and RNNs based approaches will degrade sharply. To address this problem, this paper proposes an adversarial domain adaptation with spatial-temporal graph convolutional network (Ada-STGCN) model to predict traffic indicators for a data-scarce target road network by transferring the knowledge from a data-sufficient source road network. Specifically, Ada-STGCN first develops a spatial-temporal graph convolutional network that combines the GCN and gated recurrent unit (GRU) to extract spatial-temporal dependencies from source and target road networks. Then, the technique of adversarial domain adaptation is integrated with the spatial-temporal graph convolutional network to learn discriminative and domain-invariant features to facilitate knowledge transfer. Experimental results on the real-world traffic datasets in the traffic flow prediction task demonstrate that our model yields the best prediction performance compared to state-of-the-art baseline methods.

Peak-to-average power ratio (PAPR) is an important issue for orthogonal frequency division multiplexing (OFDM) systems. In this paper, we derive a new piecewise nonlinear companding scheme for reducing PAPR in OFDM systems. Compared with current state-of-art companding scheme, the new companding scheme improves the power spectral density (PSD) performance. The companding function is derived according to the cumulative distribution function (CDF) of companded OFDM signals’ amplitudes, which is fitted by using several piecewise linear functions to approximate the original Rayleigh distribution CDF. The constraint optimization problem is formulated, and parameter selection method is provided. Simulation results verify that under precondition of similar PAPR reduction levels, the proposed companding scheme could achieve better bit error rate (BER) and PSD performance compared with other typical companding schemes.