Jinlong Sun

Urban low-altitude unmanned aerial vehicle (UAV) logistics networks face critical operational bottlenecks due to complex three-dimensional spatial blockages, continuous communication diffraction, and severe vulnerability to information-layer threats such as Automatic Dependent Surveillance—Broadcast (ADS-B) signal anomalies. To address these interconnected challenges, this paper proposes an event-driven, cloud–edge collaborative digital twin framework to guarantee continuous multi-link communication and flight safety. The architecture operates through a dual-tier “Teacher–Student” paradigm. Under secure conditions, a cloud digital twin acts as a high-capacity “Teacher,” employing Density-Based Spatial Clustering of Applications with Noise (DBSCAN) to partition heterogeneous user topologies. It then utilizes an energy-guided stochastic diffusion sampling (EGSDS) method to refine initial macroscopic routing, generating precise, outage-free global trajectories by systematically minimizing non-line-of-sight (NLoS) observation penalties and kinematic regularization costs. To counteract signal anomalies, a distributed Time Difference of Arrival (TDOA) anchor network continuously validates UAV coordinate integrity. If a threshold is breached, control authority is instantly transferred to the UAV’s edge digital twin. This resource-constrained edge tier relies on a localized “Student” network trained via progressive distillation. By compressing the computationally heavy iterative diffusion process into a rapid one-step inference model, the UAV autonomously generates a secure, short-range emergency path that strictly adheres to minimum communication thresholds. Once interference clears, the cloud seamlessly regains control to complete the logistics mission. Experimental results demonstrate that the proposed scheme significantly outperforms conventional heuristic routing methods in cloud-based scenarios. Furthermore, the edge-based distillation mechanism substantially improves the overall trajectory survival rate under signal anomalies, ensuring resilient and continuous logistics operations.

Unmanned aerial vehicles (UAVs) serve as both communication relays and aerial couriers in modern urban logistics networks. Conventional trajectory optimization methods assume perfect localization and isotropic free-space tracking signal propagation, which limits their effectiveness in urban canyons. To address the positional uncertainty and signal blockage from buildings, we propose a digital twin-driven framework for continuous trajectory and resource optimization in UAV swarms. We model an urban environment containing random high-rise structures, applying a non-line-of-sight (NLoS) uncertainty to reflect realistic communication degradation. The digital twin (DT) architecture utilizes a dual-layer spatial representation that captures a dynamically decaying positional uncertainty radius of the recipient. We define a strict visual localization boundary that initiates deterministic target tracking with a state transition mechanism. To manage the complexity of swarm routing, we apply Density-Based Spatial Clustering of Applications with Noise (DBSCAN), assigning one UAV courier and one logistics transfer station to each cluster. The system executes a continuous re-optimization loop using an adaptive multi-objective Genetic Algorithm. This framework jointly minimizes cumulative outage probability and total flight time while enforcing a signal-to-noise ratio threshold and throughput constraints. This continuous adaptation mechanism mitigates NLoS blockage risks, supporting reliable communication and efficient delivery in Global Navigation Satellite System (GNSS)-degraded and obstacle-dense urban environments.

Reliable measurement of building footprints, encompassing precise boundary localization and planar area estimation, is fundamental to urban applications using very high-resolution (VHR) remote sensing imagery. Conventional semantic segmentation pipelines optimize pixel-wise accuracy but often suffer from blurred edges and shape distortions, leading to biased geometric measurements. Although recent frequency-domain methods attempt to recover structural details, they typically rely on static filters that fail to adapt across diverse building topologies and complex background clutter. To overcome this limitation, we propose the Dynamic Frequency Selection Module (DFSM), a plug-and-play adaptive frequency selection module for geometry-aware building extraction. DFSM parameterizes the frequency cutoff into dynamically learnable, continuous variables, functioning as a content-aware filter. It adaptively modulates the spectral passband—widening it to suppress high-frequency noise for small, cluttered buildings, and narrowing it to effectively sharpen edge contours for large-scale structures. Subsequently, an attention-based fusion mechanism integrates these frequency representations with spatial context, optimizing the inherent trade-off between regional area integrity and boundary precision. Comprehensive evaluations on the ISPRS Vaihingen and WHU datasets demonstrate that DFSM consistently enhances both CNN- and Transformer-based segmenters. Beyond improving conventional regional metrics, DFSM elevates Boundary-Intersection over Union (Boundary-IoU) by 3%–4% and significantly reduces the 95% Hausdorff distance. Notably, DFSM outperforms explicit boundary-supervised baselines without requiring auxiliary edge annotations or multi-task loss tuning. By systematically tightening the 95% coverage intervals for geometric biases, DFSM provides a robust, architecture-agnostic solution for geometry-aware building extraction in remote sensing.

Space-Air-Ground Integrated Networks (SAGINs) play a crucial role in the 6 G system, offering global coverage and ultra-wide-area broadband access. Meanwhile, advancements in artificial intelligence (AI) have led to a significant increase in model inference demands with stringent latency requirements. In this paper, considering the intelligent services in SAGINs, we explore task offloading for the co-inference problem and improve the inference efficiency by performing model splitting, device association, and resource allocation. This problem is solved iteratively by decomposing it into multiple sub-problems. In particular, the bandwidth allocation problem is solved using convex optimization techniques to obtain a closed-form solution, and the model splitting problem is addressed by systematically searching for the optimal split points. Besides, the joint device association and computing resource allocation problem is reformulated into a monotone submodular function without the satellite, and a low-complexity submodular optimization algorithm is proposed. To further utilize the computing power of the satellite, we introduce a resource reallocation algorithm based on the existing optimization results. These sub-problems iterate alternately until the optimization goal converges. The simulation results show that the proposed algorithm can achieve better latency performance in several inference tasks.

Modern intelligent energy stations show new requirements for smart, green, and highly-efficient systems. This article presents opportunities of bridging domains of large-scale facility management and information and communication technology. By introducing cognitive digital twin technology, potential opportunities for the intelligent operation and management of energy stations can be investigated. In this study, a conceptual intelligent energy station architecture is outlined based on cognitive digital twins. Subsequently, key modules and use cases for the cognitive digital twin-aided architecture are discussed, focusing on intelligent management and optimal operations. Furthermore, this study identifies several key challenges and future research directions for realizing the proposed architecture. These include model-related, data-related, and collaboration-related issues.

The security of virtual power plant (VPP) communication networks is paramount, particularly owing to growing increase in the reliance on distributed energy resources (DERs) using cloud-edge architectures. VPPs are increasingly vulnerable to cyber intrusion owing to the large number of access devices involved. Existing intrusion detection methods often face challenges in addressing the complexity of VPP networks, and lack adaptability to diverse attack patterns. To address the dynamic nature of VPPs, this study proposes a novel intrusion detection approach called dynamic detection combining transformer with feature filtering (DTF-VPP), which integrates principal component analysis (PCA) with a transformer-based model to improve the detection efficiency and accuracy. The key contributions of this study include a feature selection process that uses PCA to reduce the model complexity, and a dynamic loss-weighting mechanism that adapts to high-frequency attacks. The experimental results on the NSL-KDD dataset demonstrate that DTF-VPP outperforms conventional models in terms of the accuracy and F1-score. Therefore, this approach offers a scalable and adaptive solution for enhancing the security of VPPs against cyber threats.

With the rapid development of unmanned aerial vehicle (UAV) technology and the rise of the low-altitude economy, the accurate tracking of UAVs has become a critical challenge. This paper considers a deep learning-based localization scheme that combines microphone arrays for audio source reception. The microphone array is utilized to capture sound source reception from various angles. The proposed TSNetIQ combines elaborately designed Transformer and convolutional neural networks (CNN) modules, and the raw in-phase (I) and quadrature (Q) components of the audio signals are used as input data. Hence, the direction of arrival (DOA) estimation is treated as a regression problem. Experiments are conducted to evaluate the proposed method under different signal-to-noise ratios (SNRs), sampling frequencies, and array configurations. The results demonstrate that TSNetIQ can effectively estimate the direction of the sound source, outperforming conventional architectures trained with the same dataset. This study offers superior accuracy and robustness for real-time sound source localization in UAV applications under dynamic scenarios.

Unmanned aerial vehicles (UAVs) are increasingly pivotal in large-scale wireless relay and inspection systems. However, energy constraints and infrastructure costs hinder large-scale deployment. This letter introduces a two-stage optimization combining clustering-based charger allocation and UAV trajectory optimization. The key strategy is the fusion of DBSCAN clustering with convex optimization techniques. By adaptively grouping communication nodes based on density distributions, charger deployment is minimized while maintaining coverage efficiency. We employ convex relaxation to jointly optimize UAV trajectories and charger locations, prioritizing proximity to critical nodes for enhancing communication quality. Simulations demonstrate a 36.5 % reduction in charger count and a 61.4 % improvement in minimum total throughput compared to baseline methods. The results validate a cost-effective and high-performance solution for UAV-assisted wireless networks.

The development of Industrial Internet of Things (IIoT) applications presents a critical challenge in terms of latency limitation, particularly considering the limited availability of resources that prevent a single fog device from fully executing large-scale computing tasks. In such scenarios, enabling distributed computing across multiple fog servers or collaborating with cloud servers holds promising potential. To improve the efficiency of task offloading while accounting for the crucial role of movable fog devices (e.g., robots and unmanned cars), we formulate a joint optimization problem as a partially observable Markov decision process (POMDP), incorporating offloading decisions, computing resource allocation, and trajectory optimization under constraints related to available resources and collision avoidance. Due to the non-deterministic polynomial-time hardness (NP-hardness) in the problems of task offloading and resource allocation, we reformulate a matroid-constrained submodular maximization problem and propose an iterative low-complexity algorithm to find solutions. Subsequently, extracting better solutions from submodular optimization, we propose a multi-agent reinforcement learning (MARL)-based algorithm to solve the trajectory optimization problem for the movable fog devices acting as agents, making decisions based on their local observations. Finally, simulation results have validated that the proposed scheme has a superior performance compared to the baselines.