Coverage path planning (CPP) for unmanned aerial vehicles (UAVs) plays a significant role in intelligent distributed surveillance systems. However, due to poor cooperation, most existing CPP methods may cause strongly overlapped trajectories, missing areas, or even collisions in uncertain and complex environments, leading to long task completion time and low coverage efficiency. To this end, in this paper we propose a novel multi-UAV distributed online cooperation (MDOC) CPP method that aims to minimize task completion time. Moreover, this method allows UAVs to quickly respond to unknown obstacles and complex emergencies, such as UAV breakdown or communication interruption. To establish close cooperation between UAVs, we propose an efficient environmental information map (EI-map) fusion technique that enables them to obtain global exploration in real-time in a cooperative manner. Then we innovatively develop a distributed cooperative deep Q-learning (DCDQN) algorithm to obtain UAVs' coverage paths online that are determined by minimizing task time and avoiding overlaps, missing areas, and collisions. Specifically, attributing to the fused EI-map, we expand the state space of DCDQN to collect sufficient observations and design a novel cooperative learning pattern to efficiently plan the path for global optimization. Simulation results show that our method outperforms the state-of-the-art in task completion time and coverage efficiency, especially in uncertain and complex environments. In addition, we validate that our method can efficiently complete full coverage even in emergencies.
1 August 2025 in Digital Communications and Networks
Reputation evaluation is an effective measure for maintaining secure Internet of Things (IoT) ecosystems, but there are still several challenges when applied in IoT-enabled pumped storage power stations (PSPSs), such as the limited resources of intelligent inspection devices and the threat of single-point and collusion attacks. To address these challenges, in this paper we present ReIPS, a secure cloud-based reputation evaluation system designed to manage intelligent inspection devices’ reputations in IoT-enabled PSPSs. Our ReIPS incorporates a resource-rich cloud platform to collect various reputation evaluation indexes and perform complex evaluation operations. To resist single-point attacks, we present a novel reputation evaluation model that combines backpropagation neural networks (BPNNs) with a point reputation-weighted directed network model (PR-WDNM). The BPNNs objectively evaluate device point reputations, which are further integrated into PR-WDNM to detect malicious devices and obtain corrective global reputations. To resist collusion attacks, we introduce a knowledge graph-based collusion device identification method that calculates behavioral and semantic similarities to accurately identify collusion devices. Simulation results show that our ReIPS outperforms existing systems regarding reputation evaluation performance, particularly in single-point and collusion attack scenarios.
8 July 2025 in IEEE Transactions on Consumer Electronics
Consumer-grade Unmanned Aerial Vehicles (UAVs) have been widely served as Federated Learning (FL) clients to collaboratively train a global machine learning model in a privacy-preserving manner. However, the growing diversity of contemporary UAV intelligent applications requires FL to support the training of not only a single model (single-job training) but also multiple models (multi-job training), which poses new challenges in system-wide efficiency and security. To solve these challenges, we propose a novel Multi-Job Hierarchical FL (MJHFL) framework, which guarantees multi-job training for consumer-grade UAVs with diverse QoS requirements, including low latency, high energy efficiency, and robust security. To achieve these goals, we design a joint client selection and resource allocation approach. First, we jointly minimize the total training time of multiple jobs and maximize the security-measured reputation of UAVs by developing a Deep Reinforcement Learning (DRL)-based client selection approach, which offers strong resistance to adversarial attacks. Next, to minimize the total energy consumption of multiple jobs, we propose a convex optimization-based resource allocation approach, which iteratively optimizes the computing frequency and transmit power for each selected UAV. Extensive simulations demonstrate that, compared to state-of-the-art FL benchmarks, the proposed MJHFL framework reduces training time by 56.6% and energy consumption by 69%, while improving model accuracy by 9.81% in adversarial attack scenarios.
28 November 2023 in IEEE Internet of Things Journal
Whilst blockchain technology holds promise for secure Internet of Things (IoT) data management, its deployment in the massive Internet of Unmanned Aerial Vehicles (IoUAV) still faces significant challenges to satisfy strict requirements for low-latency query services and cost-effective resource consumption. To address these challenges, we present a lightweight multitype data (MTD) blockchain architecture called LMChain with cost-effective MTD block scheduling. Specifically, LMChain incorporates cross-layer MTD blocks, wherein resource-constrained UAVs retain only lightweight block headers. Block bodies with high query probability are stored in fog nodes, while others are offloaded to cloud storage. Based on the MTD block structure, we develop a cost-effective block scheduling scheme to minimize the overall cost associated with LMChain storage and querying. A cooperative deep reinforcement learning (CDRL) algorithm is designed to efficiently schedule MTD blocks between the fog and cloud layers. Simulation results show that our LMChain significantly reduces the IoUAV blockchain system’s storage resource requirements and overall cost while supporting low-latency query services, making it well suited for massive IoUAV applications.
30 June 2025 in IEEE Transactions on Vehicular Technology
In this correspondence, we propose a novel Ordered Directed Acyclic Graph (O-DAG) blockchain to improve model parameter selection for Blockchained Federated Learning (BFL) in Intelligent Transportation Systems (ITS). Our ODAG blockchain composes an innovative Ordered Transaction Topology (OTT) and a Deep reinforcement learning-enhanced Consensus Mechanism (DCM). The OTT ensures the traceability of BFL model parameter selection by using blockchain to sequentially record local and global model parameters. By establishing traceable iteration relationships among these parameters, the OTT facilitates the efficient selection of updated model parameters for BFL. Building upon the OTT, our DCM accelerates BFL convergence by enabling adaptive and fast model parameter selection. The DCM optimizes parameter selection policies for both local training and global aggregation by getting evaluations from heterogeneous ITS clients. Simulations show that our ODAG blockchain outperforms state-of-the-art baselines, improving BFL convergence speed by 38.64% and model accuracy by 7.47%, while maintaining strong scalability in ITS networks