Powerline inspection with UAVs significantly improves efficiency and safety in remote areas. However, the lack of cellular infrastructure necessitates the use of UAV-mesh networks, whose deployment presents challenges in jointly optimizing coverage, node load, robustness, and cost under complex terrain constraints. In this paper, we investigate the computational complexity of this deployment problem by formulating it as a multi-objective optimization task and proving its NP-hardness. To address this, we presentU-Mesh+, aterrain-aware, robust, and cost-efficientdeployment framework that integrates four key components: (i) identifying line-of-sight and non-line-of-sight links to model terrain-induced communication constraints; (ii)NetConsfor cost-effective coverage and connectivity network topology construction; (iii)NetOptfor network resilience and balance node-level load improvement without extra cost; and (iv)NetEnhfor service availability enhancement via targeted local refinements. We implementU-Mesh+in a real-world 270km2mountainous forest with 174 power towers and 48km of transmission lines. Extensive experiments demonstrate its efficacy in terms of deployment cost and network performance. On-site network data from the deployed wireless network further validate its effectiveness and scalability under real-world conditions.

UAV-assisted task execution is a promising approach to powerline inspections in remote areas where no cellular network infrastructure exists for inspection data transmission. In this paper, we investigate UAV-mesh network deployment in remote areas to empower UAV-assisted powerline inspection, which is challenging considering a mountainous environment with no power supply. Particularly, given the locations of a set of power towers, we first formulate the UAV-mesh network deployment problem with connectivity and coverage constraints, which is NP-hard. Then, we propose U-Mesh, which is a cost-effective and load-balanced deployment scheme. To be specific, U-Mesh integrates three components, i.e., link identification: identifying the link conditions between power towers based on geographical barriers, NetCons: conducting local search to gradually obtain a cost-effective initial mesh nodes with connectivity and coverage constraints, and NetOpti: optimizing the initial mesh node positions to improve the mesh load and robustness from the perspectives of overall network structure. Finally, we implement U-Mesh in a 270 km2mountain forest area, and demonstrate its efficacy in terms of both deployment cost and network performance via extensive evaluations.

The deployment of high-accuracy low-distinction and multi-scale object detection models on resource-constrained edge devices is essential for ubiquitous intelligent applications, from autonomous obstacle avoidance to anomaly object recognition. However, these models' computational burden, energy consumption, and memory footprint pose significant challenges for distributed and pervasive systems. In this paper, we propose HiPOD, a hierarchical pruning framework designed to prune low-distinction and multi-scale object detection models by jointly learning layer-wise and path-wise pruning strategies. HiPOD balances the accuracy-efficiency trade-off through two novel components: Layer-Adaptive Ratio Learning, named AdaLR, which leverages network structural characteristics and a reinforcement learning-based action-feedback mechanism to adaptively generate balanced layer-wise pruning ratios; and Genetic Path Optimization, named GenPath, which employs crossover and mutation operations to optimize inter-layer kernel pruning paths, preserving critical semantic and spatial information. Extensive experiments on three benchmark datasets demonstrate the effectiveness of HiPOD, with only a 3 % drop in mAP50 and a 2 % drop in mAP50:95 compared to the full models. The ablation studies and impact analysis further validate the effectiveness of each module and highlight the robustness of our framework. Furthermore, evaluations on an edge device demonstrate the practicality of the proposed solution for powerline inspection.

UAV-assisted inspection is critical for modern power grid maintenance, enhancing efficiency and safety in remote areas. However, automatically designing UAV inspection trajectories is challenging due to the cluttered inspection environments, small inspection targets, and pervasive obstacles. We propose Auto-UIT, a novel method for generating inspection trajectories in noisy, sparse, and complex 3D point cloud. Auto-UIT has three core techniques: (1) A local structure-enhanced pylon segmentation, which accurately segments pylons, power lines, and surroundings in noisy point cloud for effective inspection target identification and trajectory planning. (2) A 3D fingerprint-based pylon type recognition that compensates for point cloud sparsity to complete missing inspection targets based on the pylon type. (3) An adaptive trajectory generation that samples positions in response to diverse pylon orientations and pervasive environmental obstacles, ensuring UAV operational safety. Our experiments on a real-world dataset across four distinct areas demonstrate that Auto-UIT outperforms existing baseline methods in all three tasks. Furthermore, a four-month deployment in a power grid inspection system—covering a 270 km2 primary mountainous area—yielded an expert first-review acceptance rate of 91.86% for the generated trajectories, and reduced design time by an average of 88.19% compared to manual methods, significantly improving inspection efficiency.

UAV-assisted inspection is critical for modern power grid maintenance, enhancing efficiency and safety in remote areas. However, automatically designing UAV inspection trajectories is challenging due to the cluttered inspection environments, small inspection targets, and pervasive obstacles. We propose a novel method for generating inspection trajectories in noisy, sparse, and complex 3D point cloud. It has three core techniques: (1) A local structure-enhanced pylon segmentation, which accurately segments pylons, power lines, and surroundings in noisy point cloud for effective inspection target identification and trajectory planning. (2) A 3D fingerprint-based pylon type recognition that compensates for point cloud sparsity to complete missing inspection targets based on the pylon type. (3) An adaptive trajectory generation that samples positions in response to diverse pylon orientations and pervasive environmental obstacles, ensuring UAV operational safety. A four-month deployment in a power grid inspection system—covering a 270 km2 primary mountainous area—yielded an expert first-review acceptance rate of 91.86% for the generated trajectories, and reduced design time by an average of 88.19% compared to manual methods, significantly improving inspection efficiency. Demo video and dataset are available at https://ljhe006.github.io/autouit/.

In this paper, we focus on a satellite-ground multi-casting scenario assisted by a free space optical (FSO) link, where multiple ground devices are requesting the same data packet from a satellite via the FSO link. Due to the extremely long link distance in satellite-ground communication, the coverage of an optical beam has been considerably enlarged. We aim at deploying the corresponding coverage benefits of the optimal beam in provisioning multicasting services to ground devices. At first, we characterize the achievable multicasting capacity for considered satellite-ground communication. Assuming the deployment of an optical beam can be switched between an activation mode and an idle mode, we formulate a multicasting throughput maximization problem under a maximum average power limit for the optical signal emission, via jointly optimizing the optical beam deployment and the activation slot scheduling. Both optical power bias and beam pointing direction will be optimized in the optical beam deployment design. For optimally solving the formulated nonconvex problem, we perform a two-fold problem reformulation and successfully convert the nonconvex problem to a convex one. The convex problem reformulation allows us to equivalently and optimally tackle the original problem via convex optimization tools. At last, in comparison with two benchmarks, we verify the optimality of our proposed design and illustrate the performance benefits of allowing idle operation mode and performing beam pointing design.

In this paper, we focus on an unmanned aerial vehicle (UAV)-assisted covert communication scenario, and introduce an optimal joint resource allocation and continuous UAV trajectory design. Our goal is to maximize the information throughput between UAV and a ground user, while protecting the transmission behavior from being detected by a warden. To tackle the formulated non-convex continuous trajectory design problem, we provide an artificial potential field (APF)-based approach, with which a closed-form optimal solution is for the first time obtained for considered UAV-assisted covert communication. In particular, by characterizing the covertness constraint and decoupling the original joint problem, we then convert the resulting pure trajectory design into a mechanical problem in the APF, which can be optimally solved based on mechanical equivalence technique. Specifically, the force field in the conducted APF corresponding to covert transmission rate is actually twisted due to the presence of the warden, for which we reorganize a brand new mechanical analysis process accordingly, including reanalyzing the direction of the force field and updating the force balance expression. Then, according to the minimum total potential energy principle, the closed-form solution of the optimal rope shape is constructed following the equilibrium analysis. Finally, we also verify our proposed algorithm and confirm the optimality of the obtained solution via simulations.

As critical infrastructure, smart grids require periodic power inspections to remain in good condition. Due to the complexities and variations in the geographical environment especially in remote areas, power inspections can be challenging. In this paper, we investigate efficient large-scale power inspections in remote areas with limited cellular network coverage by providing network support to inspection unmanned aerial vehicle (UAV) via wireless mesh networks. Specifically, we first formulate a network construction problem with the objective of balancing deployment cost and transmission delay, which is an NP-hard problem. Then, we propose U-Auto, i.e., UAV-Assisted Air-ground Network Construction (U-Auto) scheme, to construct a wireless network for UAV-assisted power inspection, which includes a group-coverage maximization selection (GMS) algorithm and two air-ground link handover rules. GMS generates a wireless network topology based on a structure termed group and a utility function. Based on the network topology constructed by GMS, two air-ground link handover rules are employed to optimize transmission delay and connection stability of the air-ground link, called minDelay and minSwitch. Finally, extensive simulations are conducted based on a real world environment of a forest in Hubei, China, and demonstrate the effectiveness of the proposed algorithm.

Mobile-edge computing (MEC) is a promising approach to support high-quality time-sensitive applications. With the increasing number of mobile devices, achieving efficient service migration management has become nontrivial in MEC. In addition, the service migration issue is difficult to be solved in real time due to user mobility and dynamic network conditions. In this article, we investigate the mobility-aware service migration problem in MEC by introducing a data-driven framework. First, service migration is formulated as an optimization problem for minimizing the long-term system delay that consists of computing, communication, and migration delays. Second, we propose a Mobility-aware Service Migration scheme, named MSM, consisting of three layers: 1) the data collection layer; 2) the association patterns analysis layer; and 3) the service migration layer. Specifically, we first collect users’ historical Wi-Fi traces to mine the association patterns. We then design a user management mechanism to reduce the complexity of decision making by using user association patterns. Finally, we formulate the service migration as a 2-D-Markov decision process and devise a deep reinforcement learning (DRL)-based algorithm to obtain service migration decisions in a large-scale MEC scenario. Extensive data-driven experiments are conducted to demonstrate the efficacy of MSM in reducing the system delay.

Real-time search is essential for accessing specific sensing data (SD) in vehicular networks to support safe, efficient, and intelligent road services. Considering the tremendous data volume, the SD search process should be carefully devised to avoid excessive retrieval and transmission delay. To alleviate the communication and computational burden for sensing devices and the cloud server, roadside edges are adopted to cache the SD in advance. Given a short lifetime of SD, the caching scheme is required to be efficient in facilitating both the search process and uplink/downlink transmission, which is quite challenging due to the coupling of resource allocation decisions. To guarantee the search efficacy and enhance the caching resource utilization, we propose a real-time search-driven caching (RSC) paradigm to enable the cooperation among storage-constrained edges. A hierarchical indexing framework is first introduced for cached data, based on which we then devise a search utility model to quantify the expected data freshness and response delay. With the objective of maximizing the long-term search reward, the RSC problem is formulated by jointly considering the search requests and utility model. A deep-reinforcement-learning-based caching (DRLC) method is proposed to solve the problem. Specifically, an action transition module is introduced to lower the computational complexity via reducing the selection space of caching actions. Extensive simulations are carried out based on the real trace data in Creteil, France, and results show that the intelligent DRLC method can improve the real-time search performance significantly comparing to the benchmark methods.

Mobile crowdsensing (MCS) can be widely adopted for undertaking a variety of tasks for the smart city by recruiting distributed participants. With the rapid proliferation of MCS applications, tasks can be devised with different sensing scales. Hence, allocating the tasks to participants with variable spatiotemporal granularity would be urgent and challenging. To this end, we propose a behavior sequentializing and task mapping (BETA) framework, where MCS tasks can be flexibly mapped based on the moving behavior of a participant’s daily activities. A sequential behavior model is first proposed to describe the moving behavior of a participant’s daily activities. Specifically, the behavior of a daily activity is represented by the spatiotemporal trajectory distribution, and a sequential behavior graph is adopted to model the relationships among multiple activities. To extract the sequential behavior from historical trajectories, a projection-clustering (PC) algorithm and a behavior sequentializing approach are developed. Then, based on the extracted sequential behavior, a behavior-to-task mapping network is proposed to evaluate the fitness between tasks and a participant. Finally, extensive simulations are conducted to demonstrate the functionality and performance of BETA. The results show that our proposed method outperforms the state-of-the-art solutions in the mapping efficiency of tasks with different sensing scales.

Aiming at traffic efficiency improvement, vehicle platoon becomes an essential driving technique to control the synchronous driving of connected and automated vehicles. Since the mature automated driving technology and cooperative willingness cannot be ensured for all vehicles, a mixed traffic paradigm that incorporates both cooperative vehicles (CVs) and non-cooperative vehicles (NCVs) will be inevitable. Due to the traffic hindrance and intermittent connections caused by the randomly distributed NCVs, traffic efficiency would be limited in the mixed traffic. Therefore, a hindrance-aware platoon formation scheme is proposed for the mixed traffic in this paper, which aims at coordinating CVs to maximize overall traffic velocity while minimize collision risk and fuel consumption. Specifically, a vehicle connection model is first established to construct the hindrance-aware relationships among vehicles, based on which, the intermittent connections of CVs are formulated as a mixed integer nonlinear programming (MINLP) problem. To reduce the search space, a novel cross-vehicle matrix is designed to represent the hindrances that each CV faces, then a traffic-maneuver-tree construction algorithm is proposed to search for feasible and hindrance-aware platoon formation connections. A length-dynamic inverse influence zone is constructed, then two decision indicators of platoon leader and follower are decoupled by evaluating leadership qualifications of all CVs. Given the hindrance-aware connections and leadership qualifications, a hindrance-aware platoon formation algorithm is proposed to jointly optimize the speed, safety and energy efficiency of CVs. To verify the effectiveness of the platoon formation mechanism, extensive simulations are conducted, and the results reveal that the road utilization, traffic capacity improvement and safety assurance in mixed traffic can be enhanced.

Real-time sensing data access is essential for vehicular networks to support safe, efficient, and intelligent road services. Considering the tremendous data volume, the sensing big data search process should be carefully devised to avoid excessive retrieval delay. Edge caching can effectively alleviate the traffic burden and shorten the data downloading route, where the sensing data has to be uploaded to the edge in advance. Given a short life-time of sensing data, the caching scheme is required to be efficient in facilitating both the search process and uplink/downlink transmission, which is challenging due to the coupling of resource allocation decisions. In this paper, an edge-cloud cooperative caching scheme is proposed. Specifically, to enable real-time data search, we first introduce a hierarchical indexing framework for cached data, based on which we then devise a search utility model to quantify the expected data freshness and response delay. Aiming at maximizing the search utility, a Caching-assisted Real-time Search (CRS) problem is formulated. Due to its NP-hardness, we devise a greedy-based algorithm to solve the CRS problem. Simulation results demonstrate that the proposed cooperative caching scheme can significantly improve the data freshness and cache hit ratio comparing to the benchmark schemes.

Predicting mobile users' web-access behavior can have substantial impacts on resource allocation and cost reduction for wireless networks. Therefore, we propose a machine learning platform to forecast the web traffic and access time of mobile users. Based on the observation, the traffic patterns exhibit complex dependency on time, location, and popularity of webpages. Thus, a Recurrent Neural Network (RNN) with Long Short Term Memory (LSTM) is developed based on distinct engineered features to learn and predict users' web browsing activities. Then, to forecast the future access-time of mobile users, we propose a Self-exciting Memory Neural Network (SMNN). The access activities are modeled as self-exciting point processes, and intensities are adopted for prediction. Moreover, we extend the proposed predicting framework to cell towers. To cope with the diversity of traffic at the cell tower, we resort to clustering methods to group the similar users of each tower. Then, we develop an LSTM model for each cluster separately to predict the web domain traffic activities for the cell tower. Finally, we show that our proposed models outperform the baseline prediction models based on cellular networks dataset. We also show that for the cell tower access prediction task, the clustering method can significantly improve the prediction accuracy.

Sensor data search is an imminent component for the booming Internet of Things (IoT). Current proposals would refer to either keyword or spatial location, then the matched sensor data should be manually selected by requesters. However, the selection is arduous as there are massive connected devices. To this end, we propose a combinatorial-oriented feedback (COF) mechanism to guarantee the reliability and accessibility of feedback results via enabling an intuitive exhibition of aggregated sensor data. Two critical issues are addressed in this article: 1) sensor data combination and 2) aggregated results ranking. To facilitate the combination process, we first propose two decisive factors for aggregated result evaluation. The multiple sensor-data combinatorial (MSC) problem is converted into a multiobjective optimization model. To balance the tradeoff between competing quality metrics, we introduce Pareto sensor set (PSS) as an optimal solution for MSC problem, and devise the elitist directive breeding (EDB) method to get PSS solutions. In order to speed up the search efficiency and improve the feedback recall, we then develop the fast EDB (FEDB) algorithm, which is able to return top-${k}$ranked results according to different searching requirements. To demonstrate the effectiveness of COF mechanism, we conduct extensive simulations based on a virtual mobile sensing scenario. The results show that our proposed COF mechanism outperforms the state-of-the-art solutions significantly in terms of search efficiency and feedback quality, and specially, FEDB responds quite faster than EDB under the command of top-${k}$ranking.

Technological advances allow perceptual physical objects to be connected to the Internet and share their information over webpages. As a predominant source of public sensor data, automatic discovery of these data is critical and desirable for general Internet of Things search service, which is fundamental to many intelligent applications. However, discovering sensor data from webpages is quite challenging, since there are diverse data presentation modes, and webpage layouts and structures are complicated and heterogeneous. To this end, we explore webpages to discover and collect sensor data under a hierarchical mechanism. In this paper, we first devise novel textual features (TFs) to recognize potential webpages that may contain sensor data; specifically, we construct sensing information corpus to provide keyword reference for the features. Then to get the position of sensor data, we develop granularity adaptive page segmentation (GAPS) algorithm to segment potential webpages into a set of informative blocks; and accordingly, we extract several visual features (VFs) of the blocks so that sensor data can be identified via a block classifier. Based on the novel created sensing information pages dataset, which consists of webpages and manual markings about sensing data, extensive experiments are conducted to evaluate the performance of our exploration methods. Results demonstrate that the TFs achieve supreme performance in sensing data recognition when compared to the state-of-the-art approaches, and GAPS is efficient to locate multimodal sensor data in cooperation with the VFs.