In GNSS Network Real-Time Kinematic (NRTK) positioning, the accuracy of ionospheric delay modeling directly determines positioning performance. During periods of high ionospheric activity, spatial gradients vary rapidly, challenging the planar modeling assumptions of conventional NRTK. To address this issue, this study proposes a crowdsourcing-based method for expressing ionospheric modeling uncertainty. The method introduces user feedback data to supplement the reference station network, forming an overdetermined model even in triangular network units and enabling statistically meaningful estimation of modeling residuals. A weighted interpolation algorithm that considers both angular and distance correlations is then applied to generate a continuous uncertainty field across the service area. Experimental results using Australian CORS data during active ionospheric periods show that the proposed method achieves a high correlation between the Ionospheric Residual Interpolation Uncertainty (IRIU) index and true modeling errors. When incorporated into the ionosphere-weighted RTK model, the adjusted IRIU improves ambiguity resolution success rates to over 95 % and enhances overall positioning accuracy by more than 50 %, demonstrating its effectiveness and robustness under challenging ionospheric conditions.

In order to enhance the efficiency of user task offloading and optimize the overall system performance, this paper introduces a novel optimization approach centered on the simultaneous consideration of delay gain and energy gain associated with user task offloading. The analysis reveals that the optimization challenge can be effectively decomposed into two main sub-problems: joint subchannel and power allocation, and Mobile Edge Computing (MEC) resource allocation.For the joint subchannel and power allocation problem, a power allocation algorithm employing the binary method is employed to efficiently allocate power resources, while the Hungarian algorithm is applied to allocate communication channels. Additionally, the Lagrange multiplier method is incorporated to address the simplified MEC computing resource allocation problem.The simulation results demonstrate the superior performance of the proposed algorithm compared to the loss function minimum gradient method. This optimization framework provides a comprehensive and effective solution for maximizing the offloading gain of user tasks, highlighting its potential for practical implementation in emerging communication systems.

According to the 5G development strategy, the coexistence of URLLC service and eMBB service will become a typical application scenario at the initial stage of 5G deployment. As the two services have the demand of wireless transmission and task computing. Therefore, the services requested by users will generate fierce competition in the limited resources of the communication system. Meanwhile, mobile edge computing (MEC) refers to offloading user computing tasks onto cell edge servers for computing. As a result, MECs not only improve the durability of the device, but also significantly speed up computing. How to reduce energy consumption under the condition of computing task is one of the key points of current academic research. This paper studies the coexistence of eMBB and URLLC services in the MEC scenario, and establishes an optimization problem with the goal of minimizing energy consumption and delay. The problem is decomposed into several convex optimization subproblems, and the iterative method is used to solve the approximate optimal solution. It can be concluded from the simulation diagram that compared with the traditional method, the proposed method has lower energy consumption.

Due to the lack of effective regulatory mechanisms, many risks and offences have emerged in the blockchain trading market. Therefore, in order to achieve anomaly detection for blockchain networks, this paper abstracts blockchain transaction data as a graph structure and proposes GraphAEAtt, a deep learning model based on multi-source embedding and attention mechanism. GraphAEAtt uses two encoders to generate structure embeddings and feature embeddings respectively, and utilizes attention mechanisms to generate composite embeddings. By using multiple embeddings and attention mechanisms, the GraphAEAtt model can integrate the structural information and feature information of the graph, while also learning the relationships between nodes to reduce the impact of abnormal nodes on the learning process. Experimental results on several datasets show that the deep learning model proposed in this paper can better explore the implicit information in blockchain transaction graphs compared to other methods, thereby more accurately identifying abnormal transactions on the blockchain.

Insulator defect detection plays a vital role in maintaining the secure operation of power systems.To address the issues of the difficulty of detecting small objects and missing objects due to the small scale, variable scale, and fuzzy edge morphology of insulator defects, we construct an insulator dataset with 1600 samples containing flashovers and breakages.Then a simple and effective surface defect detection method of power line insulators for difficult small objects is proposed.Firstly, a high-resolution feature map is introduced and a small object prediction layer is added so that the model can detect tiny objects.Secondly, a simplified adaptive spatial feature fusion (S-ASFF) module is introduced to perform cross-scale spatial fusion to improve adaptability to variable multi-scale features.Finally, we propose an enhanced deformable attention mechanism (EDAM) module.By integrating a gating activation function, the model is further inspired to learn a small number of critical sampling points near reference points.And the module can improve the perception of object morphology.The experimental results indicate that concerning the dataset of flashover and breakage defects, this method improves the performance of YOLOv5, YOLOv7, and YOLOv8.In practical application, it can simply and effectively improve the precision of power line insulator defect detection and reduce missing detection for difficult small objects.

The rapidly evolving Industrial Internet of Things (IIoT) is driving the transition from conventional manufacturing to intelligent manufacturing. Intelligent shop scheduling, as one of the essential components of intelligent manufacturing in IIoT, is desired to allocate jobs on different machines to achieve specific production targets. The flow-shop scheduling problem with batch processing machines (FSSP-BPM), which widely exists in real-world manufacturing, requires two distinct but interdependent decisions: batch formation and job scheduling. Existing approaches rely on fixed search paradigms that utilize expert knowledge to find satisfactory solutions. However, these methods struggle to ensure solution quality under real-time constraints due to the varying data distribution and the complexity of large-scale practical problems. To address this challenge, we propose a deep reinforcement learning (DRL) based method. First, we formulate the FSSP-BPM decision process as a Markov Decision Process (MDP) and design the corresponding state, action, and reward. Second, we propose a basic scheduling framework based on an encoder-decoder model with the attention mechanism. Finally, we design a batch formation module and a scheduling module trained on unlabeled multi-dimensional data. Extensive experiments on public benchmark datasets and actual production data demonstrate that the proposed method outperforms baseline algorithms and improves makespan performance by an average of 8.33%.

With the development of artificial intelligence, automobile intelligence has become a new direction for the development of automobile and intelligent industry. At the same time, the Internet of vehicles is an important part of intelligent transportation in the future. Vehicles can use the Internet of vehicles technology to communicate with other road users and infrastructure. As the key technology of 5G network, network slicing can be tailored to the emergence of more and more types of internet of vehicles services, so as to provide better services. Based on K-means++ and Elkan k-means algorithms, cluster analysis is carried out on different types of internet of vehicles services according to the similarity of demands and map them into corresponding slices. Secondly, for resource allocation, this paper adopts adaptive inertial weight particle swarm optimization algorithm (AIW-PSO), which aims at maximizing network utility. Simulation results show that the improved algorithm improves the running time and the speed of approaching the optimal value, and the network utility is also improved compared with the traditional resource allocation method.

With the development of blockchain, cryptocurrencies are also showing a boom. However, due to the decentralized and anonymous nature of blockchain, cryptocurrencies have inevitably become a hotbed for fraudulent crimes. For example, phishing scams are frequent, which not only jeopardize the financial security of blockchain, but also hinder the promotion of blockchain technology. To solve this problem, this paper proposes a graph neural network-based phishing detection method for Ethereum, and validates it using Ethereum datasets. Specifically, this paper proposes a feature learning algorithm named TransWalk, which consists of a random walk strategy for transaction networks and a multi-scale feature extraction method for Ethereum. Then, an Ethereum phishing fraud detection framework is built based on TransWalk, and conduct extensive experiments on the Ethereum dataset to verify the effectiveness of this scheme in identifying Ethereum phishing detection.

New services, such as distributed photovoltaic regulation and control, pose new service requirements for communication networks in the new power system. These requirements include low latency, high reliability, and large bandwidth. Consequently, power heterogeneous communication networks face the challenge of maintaining quality of service (QoS) while enhancing network resource utilization. Therefore, this paper puts forward a highly efficient optimization algorithm for resource slicing and scheduling in power heterogeneous communication networks. Our first step involves establishing an architectural description model of heterogeneous wireless networks for electric power based on hypergraph. This model characterizes complex dynamic relationships among service requirements, virtual networks, and physical networks. The system congruence entropy characterizes the degree of matching between the service demand and resource supply. Then an optimization problem is formed to maximize the system congruence entropy through dynamic resource allocation. To solve this problem, a joint resource allocation and routing method based on Lagrangian dual decomposition is proposed. These methods provide the optimal solutions of the nodes and link mappings of service function chains. The simulation results demonstrate that the proposed algorithm in this paper can greatly enhance resource utilization and also meet the QoS requirements of various services.

In the task of power line inspection, Unmanned Aerial Vehicles (UAVs) are frequently used for capturing images. With the rapid advancement of sensor technology, the spatial, radiometric, and spectral resolutions of UAV images are constantly improving, leading to an increased storage requirement for individual images. Given that UAVs usually operate with limited computational resources, transmission capability and storage space, there are significant challenges in image compression, storage and transmission. This underscores the importance of a high-performance image compression technique. To solve the above problem, we unveil a compression strategy for images that have been acquired through learning utilizing discrete Gaussian mixture-based probability distributions to increase the efficiency of image compression and the fidelity of reconstruction. In addition, to speed up decoding, we employ a parallel context model, which facilitates decoding in a highly parallel manner. Experimental evidence indicates that our approach attains performance that is at the forefront of the field while significantly expediting the decoding process (speeding up the decoding process by more than 49.78%) in our experiments, outpacing traditional coding standards and existing learned compression approaches by 5.75 dB and 1.23 dB in PSNR.

The unprecedented prosperity of the Industrial Internet of Things (IIoT) promotes the traditional industry transforming into intelligent manufacturing so that the whole production process can be comprehensively controlled to achieve flexible production. Intelligent scheduling, as one of the key enabling techniques, is desired to allocate the production of several machines by an efficient solution with minimum makespan. Existing approaches adopt a fixed search paradigm based on expert knowledge to seek satisfactory solutions. However, considering the varying data distribution and large sized of the practical problems, these methods fail to guarantee the quality of the obtained solution under the real-time requirement. To address this challenge, we formulate the production scheduling problem as a Markov decision process (MDP) and specifically design a job scheduling model made up of a job batching module for the hybrid flow-shop scheduling problem on batch processing machines (HFSP-BPM). Our proposed model consists of an actor network that learns the action under different conditions and a critic network that evaluates the action of the actor. We analyze the convergence of the model under different parameter settings to determine the optimal parameter. Extensive numerical experiments on both publicly available data set and real steel plant production data set demonstrate that the proposed deep reinforcement learning (DRL) approach compared with other baselines, more than 6% average improvements can be observed in many instances.

The integration of multiple wireless communication systems based on 5G is an important development trend for achieving comprehensive coverage of communication networks in power systems. However, current time synchronization in the power system cannot meet the service requirements of high reliability and low latency in 5G integrated communication networks, which is characterized by wireless link and dynamize topology. In this paper, a time synchronization architecture based on 5G-MEC and integrated wireless self-organized networks is proposed to meet the time synchronization requirements of 5G integrated communication networks. Also, by constructing synchronous message passing and error compensation as virtual network services, a VNF deployment method that considers resource constraints, latency requirements, and wireless self-organized network topology is designed. Finally, in order to solve the problem of delay jitter, a time synchronization error compensation method based on diffusion Kalman filter is proposed. Simulation results show that the method proposed can effectively improve the number of synchronized service users and success rate, reduce delay jitter, and improve synchronous accuracy of power services.

With the development of the Internet of Things in power, the complexity of business transmission in the network has increased, and traditional routing schemes are difficult to meet the specific needs of sea volume business in 5G scenarios. This article defines the concept of a virtual routing plane for 5G fusion networks from the perspective of differentiated services. Based on the divisible characteristics of the underlying physical network, corresponding virtual routing planes are established based on the needs of different services to transmit different types of services. According to the change of service requirements, the set of virtual routing planes is adjusted. This paper proposes an adaptive Dynamic routing algorithm based on virtual routing planes. Finally, the effectiveness of the proposed algorithm in resource utilization and throughput was verified through experiments.

Lightweight service identification models are very important for resource-constrained distribution grid systems. To address the increasingly larger deep learning models, we provide a method for the lightweight identification of complex power services based on knowledge distillation and network pruning. Specifically, a pruning method based on Taylor expansion is first used to rank the importance of the parameters of the small-scale network and delete some of the parameters, compressing the model parameters and reducing the amount of operation and complexity. Then, knowledge distillation is used to migrate the knowledge from the large-scale network ResNet50 to the small-scale network so that the small-scale network can fit the soft-label information output from the large-scale neural network through the loss function to complete the knowledge migration of the large-scale neural network. Experimental results show that this method can compress the model size of the small network and improve the recognition accuracy. Compared with the original small network, the model accuracy is improved by 2.24 percentage points to 97.24%. The number of model parameters is compressed by 81.9% and the number of floating-point operations is compressed by 92.1%, making it more suitable for deployment in resource-constrained devices.

室内定位服务是电网系统运行的关键环节之一，提供基于位置的服务可以有效帮助运检、安监和基建等电力系统运作流程。提出一种基于深度学习的视频定位系统，采用YOLO目标检测算法和深度简单在线实时跟踪算法，实现了对于室内人员的精准定位。在YOLO主干网络部分中加入了CBAM（Convolutional Block Attention Module）注意力机制模块以及GhostBottleneck轻量化模块，验证了不同模型类型下的检测效果并实现了性能的优化。提出了一种基于无损卡尔曼滤波（Unscented Kalman Filter, UKF）的北斗伪卫星系统与视频定位的融合方法，可以实现2种定位结果的融合。实验表明，基于深度学习的视频定位与北斗伪卫星的融合室内定位方法解算精度较高、稳定性较强，可以满足电力系统的室内定位需求。

With the rapid development of China's economy, the whole society's demand for electricity is becoming more and more extensive. Insulator is the guarantee of smooth operation of transmission line, and is also one of the equipment which is prone to failure. How to detect insulator damage with high precision and high efficiency and repair it is one of the key factors of unimpeded power. This paper proposes a method for detection of insulator damage based on improved YOLOv4-tiny network. This method is mainly aimed at improving the main feature extraction module and feature fusion module of traditional YOLOv4-tiny network. In order to solve the problem of missing detection of small targets, adaptive attention mechanism is introduced to improve the module of feature extraction to improve the accuracy of detection. In addition, in order to further improve the detection accuracy of insulator damage and balance the detection time, a multi-attention CSAR model is proposed to improve the performance of the feature fusion module. Finally, images collected from different weather conditions are used as test sets to verify the effect of the improved model proposed in this paper through experiments. According to the experimental results, the detection accuracy of the proposed method can reach 98%, and the detection time is controlled within 10ms, which meets the basic requirements of detection of insulator damage.

Abstract The significant changes brought by block-chain technology have posed many challenges to financial services, ecological security, and privacy protection. Therefore, in order to achieve intelligent block-chain supervision and assess the risk of potential money laundering, terrorist financing, and other financial crimes of customers, anomaly detection of blockchain networks is required. Structurally, blockchain data is essentially represented by a graph, where nodes represent addresses and edges represent behaviors such as transactions, and the model after constructing the transaction graph can extract high-dimensional features in the graph structure relationships. Existing anomaly detection methods ignore the interaction information between network structure and node attributes and have limited ability to detect anomalies. Based on this, this paper proposes GraphAEAtt, a deep learning framework based on self-encoder and attention mechanism, which consists of a structural auto-encoder and an attribute auto-encoder to jointly learn node and attribute feature vector representations, and in addition, introduces an attention mechanism to learn the correlation between nodes and their neighboring nodes. First the structural encoder converts the observed raw node attributes into a vector representation of the low-dimensional potential space, and then the shared attention mechanism is used to aggregate the embeddings of all neighboring nodes to finally generate node embedding. The attribute encoder uses a multi-layer perceptron to map the observed attribute data into a potential attribute embedding representation. Then, a structure decoder is used to reconstruct the adjacency matrix and an attribute decoder to reconstruct the attribute matrix, and the reconstruction error of the nodes is measured from both structure and attribute perspectives as the objective function for neural network training. Then anomaly detection is implemented based on the reconstruction error of the nodes measured from both structure and attribute perspectives. Finally, a large number of experiments are conducted to verify the effectiveness of the proposed method in real datasets.

Abstract The significant changes brought by block-chain technology have posed many challenges to financial services, ecological security, and privacy protection. Therefore, in order to achieve intelligent block-chain supervision and assess the risk of potential money laundering, terrorist financing, and other financial crimes of customers, anomaly detection of blockchain networks is required. Structurally, blockchain data is essentially represented by a graph, where nodes represent addresses and edges represent behaviors such as transactions, and the model after constructing the transaction graph can extract high-dimensional features in the graph structure relationships. Existing anomaly detection methods ignore the interaction information between network structure and node attributes and have limited ability to detect anomalies. Based on this, this paper proposes GraphAEAtt, a deep learning framework based on self-encoder and attention mechanism, which consists of a structural auto-encoder and an attribute auto-encoder to jointly learn node and attribute feature vector representations, and in addition, introduces an attention mechanism to learn the correlation between nodes and their neighboring nodes. First the structural encoder converts the observed raw node attributes into a vector representation of the low-dimensional potential space, and then the shared attention mechanism is used to aggregate the embeddings of all neighboring nodes to finally generate node embedding. The attribute encoder uses a multi-layer perceptron to map the observed attribute data into a potential attribute embedding representation. Then, a structure decoder is used to reconstruct the adjacency matrix and an attribute decoder to reconstruct the attribute matrix, and the reconstruction error of the nodes is measured from both structure and attribute perspectives as the objective function for neural network training. Then anomaly detection is implemented based on the reconstruction error of the nodes measured from both structure and attribute perspectives. Finally, a large number of experiments are conducted to verify the effectiveness of the proposed method in real datasets.

With the vigorous promotion of informatization, intelligence and ubiquity of power grid services, the flexible extension and extensive coverage of the end of power communication networks through the introduction of integrated communication terminals has become an important development direction. The deployment of integrated communication terminals affects the access range and service QoS of power service terminals. To address this issue, this paper investigates the deployment of multi-link integrated communication terminals in 5G integrated power communications network and proposes a multi-link integrated communication terminal deploying method to support the wide coverage of power 5G. Firstly, a multi-link optimization model for wide coverage 5G integrated networks containing coverage indicator, multi-service QoS indicator and cost indicator is constructed to optimize the location deployment scheme of integrated communication terminals. Based on this, an improved artificial fish swarm-based multi-link integrated communication terminal location deployment optimization algorithm is proposed to solve the high-dimensional decision space optimization problem of integrated communication terminal deployment. Simulation results show that the algorithm proposed in this thesis can rapidly find the optimal integrated communication terminal deployment location with limited cost budget, significantly improve the network coverage and service QoS indicator.

The unprecedented prosperity of the industrial internet of things (IIoT) has opened up a new path for the traditional industrial manufacturing model.Intelligent shop scheduling is one of the key technologies to achieve the overall control and flexible production of the whole production process.It requires an effective plan with a minimum makespan to allocate multiple processes and multiple machines for production scheduling.Firstly, the shop scheduling problem was defined as a Markov decision process (MDP), and a shop scheduling model based on the pointer network was established.Secondly, the job scheduling process was regarded as a mapping from one sequence to another, and a new shop scheduling algorithm based on deep reinforcement learning (DRL) was proposed.By analyzing the convergence of the model under different parameter settings, the optimal parameters were determined.Experimental results on different scales of public data sets and actual production data sets show that the proposed DRL algorithm can obtain better performances.