Recent Advances in Electrical & Electronic Engineering (Formerly Recent Patents on Electrical & Electronic Engineering) - Volume 16, Issue 2, 2023

Background: To improve the modeling efficiency of nonlinear load electric energy metering evaluation systems, a method based on an artificial intelligence algorithm was proposed. Methods: First, the artificial glowworm swarm optimization extreme learning machine, a potent tool that employs the artificial firefly algorithm for global optimization, was introduced. Then, the input weighting matrix, hidden layer offset matrix, extreme learning machine model, and hours of training error were determined. Moreover, during a certain time in a specific region of China, power load simulation using an experiment was employed to validate and evaluate the model. Results: The experimental results showed that the traditional back propagation (BP) neural network had the largest prediction relative error, the stability of BP neural network was poor, and the relative error time was large, which was related to the defect of the neural network. The prediction effect of the support vector machine (SVM) method was better than that of the BP neural network because SVM has a strict theoretical and mathematical basis; thus, its generalization ability was better than that of the BP neural network, and the algorithm showed global optimality. Conclusion: The chart analysis showed that the GSO-ELM algorithm performed better in terms of stability as well as test error. The modeling nonlinear load electrical energy measurement and evaluation system based on an artificial intelligence algorithm provides better results and is effective. The proposed algorithm outperforms the contemporary ones.

Aim: A data structure visualisation system uses object-oriented thinking and COM technology to dynamically and interactively simulate and track data structure algorithms and realize the dynamic synchronisation and visualisation of abstract data structures and algorithms using the data modelling function and self-test function. Background: Teaching data structures and algorithms is difficult because of their abstraction and dynamics; the use of icons in classroom teaching can be partially abstracted into intuition, but analysing the instantaneous dynamic characteristics of the object and the dynamic execution process of the algorithm is difficult. Objective: A data structure visualisation system employs a data modelling function, visual data structures, a user-friendly and flexible interface, and multipath features for multilevel users. Such systems can be designed more effectively by using the ant colony algorithm. Methods: The more the ants pass by a certain path, the higher the concentration of residual pheromone, and the higher the probability of the subsequent ant selecting that path. Therefore, the individuals in an ant colony communicate messages and cooperate with each other for foraging. Results: The resulting speedup ratio indicates that the speedup is smaller when the number of nodes is 100 or more; the acceleration is higher when the node reaches a certain scale, and the speedup ratio does not change considerably. In this study, the traffic simulation software VISSIM was used to generate road network data; the generated traffic data were analysed and used to design a traffic network data structure. Conclusion: The traffic network data model oriented to the ant colony algorithm was established through abstraction. Accordingly, a parallel ant colony algorithm based on cloud computing was implemented. Finally, a Hadoop cloud computing platform was established and used to run and test the parallel ant colony algorithm program; several experiments were conducted, and the experimental results were analysed concurrently.

Background: To solve the problem of accurate measurement of nonlinear harmonic electric energy, a method for improving harmonic electric energy measurement based on the discrete wavelet packet decomposition and reconstruction algorithm was proposed. Objectives: A reactive energy measurement method combined with Hilbert transformation was designed, and the frequency characteristics of wavelet function were discussed. An excessively high sampling rate could reduce the accuracy of harmonic power measurement. By setting the discrete wavelet packet transformation decomposition, the stepping of the wavelet form resulting from the excessively large wavelet packet decomposition scale was eliminated using the moncoband reconstruction algorithm. Methods: Experimental results showed that the detection error obtained by numerical simulation using the wavelet transform algorithm was close to the standard instrument, with the maximum reference error of 0.013%-0.030%. Results and Conclusion: The feasibility and measurement accuracy of the nonlinear harmonic electric energy metering system were verified, providing an effective method for accurately detecting the harmonic, interharmonic, and time-varying harmonic components of the electric power system.

Background: The efficiency of wireless sensor networks is limited by limitations in energy supply. Efficient routing strategies should be designed to save and balance the energy consumption of each node in a wireless sensor network. Aim: In this study, a transmission network based on an ant colony algorithm was proposed to meet the power load demands of a city. Objective: Based on the chaos ant colony algorithm, using a combination of wireless sensor network and node residual energy factors, a neighbor selection strategy was proposed. Results: The optimal result was 1896, and additional lines were: N14-15= 2, N4-16= 1, N5-12= 2, N7-13= L, N6-14= 1, N7-8. The coding method of solving transmission network planning based on multi-stage and multi-dimensional control variables was employed to decompose each control variable into two variables. The sum of total weight and non-zero bits was transformed into high-dimensional variables in state transition probability. Conclusion: The key analysis showed that the ant colony algorithm, as a simulated evolutionary algorithm, is an efficient internal heuristic method.

Aim: To explore information leakage tracking algorithms in online social networks and solve the problem of information leakage in the current online social network, a deterministic leaker tracking algorithm based on digital fingerprints is proposed. Background: The basic working principle of the algorithm is that the platform uses plug-ins to embed unique user-identifying information before users try to obtain digital media such as images and videos shared by others on the platform. Objective: Because the scale of users in social networks is extremely large and dynamic, while ensuring the uniqueness of digital fingerprints, it is also necessary to ensure the coding efficiency and scalability of digital fingerprint code words. Methods: Simulation experiments show that 10 experiments are performed on 10,000–100,000 nodes, the Hamming distance threshold is set to 3, and the length of the hash code and the binary random sequence code are both 64 bits. Results: The proposed digital fingerprint fast detection scheme exhibits better performance than conventional linear search. Conclusion: An index table based on hash code and user ID is established and combined with community structure to improve the detection efficiency of digital fingerprints.

Aim: To study the key technology of privacy protection and data security in the Internet of Things group intelligence perception, a cryptographic-based technology was proposed. Background: First, the background of group intelligence perception and three existing problems were briefly introduced, and the inherent contradictions among the three problems, which led to some challenges in this study, were reported. Objective: A network model, a security model, and design goals were constructed, and a solution based on cryptography-related technology was proposed. Methods: The security and cost complexity of the proposed solution was theoretically analysed. The calculation cost of mobile phone measurement verified the practical feasibility of the scheme. Results: When was considerably small, both false positive (FP) and false negative (FN) were small (close to 0). With an increase in , the FP rate increased, and the FN rate became 0. When = 0.5, the FP rate was only 0.1, and the equivalent FN rate was 0 after the user completed 50 tasks. The trust model used was highly accurate. Conclusion: This study has great significance in promoting safe and reliable application development to ensure the genuineness and trustworthiness of data in the aggregation of intermediate data and back-end data services.

Background: Currently, the function of information construction in the supervision and management of construction project quality has become increasingly prominent and cannot be ignored by administrative departments. Objective: This study aimed to effectively supervise and manage engineering safety data and display the system construction intuitively. Moreover, a method based on computer network technology was also proposed. Methods: K-means clustering, random forest, neural network, and other artificial intelligence algorithms were used for data modelling. Evaluation tools, such as the classification model and regression model, were used to evaluate the quality of the developed model, and a power engineering monitoring system was established. The functions of engineering safety supervision and management, data storage and query, graphical deformation display, data analysis and forecast, and report outputs were analyzed. Results: The mean square error of K-means was 7.74, that of the random forest was 27.5, and that of the neural network was 4.4. Conclusion: Neural network offered the smallest error and closest data. The establishment of the system provides a new research platform for the supervision and management of power engineering safety.

Aim: Clustering belongs to unsupervised learning, which divides the data objects into the data set into multiple clusters or classes, so that the objects in the same cluster have high similarity. Background: The clustering of spatial data objects can be solved by optimization based on the clustering objective function. Objective: Study on intelligent analysis and processing technology of computer big data based on clustering algorithm. Methods: First, a new dynamic self-organizing feature mapping model is proposed, and the training algorithm of the model is given. Then, the spectral clustering technology and related concepts are introduced. The spectral clustering algorithm is studied and analyzed, and a spectral clustering algorithm that automatically determines the number of clusters is proposed. Furthermore, an algorithm for constructing a discrete Morse function to find the optimal solution is proposed, proving that the constructed function is the optimal discrete Morse function. At the same time, two optimization models based on the discrete Morse theory are constructed. Finally, the optimization model based on discrete Morse theory is applied to cluster analysis, and a density clustering algorithm based on the discrete Morse optimization model is proposed. Results: This study is focused on designing and implementing a partitional-based clustering algorithm based on big data, that is suitable for clustering huge datasets to meet low computational requirements. The experiments are conducted in terms of time and space complexity and it is observed that the measure of clustering quality and the run time is capable of running in very less time without negotiating the quality of clustering. The results show that the experiments are carried out on the artificial data set and the UCI data set. Conclusion: The efficiency and superiority of the new model, are verified by comparing it with the clustering results of the DBSCAN algorithm.

Background: Buildings, in the traditional sense, are becoming increasingly incapable of meeting modern humans’ pursuit of high-quality living and working environments. With the increasing pace of urban development, modern buildings are becoming increasingly popular. Objective: We investigate an electronic data energy consumption monitoring system based on the construction of Internet of Things for the airport building. Aim: A model based on Dynamic Programming Genetic Algorithm (DPGA) is proposed to generate parameter and service models based on user scenarios. Methods: Two definitions are presented for the communication format between the middleware and the Wireless Sensor Network (WSN); the software and hardware functions of the nodes of the system's WSN are designed, and part of the node is implemented. Finally, the specific implementation of the application program interface and data interface between the modules of the middleware system are described considering the internal environment of a typical office building as an example. The deployment plan of system nodes in specific environments and the division of similar areas are discussed. Results: The platform can strictly monitor and manage energy-consuming equipment. Conclusion: The proposed model can be used to achieve reasonable distribution of energy consumption, energy saving, and humanised and automated energy consumption monitoring functions in the office areas of large office buildings in modern cities.

Aims: To effectively detect vehicle targets in remote sensing images, it can be widely used in traffic management, route planning, and vehicle flow detection. YOLOv3 deep learning neural network, which mainly studies the vehicle target detection in remote sensing images and carries out the target detection suitable for the characteristics of remote sensing images. Objective: This paper studies the information extraction of vehicle high-resolution remote sensing images based on a convolution neural network. Methods: The YOLOv3 network model of vehicle target detection in satellite remote sensing images is optimized. The iterations are set to 50002000045000, and the learning rate is 0.001. At the same time, the comparative experiments of RCNN, Fast RCNN, fast RCNN, and yolov3 network models are carried out. Results: The ca-yolov3 network model can be applied to target detection in satellite images. After 40500 times of learning, the loss function value of the model is reduced to about 0.011. Conclusion: The IOU value of the model also has a good performance in the training process, which makes the yolov3 neural network model more accurate in the image small target detection.