This study aims to explore the application of multimodal deep learning models in power system fault diagnosis. To effectively integrate SCADA time-series data and fault waveform image information, a hybrid deep learning model based on a dual-branch architecture is proposed. The model enhances fault diagnosis accuracy and robustness by performing feature fusion at an intermediate stage. Experimental results show that the proposed multimodal fusion model achieves an accuracy of 96.8% and an F1-Score of 95.7 % on the test set, outperforming both single-modality models and traditional machine learning methods. In particular, the multimodal model achieves a recall rate of over $\mathbf{9 0 \%}$ for complex fault types. Compared to traditional methods, this model not only improves diagnostic accuracy but also significantly accelerates diagnosis speed, completing the diagnosis in 0.18 seconds, a 99.9 % efficiency improvement over the 25 minutes required for manual analysis. Furthermore, the experiments reveal the advantage of image data in complex waveform analysis, while SCADA data plays a crucial role in fault localization for common fault types. This study demonstrates the immense potential of multimodal deep learning in power system fault diagnosis and provides strong technical support for intelligent operation and maintenance.

Motivated by the progress in artificial intelligence such as deep learning and IoT networks, this paper presents an intelligent flink framework for real-time voltage computing systems in autonomous and controllable environments. The proposed framework employs machine learning algorithms to predict voltage values and adjust them in real-time to ensure the optimal performance of the power grid. The system is designed to be autonomous and controllable, enabling it to adapt to changing conditions and optimize its operation without human intervention. The paper also presents experimental results that demonstrate the effectiveness of the proposed framework in improving the accuracy and efficiency of voltage computing systems. Simulation results are provided to verify that the proposed intelligent flink framework can work well for real-time voltage computing systems in autonomous and controllable environments, compared with the conventional DRL and cross-entropy methods, in terms of convergence rate and estimation result. Overall, the intelligent flink framework presented in this paper has the potential to significantly improve the performance and reliability of power grids, leading to more efficient and sustainable energy systems.

Motivated by the progress in artificial intelligence and edge computing, this paper proposes a real-time distributed computing model for low-voltage flow data in digital power grids under autonomous and controllable environments. The model utilizes edge computing through wireless offloading to efficiently process and analyze data generated by low-voltage devices in the power grid. Firstly, we evaluate the performance of the system under consideration by measuring its outage probability, utilizing both the received signal-to-noise ratio (SNR) and communication and computing latency. Subsequently, we analyze the system’s outage probability by deriving an analytical expression. To this end, we utilize the Gauss-Chebyshev approximation to provide an approximate closed-form expression. The results of our experimental evaluation demonstrate the effectiveness of the proposed model in achieving real-time processing of low-voltage flow data in digital power grids. Our model provides an efficient and practical solution for the processing of low-voltage flow data, making it a valuable contribution to the field of digital power grids.

With the continuous development of the Internet, the technical requirements for microgrids are also constantly improving. Today, micropower applications are mainly found in industrial and commercial areas, urban areas and remote areas. With the rapid development of computers and telecommunication equipment, microgrids are also integrated into the fields of computers, control technology, algorithm strategies, etc., and gradually change to the direction of automation. Microgrid technology is becoming a new force in network systems to make up for the deficiencies of traditional networks. Therefore, the development of microgrid is very important to the development of power grid. This paper aims to study the integrated dispatch and control system of microgrid based on dynamic programming algorithm. On the basis of analyzing the comparison between dynamic programming algorithm and other algorithms and the requirements of the integrated system of regulation, the integrated dispatching and control system of microgrid is analyzed. In order to verify the advantages of the proposed algorithm, this paper compares the dynamic programming algorithm with the traditional algorithms GA and PSO. The results show that the dynamic programming algorithm can directly calculate the optimal value of multiple data blocks, which speeds up the convergence process, thus greatly reducing the iteration cycle of the algorithm, and can better meet the needs of automatic power generation instruction cycle.

本文利用I EC国际电力模型标准,通过"云大物移智"等数字化技术,针对"发—输—变—配—用"各电压等级、各业务域数据,通过唯一数据编码系统源,实现数据横向贯通,构建统一的电网资源设备模型维护入口,实现发输变配图模多源异构数据的高度融合.

DCGAN is one of the most commonly used network models at present. DCGAN is not only more stable than the original GAN training, the generated pictures are clear, but also the features generated by DCGAN have the ability to represent. The structure of the ESM in the day-ahead, intra-day and RTMs is also conducive to flexible and adjustable resources to better exert their own value, fully participate in the market, and obtain better economic and environmental benefits. The main purpose of this paper is to study the design of the dispatching model of the electricity trading market based on DCGAN. This paper analyzes the connection mechanism between the DAM and the intraday market considering NE, and constructs a corresponding clearing optimization model. Experiments show that the EM transaction price with CFDs exists is lower than the EM transaction price without CFDs, and e-commerce sellers can make more profits through CFD transactions. In addition, for e-commerce retailers with better unit sales efficiency, trading through CFDs can greatly increase their profits.

Electric power data assets are important resources of electric power companies generated in the process of power generation. This article adopts the construction of an analytic hierarchy model as the evaluation system for the value evaluation of power data assets, simplifies the cost and application components of power data, and uses analytic hierarchy to calculate data asset index weights. Combined with the inherent relationship between the actual system construction investment cost and the data application, the analysis is based on the interval time domain generated by the data application, and finally the score evaluation of the data application investment interval on the value of the data asset is obtained, and then it is provided to assist in improving the overall data asset value Decision-making model.

现有的设备运行故障智能巡检系统,存在着系统运行能耗高的缺陷,为了解决上述问题,引入增强现实技术,设计设备运行故障智能巡检系统.设备运行故障智能巡检系统硬件设计包括增强现实单元、数据采集单元、中央处理单元与故障指示单元,系统软件包括增强现实三维跟踪模块、增强现实显示输出模块、故障特征信息提取与匹配模块和故障智能巡检模块.通过系统硬件与软件的设计,实现了基于增强现实的设备运行故障智能巡检系统的运行.通过实验结果显示:与现有的设备运行故障智能巡检系统相比较,设计的设备运行故障智能巡检系统极大的降低了系统运行能耗,充分说明设计的设备运行故障智能巡检系统具备更好的性能.

研究了虚拟环境在计算机取证调查分析阶段的潜在作用.提出了虚拟环境计算机取证软件工具的一般概念;指出了虚拟环境的局限性,设计了一种同时独立使用传统环境和虚拟环境的新方法,并证明这种方法可以大大缩短计算机取证调查分析阶段的时间.

随着无线网络的崛起与发展,其在各个领域开始广泛应用,为人们的生产和生活带来了极大的便利.然而,无线网络在应用过程中,也出现了一系列的网络安全问题,甚至在可控性方面也与有线网络存在很大差距,因此,关于无线网络的安全问题亟待解决.论文主要概述了无线网络的特点,然后对无线网络存在的安全性问题进行探讨,并提出相应的解决策略,从而促进无线网络的安全运行.