Knowledge graph (KG) technology is a newly emerged knowledge representation method in the field of artificial intelligence. Knowledge graphs can form logical mappings from cluttered data and establish triadic relationships between entities. Accurate derivation and reasoning of knowledge graphs play an important role in guiding power equipment operation and decision-making. Due to the complex and weak relations from multi-source heterogeneous data, the use of KGs has become popular in research to represent potential information in power knowledge reasoning. In this review, we first summarize the key technologies of knowledge graph representation and learning. Then, based on the complexity and real-time changes of power system operation and maintenance, we present multiple data processing, knowledge representation learning, and the graph construction process. In three typical power operation and fault decision application scenarios, we investigate current algorithms in power KG acquisition, representation embedding, and knowledge completion to illustrate accurate and exhaustive recommendations. Thus, using KGs to provide reference solutions and decision guidance has a significant role in improving the efficiency of power system operations. Finally, we summarize the achievements and difficulties of current research and give an outlook for future, promising roles of KG in power systems.

Electrical impedance tomography (EIT) is a state-of-the-art noninvasive imaging method, which is sensitive to the dynamic changes of the lung impedance. However, the nonlinear ill-posed mathematical problem limits its spatial resolution. In order to generate reliable reconstruction image of EIT, a supervised deep convolutional neural network (CNN)—V-shaped dense denoising net (VDD-Net) is proposed in this article, which consists of four blocks sequentially, i.e., preimaging block, feature extraction block, image reconstruction block, and image denoising block. The conjugate gradient algorithm is utilized in preimaging block to map the boundary voltage to the conductivity distribution, and the postprocess block based on deep CNN is used to filter the artifacts of the initial reconstructions and obtain the sharp features in the region of interest. The images reconstructed by VDD-Net are also compared with these of Tikhonov regularization, convolutional neural network, and V-Net methods. The resolution of the reconstruction images can reach 256 $\times256$ . The reconstruction quality is quantitatively measured by relative error (RE), structural similarity indices (SSIM), distortion (DT), and widening (WD). On average, the VDD-Net achieves 0.140 RE, 0.961 SSIM, 0.167 DT, and 0.985 WD through experimental reconstructions. These results demonstrate that VDD-Net is promising in EIT for expressing the nonlinear mapping between the measurements and the parameters in the observation domain.

Electrical impedance tomography (EIT) is an effective technique for real-time monitoring, visualization, and analysis of industrial process in a noninvasive manner. However, due to the nonlinear and “soft-field” nature of its inverse problem, image reconstruction of EIT is always limited in image resolution and, in particular, the accuracy of identifying object boundaries. In order to solve the above problems, a novel multilayer autoencoder (MLAE) image reconstruction network that consists of a feature extraction module and an image reconstruction module is proposed. In the proposed method, hierarchical structures are applied to increase the forward information flow and the selected appropriate hidden layers can solve the disappearance of the reverse gradient flow. The training process of MLAE containing self-supervised pretraining and supervised fine-tuning can provide better complex nonlinear mapping and improve the model performance. The experimental and analytical results prove that the MLAE image reconstruction method can obtain higher quality images than the typical algorithms and certain methods based on deep learning.

Electrical impedance tomography (EIT) is a promising functional and structural imaging method in process tomography. However, due to the ’soft-field’ nature and the high dependence on the prior information, it often suffers serious artifacts in quantitative analysis. Most recently, EIT image quality has improved significantly because of the state-of-the-art deep learning-based models in the aspect of solving the inverse problem, especially fully convolutional networks (FCN) and V-Net variants. Despite their success, these deep convolutional networks (CNNs) have two limitations: (1) The long-range information transition is frequently lost and the reverse gradient often disappears in deep CNNs; (2) Some novel skip connections, such as residual and dense connections, often occupy substantial computational resources. To overcome these two limitations, we propose V ² A-Net, a new neural architecture based on redesigned feature transited connections by the terms of (1) A pre-reconstructor based on the iterative Newton-Raphson method, which maps the nonlinear function between the measurements and the initial images, (2) Dual cascaded V-Net are combined, which play the role of an encoder and a decoder, respectively, (3) A new parallel attention mechanism via channel attention and coordinate attention to learn the conductivity distributions and boundary-shaped feature separately, and (4) the light-weight skip connections reduce the computational resources (or accelerate the inference speed) of EIT imaging. The V ² A-Net is evaluated by using the multi-phase flow industrial applications, and the results demonstrate that (1) V ² A-Net has better performance in shape reconstruction with sharp ’corner’, (2) V ² A-Net could reconstruct the model accurately where it has some low-contrast conductivity distributions, (3) V ² A-Net enhances the quality of interfaces with the stratified flow, and (4) the pruned V ² A-Net achieves significant speedup compared with the VDD-Net or V ² DNet. The analyses show that the average relative error is 0.05, the average correlation coefficient is 0.92, the average structural similarity is 0.92 on the testing datasets. In addition, the average relative cover ratio is 0.97 and the average relative contrast ratio is 0.98 on the testing datasets.

Recent research has demonstrated the vulnerabilities of cyber physical microgrid to different rates of denial-of-service (DoS) attacks, which send internal requests to degrade the victim’s performance. However, the interaction between the attacks and the security of microgrid remains largely unknown. In this paper, we address two fundamental questions: (1) What is the impact of intermittent DoS (IDoS) attacks on the security of cyber physical microgrid and (2) how can we analyze the stability of the cyber physical microgrid under IDoS attacks? To tackle these problems, we firstly model the cyber physical microgrid system considering the IDoS attacks on the network server. Based on the model, the interaction between the cyber system and the physical system is analyzed. Then, the impacts of IDoS attacks on the security of the cyber physical microgrid system are studied. It shows that the attack may lead to the system level oscillation with the information variation during the attack period. Therefore, a risk assessment method is proposed to investigate the stability of the cyber physcial microgrid system under IDoS attacks. Lastly, the proposed methodology is verified by simulation results.

This paper considers the problem of distributed frequency regulation based on the consensus control protocol in smart grids. In this problem, each system component is coordinated to collectively provide active power for the provision of ancillary frequency regulation service. Firstly, an approximate model is proposed for the frequency dynamic process. A distributed control algorithm is investigated, while each agent exchanges information with neighboring agents and performs behaviors based on communication interactions. The objective of each agent is to converge to a common state considering different dynamic load characteristics, and distributed frequency control strategy is developed to enable the agents to provide active power support. Then, the distributed proportional integral controllers with the state feedback are designed considering the consensus protocol with topology . The theory of distributed consensus protocol isfurther developed to prove the stability of the proposed control algorithm. Whenproperly controlled, the controllers can provide grid support services in a distributed manner that turn out the grid balanced globally. Finally, simulations of the proposed distributed control algorithm are tested to validate the availability of the proposed approach and the performance in the electrical networks.