Microgrids based on distributed control are susceptible to cyber attacks during operation, which can result in system anomalies, crashes, and even equipment damage. To ensure a secure collaborative environment, this paper proposes an attack detection mechanism based on extended cell similarity. First, a DC microgrid model and a network attack model were established. Secondly, a microgrid state interval prediction mechanism based on QRLSTM is proposed. The output of the load prediction model is used as the input of the mechanism model, and the expected state range of the terminal equipment voltage and current is obtained through simulation. Then, the cell similarity algorithm is improved to relate the similarity between the actual measured data and the expected period to the probability of cyber attacks occurring. Finally, the effectiveness and feasibility of the detection method were verified through experiments.

Grid operation state estimation of power grid operating states and power system analysis largely relies on physical layer measurements of the power system. However, the introduction of information and communication technologies in smart grids has greatly improved operational efficiency while also increasing the system’s vulnerability to attack. This can compromise data integrity and reliability, leading to data missing and then affecting subsequent steps. Additionally, data collection and transmission can encounter various issues, resulting in partial data loss or errors. Therefore, it is crucial to recover and complete the missing data.This paper proposes a solution for missing data recovery in power systems based on generative adversarial network (GAN). The approach utilizes graph convolutional network (GCN) to extract features from data, taking into account the topological connectivity between nodes. To improve the quality of data imputation and enhance the authenticity of recovered data, incomplete data containing nodes with missing data and observable nodes is used as input for the generator, and a local feature extractor is added to the existing discriminator network. This structure allows the generator to estimate unknown information by observing known data, while the discriminator focuses more on the local areas containing the recovered data when determining the authenticity, thereby helping the generator to improve its data completion capability. Correspondingly, we design context loss constraints considering both local and global ranges to ensure accurate recovery of non-missing node data while completing the missing data portions.The experimental results demonstrate that employing GCN and incorporating local features can significantly enhance recovery performance on grid data. For voltage magnitude, the mean absolute error decreased by 10.4335%. Additionally, high-precision recovery results can still be achieved even with up to half data missing, which is validated on the IEEE-14 system.

The energy scheduling strategy for microgrids based on reinforcement learning plays a very crucial role in realizing low-carbon and economic energy utilization. Considering the traditional reinforcement learning is difficult to meet the operational constraints of microgrids, this paper proposes a safety reinforcement learning method based on proximal policy optimization. Firstly, ladder-type carbon trading is introduced to strictly constrain the system carbon emission. Then, a safety proximal policy optimization method is proposed that incorporates a safety network to decouple the economic and safety factors in the traditional reward composition. Finally, experiments are conducted on real-world datasets to verify the effectiveness of the proposed algorithm. The experimental results illustrate that the proposed safety reinforcement learning method is able to minimize the economic cost and carbon emission of microgrid scheduling while strict guaranteeing safety compared to existing methods.

In the current era, a Li-ion battery pack, typically comprised of multiple cells, can offer higher voltage and output power. This plays a crucial role in various applications, including electric vehicles and energy storage. Accurate estimating the battery pack's state of charge (SOC) is crucial to offer users a clearer understanding of the battery status and to alleviate range anxiety. In the industry, it's common practice to precisely estimate the SOC for each cell, enabling an accurate assessment of the battery pack's overall SOC. However, most current methods for estimating the SOC in battery packs are centralized. In such cases, a problem with estimating the SOC of a single cell can greatly impact the overall SOC estimation of the entire battery pack. Likewise, if centralized equipment encounters issues, the SOC estimation for the entire battery pack is likely to be interrupted. This paper presents a distributed method for estimating battery pack SOC, utilizing a digital twin-based simulation platform. In the following, the each node that measures the SOC of cell is regarded as an agent that can communicate. Through communication among agents, each agent can converge to a reliable battery pack SOC estimation. In the event of a sudden issue arising in the SOC estimation of a cell, the proposed method can still uphold a dependable estimate of the battery pack's SOC, thereby bolstering the overall robustness of the SOC estimation system for the entire battery pack.

With the integration of advanced communication and sensor technologies, traditional power grids are shifting to automated smart grids, while exacerbating the risk of cyber-attacks. This paper proposes a spatio-temporal graph attention network to improve invisible attack detection in smart grids. First, graph theory and grid knowledge are utilized for modeling in order to learn graph structure and spatial features. Secondly, hidden features are extracted based on the graph attention mechanism to predict the future behavior of nodes. Thirdly, graph deviation score is calculated from the end-to-end learned node deviations, which is the judgement for identifying attacks. Simulation results demonstrate that our method identify attacks more accurately than baseline methods.

Supercapacitors, leveraging their distinctive characteristics and advantages, have evolved into efficient energy storage solutions. State of Charge (SOC) is a crucial parameter for supercapacitors, and the estimation of SOC for individual supercapacitor cells has been extensively researched. In practical applications, it is common to assemble hundreds or even thousands of cells to form a supercapacitor pack, particularly in fields like electric vehicles a nd electric b uses. Therefore, estimating the SOC for the supercapacitor pack becomes imperative. In response to the demands for supercapacitor pack SOC$(SOC_{pack})$estimation and wireless management, this paper proposes a distributed method. After modeling the supercapacitor cells, the definition of$SOC_{pack}$is introduced. The SOC of a cell in the definition is estimated based on Kalman filter. The proposed distributed method relies on wireless communication and computational updates between cells. Through iterative processes, it ultimately converges to the estimated$SOC_{pack}$. Finally, we conducted simulation experiments to analyze the performance of the proposed method under various communication conditions, thereby validating its effectiveness and robustness.

The integration of advanced communication and information technologies in smart grids has led to enhanced efficiency and reliability but also introduced security vulnera-bilities, prompting the need for robust cyber attack detection methods. Traditional approaches struggle to capture evolving attack patterns and handle high-dimensional data, highlighting the necessity for more sophisticated approaches. A neighbor-hood reconstruction-based smart grid attack detection scheme based on subgraphs is proposed. By leveraging Graph Neural Networks (GNNs), the challenge of capturing complex inter-dependencies among grid nodes is addressed. This approach employs unsupervised learning principles, training the model solely on normal data and utilizing the reconstruction error of node features to detect attacks. Additionally, by subgraph sampling and feature suppression, the model's ability to utilize neighborhood information is enhanced, thereby further improving detection effectiveness. Simulation results on IEEE 30-bus and IEEE 118-bus power system demonstrate the feasibility of the method, achieving a detection accuracy of 96.67% and 97.46%, respectively.