Table of Content

28 December 2024, Volume 57 Issue 12

Previous Issue    Next Issue

Power & Load Forecasting Technology in New Power Systems

The Application of Graph Neural Networks in Power Systems from Perspective of Perception-Prediction-Optimization

Zhuo LI, Yinzhe WANG, Lin YE, Yadi LUO, Xuri SONG, Zhenyu ZHANG

2024, 57(12):  2-16.  DOI: 10.11930/j.issn.1004-9649.202410093

Asbtract ( )   PDF (4100KB) ( )  

Figures and Tables | References | Related Articles | Metrics

With the increasing uncertainty of the generation, transmission, and consumption sides in new power systems, the complexity and scale of power system topology relationship are continuously growing. Conventional data analysis methods for Euclidean space often exhibit poor performance and low accuracy when representing the topological structures relationship with multi-source heterogeneous and irregular characteristics. Graph Neural Networks (GNNs) are capable of capturing complex dependency relationship between different nodes and edges, and effectively mining spatiotemporal features in non-Euclidean data structures, are therefore suitable for the perception and modeling of complex power system topologies. In this context, this paper builds upon previous research progress, providing the definition and characteristics of GNNs, and discussing the unique features and advantages of different variants GNNs. After that, it summarizes the current applications of GNNs in power system state perception, prediction, and graph-based power flow calculation, aiming to explore the suitability of GNNs for new power systems from the perception-prediction-optimization perspectives. Finally, a summary and outlook on the potential challenges and future development directions for GNNs are provided.

Daily Power Scenario Generation Method for Multiple Wind Farms Based on Gaussian Mixture Clustering and Improved Conditional Variational Autoencoder

Dan LI, Yunyan LIANG, Shuwei MIAO, Zeren FANG, Yue HU, Shuai HE

2024, 57(12):  17-29.  DOI: 10.11930/j.issn.1004-9649.202311050

Asbtract ( )   PDF (4972KB) ( )  

Figures and Tables | References | Related Articles | Metrics

The integration of a large number of wind farms with uncertain output into the power grid will bring potential hazards in operation and uncontrollable risks. The uncertainty of wind power output is described by uncertain scenario sets generated from the variational autoencoder-based scenario generation method. Aimed at the complex spatiotemporal correlation of multi-wind farm output and the possible "KL collapse" during the traditional variational autoencoder model training, this paper proposes a daily scenario generation method of spatiotemporal power based on the Gaussian mixture model and improved conditional variational autoencoding. The two-dimensional convolution technique is introduced to extract the spatiotemporal correlation for dimension reduction, and the maximizing min-angle regularization technique is used to strengthen the independence of latent features. Hyperspherical distribution, instead of Gaussian distribution, is used to avoid "KL collapse" and improve the stability and accuracy of scene generation training. In addition, considering the diversity and flexibility of daily power scenarios of multi-wind farm, Gaussian mixture clustering technology is introduced to generate uncertain scenario sets with differentiated and changing characteristics, enabling the generation of certain scenario sets with varied characteristics according to specific condition labels. The results of real examples show that compared with conventional methods, the proposed method reduces the accumulated error distribution of probability by 17% to 71%, and the average error of temporal and spatial correlation by 85% to 97% and 55% to 91%, respectively. Besides, the proposed method can accurately generate daily power scenario sets of multi-wind farm in different wind conditions, improving scene generation's diversity and flexibility.

A Multi-stage Scenario Tree Generation Method for Wind-Solar Load Based on Complex Feature Extraction and Sinkhorn Distance

Rui WANG, Zhixin FU, Jian WANG, Haoming LIU

2024, 57(12):  30-40.  DOI: 10.11930/j.issn.1004-9649.202402033

Asbtract ( )   PDF (4135KB) ( )  

Figures and Tables | References | Related Articles | Metrics

The uncertainty in the long-term growth of renewable energy generation output and load has heightened the complexity of power grid planning. Conducting an uncertainty analysis on the long-term scale of renewable energy output and load is of significant importance for the planning and construction of the power grid. To address this issue, a multi-stage scenario tree generation method for wind-solar load based on complex feature extraction and Sinkhorn distance was proposed. Firstly, to enhance the clustering efficiency of wind-solar load scenarios, a method based on stacked sparse autoencoders for feature extraction of wind-solar load scenarios was introduced. The feature set of wind-solar load scenarios was clustered by using an improved affinity propagation algorithm based on density peak, and typical curves of wind-solar load were obtained as the root nodes of the scenario tree. Subsequently, by considering different growth rates in load, a yearly generation of wind-solar load scenario trees was performed, and a scenario tree reduction method based on Sinkhorn distance was proposed to reduce the size of the scenario tree. Finally, a simulation example showed that the proposed method had high calculation efficiency, and the generated multi-stage scenario tree for wind-solar load can reflect the uncertainty of wind-solar output and load growth.

Photovoltaic Power Prediction Model Based on TDE-SO-AWM-GRU

Hanzhang LI, Jiangtao FENG, Pengcheng WANG, Haojie RONG, Yuhuan CHAI

2024, 57(12):  41-49.  DOI: 10.11930/j.issn.1004-9649.202401015

Asbtract ( )   PDF (4041KB) ( )  

Figures and Tables | References | Related Articles | Metrics

Accurate prediction of photovoltaic (PV) power is of great significance for the safe and economic operation of power grids, but PV power generation is characterized by time-varying, intermittent, fluctuating, and high nonlinearity characteristics due to the combined effects of multiple meteorological factors, which makes it difficult to deeply explore the implicit information of the data. To solve such problems, a PV power prediction model based on time-varying data enhancement (TDE), snake optimizer (SO), adaptive weight module (AWM), and gated recurrent unit (GRU) was proposed. The expression of data features was improved by TDE with strong correlation, and a new input matrix was constructed. Then, the enhanced input matrix was automatically weighted by AWM and entered into GRU for prediction. At the same time, by considering the difficulty of hyperparameter selection of the combined model, SO was introduced to find the optimal threshold of the model to maximize the performance of the model. Finally, the model was validated using actual data from a PV power station, and the results show that the proposed model can effectively improve the prediction accuracy of PV power.

Ultra-short-term Probabilistic Forecasting of Distributed Photovoltaic Power Generation Based on Hierarchical Correlation Modeling

Can CHEN, Zinuo SU, Yuan MA, Jialin LIU, Yuqing WANG, Fei WANG

2024, 57(12):  50-59.  DOI: 10.11930/j.issn.1004-9649.202405022

Asbtract ( )   PDF (3902KB) ( )  

Figures and Tables | References | Related Articles | Metrics

Accurate probabilistic forecasting of regional distributed photovoltaic (PV) power can provide more comprehensive information support for the optimal operation of active distribution networks. When meteorological measurement or forecasting data is lacking, mining and utilizing spatio-temporal correlation information of distributed PV can effectively improve power forecasting accuracy. However, existing research either struggles to specifically mine spatio-temporal correlation information or loses a significant amount of valuable information during the modeling process. To address this, a method for ultra-short-term probabilistic forecasting of regional distributed PV power based on hierarchical correlation modeling is proposed. Firstly, a clustering method based on deep consistency is employed to divide the distributed PV clusters into subregions, which supports targeted modeling of the spatio-temporal correlations within the subregions. On this basis, a hierarchical graph structure is constructed to simultaneously model the intra-subregion and inter-subregion spatio-temporal correlations, enabling effective utilization of correlation information across different hierarchical levels. Then, a probabilistic forecasting model based on hierarchical graph convolutional neural networks (GCNs) is proposed to mine deep spatio-temporal correlation features between PV power stations, thereby enhancing the accuracy of ultra-short-term probabilistic forecasting of regional distributed PV power. Finally, the effectiveness of the proposed method is validated using actual distributed PV power data sets.

Distributed Photovoltaic Ultra-short-term Power Forecasting Method Based on Temporal Analog Matching Approach and Transformer Network Modeling

Pengwei YANG, Liping ZHAO, Junfa CHEN, Zhao ZHEN, Fei WANG, Liming LI

2024, 57(12):  60-70.  DOI: 10.11930/j.issn.1004-9649.202403112

Asbtract ( )   PDF (4709KB) ( )  

Figures and Tables | References | Related Articles | Metrics

To address the challenge of low prediction accuracy of distributed photovoltaic (PV) power generation under sudden weather change scenarios due to the lack of meteorological data, this paper proposes a distributed PV ultra-short-term power prediction method based on temporal analog matching approach (TAMA) and Transformer network modeling. Firstly, the concept of similar time periods is extended from days to more flexible time periods, and a matching strategy integrating historical power and satellite remote sensing information is proposed to efficiently identify the most critical time periods of similar power for prediction without relying on meteorological data. Based on this, the powerful temporal modeling capability of the Transformer network is used to dynamically resolve the hidden correlations in multi-source similar time periods, and deeply mine the key features of power, thus providing more accurate ultra-short-term power prediction for distributed PV systems under sudden weather change conditions. Finally, the effectiveness of the proposed method is verified through actual distributed PV power generation data.

Short Term Photovoltaic Power Combination Prediction Method Based on Similar Day Selection and Data Reconstruction

Qingbin CHEN, Genghuang YANG, Liqing GENG, Juan SU, Jingsheng SUN

2024, 57(12):  71-81.  DOI: 10.11930/j.issn.1004-9649.202406005

Asbtract ( )   PDF (3772KB) ( )  

Figures and Tables | References | Related Articles | Metrics

A short-term photovoltaic power combination prediction method based on similar day selection and data reconstruction is proposed to address the strong randomness of photovoltaic power. Firstly, clustering analysis of photovoltaic power is performed using the kernel fuzzy C-means algorithm, and the main influencing features are extracted through the maximum information coefficient. Secondly, the cooperative game theory is used to calculate the comprehensive correlation coefficient between the predicted days and the historical days, and the historical days with strong correlation are selected to construct the training set. Then, the variational mode decomposition method is used to decompose the photovoltaic power into several subsequences, and the permutation entropy is calculated and reconstructed into trend, low-frequency, and high-frequency terms. Finally, the long short-term memory neural networks are used to predict the trend and low-frequency items, while the convolutional neural network-bidirectional long short-term memory-attention models are used to predict the high-frequency items. The final prediction result is obtained by overlaying the results. Through practical examples, it has been verified that under different weather conditions, the overall prediction error of the model is the smallest, which can effectively improve the prediction accuracy.

Power System

Aggregation and Operation Key Technology of Virtual Power Plant with Flexible Resources in Electricity Market Environment: Review

Zhongkai YI, Langbo HOU, Ying XU, Yongfeng WU, Zhimin LI, Junfei WU, Teng FENG, Liu HAN

2024, 57(12):  82-96.  DOI: 10.11930/j.issn.1004-9649.202409025

Asbtract ( )   PDF (2842KB) ( )  

Figures and Tables | References | Related Articles | Metrics

The rapid development and increasing number of flexible resource technologies offer immense potential for enhancing the flexibility and economic efficiency of power systems. Virtual power plants (VPPs) provide an effective means for supporting the participation of massive, heterogeneous, and decentralized resources in power market transactions through coordinated management and aggregated control of these resources. Addressing issues such as the difficulty in efficiently managing diverse and massive heterogeneous flexible resources within VPPs in the power market environment, benefit conflicts among different operating entities, and the coupling relationship between energy and ancillary services, this paper analyzes and summarizes the technical challenges, current research progress, and future research directions in the end-to-end operation of flexible resource VPPs in the power market environment. The analysis focuses on three aspects of flexible resource VPPs: aggregated modeling, bidding strategies, and operational control. It systematically summarizes the model characteristics, correlations, and applicable scenarios of relevant mainstream technological approaches. This comprehensive understanding of the key scientific issues, core theoretical methods, and mainstream technical solutions involved in flexible resource VPPs in the power market environment provides suggestions for future research directions and technological development of flexible resource VPPs.

Distributionally Robust Operation for Flexible Distribution Networks Considering Multi-correlation of Renewable Power Generation

Zhiwei LIU, Yue MA, Zhicheng SHA, Yunshu SHAO, Yuanfang NIU, Xiaoming DONG, Chengfu WANG

2024, 57(12):  97-108.  DOI: 10.11930/j.issn.1004-9649.202409078

Asbtract ( )   PDF (3805KB) ( )  

Figures and Tables | References | Related Articles | Metrics

The integration of a high proportion of distributed renewable energy sources (DRES) and a substantial number of fully controllable flexible power electronic devices has brought more clean electrical energy and control options to traditional distribution networks. However, the uneven temporal and spatial distribution of their output power and the complexity of regulating a vast number of devices pose significant challenges to the operation of distribution networks. In response to this, a distributionally robust optimization strategy for flexible distribution networks, considering the multiple correlations of renewable energy, is proposed. Firstly, aiming to minimize active power loss and voltage deviation in the distribution network, an optimal power flow model for flexible distribution networks is derived and constructed, incorporating various coordinated control measures for sources, grids and loads. Secondly, taking into account the multiple correlations of renewable energy in terms of time, space and power dimensions, a two-stage distributionally robust optimization model for flexible distribution networks is established based on data-driven approaches. The 1-norm and ∞-norm are employed to describe the uncertainty sets of sources and loads, and second-order cones are utilized for linearization and convex relaxation. Finally, the column and constraint generation algorithm is adopted to solve the model, and a simulation analysis is conducted using an improved IEEE 33-bus test system as an example, verifying the effectiveness and practicality of the proposed method.

Demand Response Strategy for Commercial Building Power Supply Conversion Entities Based on Alliance Chain Technology

Zhihui TANG, Xin ZHANG, Yifei NING, Huang HUANG, Kun YU, Haochen HUA, Jiawei CAO, Yuntian ZHENG

2024, 57(12):  109-119.  DOI: 10.11930/j.issn.1004-9649.202309098

Asbtract ( )   PDF (3829KB) ( )  

Figures and Tables | References | Related Articles | Metrics

Commercial buildings have abundant flexible resources and can effectively participate in demand response. However, widespread power supply conversion in commercial buildings can lead to insufficient enthusiasm for end users to participate in demand response. On the one hand the settlement information of demand response is not transparent and end users lack trust in the power supply conversion entities, on the other hand, the main power supply conversion entities have ignored the electricity utility of end users, and the incentive mechanism is unreasonable. To address above issues, by applying the alliance chain technology to the demand response of commercial building power supply conversion, this article constructs an alliance chain-based commercial building power supply conversion demand response system to achieve decentralized and reliable transfer of demand response. Based on the electricity consumption characteristics of public areas and end users in the context of power supply conversion, a demand response strategy is proposed with consideration of the power supply conversion characteristics of commercial buildings. The proposed alliance chain system was validated in a small commercial building environment in Nanjing, achieving transparent transaction and settlement functions of the alliance chain in the demand response process of commercial buildings. At the same time, simulation results show that the proposed strategy successfully reduces the electricity consumption cost of the power supply conversion entities by 33.6%, confirming the effectiveness of the proposed strategy.

A Layout Evaluation Method for Source-Network-Load-Storage and Multi-energy Complementary Projects Based on Entropy Weight and Delphi Method

Junjie KANG, Chunyang ZHAO, Guopeng ZHOU, Liang ZHAO

2024, 57(12):  120-131.  DOI: 10.11930/j.issn.1004-9649.202308035

Asbtract ( )   PDF (3518KB) ( )  

Figures and Tables | References | Related Articles | Metrics

Source-network-load-storage integration and multi-energy complementary is of great significance for accelerating the construction of new power systems, achieving high-quality development of the power system, improving the coordination and mutual aid ability of multiple energy sources, and promoting China's green and low-carbon energy transformation and economic and social development. Firstly, based on an analysis of such factors as the national resource elements for integration and complementary, national development strategy, load development, electricity price level, new energy consumption conditions and regulatory capacity demand, a subjective and objective combination weighting evaluation system is established. And then, the entropy weight method is used to determine the objective weights of the influencing factors for each development route of integration, and the Delphi method is used to determine the objective weights. Through fusion calculation, the comprehensive weights of the influencing factors are obtained. Based on the scores and weights of the influencing factors, every development route is scored, and the development priority levels are divided. Finally, the construction priority order for integration projects in all provinces across the country is obtained, which can provide a technical support for the development of the integration projects in all provinces.

Energy Storage System

An Optimization Method for Energy Storage Configuration of Isolated Island Microgrid Considering New Energy Output

Xinghua HUANG, Han WU, Shichuan CHEN, Yuanliang FAN, Gonglin ZHANG

2024, 57(12):  132-138.  DOI: 10.11930/j.issn.1004-9649.202312094

Asbtract ( )   PDF (4092KB) ( )  

Figures and Tables | References | Related Articles | Metrics

This article proposes an optimization method for energy storage configuration in isolated microgrids considering new energy output. Considering the output of new energy and the capacity of islanded microgrid energy storage systems, based on the output power of energy storage equipment, calculate the optimization parameters of energy storage configuration, establish the objective optimization function, calculate the fitness value of multi-objective optimization function, and thus obtain the optimal configuration scheme. The experimental results indicate that the proposed method is beneficial for improving the energy utilization efficiency of islanded microgrid systems and ensuring power supply stability.

VMD Based Fault Diagnosis Method for SOFC Stack Seal Failure and Leakage

Xin WU, Chao HU, Qi WANG, Xingyu XIONG, Liang HU, Xiangchen QIAN

2024, 57(12):  139-147.  DOI: 10.11930/j.issn.1004-9649.202307033

Asbtract ( )   PDF (4678KB) ( )  

Figures and Tables | References | Related Articles | Metrics

When the solid oxide fuel cell (SOFC) operates for a long time at high temperature, due to the repeated start-stop cycle and long-term operation, the reactor is prone to seal failure, which will lead to leakage failure, and then lead to thermal runaway and damage of the reactor, which seriously affects the stability of the system operation. The change of parameters may lead to the occurrence of leakage faults and consequently thermal runaway of the stack or even abnormal system shutdown. Aiming at this fault, a diagnostic method based on the variational mode decomposition (VMD) and Hilbert transform (HT) is proposed through the experiment temperature and voltage signals. This method was applied to experimentally investigate the sealing failure leakage fault in SOFC stacks. The research results demonstrate that utilizing the fault diagnosis method based on VMD and HT can determine the presence of leakage in the stack under open-circuit conditions. By collecting the temperature and voltage signals of the stack and applying this fault diagnosis method, the temperature signal can more rapidly indicate the presence of a leakage fault in the stack. When comparing the diagnosis methods based on Ensemble Empirical Mode Decomposition and VMD, it was found that the latter can detect the leakage fault in the stack 100 seconds faster.

A Two-Stage Site Selection and Capacity Determination Method for Energy Storage Power Stations Based on HC-MOPSO

Wangwang BAI, Dezhou YANG, Wanwei LI, Tao WANG, Yaozhong ZHANG

2024, 57(12):  148-156.  DOI: 10.11930/j.issn.1004-9649.202407093

Asbtract ( )   PDF (4353KB) ( )  

Figures and Tables | References | Related Articles | Metrics

A planning method for energy storage stations based on Hierarchical Clustering (HC) and Multi Objective Particle Swarm Optimization (MOPSO) is proposed to address the difficulty of balancing the coupling effects of active power and node voltage in large-scale energy storage planning. Firstly, based on the coupling effect between system active power and node voltage, a sensitivity model is established, and the HC algorithm is used to obtain the results of power grid regional division. Furthermore, based on sensitivity indicators, select the voltage dominant nodes within each sub region as the access points for energy storage power stations; Secondly, a capacity configuration model for energy storage power stations is established with the objectives of maximizing the system's static voltage stability margin, minimizing total investment and operating costs, and minimizing total active power losses. The MOPSO algorithm embedded in power flow calculation is designed to solve the model. Finally, taking the IEEE 39 node power system network as an example, the feasibility and effectiveness of the proposed method and model are verified.The simulation results show that the planning method proposed in this paper can further reduce the active line loss of the system and improve the static voltage stability margin compared to traditional methods.

Generation Technology

Inventory Optimization Model of Biomass Power Plant Considering Multiple Uncertainties

Jinliang ZHANG, Zeping HU

2024, 57(12):  157-168.  DOI: 10.11930/j.issn.1004-9649.202308050

Asbtract ( )   PDF (4841KB) ( )  

Figures and Tables | References | Related Articles | Metrics

The formulation of inventory optimization strategies for biomass power plants is the basis for ensuring regional power supply. However, the seasonality and demand uncertainty of biofuels have brought great challenges to inventory optimization. In order to reduce the impact of multiple uncertain factors on inventory optimization, a stochastic-robust inventory optimization model for biomass power plants based on multiple uncertainties was proposed. First, the uncertainties of the price and quality level of biomass fuels are described using ellipsoidal uncertainty sets. And use the scenario tree method to construct typical biomass availability scenarios to reduce the impact of fuel supply seasonality on inventory optimization strategies. Secondly, considering the randomness and ambiguity of the error, three kinds of user load curves are simulated by using the ecological cloud generator, which improves the accuracy of demand curve fitting. Finally, a stochastic-robust optimization model of biomass power plant inventory taking multiple uncertainties into account is developed with the objective of minimizing the total inventory cost. The validity of the model is verified by comparing the optimization results of the deterministic, stochastic and stochastic-robust optimization models through examples. The results show that the total cost of biomass power plant inventory in the stochastic-robust optimization model is the lowest, which is 2.6915 million yuan. Compared with the stochastic optimization model, the total inventory cost of the proposed strategy is reduced by 34.59%, which can improve the economy and reliability of the inventory optimization strategy.

Study of Dynamic Characteristics of 100 MW Cascade S-CO₂ Cycle

Mingyuan WAN, Xin REN, Du WANG, Yafei JIN, Zhigang WANG, Tingju WANG, Changhong YANG, Haokun LIU

2024, 57(12):  169-177.  DOI: 10.11930/j.issn.1004-9649.202310090

Asbtract ( )   PDF (4903KB) ( )  

Figures and Tables | References | Related Articles | Metrics

To analyze the variable load dynamic characteristics and optimal control strategy of the 100 MW cascade supercritical carbon dioxide (S-CO₂) cycle, the dynamic simulation model of the 100 MW cascade S-CO₂ cycle is established by using the multi-disciplinary simulation platform (MSP). Considering the lower cost and rapidity of valve regulation, four load control strategies were proposed (high-temperature turbine throttling regulation, low-temperature turbine throttling regulation, high-temperature turbine bypass regulation, and low-temperature turbine bypass regulation), and the changes of key parameters in the process of load raising and lowering of the system were analyzed. The results show that different load control strategies had little influence on the compressor power. The use of high-temperature turbine throttling regulation has the highest cycle efficiency, and the cycle efficiency is 27.60% and 21.22% when the load rate is 75% and 50%, respectively. The throttling regulation will cause the maximum pressure to increase, and the maximum pressure with high-temperature turbine throttling regulation is 28.57 MPa when the load rate is 50%. The risk of overpressure can be avoided by bypass adjustment, but the cycle efficiency is low. On the premise of ensuring the pressure-bearing capacity of the system, it is recommended to use the high-temperature turbine throttling adjustment method to adjust the load.

Information and Communication

Implementation of Power Communication Faults and Maintenance Aided Decision-Making Coupled with Power Network Service Constraints

Tianling HE, Libo CAI

2024, 57(12):  178-187.  DOI: 10.11930/j.issn.1004-9649.202311135

Asbtract ( )   PDF (3393KB) ( )  

Figures and Tables | References | Related Articles | Metrics

The application of high proportion new energy, AC/DC ultra-high voltage long-distance transmission, and high proportion power electronics has brought not only new challenges, but also higher requirements for the scheduling and operation management of power communication networks. The power grid and power communication network are typical interdependent networks. Faults of communication network, the highly important nodes in particular, have a serious impact only only on the communication network system itself, but also on its dependent networks, and may lead to cascading failures. Firstly, the challenges of coupling analysis between communication network and power grid business were summarized. Then, an analysis model for judging the impact of communication network fault maintenance on power grid business and a recovery model for the affected business were proposed, and a assisted decision-making platform coupling communication network with power grid for power grid security was developed, thereby realizing the automatic analysis and calculation under N-X and multi-dimensional troubleshooting scenarios. Finally, validation was conducted using a regional backbone transmission network as a practical scenario, achieving the expected results and effectively improving the rapid response capability of communication networks in extreme scenarios.

Multi-site Information Synchronization Scheme Based on Wavelet Transform to Detect Signal Singularity

Baojiang TIAN, Yan LI, Xiaoyu LIAO, Xingwei DU, Wenyan DUAN

2024, 57(12):  188-197.  DOI: 10.11930/j.issn.1004-9649.202304074

Asbtract ( )   PDF (2859KB) ( )  

Figures and Tables | References | Related Articles | Metrics

The recording files of different devices in the substation are affected by the loss of synchronization signals and damage of communication channels, resulting in asynchronous recording files. However, various main protections such as longitudinal differential protection and distance protection in the power system, as well as secondary equipment such as merging units, phasor measurement units, and recorders used for fault analysis, have strict requirements for information synchronization. To address this issue, this article proposes a self synchronization scheme for recording files of different devices in substations based on the sudden variable detection algorithm. Firstly, considering the problems of high-frequency signal loss and boundary effects in the traditional Mallat wavelet algorithm, which affect the accuracy of mutation point detection, a complementary adjacent window algorithm and an optimization strategy for data window selection are proposed, effectively solving the problems of traditional wavelet transform. On this basis, a substation information synchronization scheme based on the improved Mallat wavelet algorithm is proposed. Finally, the feasibility and advantages of the proposed improved algorithm and the information synchronization scheme were verified through on-site analysis of the actual recorded wave data.

Development and Application of a Knowledge Retrieval and Analysis System for the Power Industry Based on Knowledge Graph and Large Language Model

Jinying ZHANG, Zhefeng WANG, Hua XIE, Changying YAO, Yanli MIN, XINYing WANG

2024, 57(12):  198-205.  DOI: 10.11930/j.issn.1004-9649.202409084

Asbtract ( )   PDF (2614KB) ( )  

Figures and Tables | References | Related Articles | Metrics

With the rapid development of artificial intelligence technology, knowledge retrieval systems in the power industry are facing technological updates and iterations. A knowledge retrieval and analysis system for the power industry based on knowledge graph and big language model has been proposed. Firstly, using big language models to mine user needs and understand their intentions; Then, for knowledge information with different structures, structured knowledge graphs are constructed through strategies such as knowledge modeling, knowledge extraction, and knowledge fusion; Finally, utilizing a large language model based on user requests and professional knowledge obtained from knowledge subgraphs, and visualizing the generated content for display to users, provides a new approach for knowledge retrieval systems in the power industry.

Predicting the Risk of Unauthorized Theft of Grid Identification Information Under IoT Technology

Huahui LV, Hang YANG, Zhida LIN, Huijuan LI, Zhibo FU

2024, 57(12):  206-212.  DOI: 10.11930/j.issn.1004-9649.202311075

Asbtract ( )   PDF (2175KB) ( )  

Figures and Tables | References | Related Articles | Metrics

The power grid field usually has a complex network topology. In order to reduce the power grid security risks, this paper proposes a risk prediction method unauthorized theft of power grid identity information under the Internet of Things technology. By using the Internet of Things technology and vulnerability scanning tools, the risk of unauthorized theft of grid identity information is quantified, and the severity of different vulnerabilities is considered, using the fuzzy hierarchical analysis method for risk assessment. The research results show that prediction error of the proposed method is small, and the device authentication strength is high.