Electric Power

Low Carbon Economic Dispatch of Gas Electricity Coupling System Considering Carbon Capture and Hydrogen Mixing in Gas Grid

Yuxuan YANG, Dongliang GAO, Yiming CHEN, Buxiang ZHOU, Yang CHEN, Tianlei ZANG

2023, 56(10): 1-10. DOI: 10.11930/j.issn.1004-9649.202210024

Asbtract ( )

PDF (3554KB) ( )

Figures and Tables | References | Related Articles | Metrics

For the problem of low-carbon dispatch of gas-power integrated energy system, gas-grid hydrogen blending, carbon capture and electricity-to-gas conversion are all effective technical means. Meanwhile, carbon trading mechanism is also an effective economic means to control carbon emission. Therefore, this paper constructs a carbon capture plant model with liquid-rich and liquid-poor tanks, combined with an electric-to-methane technology model to flexibly recover and utilize CO₂ in the system. Secondly, a gas-grid hydrogen blending technology model is used to improve energy efficiency, while considering the nodal calorific value change constraint during gas-grid hydrogen blending. Then the sum of incentive carbon trading cost and operation cost is used as the objective function. Finally, an arithmetic test is carried out based on the improved Belgian 20-node natural gas system and IEEE 39-node power system models. The results verify that the integrated consideration of carbon capture, gas network hydrogen blending and incentive carbon trading mechanism can improve the low carbon economic dispatch of the system. The carbon price and incentive factor can be adjusted flexibly to regulate the system carbon emission level.

Medium and Long-Term Hydrogen Load Prediction Based on System Dynamics

Tiejiang YUAN, Yijin ZHANG, Zijuan YANG, Dongfang JIANG

2023, 56(10): 11-21. DOI: 10.11930/j.issn.1004-9649.202208038

Asbtract ( )

PDF (3984KB) ( )

Figures and Tables | References | Related Articles | Metrics

Hydrogen energy will play a great role in various fields under the background of “double carbon”, it is important to carry out medium and long-term forecasting of hydrogen demand, and propose a medium and long-term forecasting model of provincial hydrogen demand based on the system dynamics approach. Firstly, the hydrogen demand was divided into three major areas, namely, industry, heating and transportation, and the interaction of internal factors of each subsystem and the influence of external factors such as economic development and policy support were considered to analyze the cause-effect relationship and construct the prediction equation, and on this basis, a flow chart of the total system hydrogen demand prediction was drawn. Secondly, the system parameters are set, and the equation constants are obtained by least squares equation regression, and the table function parameters are set based on the development plan of the province and the gray model. Finally, the system dynamics model built was used to forecast the hydrogen demand in the province.

Capacity Planning of Integrated Energy System of Wind Photovoltaic and Hydrogen Based on Reversible Solid Oxide Cell

Zhenlan DOU, Benfeng YUAN, Chunyan ZHANG, Guoping XIAO, Jianqiang WANG

2023, 56(10): 22-32. DOI: 10.11930/j.issn.1004-9649.202211106

Asbtract ( )

PDF (4132KB) ( )

Figures and Tables | References | Related Articles | Metrics

As a new energy storage technology, reversible solid oxide cell (RSOC) can promote the renewable energy consumption and improve the system efficiency. Therefore, a capacity planning method of an integrated energy system of wind photovoltaic and hydrogen based on RSOC is proposed. Firstly, the planning model of the integrated energy system of wind photovoltaic and hydrogen is established, considering the constraints of the high energy consumption of the balance of plant (BOP) system and the limited power regulation of the RSOC system. Secondly, the particle swarm optimization (PSO) algorithm is used to solve this planning problem, aiming at minimizing the annual redundant and lacking power, and investment cost. Finally, the system planning sensitivity analysis is performed for the uncertain factors of the RSOC cost and hydrogen price. The simulation results show that the proposed method can obtain a reasonable configuration scheme, greatly reducing the redundant and lacking power and improving the flexibility of the system resource allocation.

Optimal Allocation of Hydrogen Storage Capacity Based on Improved Cat Swarm Optimization

Zhenda HU, Wenjin JIANG, Linyao ZHANG, Xiaodong YANG, Yichao ZOU, Kai WANG

2023, 56(10): 33-42. DOI: 10.11930/j.issn.1004-9649.202209013

Asbtract ( )

PDF (3568KB) ( )

Figures and Tables | References | Related Articles | Metrics

Based on the hydrogen energy storage system, a hybrid microgrid system with wind power generation and hydrogen energy storage system as the main components has been constructed. This article optimizes the capacity configuration of electrolytic cells, fuel cells, and hydrogen storage tanks in hydrogen energy storage systems. A capacity optimization configuration model for hydrogen energy storage systems was constructed by comprehensively considering the economic cost, power supply reliability, and wind abandonment rate of microgrids; Establish a capacity optimization model for hydrogen storage systems using wind power output and load from typical day and scenario sets, to reflect the impact of the randomness of wind power output and load on the optimization results; Using an improved cat swarm algorithm with dynamic weights, the capacity optimization configuration model of the proposed hydrogen energy storage system is solved. The feasibility of using the improved cat swarm algorithm to solve the capacity optimization configuration model of hydrogen storage system was verified through numerical examples, and the rationality of the proposed hydrogen storage system capacity optimization configuration model was also demonstrated.

Surface Defect Detection Algorithm for Wind Turbine Blades Based on HSCA-YOLOv7

Bing LI, Yunshan BAI, Kuan ZHAO, Congbin GUO, Yongjie ZHAI

2023, 56(10): 43-52. DOI: 10.11930/j.issn.1004-9649.202304059

Asbtract ( )

PDF (6396KB) ( )

Figures and Tables | References | Related Articles | Metrics

The blade is one of the key components of the wind turbine, which is vulnerable to the impact of natural environmental factors, resulting in gel coat falling off, cracks, corrosion, and other damage and thus affecting the efficiency of wind power generation and the safety of wind turbine operation. A defect detection algorithm for wind turbine blades based on HSCA-YOLOv7 is proposed to address the issues of inconsistent defect scale, inaccurate positioning, and low detection accuracy in wind turbine blade images by aerial photography. Firstly, based on the images of wind turbine blades collected by drones, a dataset of blades is created, and Mosaic and MixUp methods are used for data amplification. Then, deep separable convolutions with different expansion rates are introduced into the improved spatial pyramid pooling (ISPP) module to reduce the loss of details caused by pooling operations. Hybrid spatial channel attention (HSCA) is proposed to capture the global visual scene context, increase the semantic difference between target features and the environment, and solve the problem of inconsistent defect scales in blade images. The focal EIoU loss function is used to solve the problem that the length and width of the prediction box are wrongly amplified and improve the positioning ability of the model for blade defects. The experimental results show that the mAP and mAR of the proposed algorithm reach 83.64% and 71.96%, respectively, which are 3.37% and 5% higher than the YOLOv7 baseline algorithm.

Research on Active Support and Operation Control Network of Wind Turbine Based on Time-Sensitive Network

Jianjun DAI, Mingming WANG, Yunhan YOU, Yu ZHANG

2023, 56(10): 53-61. DOI: 10.11930/j.issn.1004-9649.202305137

Asbtract ( )

PDF (5729KB) ( )

Figures and Tables | References | Related Articles | Metrics

This paper aims to achieve real-time and reliable active support and operation control networks of wind turbines and meet the response time requirements of power grid dispatch. To meet the demands of multiple-service and high-traffic communication, this paper proposes a new network model based on time-sensitive network (TSN) technology. Through an optimized algorithm, the communication time slots for each service instruction are allocated, enabling single-point-to-single-business communication and ensuring real-time and reliable business communication. Experimental results show that under multi-service communication situations, this slot allocation algorithm can effectively divide the transmission intervals between services, control the delay and jitter of each service, and improve the real-time performance of the business. Therefore, the wind turbine communication network is transformed from a traditional “best effort” type Ethernet to a TSN, which can avoid resource conflicts in multi-service communication and satisfy the needs of deterministic and timely important data communication, improving the active support capability of wind turbines.

Improved Maximum Power Point Tracking Control of Power Signal Feedback Method for Permanent Magnet Synchronous Generator Considering Loss

Yunpeng CHENG, Jianhua LI, Shouguo CAI, Xuebo ZHANG, Yong WANG, Ye LU, Ying ZHU

2023, 56(10): 62-70. DOI: 10.11930/j.issn.1004-9649.202307008

Asbtract ( )

PDF (6332KB) ( )

Figures and Tables | References | Related Articles | Metrics

In the maximum power point tracking (MPPT) control of the traditional power signal feedback (PSF) method for the direct-driven permanent magnet synchronous generator (PMSG), it is necessary to obtain the power-speed curve of wind turbines in advance, and wind energy conversion efficiency of the turbines will change with time, thereby reducing the control accuracy of PSF method. Based on the traditional PSF method, this paper proposes an improved MPPT control strategy for PMSG considering internal loss. This strategy tracks the maximum power points of wind turbines through the hill climb searching method and then accurately calculates the proportion coefficient required by the PSF method and the reference power to track the maximum wind power. Both the simulation and experiments verify the effectiveness and feasibility of the proposed control strategy.

Compound Fault Feature Extraction of Wind Power Gearbox Based on DRS and Improved Autogram

Haifei MA, Wei TENG, Dikang PENG, Yibing LIU, Tao JIN

2023, 56(10): 71-79. DOI: 10.11930/j.issn.1004-9649.202303124

Asbtract ( )

PDF (5799KB) ( )

Figures and Tables | References | Related Articles | Metrics

Compound fault feature extraction is the key to analyzing the root cause of wind power gearbox faults. A compound fault feature extraction method based on DRS and improved Autogram is proposed. Based on the DRS method, the influence of the periodic components of vibration signals on the weak fault components is reduced. A new feature quantification index of spectral kurtosis and spectral negative entropy is designed to comprehensively evaluate the narrow-band components after maximum overlapping discrete wavelet packet transform and unbiased autocorrelation processing, so as to select the optimal filtering frequency band and accurately identify the signal components containing compound fault features. The method in this paper is applied to the compound fault diagnosis of wind power gearbox and bearing, which can effectively extract multiple fault features from vibration signals and has a good diagnostic effect.

Research and Development of Nondestructive Detection Technology for Wind Turbine Blades

Lei WANG, Yibing LIU, Wei TENG, Xinwei HUANG, Jiantao LIU

2023, 56(10): 80-95. DOI: 10.11930/j.issn.1004-9649.202303073

Asbtract ( )

PDF (5963KB) ( )

Figures and Tables | References | Related Articles | Metrics

In addition to withstanding aerodynamic forces, blades also experience other forces such as gravity and centrifugal force during operation, as well as damage from rain, snow, sand, salt spray, lightning and other factors, making the wind turbine blade structure and surface vulnerable. Failure to detect and repair such damage in a timely manner can lead to reduced power generation efficiency, downtime and even accidents. Therefore, damage detection of wind turbine blades is of great significance for ensuring the safe and efficient operation of wind turbines and reducing the cost of power generation over the life cycle of the system. This article provides a comprehensive review of the types and causes of wind turbine blade damage based on relevant literature from both Chinese and international sources. It also systematically introduces existing wind turbine blade damage detection technologies, categorizing them into real-time online monitoring and non-real-time detection, and compares the advantages and disadvantages of each technology. Finally, based on the actual engineering application of wind turbines and the development of non-destructive testing technology, the future development trend of non-destructive monitoring/detection technology for wind turbine blades is proposed.

Medium and Long Term Wind Power Prediction Based on Graph Convolutional Network and Wind Velocity Differential Fitting

Zihan CHEN, Wei TENG, Xuefeng XU, Xian DING, Yibing LIU

2023, 56(10): 96-105. DOI: 10.11930/j.issn.1004-9649.202303050

Asbtract ( )

PDF (5784KB) ( )

Figures and Tables | References | Related Articles | Metrics

In order to make full use of the prior relationships among data features and improve the prediction accuracy of medium and long term wind power at wind farms, a medium and long term wind power prediction model based on graph convolution neural network (GCN), wind velocity differential fitting (DF), and particle swarm optimization (PSO) is proposed. By analyzing the whole process of wind power generation, the influencing factors of wind power and the interrelation among them are explored, and the GCN model is built. The wind velocity and power utilization efficiency are fitted respectively. The wind power is calculated by combining with the wind velocity–power calculation model based on DF. The loss of the model includes three parts: power loss, wind velocity loss and power utilization efficiency loss. PSO algorithm is used to determine the appropriate weight for the three losses. The on-site examples of two wind farms show that the relative root mean square error of the wind power prediction model in the next 10 days is 11.44% and 13.09%, respectively, which has a high prediction accuracy.

Research on Online Monitoring of Crack Damage of Wind Turbine Blades Based on Working Modal Analysis

Yuhui WU, Yangfan ZHANG, Feng GAO, Yu WANG, Yaohan WANG, Weixin YANG, Hong ZHANG

2023, 56(10): 106-114. DOI: 10.11930/j.issn.1004-9649.202303035

Asbtract ( )

PDF (5754KB) ( )

Figures and Tables | References | Related Articles | Metrics

Since crack damage of wind turbine (WT) blades is easy to occur and difficult to find, online monitoring of blade crack damage is carried out by collecting and analyzing blade vibration signals. Firstly, based on the theory of working modal analysis, an online identification method of blade modal parameters based on transmissibility is constructed, and a blade vibration physical experiment platform is built for the experimental verification of the method. By comparing the experimental results with the traditional hammer excitation method, the accuracy of the method is verified. Then, with a 5 MW WT as an example, the blade crack damage fault is simulated, and the damage fault characteristics are obtained through working modal analysis. Finally, blade vibration signals, modal parameters, and WT operation data are fused into multi-source data sets, and blade crack damage fault diagnosis is performed based on the LightGBM algorithm. The diagnosis results show that the LightGBM algorithm can achieve a better diagnosis effect than the conventional machine learning algorithm, and the accuracy of the diagnosis algorithm can be significantly increased by integrating blade modal parameters into the data set, so as to improve the accuracy of online monitoring of blade crack damage.

Low-Frequency Oscillation Suppression Strategy for Power System Based on Supplementary Damping Control of Compressed Air Energy Storage

Kangkang WANG, Xinwei SUN, Bo ZHOU, Tianwen ZHENG, Wei WEI, Libo JIANG

2023, 56(10): 115-123. DOI: 10.11930/j.issn.1004-9649.202302081

Asbtract ( )

PDF (4059KB) ( )

Figures and Tables | References | Related Articles | Metrics

With significant increase of penetration of electronic equipment in the power system, the low-frequency oscillation problem of the power system under disturbance are becoming increasingly prominent. Therefore, combined with the good active power regulating ability of compressed air energy storage, a low-frequency oscillation suppression strategy is proposed based on the supplementary damping control of compressed air energy storage. Firstly, a mathematical model of compressed air energy storage is established, and the influence of the mass flow on its output power is analyzed. Secondly, the feasibility of compressed air energy storage to suppress low-frequency oscillation is analyzed, and a supplementary damping controller based on regulating valve is proposed to adjust the mass flow. And then, the output power of the compressed air energy storage is controlled to suppress the low-frequency oscillation of the power grid. Finally, a power system simulation model of 4-generator and two-area with compressed air energy storage is established to verify the effectiveness and feasibility of the proposed method. The simulation results show that the proposed method can provide positive damping for the power grid, and can rapidly suppress the low-frequency oscillation of the power grid and effectively improve the stability of the power system.

Improved NSGA Multi-objective Optimization Based Oil-Paper Insulation Status Assessment Method

Peng ZHANG, Jian ZHANG, Hang YANG, Limin QU, Heqian LIU, Muhe YU

2023, 56(10): 124-132. DOI: 10.11930/j.issn.1004-9649.202305113

Asbtract ( )

PDF (4556KB) ( )

Figures and Tables | References | Related Articles | Metrics

Oil-paper is an important component of oil-immersed power transformers, and its insulation reliability is crucial for maintaining transformer stable operation. In this paper, FDS tests on aged and damp oil-paper insulation samples are conducted, so as to obtain the relationship between the frequency domain dielectric response characteristics of oil-paper insulation and its insulation state. Based on the extended Debye model, an improved NSGA algorithm assisted recognition method for oil-paper insulation broadband dielectric characteristic parameters is proposed. The accurate extraction of the extended Debye model characteristic parameters can be achieved through the complex capacitance curve of the oil-paper insulation. The weight relationship of the characteristic parameter information entropy was considered, and the quantitative characterization equation of the model characteristic parameter and the insulation moisture content and aging was established. This method can realize the quantitative analysis of the oil-paper insulation state and provide important theoretical support for the accurate insulation state assessment of the oil-immersed power equipment.

CHPOA-DBN Transformer Fault Diagnosis Method Considering Sample Within-Class Imbalance

Shuang WANG, Qian LUO, Bo TANG, Lan JIANG, Jin LI

2023, 56(10): 133-144. DOI: 10.11930/j.issn.1004-9649.202305039

Asbtract ( )

PDF (5945KB) ( )

Figures and Tables | References | Related Articles | Metrics

In recent years, deep belief network (DBN) based transformer fault diagnosis methods have been developed. However, they share two prominent drawbacks, which are the low accuracy issue caused by the within-class imbalance of transformer faults samples and the artificial determination of the network parameters of deep belief network (DBN). In this paper, a transformer fault diagnosis method based on sample balance processing and improved DBN is proposed. Firstly, an improved K-means (IK-means) synthesis minority oversampling technique (SMOTE) algorithm is proposed to obtain within-class and between-class balanced fault samples. Then, the Tent chaotic map embedded chaotic hybrid pelican optimization algorithm (CHPOA) is developed to optimize the number of hidden layer nodes and reverse fine-tuning learning rate of DBN, and the CHPOA-DBN transformer fault diagnosis model is constructed. Finally, the classical oversampling algorithm, the classical fault diagnosis model and the proposed method are compared and analyzed, based on the experimental data, respectively. The results show that the fault diagnosis accuracy of the proposed method reaches 96.25 %, which provide an important reference for intelligent fault diagnosis under imbalanced fault samples of transformers.

Empirical Analysis of Ensuring Electricity Supply and Promoting Renewable Power Consumption Before and After the Shutdown of Nuclear Power Plants: the Germany Case

Zhilin LIU, Chuanlong XU, Haifeng ZHENG, Jiangtao LI, Li YAO, Qing LIU, Yi DU

2023, 56(10): 145-152. DOI: 10.11930/j.issn.1004-9649.202307055

Asbtract ( )

PDF (3476KB) ( )

Figures and Tables | References | Related Articles | Metrics

On April 15th 2023, Germany has shut down all their nuclear power plants as scheduled, although the Russian-Ukrainian conflict crisis remains unresolved. Up to now, its power supply security has not been significantly affected, as the results of sufficient conventional power generation capacity as well as their flexible regulation capacity, the solid and efficient transnational power grid, the efficient power market, and the high-accuracy renewable power forecasting technology. The German power system has initially accomplished the goal of a "high proportion of renewable energy penetration, flexible and stable grid operation and market-based electricity pricing", but the high costs and high electricity price have brought heavy burden. Taking Germany as a reference, this study puts forward some suggestions for ensuring a safe and reliable supply of electricity and promoting a high proportion of renewable energy consumption during the energy transition process of China.

Numerical Study of Ultra-High Voltage Transmission Tower Wind Loads Characteristics Against Tornado

Shun ZHANG, Zhenguo WANG, Wendong JIANG, Feng XU, Zhongdong DUAN

2023, 56(10): 153-163. DOI: 10.11930/j.issn.1004-9649.202305124

Asbtract ( )

PDF (4503KB) ( )

Figures and Tables | References | Related Articles | Metrics

In this paper, the wind load characteristics of the Ultra-High Voltage transmission tower under tornado are studied based on the CFD (computational fluid dynamics) numerical simulation method. The numerical model of a full-scale tornado is established. The measured radar data of Spencer tornado as the velocity inlet are adopted to generate the tornado-like wind field, and the impacts of the surface roughness are considered. The tangential velocity and core radius at different heights are obtained, then contrasted with the measured data to verify the rationality of the tornado-like vortex structure. Next, the overall refined CFD numerical modeling of the transmission tower is established, then the SST k-ω turbulence model based on RANS is used to simulate the flow around the transmission tower under tornado. The effects of the different locations and wind directions on the shape coefficients of each section of the transmission tower are studied. It is found that the wind loads of the top section 1 to section 4 of the transmission tower would take the maximum when the tower is located at the wind field of 1.5D (D is the core radius), and the wind loads of the bottom section 5 to section 9 of the transmission tower are the maximum when the tower is located at the wind field of 1.0D. The wind loads of transmission tower reach the maximum when the tower is located at the wind field of 1.0D. The worst wind attack angle of the transverse directions of the transmission tower increases from 60° to 90°, and the worst wind attack angle of the longitudinal directions of the transmission tower varies in the range of 0° to 30° as the distance from the center of tornado increases. The simulated wind load shape coefficient of the transmission tower at the locations of 1.0D and 1.5D are larger than the code values, and all sections (except for the section 7, 8 and 9 at the location of 1.5D) are also larger than the code values.

Fault Diagnosis of LSTM Network Tansformer Based on SMOTE and Bayes Optimization

Hongjie ZHANG, Guifeng CHEN, Hongwei YAN, Xiaolong YANG, Tianren HOU, Wei ZHANG

2023, 56(10): 164-170. DOI: 10.11930/j.issn.1004-9649.202210046

Asbtract ( )

PDF (3518KB) ( )

Figures and Tables | References | Related Articles | Metrics

With the improvement of power informatization, the method of transformer fault diagnosis based on intelligent algorithm and historical data has been paid more and more attention. On the basis of dissolved gas analysis, synthetic minority oversampling technique (SMOTE) algorithm was used to synthesize new samples, realize multi-dimensional expansion of samples, and use Bayes optimization algorithm to find the best setting value of long short term memory (LSTM) network model parameters to reduce the error rate of training set, and then establish transformer fault diagnosis model. The results show that the overfitting degree of the transformer fault diagnosis model after sample expansion is reduced by about 20%, and the accuracy of the test set is increased by about 10%.

Smart Substation Optical Fiber Virtual and Real Loop Mapping and Fault Diagnosis Technology

Ming ZHONG, Jun TAO, Xunyu LIU, Yi YANG, Bingyuan YANG

2023, 56(10): 171-178. DOI: 10.11930/j.issn.1004-9649.202303071

Asbtract ( )

PDF (3610KB) ( )

Figures and Tables | References | Related Articles | Metrics

At present, most of the smart substation communication uses optical fiber to link the secondary equipment, and the link relationship between the devices is not intuitive, resulting in difficulty in monitoring and diagnosis. In order to solve the problems of secondary virtual loop visualization, loop status monitoring, fault location and fault type identification in the operation and maintenance of smart substations, a smart substation optical fiber virtual and real loop mapping solution is proposed based on the breadth-first search algorithm to realize the visual display of secondary virtual loop. At the same time, the breadth priority search algorithm is used to carry out fault inference and delimit the fault area. The D-S evidence theory is used to accurately locate the faults based on the mass data of smart substation and multi-information fusion, and the evidence table method is used to finally determine the fault types, thereby meeting the practical application needs of the operation and maintenance of secondary equipment in smart substations.

Magnetic Flux Density Feature Analysis and CT Saturation Region Recognition and Reconstruction Technology

Feng WANG, Jia ZHU, Shaolin JIAO, Yiquan LI, Hua XIE, Qingchun ZHAO

2023, 56(10): 179-185, 193. DOI: 10.11930/j.issn.1004-9649.202302075

Asbtract ( )

PDF (7037KB) ( )

Figures and Tables | References | Related Articles | Metrics

To solve the problem of relay protection caused by CT saturation, a CT saturation identification method is proposed based on flux density characteristics and secondary current reconstruction technology in the distortion area. The CT saturation is identified based on the characteristics of the magnetic flux density trapezoidal region at saturation. Then the saturation region of CT is obtained using the slope of the flux variance to construct the saturation criterion based on the difference between entry saturation and exit saturation and calculate the time corresponding to the start and end point of secondary current saturation. The protection starting criterion is constructed based on the current at the maximum grid load to avoid protection misoperation. Finally, the least square method is used to reconstruct the secondary current in the saturation region to reflect the primary current reliably. The simulation results based on PSCAD/EMTDC software show that the proposed method is accurate and reliable, and can quickly and effectively identify the saturated CT segment with a time error of less than 1 ms.

Informer Photovoltaic Power Generation Forecasting Based on Cycle Information Enhancement

Qian ZHANG, Fei MENG, Tao LI, Yong YANG, Lu BAI

2023, 56(10): 186-193. DOI: 10.11930/j.issn.1004-9649.202306038

Asbtract ( )

PDF (6506KB) ( )

Figures and Tables | References | Related Articles | Metrics

Aiming at the problem that the photovoltaic power generation power prediction method is difficult to capture hierarchical time series information, which results in the limited improvement of prediction accuracy. The paper proposes a photovoltaic power generation prediction method based on the fusion of hierarchical time series information and Informer model. First, photovoltaic power sequence scalar projection, local time stamp and global time stamp are extracted to establish a prediction model embedding layer of periodic information enhancement. Then, through the probability sparse self-attention of the Informer coding layer, the important connection between the photovoltaic power generation and the characteristic variables is actively screened. The convolutional layer and pooling layer are used to optimize the model variable dimensions and network parameters for self-attention distillation. Finally, one-step prediction of single-sequence and long-sequence power generation is realized through the generative mechanism of the decoding layer. Through simulation verification, the proposed model has higher prediction accuracy and can make long-term predictions of photovoltaic power generation.

Automatic Generation Technology of Safety Measures for Digital Substation Based on Improved Support Vector Machine

Yabing YAN, Xu CHU, Haolong XIAO, Wenwu LIANG, Hui LI, Zhenxing XIA

2023, 56(10): 194-201. DOI: 10.11930/j.issn.1004-9649.202303067

Asbtract ( )

PDF (6911KB) ( )

Figures and Tables | References | Related Articles | Metrics

A digital substation safety measure automatic generation technology based on improved support vector machine is proposed to address the low efficiency of secondary maintenance safety measures in digital substations. Firstly, construct a secondary circuit model and equipment model based on adjacency matrix, and further integrate the secondary security measure rule library to form a sample dataset; Secondly, support vector machines were used to classify secondary security measures, and bacterial foraging algorithms were introduced to optimize penalty factors and kernel parameters, effectively improving the training effectiveness of the automatic generation model for security measures; Finally, the effectiveness of the proposed method was verified through numerical examples.

Simulation Analysis and Structure Optimization of Cooling System for Energy Storage Lithium-Ion Battery Pack

Zhoubin LIU, Tao ZHU, Wei JIANG, Xiaobo ZHANG, Jionggeng WANG, Qianqian GUAN, Qiushi ZHANG, Qingliang ZHAO

2023, 56(10): 202-210. DOI: 10.11930/j.issn.1004-9649.202306114

Asbtract ( )

PDF (8410KB) ( )

Figures and Tables | References | Related Articles | Metrics

The thermal management design of energy storage battery packs is an important factor in ensuring the safe operation of energy storage systems. This article is based on the STAR-CCM+platform to optimize the structure of energy storage battery packs with different cooling methods. This article compares and analyzes the heat dissipation performance of traditional indirect liquid cooling, immersion cooling, and optimized immersion models, providing important reference for the design and development of immersion energy storage battery packs. Through simulation and experimental comparison, this article verifies the accuracy of the proposed model, which can provide guidance for the design of thermal management of energy storage lithium-ion batteries.

Active Power Allocation Method for Photovoltaic Cluster Considering Output and Electricity Price Uncertainty

Hua LI, Ziyue CHENG, Xudong LI, Zhenxing LI, Zhilei NIU, Bin CHEN, Yangze WANG

2023, 56(10): 211-218. DOI: 10.11930/j.issn.1004-9649.202304042

Asbtract ( )

PDF (6492KB) ( )

Figures and Tables | References | Related Articles | Metrics

Aiming at the economic operation of high permeability photovoltaic (PV) cluster in distribution network and its participation in system power adjustment, an active power optimal scheduling allocation method for regional PV cluster is proposed. Firstly, the PV stations in the cluster are classified according to their energy storage configuration and controllable capacity. The multi-scenario method is used to transform the uncertainty of PV output and market price into a deterministic scenario. The conditional value-at-risk (CVaR) is introduced to quantify the uncertainty risk, and a regional PV cluster power allocation optimization model is established. Taking the minimum operating cost of the cluster as the optimization objective, the optimal day-ahead output plan and energy storage operation strategy are obtained. Finally, aiming at the operation mode change caused by the system disturbance, a power redistribution strategy for PV cluster participating in system adjustment is proposed. The results of the case study show that the regional PV cluster has the ability to participate in the system power adjustment and the proposed method is also proved to be effective.

Table of Content