A method and system for stability assessment of a power system, an electronic device and a medium

Abstract

The application discloses a kind of stability evaluation method, system, electronic equipment and storage medium of power system, it is related to power system field.Based on minimum damping ratio, the small disturbance stability of power system is evaluated, minimum damping ratio is related with the power flow data of power system and the saturation coefficient of generator and phase modifier, when the power flow distribution of power system or generator set and / or phase modifier changes due to factors such as transformation replacement, the saturation characteristics of the generator set and / or phase modifier will change.The application considers the influence of the change of the saturation characteristics of the generator and the phase modifier on the small disturbance stability of the power system, and the process of evaluation using the minimum damping ratio can more comprehensively reflect the operation information of the power system, improve the accuracy of the small disturbance stability evaluation, and ensure that the final evaluation result can accurately reflect the small disturbance stability of the power system.

Description

Technical Field

[0001] This invention relates to the field of power systems, and in particular to a method, system, electronic device, and storage medium for evaluating the stability of power systems. Background Technology

[0002] With the continuous development of artificial intelligence (AI) technology, machine learning methods such as deep learning have been widely applied in various fields. In the power system field, using AI to conduct small-disturbance stability assessment of power systems is an important research direction. A well-trained intelligent assessor can accurately and quickly evaluate the operating status of power systems online, overcoming to some extent the shortcomings of traditional analysis methods, such as being cumbersome and time-consuming. Currently, when conducting small-disturbance stability assessment of power systems based on AI technology, the power flow data of the grid is basically used as the input to the stability assessment model, without considering the impact of the saturation status of synchronous generators and synchronous condensers on the small-disturbance stability analysis results. Once the saturation characteristics of synchronous generators and / or synchronous condensers change due to factors such as modification or replacement, some physical quantities reflecting the small-disturbance stability of the power system may also change accordingly. However, the small-disturbance stability assessment results obtained based on power flow data will not change, failing to accurately reflect the small-disturbance stability of the power system. Therefore, there is an urgent need for a power system stability assessment model that considers the saturation effects of synchronous generators and synchronous condensers to more accurately assess the small-disturbance stability of the power system. Currently, there is no method to assess the small-disturbance stability of power systems that takes into account the saturation effects of synchronous generators and synchronous condensers. Summary of the Invention

[0003] The purpose of this invention is to provide a method, system, electronic device, and storage medium for evaluating the stability of a power system. This invention takes into account the impact of changes in the saturation characteristics of generators and synchronous condensers on the small-disturbance stability of the power system. The evaluation process using the minimum damping ratio can more comprehensively reflect the operating information of the power system, improve the accuracy of small-disturbance stability evaluation, and ensure that the final evaluation result can accurately reflect the small-disturbance stability of the power system.

[0004] To address the aforementioned technical problems, this invention provides a method for evaluating the stability of a power system, comprising:

[0005] Obtain current power flow data of the power system;

[0006] Obtain the current saturation coefficients of the generators and synchronous condensers in the power system;

[0007] The minimum damping ratio of the power system corresponding to the current power flow data and the current saturation coefficient is determined using a pre-built prediction model.

[0008] The small-disturbance stability of the power system is evaluated based on the minimum damping ratio.

[0009] Optionally, before acquiring the current power flow data of the power system, the method further includes:

[0010] Construct a simulation model of the power system and obtain several power flow samples of the simulation model under different operating states;

[0011] Obtain several saturation coefficients of the generators and synchronous condensers in the power system;

[0012] Determine the correspondence between the power flow sample, the saturation coefficient, and the minimum damping ratio of the power system;

[0013] A prediction model is constructed based on the aforementioned correspondence.

[0014] Optionally, obtaining several power flow samples of the simulation model under different operating states includes:

[0015] Determine the basic power flow data for the simulation model of the power system;

[0016] Adjust the load power and / or power output of the simulation model of the power system to obtain several power flow samples of the simulation model under different operating states based on the basic power flow data.

[0017] Optionally, obtaining several saturation coefficients of generators and synchronous condensers in the power system includes:

[0018] Determine the saturation models for generators and synchronous condensers in the power system;

[0019] The parameters of the saturation model are adjusted to obtain several saturation coefficients.

[0020] Optionally, determining the correspondence between the power flow sample, the saturation coefficient, and the minimum damping ratio of the power system includes:

[0021] After freely combining several power flow samples and several saturation coefficients, the data is divided into N groups. Each group of data includes a one-to-one corresponding power flow sample and saturation coefficient, where N is a positive integer.

[0022] The characteristic values ​​of the power system corresponding to each set of data are calculated using the power flow samples and the saturation coefficient, respectively.

[0023] The damping ratio is calculated based on the characteristic values ​​of the power system, and the minimum damping ratio of the power system is determined based on the minimum value of the damping ratio, corresponding to N sets of data, so as to obtain the correspondence between the power flow sample, the saturation coefficient and the minimum damping ratio of the power system.

[0024] Optionally, evaluating the small-disturbance stability of the power system based on the minimum damping ratio includes:

[0025] Determine whether the minimum damping ratio is less than a preset threshold;

[0026] If so, the power system is deemed to be at risk of small-scale disturbance instability.

[0027] If not, then it is determined that the power system does not pose a risk of small disturbance instability.

[0028] Optionally, determining the minimum damping ratio of the power system corresponding to the current power flow data and the current saturation coefficient using a pre-built prediction model includes:

[0029] The first feature vector output by the first feature extractor in the prediction model and the second feature vector output by the second feature extractor in the prediction model are concatenated to obtain a new feature vector. The first feature vector is the feature vector corresponding to the current power flow data of the power system, and the second feature vector is the feature vector corresponding to the current saturation coefficient of the generators and synchronous condensers in the power system.

[0030] The predicted value corresponding to the new feature vector output by the fully connected layer in the prediction model is used as the minimum damping ratio of the power system corresponding to the current power flow data and the current saturation coefficient.

[0031] To address the aforementioned technical problems, the present invention also provides a power system stability assessment system, comprising:

[0032] The first acquisition unit is used to acquire the current power flow data of the power system;

[0033] The second acquisition unit is used to acquire the current saturation coefficients of the generators and synchronous condensers in the power system;

[0034] A damping ratio determination unit is used to determine the minimum damping ratio of the power system corresponding to the current power flow data and the current saturation coefficient of the power system using a pre-built prediction model;

[0035] An evaluation unit is used to evaluate the small-disturbance stability of the power system based on the minimum damping ratio.

[0036] To address the aforementioned technical problems, the present invention also provides an electronic device, comprising:

[0037] Memory, used to store computer programs;

[0038] A processor for implementing the steps of the power system stability assessment method as described above.

[0039] To address the aforementioned technical problems, the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the power system stability assessment method described above.

[0040] This invention provides a method for assessing the stability of a power system. It utilizes a pre-built prediction model, acquired current power flow data, and the current saturation coefficients of generators and synchronous condensers to determine the minimum damping ratio of the current power system. Then, based on this minimum damping ratio, the small-disturbance stability of the power system is assessed. The minimum damping ratio is correlated with both the power flow data and the saturation coefficients of generators and synchronous condensers. When the power flow distribution or the saturation characteristics of generators and / or synchronous condensers change due to factors such as modification or replacement, the minimum damping ratio will change. This invention considers the impact of changes in the saturation characteristics of generators and synchronous condensers on the small-disturbance stability of the power system. The assessment process using the minimum damping ratio can more comprehensively reflect the operating information of the power system, improve the accuracy of the small-disturbance stability assessment, and ensure that the final assessment result accurately reflects the small-disturbance stability of the power system.

[0041] The present invention also provides a power system stability assessment system, electronic device, and computer-readable storage medium, which have the same beneficial effects as the power system stability assessment method described above. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the prior art and embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 A flowchart illustrating a method for evaluating the stability of a power system provided by the present invention;

[0044] Figure 2 A schematic diagram illustrating the process of constructing a prediction model provided by the present invention;

[0045] Figure 3A schematic diagram of the structure of a power system simulation model provided by the present invention;

[0046] Figure 4 A schematic diagram of a process for generating training samples for a prediction model provided by the present invention;

[0047] Figure 5 A schematic diagram of the saturation curve of a generator provided by the present invention;

[0048] Figure 6 A schematic diagram of the structure of a prediction model provided by the present invention;

[0049] Figure 7 A comparison chart of predicted and actual values ​​of the first test set of a prediction model provided by the present invention;

[0050] Figure 8 A comparison chart of predicted and actual values ​​of a second test set for a prediction model provided by the present invention;

[0051] Figure 9 A comparison chart of predicted values ​​and actual values ​​for the third test set of a prediction model provided by the present invention;

[0052] Figure 10 A comparison chart of predicted values ​​and actual values ​​for the fourth test set of a prediction model provided by the present invention;

[0053] Figure 11 A comparison chart of predicted and actual values ​​for the fifth test set of a prediction model provided by the present invention;

[0054] Figure 12 A schematic diagram of the structure of a power system stability assessment system provided by the present invention;

[0055] Figure 13 This is a schematic diagram of the structure of an electronic device provided by the present invention. Detailed Implementation

[0056] The core of this invention is to provide a method, system, electronic device, and storage medium for evaluating the stability of a power system. This invention takes into account the impact of changes in the saturation characteristics of generators and synchronous condensers on the small-disturbance stability of the power system. The evaluation process using the minimum damping ratio can more comprehensively reflect the operating information of the power system, improve the accuracy of small-disturbance stability evaluation, and ensure that the final evaluation result can accurately reflect the small-disturbance stability of the power system.

[0057] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0058] The power system stability assessment method provided by this invention is mainly applicable to the field of small-disturbance stability analysis of power systems. It is a small-disturbance stability assessment method for power systems that takes into account the saturation effects of generators and synchronous condensers. Detailed implementation methods are described below.

[0059] Please refer to Figure 1 , Figure 1 The present invention provides a flowchart of a power system stability assessment method; to solve the above technical problems, the present invention provides a power system stability assessment method, comprising:

[0060] S11: Obtain the current power flow data of the power system;

[0061] It is easy to understand that power flow data is the data obtained after power flow calculation. Power flow calculation involves solving for voltage and power distribution in a power system under given operating conditions and connection methods. Small-disturbance stability of a power system refers to its ability to maintain grid-generator synchronization under small disturbances. The small-disturbance stability of a power system is mainly related to its current power flow distribution. Therefore, when assessing the small-disturbance stability of a power system, it is necessary to first obtain the current power flow data to determine its current distribution. This application does not impose specific limitations on the methods for obtaining this data. Power flow data includes bus voltage amplitude, bus voltage phase angle, active power output of generators injected into the bus, reactive power output of generators injected into the bus, active power of loads connected to the bus, reactive power of loads connected to the bus, etc., which are not specifically limited here.

[0062] S12: Obtain the current saturation coefficient of generators and synchronous condensers in the power system;

[0063] It is understandable that changes in the saturation characteristics of generators and synchronous condensers in a power system can also affect the small-disturbance stability of the power system. The saturation coefficient is an important parameter reflecting the saturation characteristics of generators and synchronous condensers. Therefore, when evaluating the small-disturbance stability of a power system, it is also necessary to obtain the current saturation coefficients of generators and synchronous condensers in the power system. This application does not make any special restrictions on the specific implementation method for obtaining the current saturation coefficients of generators and synchronous condensers in the power system, nor does it make any special restrictions on the specific types and implementation methods of generators and synchronous condensers.

[0064] S13: Determine the minimum damping ratio of the power system corresponding to the current power flow data and current saturation coefficient using a pre-built prediction model;

[0065] In practical applications, a prediction model is pre-built. The prediction model can determine the minimum damping ratio of the power system corresponding to the current power flow data and the current saturation coefficients of the generators and synchronous condensers in the power system based on the obtained current power flow data and the current saturation coefficients of the power system. That is, the current minimum damping ratio of the power system. The obtained minimum damping ratio is the minimum damping ratio of the power system that takes into account both the power flow data and the saturation characteristics of the generators and synchronous condensers. This application does not make any special restrictions on the specific implementation of the prediction model.

[0066] S14: Evaluate the small-disturbance stability of power systems based on minimum damping ratio.

[0067] It is easy to understand that the result of evaluating the small disturbance stability of the power system based on the obtained minimum damping ratio is the evaluation result obtained on the basis of power flow data and taking into account the saturation effect of generators and synchronous condensers. This application does not make any special restrictions on the correspondence between the minimum damping ratio and the small disturbance stability of the power system. Usually, the evaluation of the small disturbance stability of the power system is achieved by comparing thresholds.

[0068] Specifically, this application does not impose particular limitations on the specific type and implementation method of the power system, nor is it limited to distribution networks or transmission networks. For different power systems, a prediction model corresponding to that power system needs to be pre-constructed to predict and output the minimum damping ratio. The damping ratio is calculated in advance using eigenvalues. Furthermore, to improve the accuracy of the prediction model, it can be trained. During training, the saturation coefficients of generators and synchronous condensers, as well as power flow data, serve as the model input, while the minimum damping ratio obtained through experiments or calculations serves as the output. The prediction model establishes a mapping relationship between input and output in advance. The prediction module integrates two feature extractors to obtain the current power flow data and the saturation coefficients of generators and synchronous condensers in the power system. The feature extractors output feature vectors, which are feature information extracted by the feature extraction network module and are merely intermediate products of the model calculation. Simultaneously, the prediction model integrates three fully connected layers to receive the feature vectors output by the two feature extractors and outputs the corresponding minimum damping ratio value, thus establishing a mapping relationship between input and output.

[0069] This invention provides a small-disturbance stability assessment method that takes into account the saturation effects of generators and synchronous condensers. It belongs to the field of small-disturbance stability analysis of power systems. By considering the saturation effects of generators and synchronous condensers, the input features of the small-disturbance stability assessment process are enriched. By integrating machine learning models, the advantages of different learning models are brought into play, thereby making the results of small-disturbance stability assessment more accurate and able to take into account more comprehensive power grid operation information. The model fusion method is used to overcome the drawbacks of individual models, thereby improving the accuracy of small-disturbance stability assessment.

[0070] This invention provides a method for assessing the stability of a power system. It utilizes a pre-built prediction model, acquired current power flow data, and the current saturation coefficients of generators and synchronous condensers to determine the minimum damping ratio of the current power system. Then, based on this minimum damping ratio, the small-disturbance stability of the power system is assessed. The minimum damping ratio is correlated with both the power flow data and the saturation coefficients of generators and synchronous condensers. When the power flow distribution or the saturation characteristics of generators and / or synchronous condensers change due to factors such as modification or replacement, the minimum damping ratio will change. This invention considers the impact of changes in the saturation characteristics of generators and synchronous condensers on the small-disturbance stability of the power system. The assessment process using the minimum damping ratio can more comprehensively reflect the operating information of the power system, improve the accuracy of the small-disturbance stability assessment, and ensure that the final assessment result accurately reflects the small-disturbance stability of the power system.

[0071] Based on the above embodiments: Please refer to Figure 2 , Figure 2A schematic diagram illustrating the process of constructing a prediction model provided by the present invention;

[0072] As an optional embodiment, before acquiring the current power flow data of the power system, the method further includes:

[0073] Construct a simulation model of the power system and obtain several power flow samples of the simulation model under different operating states;

[0074] Obtain several saturation coefficients of generators and synchronous condensers in the power system;

[0075] Determine the correspondence between power flow samples, saturation coefficients, and the minimum damping ratio of the power system;

[0076] A prediction model is constructed based on the correspondence.

[0077] In practical applications, a prediction model needs to be established in advance to establish the mapping relationship between power flow samples, saturation coefficients, and the minimum damping ratio of the power system. When establishing the power system simulation model, power system simulation software can be used to construct a power grid simulation model. Then, considering the saturation effects of generators and synchronous condensers in conjunction with power flow changes, power flow samples and saturation coefficients are used as sample data to generate sample data for small-disturbance stability assessment. During the sample generation process, the input features of the samples include bus power flow data, synchronous generator saturation coefficients, and synchronous condenser saturation coefficients. Then, the corresponding minimum damping ratio is determined based on the sample data, and the correspondence between power flow samples, saturation coefficients, and the minimum damping ratio of the power system is established. Based on this correspondence, a prediction model is constructed.

[0078] It is easy to understand that the prediction model needs to construct a first feature extractor to obtain the current power flow data of the power system, construct a second feature extractor to obtain the saturation coefficients of generators and synchronous condensers, and simultaneously need a predictor to output the corresponding minimum damping ratio based on the data obtained by the two feature extractors. This application does not make any special restrictions on the specific types and implementation methods of the first feature extractor, the second feature extractor, and the predictor. The first feature extractor can adopt GCN (Graph Convolutional Network), the second feature extractor can adopt GCN (Convolutional Neural Network), and the predictor can be implemented with three fully connected layers. By fusing GCN and CNN, and adding the fully connected layer as the predictor, a fusion model for evaluating small disturbance stability is obtained. By using the fusion model as the prediction model, the minimum damping ratio is evaluated, and the risk of small disturbance instability in the power system is determined accordingly.

[0079] As a specific embodiment, please refer to Figure 3 , Figure 3 This invention provides a schematic diagram of the structure of a power system simulation model. The simulation model is an IEEE 14-node example provided in PSAT software. The model includes five synchronous generators G1-G5, 14 AC buses Bus 01-Bus 14, one on-load tap-changing transformer T2, and three off-load tap-changing transformers T1, T3, and T4. This application does not impose any special limitations on the specific structure and construction method of the power system simulation model; it can be selected and adjusted according to the specific circumstances of the actual application.

[0080] It should be noted that, please refer to Figure 4 , Figure 4 This invention provides a flowchart for generating training samples for a prediction model. The process of building the prediction model involves model training. Power flow samples are generated by setting load fluctuations in the power system, and the saturation coefficients of generators and synchronous condensers are determined. Feature values ​​are calculated based on the power flow samples and saturation coefficients, and key feature values ​​are selected for damping ratio calculation. Finally, the minimum damping ratio is retained, and the minimum damping ratio, its corresponding power flow samples, and saturation coefficients are used as training samples. After obtaining sufficient training samples, model training is performed to ensure the accuracy of the prediction model.

[0081] Specifically, in the process of constructing the prediction model, it is necessary to obtain several power flow samples and several saturation coefficients as sample data by constructing a simulation model of the target power system, and calculate the minimum damping ratio corresponding to the sample data to establish the mapping relationship between the power flow samples, saturation coefficients and the minimum damping ratio of the power system, thereby completing the construction of the prediction model, further improving the construction process of the prediction model, and ensuring the reliable implementation of the power system stability assessment method.

[0082] As an optional embodiment, several power flow samples of the simulation model under different operating states are obtained, including:

[0083] Determine the basic power flow data for the simulation model of the power system;

[0084] Adjust the load power and / or power output of the power system simulation model to obtain several power flow samples of the simulation model under different operating conditions based on the basic power flow data.

[0085] It is easy to understand that when obtaining several power flow samples of a power system, a baseline power flow can be determined. Then, based on this baseline power flow, uncertainties such as load fluctuations and power output in the power system are considered to generate multiple power flow samples. The baseline power flow is the power flow under typical operating modes, including dry-heavy, dry-slight, wet-heavy, and wet-slight modes. This application does not impose any special limitations on the specific implementation of the baseline power flow. Considering uncertainties such as load fluctuations and power output in the power system involves changing the load power and the output of the generators within the power system to obtain the corresponding power flow results. This application does not impose any special limitations on the specific values ​​of the several power flow samples.

[0086] Specifically, when determining several power flow samples of the power system under different operating conditions, several power flow samples are mainly determined by considering factors such as load fluctuations and power output in the power system. By using several power flow samples, it is ensured that the final prediction model can fully consider the overall situation of the power system under different operating conditions, further improving the accuracy and reliability of the minimum damping ratio output by the prediction model, and further ensuring the accuracy of the final evaluation results of the small disturbance stability of the power system.

[0087] As an optional embodiment, obtaining several saturation coefficients of generators and synchronous condensers in the power system includes:

[0088] Determine the saturation models for generators and synchronous condensers in the power system;

[0089] Adjust the parameters of the saturation model to obtain several saturation coefficients.

[0090] It is understandable that after obtaining the power flow samples of several power systems, based on each generated power flow sample, while ensuring that the values of the generator saturation coefficient and the synchronous condenser saturation coefficient conform to the saturation curve characteristics of the corresponding equipment, sampling methods such as Latin hypercube sampling can be used to determine the saturation coefficients of the generator and the synchronous condenser, thereby obtaining multiple small-signal stability calculation samples reflecting different saturation degrees of the generator and the synchronous condenser under one power flow sample, that is, obtaining several saturation coefficients; the Latin hypercube sampling method can make the sampling points evenly distributed in the set interval, with a more reasonable distribution, avoiding the concentration of sampling points in a certain local area caused by other methods, and having a better effect. When carrying out small-signal stability analysis using a power system transient simulation software, a saturation model described by a saturation coefficient is usually used to consider the saturation effects of the generator and the synchronous condenser. The synchronous condenser can basically be regarded as a generator operating without a prime mover, and generally adopts the same saturation model as the generator, or a more complex saturation model can also be adopted, but the saturation model is still characterized by a saturation coefficient. Therefore, when obtaining several saturation coefficients, multiple saturation coefficients can be obtained by adjusting the parameters of the saturation models of the generator and the synchronous condenser. By modifying the saturation coefficients in the saturation models of the generator and the synchronous condenser, the saturation characteristics presented by the generator and the synchronous condenser under different operating conditions are simulated.

[0091] Specifically, please refer to Figure 5 , Figure 5 which is a schematic diagram of the saturation curve of a generator provided by the present invention; taking the generator as an example, Figure 5 as shown is the magnetic field saturation characteristic diagram of the generator, where the abscissa is the excitation voltage, the ordinate is the stator electromotive force, the air gap line is the air gap line, which is the extension line of the no-load characteristic in the linear part. When e′ q <0.8, the saturation curve is a linear curve. When e′ q ≥0.8, the saturation curve is approximately a quadratic interpolation curve, and S(1.0) < S(1.2) should hold, and subsequently, by modifying the S(1.0) and S(1.2) parameters provided in the generator saturation model, the saturation degree of the generator is adjusted to obtain multiple saturation coefficients. S(1.0) represents the saturation coefficient when the stator electromotive force of the generator is the rated value, and S(1.2) is the saturation coefficient when the stator electromotive force is 1.2 times the rated value. When S(1.0) changes, it indicates the deviation degree of the saturation curve from the rated value (the stator electromotive force eq’ is 1.0). Similarly, S(1.2) is the deviation degree of the curve from 1.2 times the rated value. By setting these two values, the effects of different saturation characteristics can be simulated. The saturation effect of the synchronous condenser is also considered in the same way.

[0092] It's easy to understand that the saturation curve refers to the no-load saturation curve of the equipment, obtained through no-load testing, which is a fundamental test item for generators and synchronous condensers. Even for equipment of the same capacity, the no-load saturation curves are not entirely identical. Therefore, it is necessary to consider the uncertainty of the saturation curve and generate small-disturbance stability calculation samples, that is, to obtain several saturation coefficients as samples. In power system simulation software, a saturation model is usually used to fit the no-load saturation characteristics. Modifying the parameters in the saturation model actually changes the saturation characteristics of the generator and synchronous condenser. For example, when using the simulation software PSAT, two coefficients S(1.0) and S(1.2) can be used to describe the saturation model, and the deviation of the saturation curve can be adjusted by changing these two parameters.

[0093] Specifically, several saturation coefficients are determined by using the saturation models of generators and synchronous condensers, i.e., their saturation curves. These saturation coefficients must conform to the characteristics of the saturation curves to fully characterize the saturation characteristics of generators and synchronous condensers under different conditions. By using these saturation coefficients, we can ensure that the final prediction model can fully consider the saturation characteristics of generators and synchronous condensers under different conditions, further improving the accuracy and reliability of the minimum damping ratio output by the prediction model, and further ensuring the accuracy of the final evaluation results of the small disturbance stability of the power system.

[0094] As an optional embodiment, determining the correspondence between power flow samples, saturation coefficients, and the minimum damping ratio of the power system includes:

[0095] After freely combining several power flow samples and several saturation coefficients, the data is divided into N groups. Each group of data includes a one-to-one corresponding power flow sample and saturation coefficient, where N is a positive integer.

[0096] The characteristic values ​​of the power system corresponding to each set of data are calculated using power flow samples and saturation coefficients, respectively.

[0097] The damping ratio is calculated based on the characteristic values ​​of the power system, and the minimum damping ratio of N power systems corresponding to N sets of data is determined based on the minimum damping ratio, so as to obtain the correspondence between power flow samples, saturation coefficient and minimum damping ratio of power system.

[0098] It's easy to understand that after obtaining several power flow samples and several saturation coefficients as samples for small-disturbance stability calculations, eigenvalue calculations can be performed based on the sample data. Furthermore, some eigenvalues ​​from all samples that fall under key oscillation modes can be selected, and then the damping ratio can be calculated, retaining the minimum damping ratio as prediction data. The process of determining the minimum damping ratio through eigenvalue calculations can be implemented using a small-disturbance stability calculation program. This program can calculate the eigenvalues ​​of the power system under different power flow data and saturation data from different generators and synchronous condensers, λ.i (Eigenvalue) = σ i ±jω i , σ i and ω i The two parameters have already been obtained through the calculation program; the minimum damping ratio is then calculated using these characteristic values. This application does not impose any particular limitations on the calculation, amplification, or acquisition method of the minimum damping ratio; the use of a small disturbance stability calculation program is merely one specific embodiment.

[0099] Specifically, the one-to-one corresponding power flow samples and saturation coefficients are used as a set of sample data. Then, the minimum damping ratio corresponding to each set of sample data is calculated, thereby determining the correspondence between the power flow samples, saturation coefficients and the minimum damping ratio of the power system, so as to build the prediction model. The whole process is simple and effective. The free combination of sample data can comprehensively consider various situations of the power system, further improve the accuracy and reliability of the minimum damping ratio output by the prediction model, and further ensure the accuracy of the final evaluation results of the small disturbance stability of the power system.

[0100] As an optional embodiment, evaluating the small-disturbance stability of a power system based on the minimum damping ratio includes:

[0101] Determine whether the minimum damping ratio is less than a preset threshold;

[0102] If so, then the power system is deemed to be at risk of small-scale disturbance instability;

[0103] If not, then it is determined that there is no risk of small disturbance instability in the power system.

[0104] It is easy to understand that the minimum damping ratio can be used to determine whether a power system is at risk of low-frequency oscillations or instability. When the damping ratio is less than a certain set value, the power system is at risk of low-frequency oscillations; when the damping ratio is negative, the power system is at risk of instability. Therefore, a preset threshold can be set to determine whether the power system is at risk of small-disturbance instability, thereby assessing the small-disturbance stability of the power system. This application does not impose any special limitations on the specific setting method and value of the preset threshold; it can be determined according to the actual situation of the power system. Alternatively, a corresponding range of the minimum damping ratio can be set to assess the small-disturbance stability of the power system. This application does not impose any special limitations on the specific assessment method.

[0105] Specifically, the stability of a power system under small disturbances can be evaluated by comparing it with a preset threshold. The preset threshold can be adjusted according to the specific conditions of the power system. This method is simple, convenient, and easy to implement, which is conducive to the simple implementation of power system stability evaluation methods.

[0106] Please refer to Figure 6 , Figure 6 This invention provides a schematic diagram of the structure of a prediction model; as an optional embodiment, the minimum damping ratio of the power system corresponding to the current power flow data and the current saturation coefficient of the power system is determined using a pre-built prediction model, including:

[0107] The first feature vector output by the first feature extractor in the prediction model and the second feature vector output by the second feature extractor in the prediction model are concatenated to obtain a new feature vector. The first feature vector is the feature vector corresponding to the current power flow data of the power system, and the second feature vector is the feature vector corresponding to the current saturation coefficient of the generators and synchronous condensers in the power system.

[0108] The predicted value corresponding to the new feature vector output by the fully connected layer in the prediction model is used as the minimum damping ratio output of the power system corresponding to the current power flow data and the current saturation coefficient.

[0109] Considering that the input to the prediction model involves both saturation coefficient data and power flow data, and that the matrices formed by these two data points are of different sizes, a second feature extractor is used to extract features from the saturation coefficient matrix to avoid data scrambling. A first feature extractor, which can be a GCN network, is used to extract features from the power flow data of the bus nodes. The second feature extractor can be a CNN network. The extracted features are still matrices, which can be defined as the first and second eigenvectors, respectively. Both matrices need to be expanded into one-dimensional form and concatenated to form new eigenvectors for easy regression prediction. The entire prediction model process from input to output is called regression prediction. First, CNN and GCN are used to extract features from the saturation coefficient data and the power flow data of the bus nodes, respectively. The resulting features are then concatenated and used as input to the fully connected layer. This fully connected layer acts as a predictor, outputting a single value—the damping ratio—based on the input data. Therefore, by using the pre-established prediction model, the minimum damping ratio under this operating condition can be quickly obtained by inputting the saturation coefficient and power flow data.

[0110] As a specific implementation, when constructing the prediction model, a graph convolutional neural network and a convolutional neural network are fused together to evaluate the minimum damping ratio. The saturation coefficients of generators and synchronous condensers, as well as the bus power flow data, are normalized, and the processed data is limited to the range of [-1, 1]. Then, a graph convolutional neural network, a convolutional neural network model, and a three-layer fully connected layer are constructed. The graph convolutional neural network and the convolutional neural network are used as feature extractors, and the fully connected layer is used as a predictor. The graph convolutional neural network receives the bus power flow data, and the convolutional neural network receives the saturation coefficients of generators and synchronous condensers. The two types of feature extractors extract features from their respective input data, then concatenate and combine them into a new feature vector, which is finally fed into the predictor for regression prediction to output the minimum damping ratio. In constructing the prediction model, in addition to considering the power flow data, the saturation coefficients of the generators and synchronous condensers are adjusted to simulate the effects of the saturation characteristics of the corresponding equipment. These coefficients are then used together with the power flow data as sample input data and fed into their respective feature extractors for feature extraction. The prediction model is constructed by fusing graph convolutional neural networks and convolutional neural networks, which overcomes the drawbacks of individual models such as easy overfitting and low prediction ability, resulting in more accurate prediction results.

[0111] Specifically, by integrating the first feature extractor, the second feature extractor, and the fully connected layer to construct the prediction model, the drawbacks of a single model, such as easy overfitting and low prediction ability, are overcome, making the prediction results more accurate. At the same time, the first and second feature extractors are used to obtain power flow data and saturation coefficients, so that the final evaluation result takes into account both the power flow situation of the power system and the saturation characteristics of generators and synchronous condensers. This further improves the accuracy and reliability of the minimum damping ratio output by the prediction model, and further ensures the accuracy of the final evaluation result of the small disturbance stability of the power system.

[0112] As a specific embodiment, please refer to Figure 3 and Figure 6 , Figure 6The diagram shows the structure of the graph convolutional neural network (GCN) and the fusion model of convolutional neural networks. Taking the IEEE 14-node power system as an example, the power system has 5 generators, each with two saturation characteristic coefficients, S(1.0) and S(1.2), which can be modified. The 5 generators can form a 5*2 generator saturation coefficient matrix. CNN networks are suitable for processing this kind of image-like two-dimensional data, so CNN networks are used as the second feature extractor. The power system has 14 buses, and there are line connections between the buses. GCN networks are specifically designed for processing graph data and can also consider the features of connected neighboring nodes, making them suitable for the power grid structure. Since the generators are distributed, GCN networks are used as the first feature extractor. When extracting power flow data, the GCN network directly extracts the normalized bus power flow feature data. Then, it uses graph convolutional layers and the ReLU function (Rectified Linear Unit) to extract node features. The ReLU function is then used to flatten the node features before applying a linear transformation. The CNN network directly obtains the saturation coefficient feature matrices of generators and synchronous condensers. It then activates max pooling through two ReLU convolutions, flattens the features, and applies a linear transformation. Finally, the two feature vectors output from the GCN and CNN networks are concatenated and output to a fully connected layer. The fully connected layer outputs the minimum damping ratio as the evaluation result. The linear transformation process in the GCN and CNN networks can be implemented using a fully connected layer, or other methods can be employed.

[0113] Further, please refer to Figure 7 , Figure 8 , Figure 9 , Figure 10 and Figure 11 , Figure 7 A comparison chart of predicted and actual values ​​of the first test set of a prediction model provided by the present invention; Figure 8 A comparison chart of predicted and actual values ​​of a second test set for a prediction model provided by the present invention; Figure 9 A comparison chart of predicted values ​​and actual values ​​for the third test set of a prediction model provided by the present invention; Figure 10 A comparison chart of predicted values ​​and actual values ​​for the fourth test set of a prediction model provided by the present invention; Figure 11 This is a comparison chart of the predicted and actual values ​​of the fifth test set of a prediction model provided by the present invention; after constructing the power grid simulation model, 900 data samples can be generated according to the method described in the above embodiment, and they are divided into training set and test set in a ratio of 9:1; the training set is sent into the constructed prediction model for training, and the test set is used for verification after training is completed. Figures 7-11The validation results from the test set are used to evaluate the minimum damping ratio of the prediction model. To better observe the relative positions between the predicted and actual values, all samples (90 test samples) in the test set are presented in five graphs. Figure 7 This is a comparison chart showing the predicted values ​​and actual values ​​of the prediction model for sample data numbered 1-20 in the test set. Figure 8 This is a comparison chart showing the predicted values ​​and actual values ​​of the prediction model for sample data labeled 21-40. Figure 9 This is a comparison chart showing the predicted values ​​and actual values ​​of the prediction model for sample data labeled 41-60. Figure 10 This is a comparison chart showing the predicted values ​​and actual values ​​of the prediction model for sample data labeled 61-80. Figure 11 This chart compares the predicted values ​​of the prediction model with the actual values ​​for sample data labeled 81-90. It can be seen that the predicted values ​​in the test set are very close to the actual values, indicating that the model performs well.

[0114] Please refer to Figure 12 , Figure 12 This invention provides a structural schematic diagram of a power system stability assessment system; to solve the above-mentioned technical problems, this invention also provides a power system stability assessment system, comprising:

[0115] The first acquisition unit 21 is used to acquire the current power flow data of the power system;

[0116] The second acquisition unit 22 is used to acquire the current saturation coefficients of generators and synchronous condensers in the power system;

[0117] Damping ratio determination unit 23 is used to determine the minimum damping ratio of the power system corresponding to the current power flow data and the current saturation coefficient of the power system using a pre-built prediction model;

[0118] Evaluation unit 24 is used to evaluate the small-disturbance stability of the power system based on the minimum damping ratio.

[0119] As an optional embodiment, it also includes:

[0120] The power system model building unit is used to build a simulation model of the power system and obtain several power flow samples of the simulation model under different operating states.

[0121] The saturation coefficient sample acquisition unit is used to acquire several saturation coefficients of generators and synchronous condensers in the power system.

[0122] The correspondence determination unit is used to determine the correspondence between power flow samples, saturation coefficients and minimum damping ratios of the power system.

[0123] Predictive model building unit, used to build predictive models based on correspondences.

[0124] The power system model building unit includes a power system model building subunit and a power flow sample acquisition unit. The power system model building subunit is used to build a simulation model of the power system, and the power flow sample acquisition unit is used to acquire several power flow samples of the simulation model under different operating states.

[0125] As an optional embodiment, the power flow sample acquisition unit includes:

[0126] The basic power flow determination unit is used to determine the basic power flow data of the power system simulation model.

[0127] The power flow sample acquisition subunit is used to adjust the load power and / or power output of the power system simulation model in order to obtain several power flow samples of the simulation model under different operating states based on the basic power flow data.

[0128] As an optional embodiment, the saturation coefficient sample acquisition unit includes:

[0129] The saturation model determination unit is used to determine the saturation model of generators and synchronous condensers in the power system.

[0130] The saturation coefficient sample acquisition sub-unit is used to adjust the parameters of the saturation model to obtain several saturation coefficients.

[0131] As an optional embodiment, the correspondence determination unit includes:

[0132] The grouping unit is used to freely combine several power flow samples and several saturation coefficients into N groups of data. Each group of data includes a one-to-one corresponding power flow sample and saturation coefficient, where N is a positive integer.

[0133] The eigenvalue calculation unit is used to calculate the eigenvalues ​​of the power system corresponding to each set of data using power flow samples and saturation coefficients.

[0134] The correspondence determination sub-unit is used to calculate the damping ratio based on the characteristic value of the power system, and to determine the minimum damping ratio of N power systems that correspond one-to-one with N sets of data based on the minimum value of the damping ratio, so as to obtain the correspondence between the power flow sample, the saturation coefficient and the minimum damping ratio of the power system.

[0135] As an optional embodiment, the evaluation unit 24 includes:

[0136] The judgment unit is used to determine whether the minimum damping ratio is less than a preset threshold; if yes, the first judgment unit is triggered; if no, the second judgment unit is triggered.

[0137] The first determination unit is used to determine the risk of small-disturbance instability in the power system.

[0138] The second determination unit is used to determine whether there is a risk of small disturbance instability in the power system.

[0139] As an optional embodiment, the damping ratio determining unit 23 includes:

[0140] The feature concatenation unit is used to concatenate the first feature vector output by the first feature extractor in the prediction model and the second feature vector output by the second feature extractor in the prediction model to obtain a new feature vector. The first feature vector is the feature vector corresponding to the current power flow data of the power system, and the second feature vector is the feature vector corresponding to the current saturation coefficient of the generators and synchronous condensers in the power system.

[0141] The damping ratio determination sub-unit is used to take the predicted value corresponding to the new eigenvector output by the fully connected layer in the prediction model as the minimum damping ratio output of the power system corresponding to the current power flow data and the current saturation coefficient of the power system.

[0142] For an introduction to the power system stability assessment system provided by this invention, please refer to the embodiments of the power system stability assessment method described above. This invention will not be repeated here.

[0143] Please refer to Figure 13 , Figure 13 This is a schematic diagram of the structure of an electronic device provided by the present invention. To solve the above-mentioned technical problems, the present invention also provides an electronic device, comprising:

[0144] Memory 31 is used to store computer programs;

[0145] Processor 32 is used to implement the steps of the power system stability assessment method as described above.

[0146] The processor 32 may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor 32 may be implemented using at least one hardware form selected from DSP (Digital Signal Processor), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 32 may also include a main processor and a coprocessor. The main processor, also known as the central processing unit, is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor 32 may integrate a GPU (graphics processing unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, the processor 32 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0147] The memory 31 may include one or more computer-readable storage media, which may be non-transitory. The memory 31 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In this embodiment, the memory 31 is used to store at least the following computer program, which, after being loaded and executed by the processor 32, is capable of implementing the relevant steps of the power system stability assessment method disclosed in any of the foregoing embodiments. In addition, the resources stored in the memory 31 may also include an operating system and data, and the storage method may be temporary or permanent storage. The operating system may include Windows, Unix, Linux, etc. The data may include, but is not limited to, data related to the power system stability assessment method.

[0148] In some embodiments, the electronic device may further include a display screen, an input / output interface, a communication interface, a power supply, and a communication bus.

[0149] It will be understood by those skilled in the art that Figure 13 The structures shown do not constitute a limitation on electronic devices and may include more or fewer components than those shown.

[0150] For an introduction to the electronic device provided by this invention, please refer to the embodiments of the above-described power system stability assessment method; the present invention will not be described in detail here.

[0151] To address the aforementioned technical problems, the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the aforementioned power system stability assessment method.

[0152] It is understood that if the methods in the above embodiments are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and executes all or part of the steps of the methods described in the various embodiments of this application. Specifically, the computer-readable storage medium may include, but is not limited to, any type of disk, including floppy disks, optical disks, and portable hard drives, or any type of media or device suitable for storing instructions or data, etc., and this application does not make any special limitations here.

[0153] For an introduction to the computer-readable storage medium provided by this invention, please refer to the embodiments of the above-described power system stability assessment method; the present invention will not be repeated here.

[0154] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0155] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for evaluating the stability of a power system, characterized in that, include: Obtain current power flow data of the power system; Obtain the current saturation coefficients of the generators and synchronous condensers in the power system; The minimum damping ratio of the power system corresponding to the current power flow data and the current saturation coefficient is determined using a pre-built prediction model; the prediction model has been pre-trained to establish a mapping relationship between input and output. The small-disturbance stability of the power system is evaluated based on the minimum damping ratio. The step of determining the minimum damping ratio of the power system corresponding to the current power flow data and the current saturation coefficient using a pre-built prediction model includes: The first feature vector output by the first feature extractor in the prediction model and the second feature vector output by the second feature extractor in the prediction model are concatenated to obtain a new feature vector. The first feature vector is the feature vector corresponding to the current power flow data of the power system, and the second feature vector is the feature vector corresponding to the current saturation coefficient of the generators and synchronous condensers in the power system. The predicted value corresponding to the new feature vector output by the fully connected layer in the prediction model is used as the minimum damping ratio of the power system corresponding to the current power flow data and the current saturation coefficient.

2. The power system stability assessment method as described in claim 1, characterized in that, Before acquiring the current power flow data of the power system, the method further includes: A simulation model of the power system is constructed, and several power flow samples of the simulation model under different operating states are obtained; Obtain several saturation coefficients of the generators and synchronous condensers in the power system; Determine the correspondence between the power flow sample, the saturation coefficient, and the minimum damping ratio of the power system; A prediction model is constructed based on the aforementioned correspondence.

3. The power system stability assessment method as described in claim 2, characterized in that, The step of obtaining several power flow samples of the simulation model under different operating states includes: Determine the basic power flow data for the simulation model of the power system; Adjust the load power and / or power output of the simulation model of the power system to obtain several power flow samples of the simulation model under different operating states based on the basic power flow data.

4. The power system stability assessment method as described in claim 3, characterized in that, The acquisition of several saturation coefficients of generators and synchronous condensers in the power system includes: Determine the saturation models for generators and synchronous condensers in the power system; The parameters of the saturation model are adjusted to obtain several saturation coefficients.

5. The power system stability assessment method as described in claim 2, characterized in that, Determining the correspondence between the power flow sample, the saturation coefficient, and the minimum damping ratio of the power system includes: After freely combining several power flow samples and several saturation coefficients, the data is divided into N groups. Each group of data includes a one-to-one corresponding power flow sample and saturation coefficient, where N is a positive integer. The characteristic values ​​of the power system corresponding to each set of data are calculated using the power flow samples and the saturation coefficient, respectively. The damping ratio is calculated based on the characteristic values ​​of the power system, and the minimum damping ratio of the power system is determined based on the minimum value of the damping ratio, corresponding to N sets of data, so as to obtain the correspondence between the power flow sample, the saturation coefficient and the minimum damping ratio of the power system.

6. The power system stability assessment method as described in claim 1, characterized in that, The evaluation of the small-disturbance stability of the power system based on the minimum damping ratio includes: Determine whether the minimum damping ratio is less than a preset threshold; If so, the power system is deemed to be at risk of small-scale disturbance instability. If not, then it is determined that the power system does not pose a risk of small disturbance instability.

7. A stability assessment system for a power system, characterized in that, include: The first acquisition unit is used to acquire the current power flow data of the power system; The second acquisition unit is used to acquire the current saturation coefficients of the generators and synchronous condensers in the power system; The damping ratio determination unit is used to determine the minimum damping ratio of the power system corresponding to the current power flow data and the current saturation coefficient of the power system using a pre-built prediction model; the prediction model has been pre-trained to establish a mapping relationship between input and output. An evaluation unit is used to evaluate the small-disturbance stability of the power system based on the minimum damping ratio; The damping ratio determination unit includes: The feature concatenation unit is used to concatenate the first feature vector output by the first feature extractor in the prediction model and the second feature vector output by the second feature extractor in the prediction model to obtain a new feature vector. The first feature vector is a feature vector corresponding to the current power flow data of the power system, and the second feature vector is a feature vector corresponding to the current saturation coefficient of the generators and synchronous condensers in the power system. The damping ratio determination subunit is used to output the predicted value corresponding to the new feature vector output by the fully connected layer in the prediction model as the minimum damping ratio of the power system corresponding to the current power flow data and the current saturation coefficient of the power system.

8. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor for implementing the steps of the power system stability assessment method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the power system stability assessment method as described in any one of claims 1 to 6.

Images