CN111414718B - Reactive power output modeling method and system for synchronous phase modulator and storage medium - Google Patents
Reactive power output modeling method and system for synchronous phase modulator and storage medium Download PDFInfo
- Publication number
- CN111414718B CN111414718B CN202010157427.8A CN202010157427A CN111414718B CN 111414718 B CN111414718 B CN 111414718B CN 202010157427 A CN202010157427 A CN 202010157427A CN 111414718 B CN111414718 B CN 111414718B
- Authority
- CN
- China
- Prior art keywords
- svm
- synchronous phase
- phase modulator
- training
- reactive power
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
Abstract
The invention discloses a method, a system and a storage medium for modeling reactive power output of a synchronous phase modulator, wherein the method comprises the following steps: selecting exciting current and exciting voltage of a synchronous phase modulator as SVM input, and selecting reactive output quantity of the synchronous phase modulator and voltage of a direct-current power transmission system as SVM output; selecting a training sample and a testing sample according to a reactive power regulation calculation result of the synchronous phase modulator; taking the mean square error of the training samples under the meaning of cross validation as a fitness function value in the PSO, and searching an SVM optimal parameter by adopting a PSO optimization SVM parameter; and training the SVM by using the optimal parameters, and performing generalization capability test on the SVM after training by using the test sample. The method can reduce the difficulty of reactive power output modeling of the synchronous phase modulator and improve the modeling precision.
Description
Technical Field
The invention relates to a reactive power output modeling method, a system and a storage medium for a synchronous phase modulator, and belongs to the technical field of direct-current power transmission systems.
Background
With the large-scale construction of a long-distance direct-current transmission power grid, the transmission capacity and the voltage grade of the long-distance direct-current transmission power grid are continuously improved, the compensation requirement of the reactive capacity of the converter station is larger and larger, and particularly, the dynamic reactive compensation plays an important role in stabilizing the voltage of a direct-current transmission system. Compared with other reactive compensation equipment, the synchronous phase modulator has the characteristics of larger capacity, higher reliability and strong dynamic voltage maintenance capability, and can provide large-capacity dynamic reactive power in time through forced excitation under the condition of power grid disturbance. The power grid of China enters the era of extra-high voltage, large power grid, large unit and alternating current-direct current interconnection, and the unique reactive output characteristic of the synchronous phase modulator meets the dynamic reactive power requirement of the power grid, so that the large synchronous phase modulator is applied to ensure the safe, reliable and economical operation of the power grid.
At present, SVM parameters are sometimes selected by experience in the modeling process of a synchronous phase modulator, the selected SVM parameters cannot be guaranteed to be optimal, the selection difficulty of the optimal SVM parameters is high, and the modeling precision is low; the grid search (grid search) is used to find the best SVM parameters in the CV sense, although the global optimal solution can be searched, it is time-consuming to find the best SVM parameters in a larger range. Therefore, the technical problems that the reactive power output analysis modeling of the synchronous phase modulator is difficult and the modeling precision is low still exist in the prior art.
Disclosure of Invention
The invention aims to overcome the defects in the prior art, provides a method and a system for modeling reactive power output of a synchronous phase modulator and a storage medium, and can reduce the difficulty of modeling reactive power output of the synchronous phase modulator and improve the modeling precision.
In order to achieve the purpose, the invention adopts the following technical scheme:
in a first aspect, the invention provides a reactive power output modeling method for a synchronous phase modulator, which comprises the following steps:
selecting the historical current and the excitation voltage of a synchronous phase modulator as SVM input, and the reactive output quantity of the synchronous phase modulator and the voltage of a direct-current power transmission system as SVM output;
selecting a training sample and a testing sample according to a reactive power regulation simulation result of the synchronous phase modulator;
taking the mean square error of the training samples under the meaning of cross validation as a fitness function value in the PSO, and searching an SVM optimal parameter by adopting a PSO optimization SVM parameter;
and training the SVM by using the optimal parameters, and performing generalization capability test on the SVM after training by using the test sample.
With reference to the first aspect, further, the method further includes:
and preprocessing the training samples and the test samples before searching for the optimal parameters of the SVM.
With reference to the first aspect, further, the preprocessing includes performing normalization on the training samples and the test samples using the following formula:
in the formula: p is a training sample; pmaxIs the maximum value of the training sample; pminIs the training sample minimum; pnIs a normalized training sample; t is a test sample; t ismaxIs the maximum value of the test sample; t isminIs the minimum value of the test sample; t isnIs a normalized test sample.
With reference to the first aspect, further, the calculation result of the reactive power regulation of the synchronous phase modulator is a calculation result of the reactive power regulation of the synchronous phase modulator based on PSCAD/EMTDC simulation software.
With reference to the first aspect, further, the optimal parameters include a penalty parameter c, a kernel function parameter g, and a loss function parameter p.
With reference to the first aspect, further, the method for finding the optimal parameter includes the following steps:
setting the fitness function of each particle in the PSO as a mean square error in the sense of cross validation of the training sample;
initializing the speed and position of particles in the population;
calculating the fitness of the particles according to the fitness function;
if the fitness of the particles is greater than the optimal fitness, reserving the position vector for the particles, and if the fitness of the particles is superior to the global optimal fitness, saving the position vector as the global optimal; if the termination condition is met, outputting an optimal solution (c, g, p); otherwise, the speed and the position of the particles are updated, and the optimal solution is determined.
In a second aspect, the present invention provides a synchronous phase modulator reactive power output modeling system, comprising:
an input/output selection module: the method is used for selecting the historical current and the excitation voltage of the synchronous phase modulator as the input of the SVM, and the reactive output quantity of the synchronous phase modulator and the voltage of a direct-current power transmission system as the output of the SVM;
a sample selection module: the device is used for selecting a training sample and a testing sample according to the reactive power regulation calculation result of the synchronous phase modulator;
an optimal parameter searching module: the method is used for taking the mean square error of the training samples under the meaning of cross validation as a fitness function value in the PSO, and optimizing SVM parameters by adopting the PSO to find the best parameter of the SVM;
training a testing module: the method is used for training the SVM by using the optimal parameters and carrying out generalization capability test on the SVM after training by using the test sample.
With reference to the second aspect, further, the system further includes a preprocessing module: the method is used for carrying out normalization processing on the training samples and the test samples by adopting the following formula:
in the formula: p is a training sample; pmaxIs the maximum value of the training sample; p isminIs the training sample minimum; pnIs a normalized training sample; t is a test sample; t ismaxIs the maximum value of the test sample; t isminIs the minimum value of the test sample; t isnIs a normalized test sample.
In a third aspect, the invention provides a reactive power output modeling system of a synchronous phase modulator, which comprises a processor and a storage medium;
the storage medium is used for storing instructions;
the processor is configured to operate in accordance with the instructions to perform the steps of any of the preceding methods.
In a fourth aspect, the invention provides a computer-readable storage medium, on which a computer program is stored, characterized in that the program, when executed by a processor, implements the steps of any of the methods described above.
Compared with the prior art, the method, the system and the storage medium for modeling the reactive power output of the synchronous phase modulator provided by the invention have the beneficial effects that:
the PSO algorithm is adopted to optimize SVM parameters, a global optimal solution can be found without searching all parameter points in a grid, the reactive output of the synchronous phase modulation camera and the voltage of a direct-current transmission system under different excitation currents and excitation voltages can be predicted with high precision, and the defects that the synchronous phase modulation camera is difficult to analyze and model and low in modeling precision are effectively overcome. The model can be used for parameter monitoring and reactive output regulation during the operation of the synchronous phase modulator.
Drawings
Fig. 1 is a flowchart of a method for modeling reactive power output of a synchronous phase modulator according to an embodiment of the present invention;
FIG. 2 is a flow chart of an algorithm for optimizing SVM parameters using PSO in an embodiment of the present invention;
FIG. 3 is a graph comparing the outputs of an SVM under test sample with a PSO-optimized SVM in accordance with an embodiment of the present invention;
fig. 4 is a graph comparing errors of SVM and PSO-optimized SVM of test samples in an embodiment of the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
The reactive power output is an important index for measuring the performance of the synchronous phase modifier, the synchronous phase modifier has the function of maintaining the bus voltage of a system to be stable, and the voltage of a direct-current transmission system is the most key monitoring index in the running process of the synchronous phase modifier, so the embodiment of the invention provides a reactive power output modeling method of the synchronous phase modifier, which comprehensively considers the factors, applies the reactive power regulation simulation result of the synchronous phase modifier to perform SVM training for a training sample, applies the testing sample to optimize SVM parameters by PSO to perform SVM testing, establishes a reactive power output model of the synchronous phase modifier, and overcomes the defects of difficult analysis modeling and low modeling precision of the reactive power output of the synchronous phase modifier. As shown in fig. 1, the method for modeling reactive power output of a synchronous phase modulator provided in the embodiment of the present invention specifically includes the following steps:
step 1: selecting exciting current and exciting voltage of a synchronous phase modulator as SVM input, and taking the reactive output quantity of the synchronous phase modulator and the voltage of a direct-current power transmission system as SVM output;
the method specifically comprises the following steps: according to the requirements of a direct current transmission system, the reactive output quantity of the synchronous phase modulator is adjusted by changing exciting current and exciting voltage under different reactive load working conditions, so that the reactive output of the synchronous phase modulator is related to the sizes of the exciting current and the exciting voltage, and the exciting current and the exciting voltage of the synchronous phase modulator are selected as the input of an SVM (support vector machine); the reactive output of the synchronous phase modifier is an important index for measuring the performance of the synchronous phase modifier, and the voltage of a direct-current transmission system is the most key monitoring index in the running process of the synchronous phase modifier, so that the reactive output of the synchronous phase modifier and the voltage of the direct-current transmission system are selected as the output of the SVM.
Step 2: carrying out normalization pretreatment on a training sample and a test sample obtained from a reactive power regulation simulation result of a synchronous phase modulator;
as an embodiment, the reactive power regulation simulation result of the synchronous phase modulator based on the PSCAD/EMTDC simulation software is used as a training sample and a test sample, as shown in table 1, the data of the serial numbers 8, 13, 25, and 35 can be selected from the 38 groups of samples as the test sample, and the rest are the training samples.
Table 1 with numbers 8, 13, 25 and 35 as test samples and the rest as training samples
Because the training and testing sample data have differences in dimension, order of magnitude and the like, the training and testing sample data of the SVM need to be normalized.
In the embodiment of the invention, the normalization principle formula is as follows:
in the formula: p is a training sample; pmaxIs the maximum value of the training sample; pminIs the minimum value of the training samples; p isnIs a normalized training sample; t is a test sample; t is a unit ofmaxIs the maximum value of the test sample; t isminIs the minimum value of the test sample; t isnAre normalized test samples.
And step 3: taking Mean Square Error (MSE) of training samples in the Cross Validation (CV) sense as a fitness function value in PSO, and searching SVM optimal parameters (a penalty parameter c, a kernel function parameter g and a loss function parameter p);
as shown in fig. 2, the algorithm flow for optimizing SVM parameters by using PSO mainly includes the following steps:
step 301: setting a fitness function of each particle in the PSO as a Mean Square Error (MSE) in the sense of Cross Validation (CV) on training samples, wherein the optimal SVM parameter is a parameter which enables the training samples to reach the lowest MSE under the CV idea;
step 302: initializing the speed and position of particles in the population;
step 303: calculating the fitness of the particles according to the fitness function;
step 304: if the fitness of the particles is greater than the optimal fitness, reserving the position vector for the particles, and if the fitness of the particles is superior to the global optimal fitness, saving the position vector as the global optimal; if the termination condition is met, outputting an optimal solution (c, g, p), otherwise, updating the speed and the position of the particles and determining the optimal solution.
The punishment parameters c, the kernel function parameters g and the loss function parameters p of the SVM have great influence on the learning state and the regression prediction capability of the SVM, and the performance of the SVM is greatly improved by the optimized selection of the SVM parameters. If the penalty parameter c of the SVM is too large, an over-learning state can occur, the generalization capability is reduced, and if the penalty parameter c is too small, correct regression can not be performed.
Selecting the SVM kernel function as a radial basis kernel function by comparing different kernel functions:
K(x,xi)＝exp(-gamma||x-xi||2),gamma＞0 (3)
in the formula: k (x, x)i) Is a radial basis kernel function; x is sample data; x is a radical of a fluorine atomiThe ith sample data; gamma is the SVM kernel parameter g.
And 4, step 4: and (5) carrying out SVM training by using the searched optimal parameters (c, g, p), and carrying out generalization capability test on the SVM after training by using the test sample.
The generalization ability of the PSO optimized SVM model is verified in a table 2, in order to further verify the generalization ability of the PSO optimized SVM model, the output result of the PSO optimized SVM model is compared with the output result of an unoptimized SVM model in a table 3, and the result shows that the reactive power output model of the synchronous phase modulator established based on the PSO optimized SVM can predict the reactive power output and the voltage of a direct-current power transmission system of the synchronous phase modulator under the conditions of different exciting currents and exciting voltages with higher precision, so that the defects that the reactive power output analysis modeling of the synchronous phase modulator is difficult and the modeling precision is low are effectively overcome.
TABLE 2 PSO optimization SVM model generalization ability verification
TABLE 3 generalization ability comparison of SVM model with PSO optimized SVM model
The embodiment of the invention also provides a reactive power output modeling system of the synchronous phase modulator, which comprises the following components:
an input/output selection module: the method is used for selecting exciting current and exciting voltage of a synchronous phase modulator as SVM input, and taking the reactive output quantity of the synchronous phase modulator and the voltage of a direct-current power transmission system as SVM output;
a sample selection module: the device is used for selecting a training sample and a testing sample according to the reactive power regulation calculation result of the synchronous phase modulator;
an optimal parameter finding module: the method is used for taking the mean square error of the training samples under the meaning of cross validation as a fitness function value in the PSO, and adopting POS optimization SVM parameters to search SVM optimal parameters;
training a testing module: the method is used for training the SVM by using the optimal parameters and carrying out generalization capability test on the SVM after training by using the test sample.
The reactive power output modeling system of the synchronous phase modulator provided by the embodiment of the invention can be used for realizing the reactive power output modeling method of the synchronous phase modulator, and the function realization of each module can refer to the description of the method part, and is not repeated herein. Because the system provided by the embodiment of the invention is realized based on the same technical concept as the method, when the system provided by the embodiment of the invention is applied to the reactive power output modeling of the synchronous phase modulator, the defects of difficult reactive power output analysis modeling and low modeling precision of the synchronous phase modulator can be overcome.
In order to overcome differences in dimensions, magnitude orders and the like between training and test sample data, the reactive power output modeling system of the synchronous phase modulator provided by the embodiment of the invention further comprises a preprocessing module: the method is used for carrying out normalization processing on the training samples and the test samples by adopting the following formula:
in the formula: p is a training sampleThen, the process is carried out; p ismaxIs the maximum value of the training sample; pminIs the training sample minimum; pnIs a normalized training sample; t is a test sample; t ismaxIs the maximum value of the test sample; t isminIs the minimum value of the test sample; t isnIs a normalized test sample.
The embodiment of the invention also provides a reactive power output modeling system of the synchronous phase modulator, which comprises a processor and a storage medium;
the storage medium is used for storing instructions;
the processor is configured to operate in accordance with the instructions to perform the steps of any of the preceding methods.
An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program is configured to, when executed by a processor, implement the steps of any one of the methods described above.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.
Claims (10)
1. A reactive power output modeling method of a synchronous phase modulator is characterized by comprising the following steps:
selecting exciting current and exciting voltage of a synchronous phase modulator as SVM input, and taking the reactive output quantity of the synchronous phase modulator and the voltage of a direct-current power transmission system as SVM output;
selecting a training sample and a testing sample according to a reactive power regulation simulation result of the synchronous phase modulator;
taking the mean square error of the training samples under the meaning of cross validation as a fitness function value in the PSO, and searching an SVM optimal parameter by adopting a PSO optimization SVM parameter;
and training the SVM by using the optimal parameters, and performing generalization capability test on the SVM after training by using the test sample.
2. The synchronous phase modulator reactive power modeling method of claim 1, further comprising:
and preprocessing the training samples and the test samples before searching for the optimal parameters of the SVM.
3. The method according to claim 2, wherein the preprocessing comprises normalizing the training samples and the test samples using the following formula:
in the formula: p is a training sample; pmaxIs the maximum value of the training sample; pminIs the training sample minimum; pnIs a normalized training sample; t is a test sample; t is a unit ofmaxIs the maximum value of the test sample; t isminIs the minimum value of the test sample; t isnIs a normalized test sample.
4. The modeling method of reactive power of a synchronous phase modulator according to claim 1, wherein the calculation result of reactive power modulation of the synchronous phase modulator is a calculation result of reactive power modulation of the synchronous phase modulator based on PSCAD/EMTDC simulation software.
5. The method according to claim 1, wherein the optimal parameters include a penalty parameter c, a kernel function parameter g, and a loss function parameter p.
6. The modeling method of reactive power of synchronous phase modulator according to claim 5, characterized in that said method for finding optimal parameters comprises the steps of:
setting the fitness function of each particle in the PSO as a mean square error in the sense of cross validation of the training sample;
initializing the speed and position of particles in the population;
calculating the fitness of the particles according to the fitness function;
if the fitness of the particles is greater than the optimal fitness, reserving the position vector for the particles, and if the fitness of the particles is superior to the global optimal fitness, saving the position vector as the global optimal; if the termination condition is met, outputting an optimal solution (c, g, p); otherwise, the speed and the position of the particles are updated, and the optimal solution is determined.
7. A synchronous phase modulator reactive power output modeling system, the system comprising:
an input/output selection module: the method is used for selecting the historic current and the excitation voltage of the synchronous phase modulator as the input of the SVM, and the reactive output quantity of the synchronous phase modulator and the voltage of a direct-current power transmission system as the output of the SVM;
a sample selection module: the synchronous phase modifier is used for selecting a training sample and a testing sample according to a reactive power regulation calculation result of the synchronous phase modifier;
an optimal parameter searching module: the method is used for taking the mean square error of a training sample under the meaning of cross validation as a fitness function value in the PSO, and optimizing SVM parameters by adopting the PSO to search SVM optimal parameters;
training a testing module: the method is used for training the SVM by using the optimal parameters and carrying out generalization capability test on the SVM after training by using the test sample.
8. The synchronous phase modulator reactive power modeling system of claim 7, further comprising a preprocessing module to: the method is used for carrying out normalization processing on the training samples and the test samples by adopting the following formula:
in the formula: p is a training sample; pmaxIs the maximum value of the training sample; pminIs the training sample minimum; pnIs a normalized training sample; t is a test sample; t ismaxIs the maximum value of the test sample; t isminIs the minimum value of the test sample; t isnIs a normalized test sample.
9. A reactive power output modeling system of a synchronous phase modulator is characterized by comprising a processor and a storage medium;
the storage medium is used for storing instructions;
the processor is configured to operate in accordance with the instructions to perform the steps of the method according to any one of claims 1 to 6.
10. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, is adapted to carry out the steps of the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010157427.8A CN111414718B (en) | 2020-03-09 | 2020-03-09 | Reactive power output modeling method and system for synchronous phase modulator and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010157427.8A CN111414718B (en) | 2020-03-09 | 2020-03-09 | Reactive power output modeling method and system for synchronous phase modulator and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111414718A CN111414718A (en) | 2020-07-14 |
| CN111414718B true CN111414718B (en) | 2022-06-10 |
Family
ID=71492865
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010157427.8A Active CN111414718B (en) | 2020-03-09 | 2020-03-09 | Reactive power output modeling method and system for synchronous phase modulator and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111414718B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103743980A (en) * | 2014-01-14 | 2014-04-23 | 山东科技大学 | Power quality disturbance recognition and classification method based on PSO (Particle Swarm Optimization) for SVM (Support Vector Machine) |
| CN109066818A (en) * | 2018-08-30 | 2018-12-21 | 国家电网公司华东分部 | Synchronous generator/phase modifier dynamic reactive lays in calculation method |
| CN109962479A (en) * | 2019-03-28 | 2019-07-02 | 国网山东省电力公司电力科学研究院 | A kind of synchronous capacitor electric parameter distribution joint discrimination method based on alternating iteration optimization |
| CN110703077A (en) * | 2019-09-25 | 2020-01-17 | 西安工程大学 | HPSO-TSVM-based high-voltage circuit breaker fault diagnosis method |
-
2020
- 2020-03-09 CN CN202010157427.8A patent/CN111414718B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103743980A (en) * | 2014-01-14 | 2014-04-23 | 山东科技大学 | Power quality disturbance recognition and classification method based on PSO (Particle Swarm Optimization) for SVM (Support Vector Machine) |
| CN109066818A (en) * | 2018-08-30 | 2018-12-21 | 国家电网公司华东分部 | Synchronous generator/phase modifier dynamic reactive lays in calculation method |
| CN109962479A (en) * | 2019-03-28 | 2019-07-02 | 国网山东省电力公司电力科学研究院 | A kind of synchronous capacitor electric parameter distribution joint discrimination method based on alternating iteration optimization |
| CN110703077A (en) * | 2019-09-25 | 2020-01-17 | 西安工程大学 | HPSO-TSVM-based high-voltage circuit breaker fault diagnosis method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111414718A (en) | 2020-07-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Casella | Simulation of large-scale models in modelica: State of the art and future perspectives | |
| CN112018758A (en) | Modeling method of high-proportion new energy-containing alternating current-direct current hybrid system based on digital twinning | |
| CN109638815B (en) | Method for determining safety and stability prevention control strategy of medium-and-long-term voltage of power system | |
| CN115481549A (en) | Cylindrical linear motor multi-objective optimization method, equipment and storage medium | |
| CN113139570A (en) | Dam safety monitoring data completion method based on optimal hybrid valuation | |
| CN113326869A (en) | Deep learning calculation graph optimization method based on longest path fusion algorithm | |
| CN111414718B (en) | Reactive power output modeling method and system for synchronous phase modulator and storage medium | |
| CN112072715B (en) | Method and device for determining new energy acceptance of power grid in consideration of transient voltage constraint | |
| CN113537614A (en) | Construction method, system, equipment and medium of power grid engineering cost prediction model | |
| CN112287605A (en) | Flow check method based on graph convolution network acceleration | |
| CN116305683A (en) | Power system transient stability evaluation method and system based on sample equalization | |
| CN105468726A (en) | Local computing and distributed computing based data computing method and system | |
| CN111371089B (en) | Power grid dynamic equivalence quantitative evaluation method and system | |
| CN114386510A (en) | Method and system for identifying measurement errors of power system | |
| CN110048404B (en) | Online optimization method and device for low-frequency oscillation suppressor of power system and storage medium | |
| CN113901649A (en) | Load parameter identification method, system and storage medium in frequency simulation | |
| CN112751334A (en) | Power grid online modeling method and system based on memory computing architecture | |
| CN111814394A (en) | Power system safety assessment method based on correlation and redundancy detection | |
| CN111082414A (en) | Transient voltage calculation method and system | |
| CN113822470B (en) | Output data generation method and system considering uncertainty of new energy station output | |
| CN115293083B (en) | Integrated circuit time sequence prediction method and device, electronic equipment and storage medium | |
| CN112653131B (en) | Transient voltage safety stability margin estimation method, device and system | |
| CN116244853B (en) | Harmonic balance method accelerating convergence method for predicting unsteady flow of turbine | |
| CN111641360B (en) | Method and device for obtaining transient voltage drop and starting equipment, equipment and medium | |
| CN117435308B (en) | Modelica model simulation method and system based on parallel computing algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |