Method for establishing limit clearing time prediction model of power system based on incremental updating

Through the power system's limit resection time prediction model based on incremental update, the dichotomy solution interval is simplified, the solution efficiency of the limit resection time is improved, the problem of dichotomy in the existing technology is solved, and the efficient limit resection time is achieved predict.

CN118944054AActive Publication Date: 2024-11-12HUAZHONG UNIV OF SCI & TECH
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202410948236.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-15
Publication Date
2024-11-12
Estimated Expiration
2044-07-15

AI Technical Summary

Technical Problem

In the prior art, the online solution speed of the limit resection time is slow, mainly due to the large number of attempts to dichotomy, which seriously limits the research efficiency.

Method used

The ultimate removal time prediction model for power system based on incremental update is established. By constructing the initial prediction model, the operating state of power system of multiple batches is sampled and the maximum removal time of the initial batch is solved by dichotomy, and the maximum removal time of the initial batch is increased by increasing the Quantitative learning trains the latest prediction model, simplifies the solution interval, and reduces the number of solutions of dichotomous methods.

Benefits of technology

The solution efficiency of the limit resection time is greatly improved, and the solution operation volume of the traditional dichotomy method is reduced by about 90%, which improves the efficiency of model training and sample label generation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118944054A_ABST
    Figure CN118944054A_ABST
Patent Text Reader

Abstract

The invention discloses a power system limit clearing time prediction model establishment method based on incremental updating, and belongs to the field of power system stability analysis, and the method comprises the steps: S1, sampling to obtain a plurality of batches of power system operation state quantities; s2, solving the limit clearing time corresponding to the operation state quantity of the power system of the first batch by adopting a bisection method; s3, taking the operation state quantity of the ith batch of the power system as input, taking the corresponding limit clearing time as a label, and training a latest prediction model, the initial value of i being 1; s4, utilizing the trained prediction model to determine a simplified solving interval where the limit clearing time corresponding to the operation state quantity of the electric power system of the (i + 1) th batch is located, adopting a bisection method to determine the corresponding limit clearing time from the simplified solving interval, and adding one to i; and S5, repeatedly executing the steps S3-S4 to train the prediction model. According to the method, the solution space of the bisection method in the limit clearing time can be simplified, and the algorithm solution efficiency is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the field of power system stability analysis, and more specifically, relates to a method for establishing a power system limit cut-off time prediction model based on incremental updating. Background Art

[0002] As the scale of my country's power grid continues to grow, a high proportion of renewable energy and power electronic equipment are continuously connected, the safety and stability analysis of the power system is becoming more and more important. Preventive control is one of the three lines of defense of the power system. Among them, the limit removal time, as a key evaluation indicator of the dynamic safety and stability margin of the power system, can provide effective guidance for whether to take preventive control measures.

[0003] At present, there are two online solutions for the limit removal time: direct method and data-driven method. With the rapid development of artificial intelligence, the speed of online solution of the limit removal time by the direct method has lagged far behind the data-driven method. The data-driven method requires massive data for offline training, and the basis of offline training is power system simulation data and limit removal time labels. In order to ensure the accuracy of the limit removal time label, time-domain simulation is generally used to continuously approximate the true value through binary search. However, the binary search method has many attempts, resulting in a long simulation time, which seriously limits the research efficiency. Therefore, how to simplify the binary search space and improve the limit removal time is of great research significance. Summary of the invention

[0004] In view of the defects of the prior art and the need for improvement, the present invention provides a method for establishing a prediction model of the extreme cut-off time of an electric power system based on incremental updating, which aims to simplify the solution space of the binary search method for the extreme cut-off time and improve the solution efficiency of the algorithm.

[0005] To achieve the above-mentioned purpose, according to one aspect of the present invention, a method for establishing a prediction model for the limit cut-off time of an electric power system based on incremental updating is provided, comprising: S1, constructing an initial prediction model, sampling and obtaining multiple batches of electric power system operating state quantities; S2, using the binary search method to solve the limit cut-off time corresponding to the first batch of electric power system operating state quantities; S3, using the i-th batch of electric power system operating state quantities as input and the corresponding limit cut-off time as a label, training the latest prediction model, and the initial value of i is 1; S4, using the trained prediction model to determine the simplified solution interval in which the limit cut-off time corresponding to the i+1-th batch of electric power system operating state quantities is located, using the binary search method to determine the corresponding limit cut-off time from the simplified solution interval, and adding one to i; S5, repeatedly executing S3-S4 until the loss function of the prediction model converges, or until the prediction model has been trained using all batches of electric power system operating state quantities.

[0006] Furthermore, S3 specifically includes: when i=1, the first batch of power system operating state quantities are used as input, and the corresponding limit cut-off time is used as a label, and the initial prediction model is trained in a supervised manner; when i>1, the i-th batch of power system operating state quantities are used as input, and the corresponding limit cut-off time is used as a label, and the latest prediction model is trained through incremental learning.

[0007] Furthermore, when i=1, the initial prediction model is trained as follows:

[0008]

[0009] in, is the first objective function, θ is the parameter of the prediction model, N is the number of power system operating state quantities in the same batch, represents the training set data, x (n) ,y (n) are the nth power system operating state quantity and the corresponding limit removal time in the same batch, f() represents the prediction result of the prediction model, l() represents the label loss, and Ω(θ) is the regularization term of the prediction model.

[0010] Furthermore, when i>1, the method of training the latest prediction model through incremental learning is:

[0011]

[0012] Among them, F is the latest prediction model before training, θ F is the parameter of F, The parameters that need to be updated for F in this batch, is the second objective function, Represents the training set data of this batch.

[0013] Furthermore, the simplified solution interval determined by S4 is:

[0014]

[0015] in, The prediction result of the limit removal time is obtained by inputting the i+1th batch of power system operation state quantities into the trained prediction model; ε max_i for The maximum absolute error between the actual limit removal time corresponding to the i-th batch of power system operating state quantities.

[0016] Furthermore, the S2 specifically includes: S21, determining the upper and lower limits of the limit cut-off time solution interval corresponding to the first batch of power system operating state quantities; S22, setting the fault cut-off time to the interval mean, and simulating to determine whether the power system is stable at this time. If stable, the lower limit of the limit cut-off time solution interval is set to the interval mean; if unstable, the upper limit of the limit cut-off time solution interval is set to the interval mean; S23, repeatedly executing S22 until the interval length is less than the preset limit cut-off time accuracy.

[0017] Furthermore, the power system operating state quantities include: the amplitude and phase angle of the power system node voltage, the active power, reactive power and mechanical power of the generator, the active power and reactive power of the load, and the active transmission power and reactive transmission power between lines.

[0018] According to another aspect of the present invention, a method for determining an electric power system limit cut-off time based on incremental updating is provided, comprising: inputting the current electric power system operating state quantity into a prediction model obtained by the method for establishing an electric power system limit cut-off time prediction model based on incremental updating as described above, and the prediction model outputs a corresponding limit cut-off time.

[0019] According to another aspect of the present invention, there is provided an electronic device, comprising: a processor; and a memory storing a computer executable program, wherein when the program is executed by the processor, the processor executes the method as described above.

[0020] According to another aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method described above is implemented.

[0021] In general, the above technical solutions conceived by the present invention can achieve the following beneficial effects:

[0022] (1) A method for establishing a prediction model for the extreme removal time of a power system based on incremental updating is provided. The prediction model is used as an auxiliary means to guide the solution of the extreme removal time of the power system, simplifying the solution interval of the binary method, thereby reducing the number of binary method solutions, improving the efficiency of sample label generation and model training, and improving the efficiency of solving the extreme removal time at this stage;

[0023] Model training and sample generation are carried out in an interlaced manner. During use, the prediction model is used to improve the efficiency of sample label generation, and the obtained samples are then used to improve the effect of the prediction model, thereby improving the model training efficiency and data utilization efficiency;

[0024] (2) The simplified solution interval determined by the prediction model for the next batch of power system operating state quantities is In this interval, the binary search method is used to continue to determine the precise limit removal time. Compared with the traditional binary search method, this simplified solution interval reduces the solution calculation amount by 90%, greatly improving the training efficiency of the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 A flowchart of a method for establishing a power system limit cut-off time prediction model based on incremental updating provided by an embodiment of the present invention;

[0026] Figure 2 for Figure 1 The training process of the prediction model in the method shown;

[0027] Figure 3 A single line diagram of a New England 10-machine 39-node system provided in an embodiment of the present invention;

[0028] Figure 4 A comparison diagram between the method provided by the embodiment of the present invention and the traditional dichotomy method. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0030] In the present invention, the terms "first", "second", etc. (if any) in the present invention and the accompanying drawings are used to distinguish similar objects but not necessarily to describe a specific order or sequence.

[0031] Embodiment 1

[0032] A method for establishing a prediction model for power system limit removal time based on incremental update, see Figure 1 , combined with Figure 2-Figure 4 , the method is described in detail, and the method includes operations S1 to S5.

[0033] Operation S1, constructing an initial prediction model, sampling and obtaining multiple batches of power system operating state quantities.

[0034] Preferably, the power system operating state quantities used in this embodiment include: the amplitude and phase angle of the power system node voltage, the active power, reactive power and mechanical power of the generator, the active power and reactive power of the load, and the active transmission power and reactive transmission power between lines.

[0035] Specifically, different generator output levels, load levels, and proportions of motor components in the load can be set, and the amplitude and phase angle of the node voltage of the power system, the active power, reactive power, and mechanical power of the generator, the active power and reactive power of the load, and the active transmission power and reactive transmission power between lines can be obtained through power flow calculation. For example, the output of each generator can be set to fluctuate between 90% and 110% of the standard operating conditions; the load level can fluctuate between 80% and 120% of the standard operating conditions; and the proportion of motor components in the load can be 50%, 60%, 70%, 80%, and 90%.

[0036] Operation S2, using the binary search method, solves the limit removal time corresponding to the first batch of power system operating state quantities.

[0037] According to an embodiment of the present invention, operation S2 specifically includes the following sub-operations S21 to S23.

[0038] In sub-operation S21, the upper and lower limits of the limit cut-off time solution interval corresponding to the first batch of power system operating state quantities are determined.

[0039] In sub-operation S22, the fault removal time is set to the interval mean, and the simulation determines whether the power system is stable at this time. If it is stable, the lower limit of the limit removal time solution interval is set to the interval mean. If it is unstable, the upper limit of the limit removal time solution interval is set to the interval mean to form a new limit removal time solution interval.

[0040] In sub-operation S23, sub-operation S22 is repeatedly performed until the interval length is less than the preset limit excision time accuracy, and the upper limit of the interval finally obtained is used as the limit excision time.

[0041] For example, the lower limit of the solution interval is usually set to 0s, and the upper limit is the total simulation time of 10s. At this time, the interval mean is 5s. Therefore, the fault is set to be removed after 5s to determine the stability of the power system at this time. If it is stable, the lower limit of the interval is changed to 5s, and the solution interval is updated to 5s to 10s; if it is unstable, the upper limit of the interval is changed to 5s, and the solution interval is updated to 0s to 5s. Repeat until the interval length is less than the preset limit removal time accuracy, such as 0.01s. The upper limit of the interval can be regarded as the limit removal time of the power system operation state.

[0042] Operation S3 takes the operating state of the power system in the i-th batch as input and the corresponding limit cut-off time as a label to train the latest prediction model, and the initial value of i is 1.

[0043] When i=1, operation S3 is as follows: using the first batch of power system operating state quantities as input and the corresponding limit removal time as a label, the initial prediction model is trained in a supervised manner. The prediction model initialization training method is:

[0044]

[0045] in, is the first objective function, θ is the parameter of the prediction model, N is the number of power system operating state quantities in the same batch, represents the training set data, x (n) ,y (n) are the nth power system operating state quantity and the corresponding limit removal time in the same batch, respectively; f( ) represents the prediction result of the prediction model; l( ) represents the label loss, which is calculated by the square of the difference; Ω(θ) is the regularization term of the prediction model, which is used to avoid overfitting of the model.

[0046] When i>1, operation S3 is specifically: using the power system operation state quantity of the i-th batch as input and the corresponding limit removal time as label, the latest prediction model is trained through incremental learning. The method of training the latest prediction model through incremental learning is:

[0047]

[0048] Among them, F is the latest prediction model before training, θ F is the parameter of F, The parameters that need to be updated for F in this batch, is the second objective function, Represents the training set data of this batch.

[0049] Operation S4, using the trained prediction model, determine the simplified solution interval where the limit cut-off time of the power system operating state quantity of the i+1th batch is located, use the binary search method to determine the corresponding limit cut-off time from the simplified solution interval, and add one to i.

[0050] Preferably, the simplified solution interval is determined as:

[0051]

[0052] in, The prediction result of the limit removal time is obtained by inputting the i+1th batch of power system operation state quantities into the trained prediction model; ε max_i for The maximum absolute error between the actual limit removal time corresponding to the i-th batch of power system operating state quantities.

[0053] For example, in the first sample solution of three batches, the prediction results given by the prediction model after the third batch of incremental updates are During the second batch prediction process, the maximum absolute error ε between the predicted results and the true results is obtained. max_2=0.12s, then the simplified solution interval is [1.23s, 1.47s]. Finally, for this smaller interval, the binary search method is used to solve the limit removal time corresponding to the third batch of power system operating state quantities.

[0054] Operation S5, repeatedly performing operations S3 to S4 until the loss function of the prediction model converges, or until the prediction model has been trained using all batches of power system operating state quantities.

[0055] The training process of the prediction model is as follows Figure 2 It should be noted that, in the process of training the prediction model, the limit removal time determined for each batch of power system operation state quantities can also be used to guide the power system cut-off to achieve the determination of the limit removal time of the power system.

[0056] The following is a specific description of the above method using the New England 10-machine 39-node test system as an example. The system single-line diagram is as follows: Figure 3 As shown. In the sample set generation stage, the output of each generator is set to fluctuate between 90% and 110% of the standard operating conditions; the load level fluctuates between 80% and 120% of the standard operating conditions; the motor component in the load accounts for 50%, 60%, 70%, 80%, and 90%, and a total of 4096 power system operating states are combined. The power flow calculation is performed on the PSASP software to obtain the required amplitude and phase angle of the power system node voltage, the active power, reactive power and mechanical power of the generator, the active power and reactive power of the load, and the active transmission power and reactive transmission power between the lines.

[0057] The power system operating status is randomly shuffled and divided into 32 batches. For all the power system operating status in the first batch, the binary method is used to solve the limit removal time as the label for initial model training. Then, the first batch of power system operating status is used as a sample, and the solved limit removal time is used as a label to train the initial auxiliary prediction model. Finally, the auxiliary prediction model is used to simplify the solution interval of the limit removal time of the next batch of samples to improve the solution efficiency. The final time result is as follows: Figure 4 As shown, it can be seen that compared with the traditional dichotomy method, this method can greatly reduce the simulation time and improve the efficiency of solving the limit resection time.

[0058] Embodiment 2

[0059] A method for determining the limit removal time of an electric power system based on incremental update comprises: inputting the current electric power system operation state quantity into the prediction model obtained by the above-mentioned method for establishing the limit removal time prediction model of an electric power system based on incremental update, and the prediction model outputs the corresponding limit removal time. The relevant technical scheme is the same as that of the first embodiment, and will not be repeated here.

[0060] Embodiment 3

[0061] An electronic device includes: a processor; a memory storing a computer executable program, wherein when the program is executed by the processor, the processor executes the above-mentioned method for establishing a power system limit cut-off time prediction model based on incremental update, or executes the above-mentioned method for determining the power system limit cut-off time based on incremental update. The related technical solution is the same as that of the first embodiment, and will not be repeated here.

[0062] Embodiment 4

[0063] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the above-mentioned method for establishing a power system limit cut-off time prediction model based on incremental update, or executes the above-mentioned method for determining the power system limit cut-off time based on incremental update. The related technical solution is the same as that of embodiment 1, and will not be described in detail here.

[0064] It will be easily understood by those skilled in the art that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for establishing a power system limit removal time prediction model based on incremental updating, characterized in that: include: S1, build the initial prediction model and sample multiple batches of power system operation status quantities; S2, using the dichotomy method, solve the limit removal time corresponding to the first batch of power system operation state quantities; S3, taking the i-th batch of power system operating state quantities as input and the corresponding limit removal time as label, trains the latest prediction model, and the initial value of i is 1; S4, using the trained prediction model, determine the simplified solution interval where the limit removal time of the power system operation state quantity of the i+1th batch is located, use the dichotomy method to determine the corresponding limit removal time from the simplified solution interval, and add one to i; S5, repeatedly executing S3-S4 until the loss function of the prediction model converges, or until the prediction model has been trained using all batches of power system operating state quantities.

2. The method for establishing a power system limit removal time prediction model based on incremental updating according to claim 1, characterized in that: The S3 specifically includes: When i=1, the first batch of power system operation state quantities are used as input and the corresponding limit removal time is used as the label to train the initial prediction model in a supervised manner; When i>1, the i-th batch of power system operating state quantities is used as input, and the corresponding limit cut-off time is used as the label, and the latest prediction model is trained through incremental learning.

3. The method for establishing a power system limit removal time prediction model based on incremental updating according to claim 2, characterized in that: When i=1, the way to train the initial prediction model is: in, is the first objective function, θ is the parameter of the prediction model, N is the number of power system operating state quantities in the same batch, represents the training set data, x (n) ,y (n) are the nth power system operating state quantity and the corresponding limit removal time in the same batch, f() represents the prediction result of the prediction model, l() represents the label loss, and Ω(θ) is the regularization term of the prediction model.

4. The method for establishing a power system limit removal time prediction model based on incremental updating according to claim 2, characterized in that: When i>1, the way to train the latest prediction model through incremental learning is: Among them, F is the latest prediction model before training, θ F is the parameter of F, The parameters that need to be updated for F in this batch, is the second objective function, Represents the training set data of this batch.

5. The method for establishing a power system limit removal time prediction model based on incremental updating according to claim 1, characterized in that: The simplified solution interval determined by S4 is: in, The prediction result of the limit removal time is obtained by inputting the i+1th batch of power system operation state quantities into the trained prediction model; ε max_i for The maximum absolute error between the actual limit removal time corresponding to the i-th batch of power system operating state quantities.

6. The method for establishing a power system limit removal time prediction model based on incremental updating according to any one of claims 1 to 5, characterized in that: The S2 specifically includes: S21, determining the upper and lower limits of the limit removal time solution interval corresponding to the first batch of power system operation state quantities; S22, setting the fault removal time to the interval mean, and simulating to determine whether the power system is stable at this time. If stable, setting the lower limit of the limit removal time solution interval to the interval mean; if unstable, setting the upper limit of the limit removal time solution interval to the interval mean; S23, repeatedly executing S22 until the interval length is less than a preset limit excision time accuracy.

7. The method for establishing a power system limit removal time prediction model based on incremental updating according to claim 1, characterized in that: The power system operation state quantities include: the amplitude and phase angle of the power system node voltage, the active power, reactive power and mechanical power of the generator, the active power and reactive power of the load, and the active transmission power and reactive transmission power between lines.

8. A method for determining the limit removal time of a power system based on incremental updating, characterized in that: include: The current power system operating state quantity is input into the prediction model obtained by the method for establishing a power system limit cut-off time prediction model based on incremental update as described in any one of claims 1 to 7, and the prediction model outputs the corresponding limit cut-off time.

9. An electronic device, characterized in that: include: processor; A memory storing a computer executable program, wherein when the program is executed by the processor, the processor executes the method according to any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Citation Information

Patent Citations

  • A method and system for determining a critical cut-off time of a power system based on a Siamese network model

    CN109376990A

  • Power grid safety and stability simulation sample screening and expanding method based on safety information entropy

    CN112419098A

  • Batch calculation method for limit clearing time in power system and related device

    CN115146233A

  • Method and apparatus for recognizing large power grid critical transient stability boundary state, and electronic device and storage medium

    WO2020181804A1