CN115775114A - New energy station transient voltage stability evaluation method based on gated cycle unit - Google Patents
New energy station transient voltage stability evaluation method based on gated cycle unit Download PDFInfo
- Publication number
- CN115775114A CN115775114A CN202211707754.1A CN202211707754A CN115775114A CN 115775114 A CN115775114 A CN 115775114A CN 202211707754 A CN202211707754 A CN 202211707754A CN 115775114 A CN115775114 A CN 115775114A
- Authority
- CN
- China
- Prior art keywords
- transient voltage
- new energy
- voltage stability
- data
- model
- 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.)
- Pending
Links
Images
Landscapes
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a new energy station transient voltage stability evaluation method based on a gated cyclic unit network, belonging to the technical field of new energy grid connection technology and artificial intelligence in a new energy power system, and comprising the following steps: preprocessing a transient voltage evaluation historical data set of the new energy station; constructing and dividing an evaluation model data set based on the preprocessed data set; building a transient voltage stability evaluation model of the new energy station based on the gate control cycle unit network; based on the evaluation model data set, obtaining an optimal new energy station transient voltage stability evaluation model through training and verification; establishing a model performance analysis index system; and evaluating the transient voltage stability of the new energy station based on the optimal transient voltage stability evaluation model and the model performance analysis index system of the new energy station. The new energy station voltage transient stability evaluation method capable of improving the evaluation precision is researched, and theoretical support is provided for grid-connected operation stability prejudgment and reactive voltage planning of the new energy station.
Description
Technical Field
The invention discloses a new energy field station transient voltage stability evaluation method based on a gated cyclic unit network, and belongs to the technical field of new energy grid connection technology and artificial intelligence in new energy power systems.
Background
With the continuous decline of fossil energy reserves all over the world, the utilization of new energy is gradually paid attention to. However, after the large-scale new energy station is incorporated into a power grid, the reactive power regulation capability of the system is insufficient. Transient voltage instability is easily caused when disturbance such as short-circuit fault occurs, a series of problems such as grid disconnection of a new energy source unit and system voltage drop are caused, and safety and stability of a power grid are affected. Therefore, after a large-scale new energy station is connected to the grid, how to quickly and accurately evaluate the transient voltage stability is very necessary, and meanwhile, the method has extremely important significance on safe operation of a power grid in the future. In order to realize rapid evaluation, various artificial intelligence methods are adopted at home and abroad, but the precision needs to be improved.
Disclosure of Invention
The invention discloses a new energy station transient voltage stability evaluation method based on a gated cyclic unit network, which solves the problem of low transient voltage rapid evaluation precision in the prior art.
The new energy station transient voltage stability evaluation method based on the gated cyclic unit network comprises the following steps:
step 1: preprocessing a transient voltage evaluation historical data set of the new energy station;
and 2, step: constructing and dividing an evaluation model data set based on the data set preprocessed in the step 1;
and step 3: building a transient voltage stability evaluation model of the new energy station based on the gate control cycle unit network;
and 4, step 4: based on the evaluation model data set in the step 2, an optimal new energy station transient voltage stability evaluation model is obtained through training and verification;
and 5: establishing a model performance analysis index system;
step 6: and (5) evaluating the transient voltage stability of the new energy station based on the optimal transient voltage stability evaluation model of the new energy station in the step (4) and the model performance analysis index system in the step (5).
The step 1 comprises the following steps:
step 1.1: acquiring historical data of a new energy station grid-connected system in a certain time period, wherein the historical data comprises the voltage of a central bus, the voltage of a station bus, the active power output of the station, the total load, the motor load ratio and the transient voltage stability index in the current state;
step 1.2: randomly selecting m groups of data from historical data, wherein each group of data comprises k 1 Voltage V of central bus 1 ,…,k 2 Bus voltage V of individual station 1 ′,…,k 2 Active power output P of individual station 1 ,…,The total load L, the motor load ratio eta and the transient voltage stability index alpha, wherein each group of data comprises (k) 1 +2k 2 + 3) data, and obtaining a transient voltage stability evaluation historical data set D by selecting m groups of data 1 ;
Step 1.3: for historical dataCollection D 1 All the data in the data are normalized to eliminate the influence of dimension on the evaluation result, and a preprocessed transient voltage stability evaluation data set D is obtained 2 。
The step 2 comprises the following steps:
step 2.1: based on the preprocessed data set D 2 Determining n (n = k) of the evaluation model 1 +2k 2 + 2) input features and 1 output feature, using the central bus voltage, the station active output, the total load and the motor load ratio in each group of data as the input data of an evaluation model, using the transient voltage stability index as the output data of the evaluation model, and constructing an evaluation model data set D 3 ={(x i ,y i )|x i =(x i1 ;...;x in ) I = 1.. M }, where x is i And y i Input data and output data corresponding to each group of data respectively;
step 2.2: will evaluate the model data set D 3 The m groups of data in (1) are divided into a training set Tr, a verification set Va and a test set Te according to the proportion of a, b and c.
The step 3 comprises the following steps:
step 3.1: building a gate control cycle unit network, wherein the gate control cycle unit network comprises a network input layer, a gate control cycle unit layer and a full connection layer, and the gate control cycle unit layer comprises a reset gate and an update gate;
step 3.2: setting and initializing hyper-parameters of a gated cycle unit network, wherein the hyper-parameters comprise the number d of memories of the gated cycle unit, the number k of neuron nodes of a full connection layer, an activation function sigma of the full connection layer and the number Batchsize of samples of the network batch, and obtaining a transient voltage stability evaluation model of the new energy field station based on the gated cycle unit network.
The step 4 comprises the following steps:
step 4.1: sequentially inputting each group of data in the training set Tr into the new energy station transient voltage stability evaluation model set up in the step 3, training the hyper-parameters in the model, and setting the model training round number Epoch;
step 4.2: after each round of training is finished, sequentially inputting each group of data in the verification set Va into the current model to obtain corresponding output and output errors, calculating the error of the whole verification set, reserving the model parameter which enables the error of the whole verification set to be minimum, returning to the step 4.1 until reaching the set training round number or meeting the early stop condition, namely, continuously increasing the error of the verification set for M times, and obtaining the optimal transient voltage stability evaluation model of the new energy field station.
The step 5 comprises the following steps:
step 5.1: selecting two indexes of a root mean square error and an average absolute error, and calculating an error between a stability evaluation result output by the analysis model and a historical known result so as to measure the accuracy of the evaluation result;
step 5.2: and selecting a qualification rate index, and calculating the number of the evaluation results within an allowable error range to measure the accuracy of the evaluation results.
The step 6 comprises the following steps:
step 6.1: sequentially inputting each group of data in the test set Te into an optimal transient voltage stability evaluation model of the new energy station, and outputting a corresponding transient voltage stability evaluation index;
step 6.2: and comparing the transient voltage stability evaluation index output by the evaluation model with a historical known value of the transient voltage stability evaluation index, and analyzing the evaluation effect based on a model performance analysis index system.
The invention has the beneficial effects that: according to the new energy field station transient voltage stability evaluation method, bus voltage influencing transient voltage stability, active power output of the new energy field station, bus voltage of the new energy field station and other factors are comprehensively considered, a gated circulation unit network in the field of artificial intelligence is applied to evaluation of transient voltage stability, and accuracy of evaluation can be further improved.
Drawings
FIG. 1 is a technical flow diagram of the present invention;
FIG. 2 is a schematic diagram of a new energy station transient voltage stability evaluation method based on a gate control cycle unit;
fig. 3 is a structure of a gated loop cell network.
Detailed Description
The following description will further illustrate embodiments of the present invention with reference to specific examples:
a new energy station transient voltage stability assessment method based on a gated cyclic unit network comprises the following steps:
step 1: preprocessing a transient voltage evaluation historical data set of the new energy station;
and 2, step: constructing and dividing an evaluation model data set based on the data set preprocessed in the step 1;
and step 3: building a transient voltage stability evaluation model of the new energy field station based on the gated cyclic unit network;
and 4, step 4: based on the evaluation model data set in the step 2, an optimal new energy station transient voltage stability evaluation model is obtained through training and verification;
and 5: establishing a model performance analysis index system;
step 6: and (5) evaluating the transient voltage stability of the new energy station based on the optimal transient voltage stability evaluation model of the new energy station in the step (4) and the model performance analysis index system in the step (5).
The step 1 comprises the following steps:
step 1.1: acquiring historical data of a new energy station grid-connected system in a certain time period, wherein the historical data comprises the voltage of a central bus, the voltage of a station bus, the active power output of the station, the total load, the motor load ratio and the transient voltage stability index in the current state;
step 1.2: randomly selecting m groups of data from historical data, wherein each group of data comprises k 1 Voltage V of central bus 1 ,…,k 2 Bus voltage V of individual station 1 ′,…,k 2 Active power output P of individual station 1 ,…,The total load L,The motor load ratio eta and the transient voltage stability index alpha, and each set of data comprises (k) 1 +2k 2 + 3) data, and obtaining a transient voltage stability evaluation historical data set D by selecting m groups of data 1 ;
Step 1.3: for historical data set D 1 All data in the data are normalized to eliminate the influence of dimension on the evaluation result, and a preprocessed transient voltage stability evaluation data set D is obtained 2 。
The step 2 comprises the following steps:
step 2.1: based on the preprocessed data set D 2 Determining n (n = k) of the evaluation model 1 +2k 2 + 2) input features and 1 output feature, using the central bus voltage, the station active output, the total load and the motor load ratio in each group of data as the input data of an evaluation model, using the transient voltage stability index as the output data of the evaluation model, and constructing an evaluation model data set D 3 ={(x i ,y i )|x i =(x i1 ;…;x in ) I =1, \ 8230;, m }, where x i And y i Input data and output data corresponding to each group of data are respectively;
step 2.2: will evaluate the model data set D 3 The m groups of data in (1) are divided into a training set Tr, a verification set Va and a test set Te according to the proportion of a, b and c.
The step 3 comprises the following steps:
step 3.1: building a gate control cycle unit network, wherein the gate control cycle unit network comprises a network input layer, a gate control cycle unit layer and a full connection layer, and the gate control cycle unit layer comprises a reset gate and an update gate;
step 3.2: and setting and initializing the hyperparameters of the gated cyclic unit network, including the number d of memories of the gated cyclic unit, the number k of neuron nodes of the full connection layer, the activation function sigma of the full connection layer and the number Batchsize of network batch samples, to obtain a new energy field station transient voltage stability evaluation model based on the gated cyclic unit network.
Step 4 comprises the following steps:
step 4.1: sequentially inputting each group of data in the training set Tr into the new energy station transient voltage stability assessment model set up in the step 3, training the hyper-parameters in the model, and setting a model training round number Epoch;
step 4.2: after each round of training is finished, sequentially inputting each group of data in the verification set Va into the current model to obtain corresponding output and output errors, calculating the error of the whole verification set, reserving the model parameter which enables the error of the whole verification set to be minimum, returning to the step 4.1 until reaching the set training round number or meeting the early stop condition, namely, continuously increasing the error of the verification set for M times, and obtaining the optimal transient voltage stability evaluation model of the new energy field station.
The step 5 comprises the following steps:
step 5.1: selecting two indexes of a root-mean-square error and an average absolute error, and calculating an error between a stability evaluation result output by the analysis model and a historical known result to measure the accuracy of the evaluation result;
step 5.2: and selecting a qualification rate index, and calculating the number of the evaluation results within an allowable error range to measure the accuracy of the evaluation results.
The step 6 comprises the following steps:
step 6.1: sequentially inputting each group of data in the test set Te into an optimal transient voltage stability evaluation model of the new energy station, and outputting a corresponding transient voltage stability evaluation index;
step 6.2: and comparing the transient voltage stability evaluation index output by the evaluation model with a historical known value of the transient voltage stability evaluation index, and analyzing the evaluation effect based on a model performance analysis index system.
As shown in the step flow chart of the invention shown in fig. 1 and the method schematic diagram shown in fig. 2, a new energy station transient voltage stability evaluation method based on a gating cycle unit is introduced, and the specific steps include:
step 1: and preprocessing a transient voltage evaluation historical data set of the new energy station. Acquiring 2 central bus voltages V of new energy station grid-connected system in certain time period 1 ,V 2 And 3 bus voltages V 'of new energy station' 1 ,V′ 2 ,V′ 3 Active power output P of 3 new energy stations 1 ,P 2 ,P 3 Selecting m groups of data to summarize to form a transient voltage evaluation historical data set D 1 . To D 1 The data in (2) are normalized to [0,1 ] by the maximum-minimum normalization process according to equation (1)]Within the range, obtaining a transient voltage evaluation data set D after preprocessing 2 ,In the formula, z max Represents the maximum value in each data, z min Represents the minimum value in each data, z represents the true value of each data, z represents the minimum value in each data std Representing the values after each data normalization process.
And 2, step: based on the preprocessed data set D 2 And constructing and dividing an evaluation model data set. Determining 10 input features of the evaluation model, i.e.And 1 output characteristic of the evaluation model is the corresponding stability index alpha std And then:
will D 3 The m groups of data in (1) are divided into a training set Tr, a verification set Va and a test set Te according to the ratio of a, b and c.
And step 3: and constructing a transient voltage stability evaluation model of the new energy station based on the gate control cycle unit network. The structure of the gated cyclic unit network is shown in fig. 3, and mainly includes a network input layer, a GRU unit layer and a full connection layer, where the GRU unit includes a reset gate and an update gate. Setting and initializing model hyper-parameters such as the number d of memories of a gating cycle unit, the number k of neuron nodes of a full connection layer, an activation function sigma of the full connection layer, the number of Batchsize of network batch samples and the like.
And 4, step 4: and based on the evaluation model data set, obtaining an optimal new energy station transient voltage stability evaluation model through training and verification. And training and optimizing parameters of the built gated circulation unit network evaluation model by using data in the training set Tr. After each round of training is finished, the current model is verified by using the verification set Va, and model parameters enabling the error of the whole verification set to be minimum are reserved. And repeating the training and verifying steps until the set model training round number Epoch is reached or the early stop condition is met, and obtaining the optimal new energy station transient voltage stability evaluation model.
And 5: and establishing a model performance analysis index system. In order to comprehensively analyze the evaluation effect of the transient voltage stability evaluation model, three indexes of Root Mean Square Error (RMSE), mean Absolute Error (MAE) and percent of Pass (PR) are selected, and the calculation formula is as follows:
in the formula (I), the compound is shown in the specification,for evaluating the i-th stability index, α, output by the model i Is the historical known value of the ith stability indicator.
Step 6: and evaluating the transient voltage stability of the new energy station based on the optimal transient voltage stability evaluation model and the model performance analysis index system of the new energy station. And inputting each group of data in the test set Te into an optimal transient voltage stability evaluation model of the new energy station, outputting a corresponding transient voltage stability evaluation index, comparing the transient voltage stability evaluation index with a corresponding historical known value, and calculating an evaluation index.
The transient voltage stability evaluation method provided by the invention is applied to a specific experiment, and data is derived from historical operation data of a grid-connected system of a new energy station. The experiment is carried out by collecting 100 groups of data in the current time, wherein the data of a training set, a verification set and a test set are respectively 60, 20 and 20 groups, and the example verification specifically comprises the following steps:
step 1: 100 groups of data in a certain time range are collected to form a historical data set:
D 1 ={(V 1i ,V 2i ,V 1i ′,V 2 ′ i ,V 3 ′ i ,P 1i ,P 2i ,P 3i ,P i ,η i ,α i ) I =1, \ 8230;, 100}. To D 1 After the data in the step (1) is subjected to normalization processing work, a preprocessed transient voltage evaluation data set D is obtained 2 。
Step 2: the evaluation model input feature matrix size is determined to be (1, 10), and the output label size is determined to be (1, 1). The 100 groups of data were divided into training set, validation set and test set according to the ratio of 6.
And step 3: and (3) building a gated cycle unit network, wherein the gated cycle unit network comprises an input layer, three GRU layers and a full connection layer, and the structure is shown in FIG. 3, so that the output size of the sample (1, 10) is (1, 1) after the sample is input into the gated cycle unit network. The model hyper-parameters are set and initialized.
And 4, step 4: inputting training set data into the constructed gate control cycle unit network for 500 rounds of training, and verifying the network by using verification set data after each round of training is finished. If the current verification set RMSE is minimum, the current network parameters are saved, otherwise, the previous network parameters are continuously adopted, and the next training round is carried out until the 500 training rounds are finished or the verification set RMSE is increased for 50 times continuously, and the network training is terminated. By continuously optimizing the network hyperparameter, an optimal new energy station transient voltage stability evaluation model is obtained, and the specific structure of the model is shown in table 1.
TABLE 1 best new energy station transient voltage stability evaluation model hyperparameters
And 5: and selecting three indexes of Root Mean Square Error (RMSE), mean Absolute Error (MAE) and percent of Pass (PR) to analyze the evaluation effect of the model.
And 6: and inputting 20 groups of data of the test set into an optimal transient voltage stability evaluation model of the new energy station, outputting a corresponding transient voltage stability evaluation index, comparing the transient voltage stability evaluation index with a corresponding historical known value, and calculating a Root Mean Square Error (RMSE), an average absolute error (MAE) and a qualification rate (PR).
In order to verify the effectiveness and the advancement of the transient voltage stability evaluation method, the evaluation model (GRU) based on the gated cyclic unit network, the evaluation model (CNN) based on the convolutional neural network, the evaluation model (TCN) based on the time domain convolutional network and the evaluation model (ANN) based on the artificial neural network are compared and analyzed. By calculating three evaluation indexes of RMSE, MAE and PR of the whole test set, the evaluation effects of different evaluation models are comprehensively compared, and the specific evaluation index comparison result is shown in Table 2. As can be seen from table 2, on the one hand, the GRU model has the smallest MAE and RMSE, and the evaluation errors of the other models are all greater than 10%; on the other hand, the GRU model achieves 85% of yield, which is much higher than other models. In summary, compared with other evaluation methods, the new energy station transient voltage stability evaluation method based on the GRU provided by the invention has higher accuracy and precision.
TABLE 2 comparison of performance indexes of different transient voltage stability evaluation models
The above example analysis shows that: according to the method, historical sample data is fully utilized, the transient voltage stability of the new energy station can be rapidly and accurately evaluated through an optimal new energy station transient voltage stability evaluation model obtained through training and verification, and guarantee is provided for safe and stable operation of a power system.
It is to be understood that the above description is not intended to limit the present invention, and the present invention is not limited to the above examples, and those skilled in the art may make various changes, modifications, additions and substitutions within the spirit and scope of the present invention.
Claims (7)
1. A new energy station transient voltage stability assessment method based on a gated cyclic unit network is characterized by comprising the following steps:
step 1: preprocessing a transient voltage evaluation historical data set of the new energy station;
and 2, step: constructing and dividing an evaluation model data set based on the data set preprocessed in the step 1;
and step 3: building a transient voltage stability evaluation model of the new energy station based on the gate control cycle unit network;
and 4, step 4: based on the evaluation model data set in the step 2, an optimal new energy station transient voltage stability evaluation model is obtained through training and verification;
and 5: establishing a model performance analysis index system;
step 6: and (5) evaluating the transient voltage stability of the new energy station based on the optimal transient voltage stability evaluation model of the new energy station in the step (4) and the model performance analysis index system in the step (5).
2. The new energy yard transient voltage stability evaluation method based on gated cyclic unit network of claim 1, wherein step 1 comprises:
step 1.1: acquiring historical data of a new energy station grid-connected system in a certain time period, wherein the historical data comprises the voltage of a central bus, the voltage of a station bus, the active power output of the station, the total load, the motor load ratio and the transient voltage stability index in the current state;
step 1.2: randomly selecting m groups of data from historical data, wherein each group of data comprises k 1 Voltage of central busk 2 Bus voltage of individual stationk 2 Active power output of individual stationThe total load L, the motor load ratio eta and the transient voltage stability index alpha, wherein each group of data comprises (k) 1 +2k 2 + 3) data, and obtaining a transient voltage stability evaluation historical data set D by selecting m groups of data 1 ;
Step 1.3: for historical data set D 1 All the data in the data are normalized to eliminate the influence of dimension on the evaluation result, and a preprocessed transient voltage stability evaluation data set D is obtained 2 。
3. The new energy station transient voltage stability assessment method based on the gated cyclic unit network according to claim 2, wherein the step 2 comprises:
step 2.1: based on the preprocessed data set D 2 Determining n (n = k) of the evaluation model 1 +2k 2 + 2) input features and 1 output feature, using the central bus voltage, the station active output, the total load and the motor load ratio in each group of data as the input data of an evaluation model, using the transient voltage stability index as the output data of the evaluation model, and constructing an evaluation model data set D 3 ={(x i ,y i )|x i =(x i1 ;…;x in ) I =1, \ 8230;, m }, where x i And y i Input data and output data corresponding to each group of data respectively;
step 2.2: will evaluate the model data set D 3 The m groups of data in (1) are divided into a training set Tr, a verification set Va and a test set Te according to the ratio of a, b and c.
4. The new energy yard transient voltage stability evaluation method based on gated cyclic unit network of claim 3, wherein step 3 comprises:
step 3.1: building a gate control cycle unit network, wherein the gate control cycle unit network comprises a network input layer, a gate control cycle unit layer and a full connection layer, and the gate control cycle unit layer comprises a reset gate and an update gate;
step 3.2: setting and initializing hyper-parameters of a gated cycle unit network, wherein the hyper-parameters comprise the number d of memories of the gated cycle unit, the number k of neuron nodes of a full connection layer, an activation function sigma of the full connection layer and the number Batchsize of samples of the network batch, and obtaining a transient voltage stability evaluation model of the new energy field station based on the gated cycle unit network.
5. The new energy station transient voltage stability assessment method based on the gated cyclic unit network according to claim 4, wherein the step 4 comprises:
step 4.1: sequentially inputting each group of data in the training set Tr into the new energy station transient voltage stability evaluation model set up in the step 3, training the hyper-parameters in the model, and setting the model training round number Epoch;
step 4.2: after each round of training is finished, sequentially inputting each group of data in the verification set Va into the current model to obtain corresponding output and output errors, calculating the error of the whole verification set, reserving the model parameter which enables the error of the whole verification set to be minimum, returning to the step 4.1 until reaching the set training round number or meeting the early stop condition, namely, continuously increasing the error of the verification set for M times, and obtaining the optimal transient voltage stability evaluation model of the new energy field station.
6. The new energy yard transient voltage stability evaluation method based on gated cyclic unit network of claim 5, wherein step 5 comprises:
step 5.1: selecting two indexes of a root mean square error and an average absolute error, and calculating an error between a stability evaluation result output by the analysis model and a historical known result so as to measure the accuracy of the evaluation result;
step 5.2: and selecting a qualification rate index, and calculating the number of the evaluation results within an allowable error range to measure the accuracy of the evaluation results.
7. The new energy station transient voltage stability assessment method based on the gated cyclic unit network according to claim 6, wherein the step 6 comprises:
step 6.1: sequentially inputting each group of data in the test set Te into an optimal transient voltage stability evaluation model of the new energy station, and outputting a corresponding transient voltage stability evaluation index;
step 6.2: and comparing the transient voltage stability evaluation index output by the evaluation model with a historical known value of the transient voltage stability evaluation index, and analyzing the evaluation effect based on a model performance analysis index system.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211707754.1A CN115775114A (en) | 2022-12-29 | 2022-12-29 | New energy station transient voltage stability evaluation method based on gated cycle unit |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211707754.1A CN115775114A (en) | 2022-12-29 | 2022-12-29 | New energy station transient voltage stability evaluation method based on gated cycle unit |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115775114A true CN115775114A (en) | 2023-03-10 |
Family
ID=85393184
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211707754.1A Pending CN115775114A (en) | 2022-12-29 | 2022-12-29 | New energy station transient voltage stability evaluation method based on gated cycle unit |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115775114A (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107993012A (en) * | 2017-12-04 | 2018-05-04 | 国网湖南省电力有限公司娄底供电分公司 | A kind of adaptive electric system on-line transient stability appraisal procedure of time |
CN114091816A (en) * | 2021-10-15 | 2022-02-25 | 浙江大学 | Power distribution network state estimation method based on gated graph neural network of data fusion |
CN114626957A (en) * | 2022-01-28 | 2022-06-14 | 西安理工大学 | Voltage sag state evaluation method based on gate control cycle unit deep learning model |
-
2022
- 2022-12-29 CN CN202211707754.1A patent/CN115775114A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107993012A (en) * | 2017-12-04 | 2018-05-04 | 国网湖南省电力有限公司娄底供电分公司 | A kind of adaptive electric system on-line transient stability appraisal procedure of time |
CN114091816A (en) * | 2021-10-15 | 2022-02-25 | 浙江大学 | Power distribution network state estimation method based on gated graph neural network of data fusion |
CN114626957A (en) * | 2022-01-28 | 2022-06-14 | 西安理工大学 | Voltage sag state evaluation method based on gate control cycle unit deep learning model |
Non-Patent Citations (1)
Title |
---|
孙黎霞 等: "基于混合门控循环单元子层的多任务暂态稳定评估", 电力建设, vol. 43, no. 2, pages 63 - 68 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107292502B (en) | Power distribution network reliability assessment method | |
CN111475909B (en) | Wind turbine generator output correlation mapping modeling method based on long-term and short-term memory network | |
WO2023005700A1 (en) | Model-data-hybrid-driven electrical grid reliability rapid calculation method and device | |
CN112329339B (en) | Short-term wind speed prediction method for wind power plant | |
CN112241836B (en) | Virtual load leading parameter identification method based on incremental learning | |
CN113344288A (en) | Method and device for predicting water level of cascade hydropower station group and computer readable storage medium | |
CN106768933A (en) | A kind of wind power generation unit blade method for diagnosing faults based on genetic algorithm | |
CN111900713A (en) | Multi-scene power transmission network planning method considering load and wind power randomness under network source coordination | |
Zhang et al. | Transient stability prediction of power systems based on deep belief networks | |
Syu et al. | Ultra-short-term wind speed forecasting for wind power based on gated recurrent unit | |
Wang et al. | Ultra-short-term wind power forecasting based on deep belief network | |
CN111091141B (en) | Photovoltaic backboard fault diagnosis method based on layered Softmax | |
CN104951654A (en) | Method for evaluating reliability of large-scale wind power plant based on control variable sampling | |
CN106056305A (en) | Power generation system reliability rapid assessment method based on state clustering | |
CN110555566B (en) | B-spline quantile regression-based photoelectric probability density prediction method | |
CN110991741B (en) | Section constraint probability early warning method and system based on deep learning | |
CN112836876A (en) | Power distribution network line load prediction method based on deep learning | |
CN115775114A (en) | New energy station transient voltage stability evaluation method based on gated cycle unit | |
CN116307139A (en) | Wind power ultra-short-term prediction method for optimizing and improving extreme learning machine | |
CN116306236A (en) | Wind power plant dynamic equivalent modeling method and system based on GRU-LSTM-FC combined network | |
CN113627655B (en) | Method and device for simulating and predicting pre-disaster fault scene of power distribution network | |
CN112232714B (en) | Deep learning-based risk assessment method for distribution network under incomplete structural parameters | |
Wang et al. | An alternative method for estimating wind-power capacity credit based on reliability evaluation using intelligent search | |
Liu et al. | Short-Term Wind Speed and Wind Power Prediction Based on Meteorological Model Modification | |
Wu et al. | Convolutional deep leaning-based distribution system topology identification with renewables |
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 |