CN113991652A - Data-driven multi-output calculation method for short-circuit current of IIDG-containing power distribution network - Google Patents
Data-driven multi-output calculation method for short-circuit current of IIDG-containing power distribution network Download PDFInfo
- Publication number
- CN113991652A CN113991652A CN202111255829.2A CN202111255829A CN113991652A CN 113991652 A CN113991652 A CN 113991652A CN 202111255829 A CN202111255829 A CN 202111255829A CN 113991652 A CN113991652 A CN 113991652A
- Authority
- CN
- China
- Prior art keywords
- distribution network
- short
- output
- power distribution
- circuit current
- 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.)
- Granted
Links
- 238000004364 calculation method Methods 0.000 title claims abstract description 49
- 238000000034 method Methods 0.000 claims abstract description 45
- 238000012549 training Methods 0.000 claims description 25
- 238000004422 calculation algorithm Methods 0.000 claims description 15
- 238000011156 evaluation Methods 0.000 claims description 13
- 238000012360 testing method Methods 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 8
- 238000005259 measurement Methods 0.000 claims description 7
- 230000004927 fusion Effects 0.000 claims description 6
- 230000001360 synchronised effect Effects 0.000 claims description 4
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 claims 2
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 claims 2
- 230000007246 mechanism Effects 0.000 abstract description 6
- 229910052799 carbon Inorganic materials 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 6
- 230000006978 adaptation Effects 0.000 description 5
- 230000009466 transformation Effects 0.000 description 5
- 238000013507 mapping Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000011426 transformation method Methods 0.000 description 3
- 238000011217 control strategy Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/10—Power transmission or distribution systems management focussing at grid-level, e.g. load flow analysis, node profile computation, meshed network optimisation, active network management or spinning reserve management
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a data-driven multi-output calculation method for short-circuit current of a power distribution network containing an IIDG. A large amount of IIDGs are connected to the power distribution network under the double-carbon target, so that the contradiction between the calculation speed and the accuracy is increasingly prominent in the short-circuit current calculation of the power distribution network based on mechanism modeling. The invention provides a data-driven multi-output regression calculation model and method for short-circuit current of a power distribution network, wherein XGboost is used as a basis, a multi-output modeling is carried out by adopting an MTRS method, the short-circuit current of all branches on the power distribution network is calculated simultaneously, the problem of fast and accurate calculation of the short-circuit current of the power distribution network containing IIDG is solved, the calculation performance of the multi-output model is stronger than that of a single-output model, and the problem of the number of models of the single-output model is avoided.
Description
Technical Field
The invention belongs to the field of electric power systems, and particularly relates to a method for calculating short-circuit currents of all branches by establishing a short-circuit current calculation multi-output model of an IIDG-containing power distribution network by adopting a research mode of data science and researching a machine learning multi-output algorithm.
Background
The double-carbon strategic objective of China prompts an inverter type distributed generator (IIDG) to gradually show a high-proportion development trend in a power distribution network. Unlike the traditional synchronous motor power supply, the IIDG has a strong nonlinear fault characteristic, not only needs to meet the low-voltage ride-through requirement, but also is influenced by factors such as the operation characteristic before the fault, the access position, the control strategy and the like. Due to the fact that a large number of IIDGs are connected, the traditional short-circuit current calculation method is difficult to directly apply, and research on the short-circuit current calculation method of the power distribution network containing the IIDGs is urgently needed.
Currently, most of researches on IIDG fault characteristics and short-circuit current calculation methods are based on mechanism physical modeling researches. Due to the fact that IIDG mechanism models under different control strategies are different, the difference of short-circuit current calculation methods under different fault types is large, and a large number of iterations are needed in the calculation process. When the number of IIDG accesses or the network size increases, the time consumption of the physical modeling method is increased greatly due to iterative computation, and even the situation of non-convergence may occur. In order to increase the calculation speed, the IIDG model is subjected to extremely simple processing, and if the IIDG model is represented by 1.2-2 times of rated current, the calculation accuracy is necessarily sacrificed. Therefore, the existing physical modeling method is applied to a large-scale power distribution network with high IIDG ratio, and the contradiction between the calculation rapidity and the calculation accuracy is difficult to solve.
In order to solve the contradiction, the applicant proposes a mechanism and data fusion driven method for calculating the short-circuit current of the power distribution network containing the IIDG, which is detailed in electric power automation equipment (volume No. 01P 41-48 in 2021). The method is based on a machine learning idea, a single output model containing IIDG power distribution network short-circuit current calculation is established, and compared with a detailed physical modeling method, the calculation error is similar to or smaller than that of the method, and the calculation speed is high. Meanwhile, the influence of the power grid scale and the IIDG access number on the calculation performance of the method is small. However, this method uses a single-output learning model, and when it is necessary to calculate the current values of a plurality of measurement points in the power distribution network, it is necessary to train a respective model for each measurement point, and thus a problem of a disaster in the number of models may occur.
Disclosure of Invention
The technical problem to be solved by the invention is to overcome the defects in the prior art and provide a data-driven multi-output calculation method for the short-circuit current of the power distribution network containing the IIDG, machine learning and data-driven modeling are integrated into the calculation of the short-circuit current of the power distribution network, a mapping relation between input characteristics and a plurality of output quantities is obtained by training a multi-output model, the calculation speed can be increased under the condition of accurately calculating the short-circuit current of the power distribution network containing the IIDG, all branch short-circuit currents are output, and the problem of excessive single-output model is solved.
In order to achieve the purpose, the invention adopts the following technical scheme:
the invention comprises the following steps:
s1: establishing a short-circuit current sample set of the power distribution network containing the IIDG, wherein the sample set comprises a training set and a testing set;
s2: selecting and establishing an MTRS-XGboost multi-output model by analyzing and comparing a plurality of multi-output models in a large quantity;
s3: training an MTRS-XGboost model by using a training set, and finishing training when the loss function is not reduced in the iteration process and the evaluation index is not reduced;
s4: and calculating the short-circuit current of the distribution network containing the IIDG by using the MTRS-XGboost multi-output model after training, and outputting all branch currents in the corresponding operation state.
Preferably, the sources of the IIDG-containing power distribution network short circuit current sample set in step S1 are, but not limited to, Matlab/Simulink software simulation and actual power distribution network operation data. The proportion of the training set to the test set in the sample set is 4: 1.
according to the actual distribution network equipment condition, namely whether a micro synchronous phasor measurement unit (mu PMU) is installed or not, different input characteristics can be selected, the voltage amplitude, the phase and the active and reactive power values in a distribution network can be selected by the distribution network equipped with the mu PMU, and the current value in the power network can be selected as the input characteristic by the distribution network not equipped with the mu PMU.
Preferably, in step S2, the MTRS-XGBoost multi-output model is a multi-target regression Modeling (MTRS) model used to convert the multi-output problem into a plurality of single-output problems, where the XGBoost method is adopted by the base learner.
Preferably, the loss function in step S3 uses the Mean Absolute Percentage Error (MAPE), and the evaluation index uses the MAPE and the Mean Absolute Error (MAPE)r, MAE). The evaluation index is obtained by calculating the true value yjAnd the calculated value
The smaller the evaluation index value is, the higher the model accuracy is.
The invention has the beneficial effects that: the invention provides a data-driven short-circuit current calculation multi-output model containing an IIDG, which can ensure the accuracy of short-circuit current calculation, simultaneously meet the requirement of quick calculation, simultaneously output short-circuit currents of all branches of a power distribution network, meet the requirement of actual engineering, and can be popularized and applied to the short-circuit current calculation of the power distribution network containing the IIDG.
Drawings
FIG. 1 is a flow chart of the data-driven IIDG-containing short-circuit current calculation multi-output model establishment.
Fig. 2 is a wiring diagram of an IEEE 34 node power distribution network system accessing four distributed power supplies.
FIG. 3 is a graph comparing the performance of different multi-output methods at high data loss ratios.
Detailed Description
The invention is further described below with reference to the accompanying drawings, comprising the steps of:
referring to fig. 1, the data-driven multiple output model for establishing a short-circuit current of a power distribution network including an IIDG according to the present invention has a capability of outputting short-circuit currents of all branches simultaneously, and includes the following steps:
s1: establishing a short-circuit current sample set of the power distribution network containing the IIDG, wherein the sample set comprises a training set and a testing set;
in the step S1, the source of the IIDG-containing power distribution network short-circuit current sample set is, but not limited to, Matlab/Simulink software simulation and actual power distribution network operation data. The ratio of training set to test set in the sample set is typically set to 4: 1.
different sample characteristics can be selected according to the actual power distribution network equipment condition, namely whether a micro synchronous phasor measurement unit (mu PMU) is installed or not. For a power distribution network with K nodes and E branches, one node is generally arrangedAnd if R IIDG access nodes are provided, the input sample characteristics of the short-circuit current calculation model are as follows: x1Corresponding to a distribution network with mu PMU, X2Then the power distribution network without the mu PMU is configured:
in the formula, | V |, theta and P, Q are node voltage amplitude, phase and branch active and reactive power which can be directly obtained by mu PMU; subscript w represents a node number, and the number 1 is a system power supply access node; t represents a branch line number; flineIndicating a faulty line number; flocIndicating the percentage of the fault location from the head end of the line; ftypeThe fault type is shown, the three-phase short circuit is set, and other types of faults can also be set; DGhIs the h IIDG access node;
is the h IIDG capacity; i is an effective value of each obtained branch current which is not provided with a mu PMU but provided with a current transformer; v is a voltage effective value obtained by installing a voltage transformer at the connection position of a system power supply and the IIDG; all the I V I, the theta and the P, Q, I, V contain A/B/C three-phase electric quantity values, so the method can be applied to an asymmetric power distribution network.
Besides considering the actual measurement conditions of the power distribution network, the two types of electric quantities are used as characteristic information of the operation mode of the power distribution network, and fault information of fault positions and fault types is needed to form input characteristics of the sample. The difference of each characteristic value in the sample set is large, so normalization processing is needed, and the convergence capability in the training process is enhanced. The label of the sample is obtained through modeling simulation, and specifically is a steady-state value of each line short-circuit current corresponding to the input characteristics.
S2: establishing an MTRS-XGboost multi-output model;
according to the subtask correlation mode of multi-output regression, the method can be roughly divided into problem transformation and algorithm adaptation.
The core idea of problem transformation is to transform the corresponding mapping relation into a plurality of single output forms, and then combine a plurality of single output models into a multi-output model, so as to achieve the purpose of outputting a plurality of predicted values at the same time. The problem transformation algorithm includes a single-target method (ST), a multi-target regression model fusion algorithm (MTRS), a regression chain algorithm (RC), and the like. Aiming at different practical problems, different problem transformation methods are selected according to the correlation between output tasks, and the optimal multi-output performance is achieved.
The short-circuit current calculation problem of the distribution network containing the IIDG is that the phase angle of the short-circuit current provided by the IIDG power supply and the system power supply is different, the amplitude of the steady-state current of each branch does not explicitly meet the kirchhoff current law any more, but the current vectors meet the kirchhoff current law, so that certain correlation exists between the outputs, and an MTRS (maximum temperature differential) or RC (resistance capacitance) method needs to be selected. In addition, the single output model spliced by the problem transformation method is called a base learner, and under the same splicing method, the stronger the performance of the base learner is, the better the splicing output effect is. Currently, the base learners with superior performance are XGBoost, LightGBM and the like, and all show up in the corner in various big competitions in recent years, and are representative base learners.
The algorithm adaptation method is to modify a single output model according to actual problems and simultaneously output a plurality of predicted values by using one model. The output mapping of the algorithm adaptation method needs to consider not only the input variables but also the relationships among different output variables, so that the accuracy of a plurality of predicted values is improved. The algorithm adaptation method comprises various methods such as a statistical method, a multi-output support vector machine, a multi-output regression tree, a kernel function method, a neural network and the like. The algorithm is suitable for a single-output model before modification, and parameters such as input, a model structure, an output label and a loss function in the algorithm need to be modified aiming at different practical problems. The different algorithm adaptation methods are not modified in exactly the same way.
According to the invention, through a large amount of analysis and comparison, the MTRS-XGboost multi-output model with the optimal comprehensive performance is finally selected. The multi-output model is used for converting a multi-output problem into a plurality of single-output problems by using a multi-objective regression model fusion algorithm MTRS, wherein the XGboost method is adopted by a base learner.
The MTRS process is a problem transformation process that requires two stages of processing. Is provided with N groups of samples, XlAs input to the l group, YlThe corresponding output for the ith group, i.e. the input and output of the ith group of samples, is:
in the formula (I), the compound is shown in the specification,
for the ith input feature in the ith group, i belongs to {1, …, M }, and M is the number of input features;
for the jth output value in the jth group, j ∈ {1, …, D }, D is the number of output labels. In the first stage of MTRS, mapping between all outputs and inputs is respectively established, D single-output models are required to be established for D outputs, and each single-output model is responsible for a single output prediction value, namely a training set D of jth outputMTRS-1Comprises the following steps:
the second step of MTRS is the output quantity of the first step
And original input quantity XlMerge into a new input X*l：
Second order using new input X*lAnd the original output YlAs training set of D output models, i.e. training set of jth output DMTRS-2Comprises the following steps:
in the second order, the predicted value of the first order output is spliced to be used as the input of the training set, the potential relation among a plurality of outputs is considered to a certain extent, the deviation of the problem transformation predicted value is corrected to a certain extent, and the prediction accuracy can be improved.
S3: training an MTRS-XGboost model by using a training set, and finishing training when the loss function is not reduced in the iteration process and the evaluation index is not reduced;
the loss function in step S3 uses the Mean Absolute Percentage Error (MAPE), and the evaluation index uses the MAPE and the Mean Absolute Error (MAE). The evaluation index is obtained by calculating the true value yjAnd the calculated value
The smaller the evaluation index value is, the higher the model accuracy is. The evaluation indices MAPE and MAE are defined as follows:
s4: and the trained MTRS-XGboost multi-output model is used as a multi-output model for calculating the short-circuit current of the distribution network containing the IIDG, and when the input characteristics of the distribution network in a certain fault state are input, all branch short-circuit currents in a corresponding operation state can be quickly output.
Application example
In order to verify the effectiveness of the data-driven multi-output calculation method for the short-circuit current of the power distribution network with the IIDG, the IEEE 34 node power distribution network system shown in figure 2 is used as an example for verification. The node with the number of 800 is a system power supply access point, the system is an unbalanced system, single-phase and three-phase feeder lines exist, model parameter setting is the same as that of a document [ Zhengxiang, Wanghuafang, Jiangdu, and the like ] mechanism and data fusion driven IIDG-containing power distribution network short-circuit current calculation method [ J ] power automation equipment, 2021, 41 (01): 41-48. The operation mode of the distribution network is determined by random generation of system equivalent power source impedance, IIDG capacity and load within [0.8,1.2] times of the original value.
Setting a fault to f in FIG. 2 in simulation1A three-phase short fault occurs on the lines 834-860. In order to accurately explain the capability of outputting short-circuit current simultaneously in a multi-output model, the short-circuit current of three measurement points marked as I, II and III in a dotted line frame in FIG. 2 is selected for calculation, and data in a mechanism and data fusion driven IIDG-containing power distribution network short-circuit current calculation method disclosed by a reference group in the paper of electric power automation equipment (No. 2021, No. 01, vol.41, No. P41-48) is adopted as comparison. Meanwhile, in order to verify the advantage of the XGboost selected by the base learner, under the same method, the LightGBM is selected as a comparison base learner, and the validity of the MTRS-XGboost is demonstrated through comparison. Table 1 shows the results of short-circuit current prediction and performance in different ways.
TABLE 1 Single output model and multiple output model results
As can be seen from Table 1, the XGboost single-output model can only predict the short-circuit current of a single measuring point, and the percentage error APE is within an acceptable range; and the short-circuit current predicted by the multi-output model is lower in percentage error than that of single output due to the consideration of the correlation among the outputs. In addition, the short-circuit current of different measuring points uses different basic learner models, and the error condition of the short-circuit current is slightly different. In conclusion, the method for calculating the short-circuit current of the power distribution network containing the IIDG by adopting the multi-output model is effective and higher in accuracy.
Corresponding discussion is also made for different multi-output methods, and examples of influence on the performance of the multi-output model among the basis learners and the input features. And simultaneously comparing the influence of the two input characteristics of the formulas (1) and (2) on the calculation performance. The multi-output method uses two problem conversion methods of MTRS and RC, and the base learner adopts two algorithms of XGboost and LightGBM. The results are shown in Table 2, where the training time is the time to complete model training using 8000 sets of samples and the testing time is the total elapsed time to complete testing of 2000 sets of samples, and the bold values in the table represent the performance optima for each of the multiple output models.
As can be seen from table 2, the 4 models and both input features achieved better performance, with the maximum and average values of MAPE and MAE within acceptable ranges. The aspect of the calculation speed is more dependent on the adopted problem transformation method, the MTRS method is obviously slower than the RC method, the maximum value of the test time is 11.75062s, namely the maximum value of the test time of each group is 5.875ms on average, and the method is faster than a single-output model, so that the method can also meet the scene with high calculation speed requirement. In addition, the two types of characteristics do not greatly affect the output accuracy of the multi-output model, and the characteristics of formula (2) can be used when the configuration of the μ PMU in the power distribution network is not popularized yet. The error of the XGboost-based learner is slightly smaller than that of the LightGBM-based learner.
TABLE 2 comparison of Performance for different Multi-output models, different base learners, different input features
In practical application, part of characteristic data may be lost in the data acquisition process. A method with better comprehensive performance in the table 2 is selected, namely, an XGboost algorithm of MTRS and RC splicing is respectively used, the characteristics adopt the characteristics of a formula (1), and data loss is expressed in a random zero setting mode. The performance of the two models at different data loss ratios is shown in table 3 and fig. 3, with the bold values in table 3 representing the less error data.
The data in table 3 shows that the error is smaller for both models at 1% data loss. The multi-output model can still maintain better performance under the condition of losing 5% and 10% of data quantity, wherein the error of the MTRS model is slightly better than that of the RC model.
TABLE 3 comparison of Performance of multiple output models at different data loss ratios
FIG. 3 shows MAPE-mean values for different multi-output models for data loss ratios above 10%. When the data loss rate is less than 30%, the error values of the MTRS and the RC methods are small, and when the data loss rate exceeds 30%, the average value of the errors of the MTRS and the RC rises rapidly. Therefore, under the condition of small data loss, the MTRS and the RC have good anti-interference capability, and when the data loss occupation ratio is high, the errors of the MTRS and the RC increase rapidly along with the increase of the data loss occupation ratio.
According to the application example, the data-driven multiple-output calculation method for the short-circuit current of the power distribution network with the IIDG can meet requirements of calculation accuracy and calculation rapidity at the same time, can calculate the short-circuit current of all branches at the same time in one operation, can be applied to short-circuit current calculation of the power distribution network with the IIDG, and is popularized to novel power systems with a large amount of new energy connected at all levels to achieve rapid and accurate calculation of the short-circuit current.
Claims (5)
1. The data-driven multi-output calculation method for the short-circuit current of the power distribution network containing the IIDG is characterized by comprising the following steps of:
s1: establishing a short-circuit current sample set of the power distribution network containing the IIDG, wherein the sample set comprises a training set and a testing set;
s2: selecting and establishing a MTRS-XGboost multi-output model through a large number of analysis comparison multi-output models, wherein the multi-output model has the capacity of outputting short-circuit currents of all branches simultaneously;
s3: training an MTRS-XGboost model by using a training set, and finishing training when the loss function is not reduced in the iteration process and the evaluation index is not reduced;
s4: and calculating the short-circuit current of the distribution network containing the IIDG by using the MTRS-XGboost multi-output model after training, and outputting all branch currents in the corresponding operation state.
2. The data-driven multiple-output calculation method for the short-circuit current of the power distribution network containing the IIDG, according to claim 1, is characterized in that: in the step S1, the sources of the power distribution network short-circuit current sample set containing the IIDG are, but not limited to, Matlab/Simulink software simulation and actual power distribution network operation data, and the proportion of the training set to the test set in the sample set is 4: 1.
3. the data-driven multiple-output calculation method for the short-circuit current of the power distribution network containing the IIDG, according to claim 2, is characterized in that: different input characteristics can be selected according to the actual power distribution network equipment condition, namely whether a micro synchronous phasor measurement unit (mu PMU) is installed or not; the distribution network equipped with the mu PMU can select the voltage amplitude, the phase and the active and reactive power values in the distribution network, and the distribution network not equipped with the mu PMU can select the current value in the power grid as an input characteristic.
4. The data-driven multiple-output calculation method for the short-circuit current of the power distribution network containing the IIDG, according to claim 1, is characterized in that: step S2, the MTRS-XGboost multi-output model is used for converting multi-output problems into a plurality of single-output problems by using a multi-objective regression model fusion algorithm MTRS, wherein the XGboost method is adopted by a base learner.
5. The data-driven multiple-output calculation method for the short-circuit current of the power distribution network containing the IIDG, according to claim 1, is characterized in that: step S3, the loss function adopts a mean absolute percentage error MAPE, and the evaluation index adopts the mean absolute percentage error MAPE and a mean absolute error MAE; the evaluation index is obtained by calculating the true value yjAnd the calculated value
The smaller the evaluation index value is, the higher the model accuracy is.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111255829.2A CN113991652B (en) | 2021-10-27 | 2021-10-27 | Data-driven multi-output calculation method for short-circuit current of distribution network containing IIDG |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111255829.2A CN113991652B (en) | 2021-10-27 | 2021-10-27 | Data-driven multi-output calculation method for short-circuit current of distribution network containing IIDG |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113991652A true CN113991652A (en) | 2022-01-28 |
| CN113991652B CN113991652B (en) | 2024-05-17 |
Family
ID=79742587
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111255829.2A Active CN113991652B (en) | 2021-10-27 | 2021-10-27 | Data-driven multi-output calculation method for short-circuit current of distribution network containing IIDG |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113991652B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114971388A (en) * | 2022-06-20 | 2022-08-30 | 山东安能信息技术有限公司 | Power distribution network line loss fine management system based on big data |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111064182A (en) * | 2019-11-25 | 2020-04-24 | 国网浙江省电力有限公司湖州供电公司 | Short-circuit current calculation method based on power grid characteristics |
| CN111159841A (en) * | 2019-11-25 | 2020-05-15 | 国网浙江省电力有限公司湖州供电公司 | Power distribution network short-circuit current calculation method based on data fusion |
| CN111262238A (en) * | 2020-02-12 | 2020-06-09 | 浙江大学 | Machine learning-based method for predicting short-circuit current of power distribution network containing IIDG |
-
2021
- 2021-10-27 CN CN202111255829.2A patent/CN113991652B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111064182A (en) * | 2019-11-25 | 2020-04-24 | 国网浙江省电力有限公司湖州供电公司 | Short-circuit current calculation method based on power grid characteristics |
| CN111159841A (en) * | 2019-11-25 | 2020-05-15 | 国网浙江省电力有限公司湖州供电公司 | Power distribution network short-circuit current calculation method based on data fusion |
| CN111262238A (en) * | 2020-02-12 | 2020-06-09 | 浙江大学 | Machine learning-based method for predicting short-circuit current of power distribution network containing IIDG |
Non-Patent Citations (3)
| Title |
|---|
| SAULO MARTIELLO MASTELINI等: "DSTARS: A Multi-Target Deep Structure for Tracking Asynchronous Regressor Stack", 《2017 BRAZILIAN CONFERENCE ON INTELLIGENT SYSTEMS》, pages 19 - 24 * |
| XIANG ZHENG等: "A Novel Machine Learning-Based Short-Circuit Current Prediction Method for Active Distribution Networks", 《ENERGIES》, pages 1 - 15 * |
| 郑翔: "基于数据驱动的含IIDG配电网短路电流计算模型研究", 《中国优秀硕士学位论文全文数据库(工程科技Ⅱ辑)》, pages 042 - 204 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114971388A (en) * | 2022-06-20 | 2022-08-30 | 山东安能信息技术有限公司 | Power distribution network line loss fine management system based on big data |
| CN114971388B (en) * | 2022-06-20 | 2023-06-13 | 山东安能信息技术有限公司 | Power distribution network line loss fine management system based on big data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113991652B (en) | 2024-05-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107577870B (en) | Power distribution network voltage power sensitivity robust estimation method based on synchronous phasor measurement | |
| US20140309952A1 (en) | Method for Analyzing Faults in Ungrounded Power Distribution Systems | |
| CN108306285B (en) | Reliability evaluation method for active power distribution network containing distributed power supply based on TOPSIS method | |
| CN110299762B (en) | PMU (phasor measurement Unit) quasi-real-time data-based active power distribution network robust estimation method | |
| CN111262238B (en) | Machine learning-based method for predicting short-circuit current of power distribution network containing IIDG | |
| CN111159841B (en) | Power distribution network short-circuit current calculation method based on data fusion | |
| Gianto | T-circuit model of asynchronous wind turbine for distribution system load flow analysis | |
| CN111401792A (en) | Dynamic safety assessment method based on extreme gradient lifting decision tree | |
| CN113991652A (en) | Data-driven multi-output calculation method for short-circuit current of IIDG-containing power distribution network | |
| Mohammadi-Ivatloo et al. | Optimal PMU placement for power system observability considering secondary voltage control | |
| CN116488267A (en) | Modeling-based wind farm reactive capacity limit simulation calculation method and device | |
| CN113224788B (en) | Static voltage stability evaluation method for AC/DC hybrid power grid with wind power access | |
| CN112670966B (en) | Self-adaptive current protection method for photovoltaic power distribution network | |
| CN115494349A (en) | Active power distribution network single-phase earth fault section positioning method | |
| CN112910006B (en) | Universal electromagnetic transient modeling method for direct-drive wind turbine generator | |
| CN113162063B (en) | Design method of multi-direct-current coordination controller for inhibiting ultralow frequency oscillation | |
| CN109193617B (en) | Power system vulnerability evaluation method and system based on tight constraint recognition | |
| Yao et al. | Short-circuit current calculation in distribution network with IIDGs based on artificial neural network | |
| Dufour et al. | Renewable integration and protection studies on a 750-node distribution grid using a real-time simulator and a delay-free parallel solver | |
| Wei et al. | Dynamic equivalent model of active distribution network based on improved reinforcement learning algorithm | |
| Sangsarawut et al. | Optimal reactive power planning of doubly fed induction generators using genetic algorithms | |
| CN112564158B (en) | Direct current commutation failure prediction method | |
| CN109919797A (en) | A kind of parameter Estimation and bearing calibration of power supply transien process | |
| Tian et al. | Security Region-Based Time Series Production Simulation of Renewable Energy Power Grids | |
| Acurio et al. | State Estimation for Unbalanced Three-Phase AC Microgrids Based on Mathematical Programming |
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 |