CN118094189A - Transient overvoltage feature extraction method, system, terminal and medium - Google Patents
Transient overvoltage feature extraction method, system, terminal and medium Download PDFInfo
- Publication number
- CN118094189A CN118094189A CN202410256477.XA CN202410256477A CN118094189A CN 118094189 A CN118094189 A CN 118094189A CN 202410256477 A CN202410256477 A CN 202410256477A CN 118094189 A CN118094189 A CN 118094189A
- Authority
- CN
- China
- Prior art keywords
- input characteristic
- input
- transient overvoltage
- correlation
- characteristic quantity
- 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
- 230000001052 transient effect Effects 0.000 title claims abstract description 83
- 238000000605 extraction Methods 0.000 title claims abstract description 46
- 238000007689 inspection Methods 0.000 claims abstract description 5
- 238000000034 method Methods 0.000 claims description 31
- 238000004590 computer program Methods 0.000 claims description 24
- 230000005540 biological transmission Effects 0.000 claims description 17
- 230000004044 response Effects 0.000 claims description 13
- 230000008859 change Effects 0.000 claims description 10
- 238000012360 testing method Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 8
- 238000010998 test method Methods 0.000 claims description 2
- 238000013210 evaluation model Methods 0.000 abstract description 5
- 238000010219 correlation analysis Methods 0.000 abstract description 3
- 230000000875 corresponding effect Effects 0.000 description 7
- 230000006870 function Effects 0.000 description 7
- 230000007246 mechanism Effects 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000013473 artificial intelligence Methods 0.000 description 3
- 230000007423 decrease Effects 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 230000009467 reduction Effects 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000010187 selection method Methods 0.000 description 2
- 238000013097 stability assessment Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 239000003990 capacitor Substances 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000556 factor analysis Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/211—Selection of the most significant subset of features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Tourism & Hospitality (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention relates to the technical field of transient voltage of an electric power system, and discloses a transient overvoltage characteristic extraction method, a system, a terminal and a medium, which comprise the steps of obtaining input characteristic quantity and constructing an initial input characteristic set according to the input characteristic quantity; removing the input characteristic quantity in the initial input characteristic set to obtain an input characteristic quantity with low redundancy degree; and performing correlation feature inspection on the input feature quantity with low redundancy degree to obtain a final input feature quantity, completing transient overvoltage feature extraction, reducing redundancy among high-dimensional electrical characteristic input features, and performing inspection on correlation analysis values to obtain a final input feature quantity, so that the performance and prediction efficiency of the evaluation model are improved.
Description
Technical Field
The invention relates to the technical field of transient voltage of an electric power system, in particular to a method, a system, a terminal and a medium for extracting transient overvoltage characteristics.
Background
Under the strategic background of the double-carbon target, the wide acceptance of renewable energy sources and the operation of multi-terminal extra-high voltage direct current transmission projects lead the operation characteristics of the power system to be changed greatly. The uncertainty between the source and the load is aggravated, and the dynamic characteristics of the power grid are deeply influenced by high-proportion power electronic equipment. In addition, the reduction of fault tolerance increases the risk of transient voltage instability, thus posing a threat to safe and stable operation of the power system. Therefore, there is a need for an effective strategy for rapidly achieving Transient Voltage Stability Assessment (TVSA).
With the development of big data theory and artificial intelligence technology and the rapid popularization of measurement equipment, the data-driven artificial intelligence method provides possibility for realizing rapid transient voltage stability evaluation. However, due to the large scale and numerous components of the actual power system, the high-dimensional electrical characteristics can lead to redundancy among input features, which seriously affects the performance and prediction efficiency of the evaluation model. In recent years, in order to fully exploit key features under system disturbances, dynamic time series data is applied to transient stability analysis, which increases the computational effort and the risk of overfitting. Therefore, in order to facilitate the application of artificial intelligence methods in power system transient voltage stability assessment, it is still necessary to explore suitable feature selection strategies to reduce the dimensionality of the original features.
Conventional methods typically involve manually selecting key features and relying on expert experience to select variable features for stability analysis. However, as the fault characteristics of the new equipment are not clear, the transient voltage instability mechanism is not clear, and the variable characteristic selection is more and more difficult to adapt to the complex characteristics of a large-scale power grid by relying on manual expertise.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention aims to provide a transient overvoltage feature extraction method, a transient overvoltage feature extraction system, a transient overvoltage feature extraction terminal and a transient overvoltage feature extraction medium, so as to solve the technical problems that redundancy exists among input features in the prior art, and evaluation model performance and prediction efficiency are affected.
The invention is realized by the following technical scheme:
in a first aspect, the present invention provides a method for extracting transient overvoltage characteristics, comprising
Acquiring an input characteristic quantity, and constructing an initial input characteristic set according to the input characteristic quantity;
Removing the input characteristic quantity in the initial input characteristic set to obtain an input characteristic quantity with low redundancy degree;
and performing correlation feature inspection on the input feature quantity with low redundancy degree to obtain a final input feature quantity, and completing transient overvoltage feature extraction.
Preferably, the input characteristic quantity is obtained by combining main influence factors of grid voltage instability or transient overvoltage level, wherein the input characteristic quantity comprises a direct current related response characteristic quantity before and after the characterization of faults and a new energy system output characteristic related response characteristic quantity.
Further, the main influencing factors include the access proportion of the new energy source at the transmitting end and the conventional unit, the transmission power of the direct current system, and the output characteristics of the direct current and new energy source system during the fault.
Preferably, the input feature quantity in the initial input feature set is removed to obtain the input feature quantity with low redundancy, and the specific process is as follows:
S1, calculating input characteristic quantities in an initial input characteristic set and voltage change degrees to obtain a plurality of correlation coefficients, performing first condition judgment on the plurality of correlation coefficients, and performing first stage rejection on the input characteristic quantities corresponding to the correlation coefficients which do not meet the first condition judgment to obtain input characteristic quantities with high correlation with the voltage change degrees;
S2, calculating the input characteristic quantities with high voltage change degree correlation in pairs to obtain a plurality of correlation coefficients, performing second condition judgment on the plurality of correlation coefficients, and performing second stage rejection on any one of the two input characteristic quantities corresponding to the correlation coefficients which do not meet the second condition judgment to obtain the input characteristic quantity with low redundancy degree.
Further, a Spearman correlation coefficient method is adopted to calculate a correlation coefficient, wherein the Spearman correlation coefficient has the following calculation formula:
Wherein: x i and Y i each represent a level to which the i-th group data corresponds, And/>The average levels of the variables x and y, respectively.
Further, in the step S1, the specific process of performing the first condition determination on the plurality of correlation coefficients is as follows:
Setting a first threshold, and eliminating the input characteristic quantity corresponding to the correlation coefficient when the absolute value of a plurality of correlation coefficients obtained by calculating the input characteristic quantity in the initial input characteristic set and the voltage variation degree is smaller than the first threshold to obtain the input characteristic quantity with high correlation with the voltage variation degree;
in the step S2, the specific process of performing the second condition determination on the plurality of correlation coefficients is as follows:
Setting a second threshold value, and when the absolute values of a plurality of correlation coefficients obtained by two-by-two calculation in the rest input characteristic quantities are larger than the second threshold value, eliminating any one of the two input characteristic quantities corresponding to the correlation coefficients to obtain the input characteristic quantity with low redundancy.
Preferably, the correlation feature test is performed on the input feature quantity with a low redundancy level, a p-value test method is used, a threshold value is set, and an input feature quantity with a p-value smaller than the threshold value is used as a final input feature quantity.
In a second aspect, the present invention provides a transient overvoltage feature extraction system, comprising:
the data set construction module is used for acquiring input characteristic quantities and constructing an initial input characteristic set according to the input characteristic quantities;
the rejecting module is used for rejecting the input characteristic quantity in the initial input characteristic set to obtain an input characteristic quantity with low redundancy degree;
And the checking module is used for carrying out correlation characteristic checking on the input characteristic quantity with low redundancy degree to obtain a final input characteristic quantity, and finishing transient overvoltage characteristic extraction.
In a third aspect, the present invention provides a mobile terminal comprising a memory, a processor and a computer program stored in said memory and executable on said processor, characterized in that said processor implements the steps of the method for extracting transient overvoltage features as described above when said computer program is executed by said processor.
In a fourth aspect, the present invention provides a computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the method for extracting transient overvoltage features as described above.
Compared with the prior art, the invention has the following beneficial technical effects:
the invention provides a transient overvoltage feature extraction method, a transient overvoltage feature extraction system, a transient overvoltage feature extraction terminal and a transient overvoltage feature extraction medium.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a schematic diagram of a DC power supply system with wind power in an embodiment of the invention;
FIG. 3 is a schematic diagram of a variation characteristic of a system response in an embodiment of the present invention;
FIG. 4 is a schematic diagram of a local area DC delivery system according to an embodiment of the present invention;
FIG. 5 is a Spearman correlation thermodynamic diagram of an embodiment of the present invention;
FIG. 6 illustrates the deviation between the true value and the predicted value in different feature extraction states according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of the system principle structure of the present invention;
in the figure: 1-a data set construction module; 2-removing the module; 3-a checking module.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
The invention is described in further detail below with reference to the attached drawing figures:
the invention aims to provide a transient overvoltage feature extraction method, a transient overvoltage feature extraction system, a transient overvoltage feature extraction terminal and a transient overvoltage feature extraction medium, so as to solve the technical problems that redundancy exists among input features in the prior art, and the performance of an evaluation model and the prediction efficiency are affected.
Example 1
Taking the extraction of key response characteristics reflecting the transient overvoltage level of the transmitting end as an example, the effectiveness of the proposed method is verified by adopting an example of a typical wind-fire bundling direct current transmission simulation system in a local area shown in fig. 4. The test system is constructed based on a 500kV grid structure, and comprises 210 nodes, and the reference capacity is 100MW. The wind turbine generator and the conventional machine are assembled in the sizes 4470MW and 8460MW respectively. The system comprises a return + -500 kV direct current circuit, and the rated transmission active power of the direct current system is 5000MW.
Referring to fig. 1, in one embodiment of the present invention, a transient overvoltage feature extraction method is provided, which specifically includes the following steps:
Firstly, combining transient overvoltage level main influence factor analysis results and input data selection principles, selecting relevant response characteristics capable of representing output characteristics of direct current, new energy and conventional units, and constructing an initial input characteristic set, as shown in table 1. And setting direct current commutation failure faults to perform multiple simulation to finish sampling by considering the renewable energy access proportion, direct current transmission power and other factors, and obtaining multiple groups of data with different input characteristics and corresponding transient overvoltage levels. For the operation mode, the output of the conventional unit and the wind power plant is adjusted under the load levels of 90%, 100% and 110%, and the new energy access proportion is set to be 30%, 35%, 40%, 45%, 50% and 55%. The load model consists of static load and induction motor according to a certain proportion, including 40%, 50% and 60%. In addition, the dc transmission power is adjusted in 10% increments within the range of 60% to 100% of the rated power. For fault types, commutation failures include both monopolar and bipolar faults. The number of commutation failures was set to 1, 2 and 3, respectively. Meanwhile, the duration of a single commutation failure is from 0.15s to 0.25s, and 3 durations are set in steps of 0.05 s. The simulation time was 5s and the total number of samples was 4480.
TABLE 1 initial input feature construction
And carrying out correlation analysis on the sampled data based on the method, respectively completing the elimination of low-correlation features and redundant features, and verifying the significance level of the correlation among the features by adopting p-value test, thereby obtaining the final input features.
As shown in FIG. 5, the darker the color of the square block, the higher the correlation between the two corresponding features, and it can be seen that the selected features satisfy the proposed feature selection principle.
In order to verify the effectiveness of the proposed feature selection method and the rationality of the selected key input features, regression prediction is performed on the transient overvoltage amplitude by using a classical BP neural network, the selected features are used as inputs, the transient overvoltage amplitude of the corresponding scene is used as output, 80% of samples are used as training data sets, and the other 20% are used as test data sets. The Root Mean Square Error (RMSE), the Mean Absolute Error (MAE) and the Mean Absolute Percent Error (MAPE) are used as performance evaluation indexes, and the calculation formulas of the indexes are as follows:
wherein: n represents the total number of test set samples, j represents the j-th test sample, y' represents the predicted value, and y represents the true value. The overall error level of the overvoltage amplitude prediction is reflected by each index, and the lower the evaluation index value is, the better the model prediction effect is.
Table 2 compares the predicted performance of BP neural networks in different feature extraction states. As can be seen from table 2, the model has a poor prediction effect under the initial input feature set, and has a certain improvement effect on each index along with the progress of the feature extraction process, thus proving the effectiveness of the proposed method.
TABLE 2 prediction effect in different feature extraction states
In addition, in different feature extraction states, the deviation value between the true value and the predicted value of the BP network is shown in fig. 6. It can be obtained that the key response characteristics extracted by the method are used as input, the regression prediction effect on the test set is good, the predicted value is closer to the true value, and the effectiveness of the method is further verified.
The invention analyzes the mechanism of the transmitting end transient overvoltage caused by the commutation failure fault of the alternating current system based on the renewable energy and the dynamic characteristics of the asynchronous motor during the fault before the transient overvoltage characteristic extraction method
Take the HVDC system with wind power as shown in fig. 3 as an example. Under normal operating conditions, the reactive balance relationship of the sending end system can be expressed as:
ΔQ＝Qac+Qw+Qcr-Qdr＝0 (4)
Wherein: q cr、Qac and Q w are respectively an alternating current filter, a reactive power compensation device, a transmitting end alternating current system and reactive power output by a wind farm; q dr is reactive power consumption of the rectifying station.
Reactive power consumption of the rectifying station is as follows:
Wherein: p dr is the active power of direct current transmission, E r is the effective value of the no-load line voltage of the transformer at the rectifying side, N 1 is the number of pulse converters at the rectifying station 6, alpha is the emitting angle of the rectifying station, X r is the leakage reactance of the rectifying transformer, and I d is direct current. As can be seen from equation (2), the reactive power consumed by the rectifier is related to the emission angle α and increases with increasing emission angle. The reactive power consumption of the rectifier station is generally between 40% and 60% of the direct current transmission power. Thus, higher dc power transmission requires increased reactive compensation on the rectifier side.
When the direct current commutation failure is caused by serious short circuit fault of the receiving-end alternating current system, the direct current voltage is rapidly reduced and the direct current is rapidly increased due to the conduction of the receiving-end inverter. The transmitting-end rectifier station starts the low-voltage limit control unit to restrain the rising of the direct current by increasing the emission angle. In this process, the reactive power consumption of the rectifying station increases with an increase in the emission angle, resulting in a voltage drop in the vicinity of the transmitting-side ac system.
Under the regulation of the low-voltage limit control unit, the emission angle is continuously increased to be more than 90 degrees, so that the rectifier is stopped, and equipment is protected. The dc current gradually decreases and may even reach 0, resulting in a momentary blocking of the dc system. As the direct current decreases, the reactive power consumption of the rectifying station also gradually decreases. When the direct current approaches 0, the reactive power consumption of the rectifying station is negligible. In the process, the alternating current filter and the reactive compensation device of the rectifying station keep running, and the reactive power consumption of the inverter is far lower than the reactive power generated by the filter. Thus, a large amount of reactive power is sent back to the ac system, resulting in an increase in the transient voltage of the ac system at the send side. In addition, during the dc recovery phase, the dc is still low and the reactive power consumption of the transmitting-side rectifying station is still low, which may lead to a degree of overvoltage.
From the above analysis, after the commutation failure, the transmitting system presents transient characteristics that the voltage of the transmitting bus is reduced and then increased, which can cause transient overvoltage. The changes in dc current, bus voltage and emission angle upon commutation failure are shown in fig. 2.
And secondly, analyzing the relation between the voltage variation of the alternating current bus of the transmitting end and the output reactive power of the alternating current filter and the reactive power compensation device, the consumption reactive power of the direct current rectifying side, the transmission reactive power of the wind farm and the short-circuit capacity of the transmitting end by combining a transmitting end transient overvoltage mechanism caused by the commutation failure fault of the alternating current system, and mining main influence factors reflecting the transient overvoltage level.
During commutation failure, the amount of change in the voltage of the ac busbar at the transmitting end can be expressed as:
Wherein: Δu t represents the degree of change in the voltage of the power transmission side bus bar, and S cr represents the short-circuit capacity of the rectifying side converter bus bar. As is known from the transient overvoltage mechanism, during transient voltage rise, Δq >0, the rectifier station consumes relatively little reactive power, resulting in a large amount of reactive power being fed back into the feed-side system. During transients, Q ac may be approximated as a steady state value. Therefore, the change degree Δut of the voltage of the sending-end bus is mainly affected by the output reactive power Q cr of the ac filter and the reactive power compensation device, the consumption reactive power Q dr of the dc rectifying side, the wind farm delivery reactive power Q w and the sending-end short-circuit capacity S cr.
Analysis was made of the relationship between the bus voltage change degree Δu t and Q cr,Qdr,Qw,Scr:
(1) Influence of AC filter and reactive compensation device
Typically the ac filter and reactive compensation means are capacitors, and considering their inherent reactive-voltage dynamics, Q cr can be expressed as follows:
Wherein: q crN represents the reactive power compensation capacity of the ac filter and the reactive power compensation device in the normal operation state, and mainly depends on the transmission power of the dc system in the normal operation state, and the reactive power compensation amount increases with the increase of the transmission power, which may cause a more serious overvoltage level.
(2) Influence of DC system
According to the reactive power expression consumed by the rectifying station in the transient overvoltage mechanism, when the direct current commutation fails, the reactive power consumed by the rectifying side mainly depends on the direct current I d, the emission angle alpha and the direct current transmission power P dr. The reactive power absorbed by the rectifier when commutation fails varies with the dc voltage and current. When the dc current and voltage drop to the limit values, the rectifier will absorb the minimum reactive power. At this time, the reactive power generated by the direct current system has the most serious influence on the transient voltage of the alternating current system at the transmitting end, so that the transient overvoltage peak value occurs to the bus at the transmitting end.
(3) Influence of wind power generation system
After the commutation fault occurs, low voltage ride through protection may occur in the voltage reduction process of the near-area wind power plant. The fan adopts a reactive priority control mode during low voltage ride through to provide the system with as much reactive power as possible while avoiding significant reduction in active power output and excessive generator speed and disconnection from the power system due to significant reduction in active power output. The active power and reactive power variation of the wind turbine generator during low voltage ride through can be expressed as follows:
ΔQw＝[kq(0.9-Uw)-1]Qw0 (8)
ΔPw＝(kp-1)Pw0 (9)
Wherein: k q and k p respectively represent the reactive power output and the active power output coefficient of the fan during low-voltage threading; p w0 and Q w0 respectively represent rated active power and reactive power of the fan, and U w is fan terminal voltage. During low voltage ride through, the fan active power is greatly reduced (delta P w > 0), the reactive power output is increased (delta Q w > 0), and therefore reactive surplus occurs on the wind power plant side after faults, the surplus reactive power can flow backwards to the power supply system and act together with surplus reactive power of the converter station, the power supply transient overvoltage level is further deteriorated, and the transient overvoltage level is seen to be connected with various response characteristics of the wind power system.
(4) Influence of short-circuit capacity at the feed end
The strength of the feed-side system is typically measured by the ratio of the short-circuit capacity of the feed-side converter bus to the rated dc power, i.e., the short-circuit ratio. The calculation formula thereof according to the short-circuit ratio definition can be expressed as:
generally the higher the system strength, the lower the transient overvoltage level. For a direct current system with a fixed rated transmission power, the short-circuit capacity of the transmitting bus directly affects the transient overvoltage level of the system. Under the same conditions, the short-circuit capacity of the conventional unit is larger, the supporting capacity is stronger, the short-circuit capacity of the new energy unit is relatively smaller, and the supporting capacity is weaker, so that the direct current near-area conventional unit and the new energy have important influence on the short-circuit capacity, the short-circuit capacity of a large-scale new energy access back-end sending system is reduced, and more serious transient overvoltage is caused during the fault period.
In combination with the above analysis, a main influencing factor reflecting the transient overvoltage level is obtained: the ratio of the new energy source at the transmitting end to the conventional unit, the transmission power of the direct current system, the output characteristics of the direct current system, the new energy source and other systems during the fault period.
In the embodiment, the transient overvoltage characteristic extraction adopts the Spearman correlation coefficient to perform characteristic extraction, and the key response characteristic reflecting the safety and stability level of the power grid voltage is extracted, so that the calculation accuracy and the calculation speed of a response driving algorithm are improved.
Data driven methods typically require the construction of a sample set, the key being the selection of the appropriate input features. The input features need to adequately reflect the operating state of the system and be available on-line. Furthermore, the dimension of the input features cannot be too high. In the case of topology changes, too many features may lead to dimension disasters, resulting in lengthy online updates. Thus, it is necessary to determine the appropriate model input features in an offline process. The invention provides a feature selection method based on Spearman correlation coefficient, which comprehensively considers convenience of data acquisition, rationality of data dimension and capability of data reflecting system state.
The Spearman correlation coefficient is used for measuring the correlation between two variables, and solving is carried out according to the sorting position of the original data so as to reduce the dependence on the linear relation of the data. For either discrete data or data that does not fit a normal distribution, a Spearman correlation coefficient may be used to evaluate correlation. Assuming that there are n sets of data, including (x 1,y1),(x2,y2),…,(xi,yi),…,(xn,yn), the Spearman correlation coefficient is calculated as follows:
Wherein: x i and Y i each represent a level to which the i-th group data corresponds, And/>The average levels of the variables x and y are respectively, and the value range of the Spearman correlation coefficient is [ -1,1] as shown in the formula (8), when R s is close to 0, the variables x and y are uncorrelated, and when R s is close to 1 or-1, the variables x and y are strongly correlated. After obtaining the correlation analysis value, a hypothesis test (p-value test) is also required to verify the intensity and significance level of the correlation between the features. If the p-value is greater than 0.05, there is no significant difference, i.e., no correlation. If the p value is less than 0.05, the significant difference exists among the characteristics, and the correlation is strong.
In conclusion, the invention explains the mechanism of transient overvoltage generation of the sending end system under commutation failure fault based on the renewable energy and the dynamic characteristics of the asynchronous motor during the fault period, and provides theoretical support for the transient voltage instability analysis under the condition of defining the large-scale grid connection of new energy.
According to the invention, by combining a transmitting-end transient overvoltage mechanism caused by commutation failure faults of an alternating current system, main influencing factors reflecting the transient overvoltage level are excavated according to transient characteristics after the commutation failure, and a basis is provided for screening input features of a feature extraction method.
According to the characteristic extraction method based on the Spearman correlation coefficient, which is provided by the invention, the key response characteristic reflecting the safety and stability level of the power grid voltage is extracted by combining the main influence factors reflecting the transient overvoltage level, the calculation precision and calculation speed of a response driving algorithm are improved, redundancy among high-dimensional electrical characteristic input characteristics is reduced, the performance and prediction efficiency of an evaluation model are improved, and the characteristic extraction method is more suitable for complex characteristics of a large power grid.
Example 2
According to fig. 7, the present invention further provides a transient overvoltage feature extraction system, including:
The data set construction module 1 is used for acquiring input characteristic quantities and constructing an initial input characteristic set according to the input characteristic quantities;
The rejecting module 2 is used for rejecting the input characteristic quantity in the initial input characteristic set to obtain an input characteristic quantity with low redundancy degree;
And the checking module 3 is used for performing correlation feature checking on the input feature quantity with low redundancy degree to obtain a final input feature quantity, and finishing transient overvoltage feature extraction.
Example 3
The invention also provides a mobile terminal comprising a memory, a processor and a computer program stored in the memory and executable on the processor, such as a transient overvoltage feature extraction program.
The steps of the above-mentioned transient overvoltage feature extraction method are implemented when the processor executes the computer program, for example:
acquiring an input characteristic quantity, and constructing an initial input characteristic set according to the input characteristic quantity;
Removing the input characteristic quantity in the initial input characteristic set to obtain an input characteristic quantity with low redundancy degree;
and performing correlation feature inspection on the input feature quantity with low redundancy degree to obtain a final input feature quantity, and completing transient overvoltage feature extraction.
Or the processor, when executing the computer program, performs the functions of the modules in the system, for example:
The data set construction module 1 is used for acquiring input characteristic quantities and constructing an initial input characteristic set according to the input characteristic quantities;
The rejecting module 2 is used for rejecting the input characteristic quantity in the initial input characteristic set to obtain an input characteristic quantity with low redundancy degree;
And the checking module 3 is used for performing correlation feature checking on the input feature quantity with low redundancy degree to obtain a final input feature quantity, and finishing transient overvoltage feature extraction.
The computer program may be divided into one or more modules/units, which are stored in the memory and executed by the processor to accomplish the present invention, for example. The one or more modules/units may be a series of computer program instruction segments capable of performing the specified functions, which instruction segments are used for describing the execution of the computer program in the mobile terminal.
For example, the computer program may be partitioned into a dataset construction module 1, a culling module 3 and a verification module 4; the specific functions of each module are as follows:
The data set construction module 1 is used for acquiring input characteristic quantities and constructing an initial input characteristic set according to the input characteristic quantities;
The rejecting module 2 is used for rejecting the input characteristic quantity in the initial input characteristic set to obtain an input characteristic quantity with low redundancy degree;
And the checking module 3 is used for performing correlation feature checking on the input feature quantity with low redundancy degree to obtain a final input feature quantity, and finishing transient overvoltage feature extraction.
The mobile terminal can be a computing device such as a desktop computer, a notebook computer, a palm computer, a cloud server and the like. The mobile terminal may include, but is not limited to, a processor, memory.
The processor may be a central processing unit (CentralProcessingUnit, CPU), but may also be other general purpose processors, digital signal processors (DigitalSignalProcessor, DSP), application specific integrated circuits (ApplicationSpecificIntegratedCircuit, ASIC), off-the-shelf programmable gate arrays (Field-ProgrammableGateArray, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, which is a control center of the mobile terminal, connecting various parts of the entire mobile terminal using various interfaces and lines.
The memory may be used to store the computer program and/or module, and the processor may implement various functions of the mobile terminal by running or executing the computer program and/or module stored in the memory and invoking data stored in the memory.
The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data (such as audio data, phonebook, etc.) created according to the use of the handset, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart memory card (SMARTMEDIACARD, SMC), secure digital (SecureDigital, SD) card, flash memory card (FLASHCARD), at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device.
Example 4
The invention also provides a computer readable storage medium storing a computer program which when executed by a processor implements the steps of the method of transient overvoltage feature extraction.
The mobile terminal integrated modules/units may be stored in a computer readable storage medium if implemented in the form of software functional units and sold or used as a stand alone product.
Based on such understanding, the present invention may implement all or part of the above-mentioned method, or may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and the computer program may implement the steps of the above-mentioned transient overvoltage feature extraction method when executed by a processor. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc.
The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer memory, a Read-only memory (ROM), a random access memory (RAM, randomAccessMemory), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth.
It should be noted that the computer readable medium contains content that can be appropriately scaled according to the requirements of jurisdictions in which such content is subject to legislation and patent practice, such as in certain jurisdictions in which such content is subject to legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunication signals.
Finally, it should be noted that: the above embodiments are only for illustrating the technical aspects of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the above embodiments, it should be understood by those of ordinary skill in the art that: modifications and equivalents may be made to the specific embodiments of the invention without departing from the spirit and scope of the invention, which is intended to be covered by the claims.
Claims (10)
1. The transient overvoltage characteristic extraction method is characterized by comprising the following steps of
Acquiring an input characteristic quantity, and constructing an initial input characteristic set according to the input characteristic quantity;
Removing the input characteristic quantity in the initial input characteristic set to obtain an input characteristic quantity with low redundancy degree;
and performing correlation feature inspection on the input feature quantity with low redundancy degree to obtain a final input feature quantity, and completing transient overvoltage feature extraction.
2. The method for extracting transient overvoltage characteristics according to claim 1, wherein the input characteristic quantity is obtained by combining main influence factors of grid voltage instability or transient overvoltage level, wherein the input characteristic quantity comprises a direct current related response characteristic quantity before and after a fault and a new energy system output characteristic related response characteristic quantity.
3. The method according to claim 2, wherein the main influencing factors include the access ratio of the new energy source and the conventional unit at the transmitting end, the transmission power of the direct current system, and the output characteristics of the direct current and the new energy source system during the fault.
4. The method for extracting transient overvoltage features according to claim 1, wherein the step of eliminating the input features in the initial input feature set to obtain the input features with low redundancy comprises the following steps:
S1, calculating input characteristic quantities in an initial input characteristic set and voltage change degrees to obtain a plurality of correlation coefficients, performing first condition judgment on the plurality of correlation coefficients, and performing first stage rejection on the input characteristic quantities corresponding to the correlation coefficients which do not meet the first condition judgment to obtain input characteristic quantities with high correlation with the voltage change degrees;
S2, calculating the input characteristic quantities with high voltage change degree correlation in pairs to obtain a plurality of correlation coefficients, performing second condition judgment on the plurality of correlation coefficients, and performing second stage rejection on any one of the two input characteristic quantities corresponding to the correlation coefficients which do not meet the second condition judgment to obtain the input characteristic quantity with low redundancy degree.
5. The method for extracting transient overvoltage features of claim 4, wherein the correlation coefficient is calculated by using a Spearman correlation coefficient method, and wherein the Spearman correlation coefficient is calculated according to the following formula:
Wherein: x i and Y i each represent a level to which the i-th group data corresponds, And/>The average levels of the variables x and y, respectively.
6. The method for extracting transient overvoltage features according to claim 4, wherein in S1, the specific process of performing the first condition determination on the plurality of correlation coefficients is as follows:
Setting a first threshold, and eliminating the input characteristic quantity corresponding to the correlation coefficient when the absolute value of a plurality of correlation coefficients obtained by calculating the input characteristic quantity in the initial input characteristic set and the voltage variation degree is smaller than the first threshold to obtain the input characteristic quantity with high correlation with the voltage variation degree;
in the step S2, the specific process of performing the second condition determination on the plurality of correlation coefficients is as follows:
Setting a second threshold value, and when the absolute values of a plurality of correlation coefficients obtained by two-by-two calculation in the rest input characteristic quantities are larger than the second threshold value, eliminating any one of the two input characteristic quantities corresponding to the correlation coefficients to obtain the input characteristic quantity with low redundancy.
7. The method according to claim 1, wherein the correlation feature test is performed on the input feature quantity with low redundancy, a p-value test method is used, a threshold value is set, and an input feature quantity with p-value smaller than the threshold value is used as the final input feature quantity.
8. A transient overvoltage feature extraction system, comprising:
the data set construction module (1) is used for acquiring input characteristic quantities and constructing an initial input characteristic set according to the input characteristic quantities;
The rejecting module (2) is used for rejecting the input characteristic quantity in the initial input characteristic set to obtain an input characteristic quantity with low redundancy degree;
And the checking module (3) is used for carrying out correlation characteristic checking on the input characteristic quantity with low redundancy degree to obtain a final input characteristic quantity and finishing transient overvoltage characteristic extraction.
9. A mobile terminal comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the transient overvoltage feature extraction method according to any one of claims 1-7 when the computer program is executed.
10. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the transient overvoltage feature extraction method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410256477.XA CN118094189A (en) | 2024-03-06 | 2024-03-06 | Transient overvoltage feature extraction method, system, terminal and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410256477.XA CN118094189A (en) | 2024-03-06 | 2024-03-06 | Transient overvoltage feature extraction method, system, terminal and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118094189A true CN118094189A (en) | 2024-05-28 |
Family
ID=91163028
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410256477.XA Pending CN118094189A (en) | 2024-03-06 | 2024-03-06 | Transient overvoltage feature extraction method, system, terminal and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118094189A (en) |
-
2024
- 2024-03-06 CN CN202410256477.XA patent/CN118094189A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109638810B (en) | Energy storage planning method and system based on transient stability of power system | |
| CN109474014B (en) | Quantitative evaluation method for dual-fed wind field access power grid friendliness | |
| CN106875127B (en) | Unified power flow controller reliability modeling and access power grid reliability assessment method thereof | |
| CN113240350B (en) | Comprehensive utility evaluation method and system based on energy storage grid connection | |
| CN111404147B (en) | Offline timing sequence-based online decision method and device for inhibiting chain offline of new energy | |
| Uchendu | Placement of distributed generation and shunt capacitor in distribution network using cuckoo search algorithm | |
| CN113612272B (en) | Charging control method and device for uninterruptible power supply of new energy power generation system | |
| CN109038657B (en) | Processing method, device, server and medium for primary system of offshore wind farm | |
| CN114491886A (en) | General modeling method and device for active power distribution network containing multi-type distributed new energy | |
| CN116611011A (en) | Transient overvoltage amplitude prediction method, system, terminal and medium | |
| CN117094209A (en) | BP neural network-based hybrid wind power plant fault characteristic grouping method | |
| CN118094189A (en) | Transient overvoltage feature extraction method, system, terminal and medium | |
| CN115940157A (en) | Method, device and equipment for automatically generating load flow scene of stability control strategy checking task | |
| CN108336731A (en) | A kind of computational methods of power distribution network distributed generation resource allowed capacity | |
| CN111030160B (en) | Method and device for evaluating distributed power supply accepting capacity of power distribution network | |
| CN113722678A (en) | Transformer area line loss calculation method, system, storage medium and calculation device | |
| Russell et al. | Single Line Outage Analysis on IEEE 39 Bus Network | |
| CN111092453A (en) | Power grid key line identification method for multipoint access photovoltaic power supply | |
| Li et al. | Interval Electrical Betweenness Method for Power Grid Vulnerability Assessment Considering Wind Power | |
| CN111884234A (en) | Emergency control method and device for precise cutting machine, electronic equipment and storage medium | |
| Ma et al. | Cyber-physical Modeling Technique based Dynamic Aggregation of Wind Farm Considering LVRT Characteristic | |
| CN117171502B (en) | Method for calculating DC fault overvoltage peak value of multi-DC external power supply system by bundling wind and fire | |
| Zhang et al. | An improved decision tree-based method for predicting overvoltage peak values integrating a model-driven scheme | |
| CN117691942A (en) | Fault detection method and device for distributed photovoltaic power generation system | |
| CN114825379A (en) | Optimization method, system and storage medium of self-synchronizing voltage source type new energy station |
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 |