CN116304699A - Critical sample set generation method and system based on new energy multi-station short circuit ratio - Google Patents
Critical sample set generation method and system based on new energy multi-station short circuit ratio Download PDFInfo
- Publication number
- CN116304699A CN116304699A CN202310216014.6A CN202310216014A CN116304699A CN 116304699 A CN116304699 A CN 116304699A CN 202310216014 A CN202310216014 A CN 202310216014A CN 116304699 A CN116304699 A CN 116304699A
- Authority
- CN
- China
- Prior art keywords
- new energy
- power
- critical
- point
- connected point
- 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
- 238000000034 method Methods 0.000 title claims abstract description 34
- 230000003068 static effect Effects 0.000 claims abstract description 54
- 238000004364 calculation method Methods 0.000 claims description 27
- 230000001965 increasing effect Effects 0.000 claims description 8
- 230000002159 abnormal effect Effects 0.000 claims description 7
- 230000008859 change Effects 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 7
- 230000005856 abnormality Effects 0.000 claims description 6
- 239000004973 liquid crystal related substance Substances 0.000 claims 4
- 238000005516 engineering process Methods 0.000 abstract description 4
- 230000008846 dynamic interplay Effects 0.000 abstract description 3
- 238000004088 simulation Methods 0.000 abstract description 3
- 208000003569 Central serous chorioretinopathy Diseases 0.000 description 16
- 238000010586 diagram Methods 0.000 description 9
- 238000004590 computer program Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 230000006399 behavior Effects 0.000 description 5
- 238000012360 testing method Methods 0.000 description 5
- 238000012549 training Methods 0.000 description 5
- 238000009826 distribution Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 239000002109 single walled nanotube Substances 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000011160 research 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
- H02J3/04—Circuit arrangements for ac mains or ac distribution networks for connecting networks of the same frequency but supplied from different sources
- H02J3/06—Controlling transfer of power between connected networks; Controlling sharing of load between connected networks
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- 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
- H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
- H02J3/46—Controlling of the sharing of output between the generators, converters, or transformers
- H02J3/48—Controlling the sharing of the in-phase component
-
- 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
- H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
- H02J3/46—Controlling of the sharing of output between the generators, converters, or transformers
- H02J3/50—Controlling the sharing of the out-of-phase component
-
- 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]
-
- 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
- H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
- H02J2300/20—The dispersed energy generation being of renewable origin
- H02J2300/22—The renewable source being solar energy
- H02J2300/24—The renewable source being solar energy of photovoltaic origin
-
- 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
- H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
- H02J2300/20—The dispersed energy generation being of renewable origin
- H02J2300/28—The renewable source being wind energy
Abstract
The invention discloses a critical sample set generation method and a system based on a new energy multi-station short circuit ratio, wherein the method comprises the following steps: acquiring a point set of static voltage stability critical points corresponding to each new energy grid-connected point, forming a static voltage stability domain boundary of each new energy grid-connected point based on the point set, and taking a critical short circuit ratio of each new energy grid-connected point as a prediction label; acquiring voltage amplitude and phase angle of the whole network bus and active power and reactive power of a line in all initial tide states, and taking the voltage amplitude and the phase angle of the whole network bus and the active power and the reactive power of the line as input characteristics; and constructing a two-dimensional array based on the input features and the predictive labels to obtain a critical sample set. According to the method, the critical short circuit ratio sample set batch simulation function is realized through dynamic interaction of Python and BPA, the problems of large workload, low efficiency, easy error and the like existing in manual repeated operation can be avoided, and a data basis is provided for the field of introducing voltage support strength in a data driving technology.
Description
Technical Field
The invention relates to the technical field of large power grid stability analysis and control application, in particular to a critical sample set generation method and system based on a new energy multi-station short circuit ratio.
Background
With the concentrated access of new energy with high proportion randomness, volatility and intermittence to the power grid, the problem of voltage safety and stability of the power grid is outstanding. In order to ensure the stability of the power system after a large amount of new energy is accessed, the safety and stability guide rule of the GB38755-2019 power system recommends that the voltage support strength of the new energy accessed to the power grid is evaluated by utilizing the short circuit ratio (mu l t i p l e renewab l e energy stat i on short ci rcu it rat i o, MRSCR) of the new energy multiple stations. MRSCR fully considers the mutual influence among new energy stations and the reactive power influence of new energy power generation equipment, and has good characterization capability. In terms of setting the stability criterion, a critical value of mrsc r, i.e. critical short-circuit ratio (cr i t i ca l short ci rcu it rat i o, CSCR), is obtained by calculation of typical grid parameters. CSCR, however, is dynamically changing under different scenarios, and CSCR set by engineering experience can only coarsely characterize the critical state of the system. In fact, most of short-circuit ratios suitable for high-proportion new energy power systems adopt the method to set corresponding CSCR, so that the selection of the stability criterion becomes a weak link for evaluating the voltage support strength, and a large error exists.
In recent years, due to the breakthrough development of deep learning, the use of the deep learning to solve the problem of power system stability is becoming a research hotspot again. In this context, the weak link of the method for enhancing the voltage support strength by using the deep learning technology is a brand new exploration. However, the construction of CSCR sample sets is the primary link of the related study, and the representativeness and completeness of the sample sets also determine the generalization performance of the deep learning model.
Therefore, a new energy multi-station short circuit ratio CSCR sample set generation method needs to be proposed.
Disclosure of Invention
The invention provides a critical sample set generation method and a system based on a new energy multi-station short-circuit ratio, which are used for solving the problem of how to efficiently generate a critical sample set of the new energy multi-station short-circuit ratio.
In order to solve the above problems, according to an aspect of the present invention, there is provided a critical sample set generating method based on a new energy multi-station short ratio, the method comprising:
acquiring a point set of static voltage stability critical points corresponding to each new energy grid-connected point, forming a static voltage stability domain boundary of each new energy grid-connected point based on the point set, and taking a critical short circuit ratio of each new energy grid-connected point as a prediction label;
acquiring voltage amplitude and phase angle of the whole network bus and active power and reactive power of a line in all initial tide states, and taking the voltage amplitude and the phase angle of the whole network bus and the active power and the reactive power of the line as input characteristics;
and constructing a two-dimensional array based on the input features and the predictive labels to obtain a critical sample set.
Preferably, the obtaining the point set of the static voltage stability critical point corresponding to each new energy grid-connected point includes:
dividing active power according to the number of new energy stations and the total power of new energy sources of the power system, and carrying out power flow calculation to determine an initial power flow state;
based on the initial power flow state, carrying out automatic positioning of the maximum transmittable power point, obtaining the maximum transmittable power of each new energy grid-connected point, and storing the power flow result when each new energy grid-connected point reaches the static critical voltage stable state;
and calculating the critical short-circuit ratio of each new energy grid-connected point under the critical steady state of the static voltage according to the tide result so as to determine the point set of the static voltage steady critical point corresponding to each new energy grid-connected point.
Preferably, the dividing the active power according to the number of new energy stations and the total power of the new energy stations of the power system, and performing power flow calculation to determine an initial power flow state, includes:
analyzing the power flow file DAT to determine the number of new energy stations and the total power of the new energy in the power system;
according to the total power of the new energy sources, the active power of each new energy station is randomly divided, and the active power of each new energy station in the DAT is modified;
carrying out load flow calculation and judging whether a load flow result is converged or not; if the power flow result is converged, a stable calculation program SWNT is operated based on a power flow calculation result file to judge whether the condition of power output out-of-limit and P I D limiting exists or not, and if no abnormal error is reported, the current power flow state is determined to be the initial power flow state of the system; otherwise, the active power of each new energy station needs to be divided again until no abnormality exists, and the current power flow state is determined to be the initial power flow state of the system.
Preferably, the automatic positioning of the maximum transmittable power point based on the initial power flow state, obtaining the maximum transmittable power of each new energy grid-connected point, includes:
and for any new energy grid-connected point, increasing the active Power of the new energy grid-connected point according to a constant Power factor, tracking the steady-state behavior of the system under the condition of Power change, and tracking the Power-Vo l tage curve to the nose point so as to determine the maximum transmittable Power of any new energy grid-connected point.
Preferably, the calculating the critical short-circuit ratio of each new energy grid-connected point in the static voltage critical steady state according to the tide result includes:
wherein MRSCR i The critical short-circuit ratio of the ith new energy grid-connected point is set;
the nominal voltage of the ith grid-connected bus node is the nominal voltage; />
The voltage generated on the ith node for the new energy source; />
The apparent power injected into the bus node of the ith new energy grid-connected point; />
The elements of the ith row and the j columns of the equivalent impedance matrix of the alternating current power grid at the new energy grid connection position are selected; the short-circuit ratio of the new energy multi-station is the relative magnitude between the nominal voltage of the system and the new energy generation voltage: the current injected into the alternating current system by the bus of each new energy grid-connected point is +.>
The voltage of each new energy grid-connected point bus node is shown as +.>
n is the number of new energy grid-connected points.
According to another aspect of the present invention, there is provided a critical sample set generating system based on a new energy multi-station short circuit ratio, the system comprising:
the prediction tag acquisition unit is used for acquiring a point set of static voltage stability critical points corresponding to each new energy grid-connected point, forming a static voltage stability domain boundary of each new energy grid-connected point based on the point set, and taking the critical short circuit ratio of each new energy grid-connected point as a prediction tag;
the input characteristic acquisition unit is used for acquiring the voltage amplitude and phase angle of the whole network bus and the active power and reactive power of the line in all initial tide states and is used as an input characteristic;
and the critical sample set generating unit is used for constructing a two-dimensional array based on the input characteristics and the prediction labels so as to acquire a critical sample set.
Preferably, the prediction tag obtaining unit obtains a point set of static voltage stability critical points corresponding to each new energy grid-connected point, including:
dividing active power according to the number of new energy stations and the total power of new energy sources of the power system, and carrying out power flow calculation to determine an initial power flow state;
based on the initial power flow state, carrying out automatic positioning of the maximum transmittable power point, obtaining the maximum transmittable power of each new energy grid-connected point, and storing the power flow result when each new energy grid-connected point reaches the static critical voltage stable state;
and calculating the critical short-circuit ratio of each new energy grid-connected point under the critical steady state of the static voltage according to the tide result so as to determine the point set of the static voltage steady critical point corresponding to each new energy grid-connected point.
Preferably, the prediction tag obtaining unit divides active power according to the number of new energy stations and total power of new energy sources of the power system, and performs power flow calculation to determine an initial power flow state, including:
analyzing the power flow file DAT to determine the number of new energy stations and the total power of the new energy in the power system;
according to the total power of the new energy sources, the active power of each new energy station is randomly divided, and the active power of each new energy station in the DAT is modified;
carrying out load flow calculation and judging whether a load flow result is converged or not; if the power flow result is converged, a stable calculation program SWNT is operated based on a power flow calculation result file to judge whether the condition of power output out-of-limit and PID limiting exists or not, and if no abnormal error is reported, the current power flow state is determined to be the initial power flow state of the system; otherwise, the active power of each new energy station needs to be divided again until no abnormality exists, and the current power flow state is determined to be the initial power flow state of the system.
Preferably, the predictive tag obtaining unit performs automatic positioning of a maximum transmittable power point based on the initial power flow state, and obtains the maximum transmittable power of each new energy grid-connected point, including:
and for any new energy grid-connected point, increasing the active Power of the new energy grid-connected point according to a constant Power factor, tracking the steady-state behavior of the system under the condition of Power change, and tracking the Power-Vo l tage curve to the nose point so as to determine the maximum transmittable Power of any new energy grid-connected point.
Preferably, the predictive tag obtaining unit calculates, according to the trend result, a critical short-circuit ratio of each new energy grid-connected point in a static voltage critical steady state, including:
wherein MRSCR i The critical short-circuit ratio of the ith new energy grid-connected point is set;
the nominal voltage of the ith grid-connected bus node is the nominal voltage; />
The voltage generated on the ith node for the new energy source; />
The apparent power injected into the bus node of the ith new energy grid-connected point; />
The elements of the ith row and the j columns of the equivalent impedance matrix of the alternating current power grid at the new energy grid connection position are selected; the short-circuit ratio of the new energy multi-station is the relative magnitude between the nominal voltage of the system and the new energy generation voltage: the current injected into the alternating current system by the bus of each new energy grid-connected point is +.>
The voltage of each new energy grid-connected point bus node is shown as +.>
n is the number of new energy grid-connected points.
The invention provides a critical sample set generation method and a system based on a new energy multi-station short circuit ratio, wherein the method comprises the following steps: acquiring a point set of static voltage stability critical points corresponding to each new energy grid-connected point, forming a static voltage stability domain boundary of each new energy grid-connected point based on the point set, and taking a critical short circuit ratio of each new energy grid-connected point as a prediction label; acquiring voltage amplitude and phase angle of the whole network bus and active power and reactive power of a line in all initial tide states, and taking the voltage amplitude and the phase angle of the whole network bus and the active power and the reactive power of the line as input characteristics; and constructing a two-dimensional array based on the input features and the predictive labels to obtain a critical sample set. According to the method, the critical short circuit ratio sample set batch simulation function is realized through dynamic interaction of Python and BPA, the problems of large workload, low efficiency, easy error and the like existing in manual repeated operation can be avoided, and a data basis is provided for the field of introducing voltage support strength in a data driving technology.
Drawings
Exemplary embodiments of the present invention may be more completely understood in consideration of the following drawings:
FIG. 1 is a flow chart of a new energy multi-station short ratio based critical sample set generation method 100 according to an embodiment of the present invention;
FIG. 2 is a flow chart of the construction of a critical short ratio dataset according to an embodiment of the present invention;
FIG. 3 is a flow chart of a set of points for obtaining a number of static voltage stability threshold points according to an embodiment of the present invention;
FIG. 4 is a label distribution histogram of a CSCR dataset according to an embodiment of the present invention;
FIG. 5 is a training pattern diagram according to an embodiment of the present invention;
FIG. 6 is a label distribution graph of critical short ratios according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of a critical sample set generating system 700 based on a new energy multi-station short circuit ratio according to an embodiment of the present invention.
Detailed Description
The exemplary embodiments of the present invention will now be described with reference to the accompanying drawings, however, the present invention may be embodied in many different forms and is not limited to the examples described herein, which are provided to fully and completely disclose the present invention and fully convey the scope of the invention to those skilled in the art. The terminology used in the exemplary embodiments illustrated in the accompanying drawings is not intended to be limiting of the invention. In the drawings, like elements/components are referred to by like reference numerals.
Unless otherwise indicated, terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art. In addition, it will be understood that terms defined in commonly used dictionaries should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense.
Fig. 1 is a flowchart of a critical sample set generating method 100 based on a new energy multi-station short circuit ratio according to an embodiment of the present invention. As shown in fig. 1, the method for generating the critical sample set based on the short-circuit ratio of the new energy multi-station provided by the embodiment of the invention realizes the batch simulation function of the critical short-circuit ratio sample set through dynamic interaction of Python and BPA, can avoid the problems of large workload, low efficiency, easy error and the like existing in manual repeated operation, and provides a data basis for introducing the field of voltage support strength for the data driving technology. In the method 100 for generating the critical sample set based on the short-circuit ratio of the new energy multi-station provided by the embodiment of the invention, starting from the step 101, in the step 101, a point set of static voltage stability critical points corresponding to each new energy grid-connected point is obtained, a static voltage stability domain boundary of each new energy grid-connected point is formed based on the point set, and the critical short-circuit ratio of each new energy grid-connected point is used as a prediction label.
Preferably, the obtaining the point set of the static voltage stability critical point corresponding to each new energy grid-connected point includes:
dividing active power according to the number of new energy stations and the total power of new energy sources of the power system, and carrying out power flow calculation to determine an initial power flow state;
based on the initial power flow state, carrying out automatic positioning of the maximum transmittable power point, obtaining the maximum transmittable power of each new energy grid-connected point, and storing the power flow result when each new energy grid-connected point reaches the static critical voltage stable state;
and calculating the critical short-circuit ratio of each new energy grid-connected point under the critical steady state of the static voltage according to the tide result so as to determine the point set of the static voltage steady critical point corresponding to each new energy grid-connected point.
Preferably, the dividing the active power according to the number of new energy stations and the total power of the new energy stations of the power system, and performing power flow calculation to determine an initial power flow state, includes:
analyzing the power flow file DAT to determine the number of new energy stations and the total power of the new energy in the power system;
according to the total power of the new energy sources, the active power of each new energy station is randomly divided, and the active power of each new energy station in the DAT is modified;
carrying out load flow calculation and judging whether a load flow result is converged or not; if the power flow result is converged, a stable calculation program SWNT is operated based on a power flow calculation result file to judge whether the condition of power output out-of-limit and P I D limiting exists or not, and if no abnormal error is reported, the current power flow state is determined to be the initial power flow state of the system; otherwise, the active power of each new energy station needs to be divided again until no abnormality exists, and the current power flow state is determined to be the initial power flow state of the system.
Preferably, the automatic positioning of the maximum transmittable power point based on the initial power flow state, obtaining the maximum transmittable power of each new energy grid-connected point, includes:
and for any new energy grid-connected point, increasing the active Power of the new energy grid-connected point according to a constant Power factor, tracking the steady-state behavior of the system under the condition of Power change, and tracking the Power-Vo l tage curve to the nose point so as to determine the maximum transmittable Power of any new energy grid-connected point.
Preferably, the calculating the critical short-circuit ratio of each new energy grid-connected point in the static voltage critical steady state according to the tide result includes:
wherein MRSCR i The critical short-circuit ratio of the ith new energy grid-connected point is set;
the nominal voltage of the ith grid-connected bus node is the nominal voltage; />
The voltage generated on the ith node for the new energy source; />
The apparent power injected into the bus node of the ith new energy grid-connected point; />
The elements of the ith row and the j columns of the equivalent impedance matrix of the alternating current power grid at the new energy grid connection position are selected; the short-circuit ratio of the new energy multi-station is the relative magnitude between the nominal voltage of the system and the new energy generation voltage: the current injected into the alternating current system by the bus of each new energy grid-connected point is +.>
The voltage of each new energy grid-connected point bus node is shown as +.>
n is the number of new energy grid-connected points.
In step 102, the voltage amplitude and phase angle of the bus of the whole network and the active power and reactive power of the line in all initial tide states are obtained and used as input characteristics.
In step 103, a two-dimensional array is constructed based on the input features and the predictive labels to obtain a set of critical samples.
Referring to fig. 2, in the present invention, first, a large number of point sets of static voltage stability critical points are obtained according to the number of samples required, the point sets form the static voltage stability domain boundary of each point-to-point, and CSCR of each point-to-point is used as a prediction label. And then, extracting the voltage amplitude and phase angle of the whole network bus, the active power and the reactive power of the line in all initial tide states as input characteristics. And finally, merging the input features and the prediction labels of all samples into a two-dimensional array, and storing the two-dimensional array as a CSV file.
The process of obtaining a plurality of point sets of static voltage stability critical points is shown in fig. 3. Specifically, the method comprises the following steps:
Firstly, analyzing a tide file (DAT) to count information of each node and each line, and determining the number of new energy stations and the total power of new energy in a power system. Then, the active power of each station is divided randomly according to the total power of the new energy. When the active power of each station in DAT is modified, corresponding data is input in a designated column according to a designated format of a B card (alternating current node card), otherwise, errors may occur after the data are read by a tide calculation Program (PFNT) and a stability calculation program (SWNT). After modification, the PFNT is operated to determine whether the flow result is converged. If the power flow results are converged, the SWNTs are operated based on a power flow calculation result file (BSE) to judge whether the power output of the generator is out of limit, PID limiting and the like exist. If no abnormal fault is reported, the current power flow state can be used as an initial power flow state of the system; otherwise, the output of the new energy station is not reasonably divided and needs to be divided again.
Firstly, according to the physical definition of CSCR, selecting a new energy station to make its active power increase according to constant power factor. Then, the steady state behavior of the system under the condition of Power change is tracked, and a Power-Vo voltage curve is tracked until a nose point, wherein surplus Power is consumed by means of a generator of a balance node. The essence of the above operation is the application of a continuous power flow method, thus requiring repeated modification of the L I card (power continuously increasing card) of the steady file (SWL) and running the SWNTs until the maximum transmissible power of all the grid-connected points is obtained. And finally, storing the tide results when each grid-connected point reaches the static critical voltage stable state. In view of the complex and diverse ways in which the active power of multiple new energy stations is simultaneously increased, this step achieves a relatively conservative critical short ratio by simulating the increase in active power of a single station.
Step 3, calculating the CSCR of each station as a sample tag
The current injected into the alternating current system by the bus of each new energy grid-connected point is respectively
The voltage of the bus node of each grid-connected point can be expressed as +.>
In the middle of
The elements of the ith row and the j columns of the equivalent impedance matrix of the alternating current power grid at the new energy grid connection position are obtained. The new energy multi-station short-circuit ratio is defined as the relative magnitude between the system nominal voltage and the new energy generation voltage:
in the middle of
The nominal voltage of the ith grid-connected bus node is the nominal voltage; />
The voltage generated on the ith node for the new energy source; />
And injecting apparent power for the bus node of the ith new energy grid-connected point.
Then, MRSCR, namely CSCR of each station in the static voltage critical steady state is calculated according to the critical power flow result and the formula (2). The relationship between MRSCR and system static voltage stability can be established through CSCR. Thus CSCR for each station acts as a sample tag.
And (3) obtaining a plurality of point sets of static voltage stability critical points by repeating the steps 1-3.
The invention takes a CEPRI-102 node system as a test system, wherein 6 wind power stations and 6 photovoltaic stations are respectively marked as Wi and Pi. According to FIG. 2, a batch simulation program based on Python and PSD-BPA was developed to construct a critical short ratio dataset containing 10000 samples, and the distribution of the tags was counted, as shown in FIG. 4. CSCR for each station in fig. 4 is dynamically changing and fluctuates in a range of 1.2 to 2.3. Obviously, the severe fluctuation range causes that 1.5 set according to engineering experience is difficult to adapt to various scenes, so that a large error exists in the evaluation result. Further, from the CSCR distribution, there is a similarity or a difference between the grid-connected points.
To verify the effectiveness of the present invention, 80% of the dataset was divided into training sets, with the remaining 20% being test sets. Because of the large number of stations, a dedicated network needs to be trained for each station, with the training pattern shown in fig. 5. In the aspect of the model, a deep neural network is selected for training and testing, the network structure is 512-256-128-64-1, the learning rate is 0.001, and the optimizer is Adam. In order to show the intelligent enhancement effect, the experiment is analyzed by enhancing errors before and after the enhancement and adverse effects caused by the errors. Taking a W1 station as an example, samples of the training set and the test set are arranged in an ascending order according to the true values of the samples, and corresponding predicted values and experience values are plotted in fig. 6. Fig. 6 shows that the predicted value is closer to the true value, while the empirical value is far from the true value for most samples. Obviously, the empirical value is a main factor causing the evaluation error, and the error can be effectively reduced by applying the DL technique to enhance the calculation link of CSCR. From the predictive effect of the test set, the data set is representative and complete, and the validity of the invention is verified.
Fig. 7 is a schematic structural diagram of a critical sample set generating system 700 based on a new energy multi-station short circuit ratio according to an embodiment of the present invention. As shown in fig. 7, a critical sample set generating system 700 based on a new energy multi-station short circuit ratio according to an embodiment of the present invention includes: a predictive label acquisition unit 701, an input feature acquisition unit 702, and a critical sample set generation unit 703.
Preferably, the prediction tag obtaining unit 701 is configured to obtain a point set of static voltage stability critical points corresponding to each new energy grid-connected point, form a static voltage stability domain boundary of each new energy grid-connected point based on the point set, and use a critical short-circuit ratio of each new energy grid-connected point as a prediction tag.
Preferably, the prediction tag obtaining unit 701 obtains a point set of static voltage stability critical points corresponding to each new energy grid-connected point, including:
dividing active power according to the number of new energy stations and the total power of new energy sources of the power system, and carrying out power flow calculation to determine an initial power flow state;
based on the initial power flow state, carrying out automatic positioning of the maximum transmittable power point, obtaining the maximum transmittable power of each new energy grid-connected point, and storing the power flow result when each new energy grid-connected point reaches the static critical voltage stable state;
and calculating the critical short-circuit ratio of each new energy grid-connected point under the critical steady state of the static voltage according to the tide result so as to determine the point set of the static voltage steady critical point corresponding to each new energy grid-connected point.
Preferably, the prediction tag obtaining unit 701 divides active power according to the number of new energy stations and total power of new energy sources of the power system, and performs power flow calculation to determine an initial power flow state, including:
analyzing the power flow file DAT to determine the number of new energy stations and the total power of the new energy in the power system;
according to the total power of the new energy sources, the active power of each new energy station is randomly divided, and the active power of each new energy station in the DAT is modified;
carrying out load flow calculation and judging whether a load flow result is converged or not; if the power flow result is converged, a stable calculation program SWNT is operated based on a power flow calculation result file to judge whether the condition of power output out-of-limit and PID limiting exists or not, and if no abnormal error is reported, the current power flow state is determined to be the initial power flow state of the system; otherwise, the active power of each new energy station needs to be divided again until no abnormality exists, and the current power flow state is determined to be the initial power flow state of the system.
Preferably, the predictive tag obtaining unit 701 performs automatic positioning of a maximum transmittable power point based on the initial power flow state, and obtains the maximum transmittable power of each new energy grid-connected point, including:
and for any new energy grid-connected point, increasing the active Power of the new energy grid-connected point according to a constant Power factor, tracking the steady-state behavior of the system under the condition of Power change, and tracking the Power-Vo voltage curve to the nose point so as to determine the maximum transmittable Power of any new energy grid-connected point.
Preferably, the prediction tag obtaining unit 701 calculates, according to the trend result, a critical short-circuit ratio of each new energy grid-connected point in a static voltage critical steady state, including:
wherein MRSCR i The critical short-circuit ratio of the ith new energy grid-connected point is set;
the nominal voltage of the ith grid-connected bus node is the nominal voltage; />
The voltage generated on the ith node for the new energy source; />
The apparent power injected into the bus node of the ith new energy grid-connected point; />
The elements of the ith row and the j columns of the equivalent impedance matrix of the alternating current power grid at the new energy grid connection position are selected; the short-circuit ratio of the new energy multi-station is the relative magnitude between the nominal voltage of the system and the new energy generation voltage: the current injected into the alternating current system by the bus of each new energy grid-connected point is +.>
The voltage of each new energy grid-connected point bus node is shown as +.>
n is the number of new energy grid-connected points.
Preferably, the input feature obtaining unit 702 is configured to obtain the voltage amplitude and phase angle of the full-network bus and the active power and reactive power of the line in all the initial power flow states, and use the obtained voltage amplitude and phase angle as the input feature.
Preferably, the critical sample set generating unit 703 is configured to construct a two-dimensional array based on the input features and the prediction tags, so as to obtain a critical sample set.
The critical sample set generating system 700 based on the short-circuit ratio of the new energy multi-station according to the embodiment of the present invention corresponds to the critical sample set generating method 100 based on the short-circuit ratio of the new energy multi-station according to another embodiment of the present invention, and is not described herein.
The invention has been described with reference to a few embodiments. However, as is well known to those skilled in the art, other embodiments than the above disclosed invention are equally possible within the scope of the invention, as defined by the appended patent claims.
Generally, all terms used in the claims are to be interpreted according to their ordinary meaning in the technical field, unless explicitly defined otherwise therein. All references to "a/an/the [ means, component, etc. ]" are to be interpreted openly as referring to at least one instance of said means, component, etc., unless explicitly stated otherwise. The steps of any method disclosed herein do not have to be performed in the exact order disclosed, unless explicitly stated.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
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. A critical sample set generation method based on a new energy multi-station short circuit ratio is characterized by comprising the following steps:
acquiring a point set of static voltage stability critical points corresponding to each new energy grid-connected point, forming a static voltage stability domain boundary of each new energy grid-connected point based on the point set, and taking a critical short circuit ratio of each new energy grid-connected point as a prediction label;
acquiring voltage amplitude and phase angle of the whole network bus and active power and reactive power of a line in all initial tide states, and taking the voltage amplitude and the phase angle of the whole network bus and the active power and the reactive power of the line as input characteristics;
and constructing a two-dimensional array based on the input features and the predictive labels to obtain a critical sample set.
2. The method of claim 1, wherein the obtaining the point set of static voltage stability critical points corresponding to each new energy grid-connected point comprises:
dividing active power according to the number of new energy stations and the total power of new energy sources of the power system, and carrying out power flow calculation to determine an initial power flow state;
based on the initial power flow state, carrying out automatic positioning of the maximum transmittable power point, obtaining the maximum transmittable power of each new energy grid-connected point, and storing the power flow result when each new energy grid-connected point reaches the static critical voltage stable state;
and calculating the critical short-circuit ratio of each new energy grid-connected point under the critical steady state of the static voltage according to the tide result so as to determine the point set of the static voltage steady critical point corresponding to each new energy grid-connected point.
3. The method according to claim 2, wherein the dividing the active power according to the number of new energy stations and the total power of the new energy in the power system and performing a power flow calculation to determine an initial power flow state includes:
analyzing the power flow file DAT to determine the number of new energy stations and the total power of the new energy in the power system;
according to the total power of the new energy sources, the active power of each new energy station is randomly divided, and the active power of each new energy station in the DAT is modified;
carrying out load flow calculation and judging whether a load flow result is converged or not; if the power flow result is converged, a stable calculation program SWNT is operated based on a power flow calculation result file to judge whether the condition of power output out-of-limit and PID limiting exists or not, and if no abnormal error is reported, the current power flow state is determined to be the initial power flow state of the system; otherwise, the active power of each new energy station needs to be divided again until no abnormality exists, and the current power flow state is determined to be the initial power flow state of the system.
4. The method according to claim 2, wherein the automatically locating the maximum transmittable power point based on the initial power flow state, and obtaining the maximum transmittable power of each new energy grid-connected point, includes:
and for any new energy grid-connected point, increasing the active Power of the new energy grid-connected point according to a constant Power factor, tracking the steady-state behavior of the system under the condition of Power change, and tracking a Power-Voltage curve to a nose point so as to determine the maximum transmittable Power of any new energy grid-connected point.
5. The method according to claim 2, wherein calculating the critical short-circuit ratio of each new energy grid-connected point in the static voltage critical steady state according to the tide result comprises:
wherein, the liquid crystal display device comprises a liquid crystal display device, MRSCR i the critical short-circuit ratio of the ith new energy grid-connected point is set;
the nominal voltage of the ith grid-connected bus node is the nominal voltage;
the voltage generated on the ith node for the new energy source; />
The apparent power injected into the bus node of the ith new energy grid-connected point; />
The elements of the ith row and the j columns of the equivalent impedance matrix of the alternating current power grid at the new energy grid connection position are selected; the short-circuit ratio of the new energy multi-station is the relative magnitude between the nominal voltage of the system and the new energy generation voltage: the current injected into the alternating current system by the bus of each new energy grid-connected point is +.>
The voltage of each new energy grid-connected point bus node is shown as +.>
n is the number of new energy grid-connected points.
6. A critical sample set generation system based on a new energy multi-station short circuit ratio, the system comprising:
the prediction tag acquisition unit is used for acquiring a point set of static voltage stability critical points corresponding to each new energy grid-connected point, forming a static voltage stability domain boundary of each new energy grid-connected point based on the point set, and taking the critical short circuit ratio of each new energy grid-connected point as a prediction tag;
the input characteristic acquisition unit is used for acquiring the voltage amplitude and phase angle of the whole network bus and the active power and reactive power of the line in all initial tide states and is used as an input characteristic;
and the critical sample set generating unit is used for constructing a two-dimensional array based on the input characteristics and the prediction labels so as to acquire a critical sample set.
7. The system according to claim 6, wherein the prediction tag obtaining unit obtains a point set of static voltage stability critical points corresponding to each new energy grid-connected point, and the method includes:
dividing active power according to the number of new energy stations and the total power of new energy sources of the power system, and carrying out power flow calculation to determine an initial power flow state;
based on the initial power flow state, carrying out automatic positioning of the maximum transmittable power point, obtaining the maximum transmittable power of each new energy grid-connected point, and storing the power flow result when each new energy grid-connected point reaches the static critical voltage stable state;
and calculating the critical short-circuit ratio of each new energy grid-connected point under the critical steady state of the static voltage according to the tide result so as to determine the point set of the static voltage steady critical point corresponding to each new energy grid-connected point.
8. The system according to claim 7, wherein the predictive tag obtaining unit divides active power according to the number of new energy stations and total power of new energy sources of the power system and performs power flow calculation to determine an initial power flow state, comprising:
analyzing the power flow file DAT to determine the number of new energy stations and the total power of the new energy in the power system;
according to the total power of the new energy sources, the active power of each new energy station is randomly divided, and the active power of each new energy station in the DAT is modified;
carrying out load flow calculation and judging whether a load flow result is converged or not; if the power flow result is converged, a stable calculation program SWNT is operated based on a power flow calculation result file to judge whether the condition of power output out-of-limit and PID limiting exists or not, and if no abnormal error is reported, the current power flow state is determined to be the initial power flow state of the system; otherwise, the active power of each new energy station needs to be divided again until no abnormality exists, and the current power flow state is determined to be the initial power flow state of the system.
9. The system according to claim 7, wherein the predictive tag obtaining unit performs automatic positioning of a maximum transmittable power point based on the initial power flow state, obtains maximum transmittable power of each new energy grid-connected point, and includes:
and for any new energy grid-connected point, increasing the active Power of the new energy grid-connected point according to a constant Power factor, tracking the steady-state behavior of the system under the condition of Power change, and tracking a Power-Voltage curve to a nose point so as to determine the maximum transmittable Power of any new energy grid-connected point.
10. The system according to claim 7, wherein the predictive tag obtaining unit calculates a critical short circuit ratio of each new energy grid-connected point in a static voltage critical steady state according to the tide result, comprising:
wherein, the liquid crystal display device comprises a liquid crystal display device, MRSCR i the critical short-circuit ratio of the ith new energy grid-connected point is set;
is the ith grid-connected bus bar sectionA point nominal voltage;
the voltage generated on the ith node for the new energy source; />
The apparent power injected into the bus node of the ith new energy grid-connected point; />
The elements of the ith row and the j columns of the equivalent impedance matrix of the alternating current power grid at the new energy grid connection position are selected; the short-circuit ratio of the new energy multi-station is the relative magnitude between the nominal voltage of the system and the new energy generation voltage: the current injected into the alternating current system by the bus of each new energy grid-connected point is +.>
The voltage of each new energy grid-connected point bus node is shown as +.>
n is the number of new energy grid-connected points.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310216014.6A CN116304699A (en) | 2023-03-08 | 2023-03-08 | Critical sample set generation method and system based on new energy multi-station short circuit ratio |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310216014.6A CN116304699A (en) | 2023-03-08 | 2023-03-08 | Critical sample set generation method and system based on new energy multi-station short circuit ratio |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116304699A true CN116304699A (en) | 2023-06-23 |
Family
ID=86779137
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310216014.6A Pending CN116304699A (en) | 2023-03-08 | 2023-03-08 | Critical sample set generation method and system based on new energy multi-station short circuit ratio |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116304699A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116632948A (en) * | 2023-07-25 | 2023-08-22 | 昆明理工大学 | New energy permeability boundary determination method based on generalized short-circuit ratio |
-
2023
- 2023-03-08 CN CN202310216014.6A patent/CN116304699A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116632948A (en) * | 2023-07-25 | 2023-08-22 | 昆明理工大学 | New energy permeability boundary determination method based on generalized short-circuit ratio |
| CN116632948B (en) * | 2023-07-25 | 2023-10-10 | 昆明理工大学 | New energy permeability boundary determination method based on generalized short-circuit ratio |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Katoen et al. | The ins and outs of the probabilistic model checker MRMC | |
| CN110287324B (en) | Data dynamic labeling method and device for coarse-grained text classification | |
| US11720070B2 (en) | Determining causal models for controlling environments | |
| CN104750731A (en) | Method and device for obtaining complete user portrait | |
| CN105184367A (en) | Model parameter training method and system for depth neural network | |
| CN116304699A (en) | Critical sample set generation method and system based on new energy multi-station short circuit ratio | |
| Beldiceanu et al. | Describing and generating solutions for the EDF unit commitment problem with the ModelSeeker | |
| CN116245019A (en) | Load prediction method, system, device and storage medium based on Bagging sampling and improved random forest algorithm | |
| CN115185804A (en) | Server performance prediction method, system, terminal and storage medium | |
| CN112905451B (en) | Automatic testing method and device for application program | |
| CN113537614A (en) | Construction method, system, equipment and medium of power grid engineering cost prediction model | |
| CN116777281A (en) | ARIMA model-based power equipment quality trend prediction method and device | |
| CN110717601A (en) | Anti-fraud method based on supervised learning and unsupervised learning | |
| Mohammadi et al. | Machine learning assisted stochastic unit commitment: A feasibility study | |
| CN115587017A (en) | Data processing method and device, electronic equipment and storage medium | |
| CN113495831A (en) | Method, system, device and medium for generating test case based on keyword | |
| Armstrong et al. | Runtime sparse matrix format selection | |
| Kong et al. | Integrating Machine Learning Techniques into the Decision-making Process for Hydro Scheduling | |
| CN117308136A (en) | Industrial boiler load distribution method based on historical operation data statistics | |
| CN115048291A (en) | Software testing method and device and electronic equipment | |
| CN116822739A (en) | Medium-long-term sales electricity quantity prediction method, device, terminal and storage medium | |
| Kumar et al. | Heuristic algorithm for constrained redundancy reliability optimization and performance evaluation | |
| CN116385167A (en) | Seasonal stock price prediction method and device | |
| CN116012654A (en) | Interactive incremental learning method and system for remarkably reducing image annotation cost | |
| CN117493810A (en) | Industrial chain time sequence data storage analysis method and system |
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 |