Starting decision-making method, device and equipment of black-start unit, medium and product

Abstract

The invention relates to the technical field of black start, and discloses a start decision method, device and equipment of a black start unit, a medium and a product, and the start decision method of the black start unit comprises the steps: carrying out the range division of a plurality of observation variables which affect the stability intensity of a plurality of black start units, so as to obtain the influence degree corresponding to each observation variable; according to the influence degree, generating stability intensity probabilities of the plurality of black-start units; wherein the stability intensity probability is the stability intensity probability of the power system after the plurality of black-start units are connected to the grid; one black start unit corresponds to a first preset number of stability intensity probabilities; according to the first preset number of stability intensity probabilities corresponding to each black-start unit, scores of the multiple black-start units are determined; according to the method, the multiple observation variables influencing the stability strength of the multiple black-start units are considered, the reliability of the target black-start unit is improved, and the success rate of black start is increased.

Description

Technical Field

[0001] The present invention relates to the technical field of black start, and in particular to a startup decision method, device, equipment, medium and product for a black start unit. Background Art

[0002] As the world pays more attention to environmental protection and sustainable energy development, the proportion of new energy in the power system is increasing. At present, it is a trend to connect a large amount of electricity generated by new energy to the power grid. However, the wind turbines, photovoltaic cells and other equipment used in new energy power generation are fundamentally different from traditional synchronous generators. Connecting a large amount of electricity generated by new energy to the power grid reduces the ability of the power grid to maintain its original power generation state. Therefore, the power system faces a greater risk of power outages.

[0003] Black start is the first step to restore power supply after a power outage. Through effective black start, some important power loads can regain power supply in the shortest time. In order to restore power supply as soon as possible, a reliable black start power supply is indispensable. In order to improve the starting capability of the power system, the wind power generation system can be used as a black start power supply.

[0004] In the early stage of black start, the power system is very fragile. If the restored path is permanently disconnected again, it will cause another failure of the power system and bring greater economic losses. Therefore, it is necessary to make a decision on the startup sequence of the black start units.

[0005] In the related art, the method for deciding the startup sequence of black start units includes: taking the shortest unit recovery time as the goal, using the ant colony algorithm to determine the startup sequence of the black start units. However, this method only considers a single factor corresponding to the objective function. In the actual black start process of the power system, there are many other factors. When only a single factor is considered, the reliability of the startup sequence of the black start units is weak, which is easy to cause the problem of black start failure. Summary of the invention

[0006] In view of this, the present invention provides a startup decision method, device, equipment, medium and product for a black start unit to solve the problem of weak reliability of the startup sequence of the black start unit.

[0007] In a first aspect, the present invention provides a startup decision method for a black start unit, comprising: dividing a plurality of observed variables that affect the stability strength of a plurality of black start units into ranges to obtain the degree of influence corresponding to each observed variable; the degree of influence is used to characterize the degree of influence of each observed variable on the stability strength of a power system after the plurality of black start units are started under different scenarios; generating stability strength probabilities of a plurality of black start units according to the degree of influence; wherein the stability strength probability is the probability of the stability strength of a plurality of black start units in a power system after being connected to the grid; a black start unit corresponds to a first preset number of stability strength probabilities; determining scores of a plurality of black start units according to the first preset number of stability strength probabilities corresponding to each black start unit; and selecting a target black start unit from a plurality of black start units for startup according to the scores.

[0008] The present invention divides the range of multiple observation variables that affect the stability strength of multiple black start units to obtain the degree of influence of each observation variable on the stability strength of the power system after the multiple black start units are started under different scenarios, and generates the stability strength probability of multiple black start units according to the degree of influence. The present invention comprehensively considers multiple observation variables that affect the stability strength of the black start units, and more accurately evaluates the effects of various observation variables on the black start units and the stability strength of the power system after grid connection. The present invention determines the scores of multiple black start units according to the stability strength probabilities of the first preset number corresponding to each black start unit, and selects the target black start unit from the multiple black start units for startup according to the scores. The present invention provides clear quantitative indicators and data support for the startup of black start units in the power system by quantitatively representing the observation variables, avoids the limitations of considering a single influencing factor in the related technology, makes the startup decision of the black start unit based on a more scientific basis, improves the accuracy and reliability of the startup decision of the black start unit, and helps to restore the power supply of the power system more efficiently.

[0009] In an optional implementation, multiple observation variables that affect the stability strength of multiple black-start units are divided into ranges to obtain the degree of influence corresponding to each observation variable, including: constructing membership functions of multiple observation variables respectively; wherein one observation variable corresponds to a second preset number of membership functions; and dividing the range of each observation variable according to the observed values ​​of the multiple observation variables and the membership functions respectively corresponding to the multiple observation variables to obtain the second preset number of degrees of influence corresponding to each observation variable.

[0010] In an optional implementation, membership functions of multiple observation variables are constructed respectively; each observation variable is divided into a range according to the observed values ​​of the multiple observation variables and the membership functions corresponding to the multiple observation variables respectively, so as to obtain the influence degree of the second preset quantity corresponding to each observation variable, including: determining the target range and the membership function type corresponding to the multiple observation variables respectively according to the acquired multiple observation variables; obtaining function parameters corresponding to the membership function type, and constructing the membership functions of the multiple observation variables according to the target range, the membership function type and the function parameters; substituting the observed value into the membership function corresponding to each observation variable to divide the range of each observation variable, so as to obtain the influence degree of the second preset quantity corresponding to each observation variable.

[0011] In an optional embodiment, according to the degree of influence, the stability strength probabilities of multiple black-start units are generated, including: inputting the degree of influence into a trained fuzzy variable structure dynamic Bayesian network model to obtain the stability strength probabilities of multiple black-start units; wherein the input of the fuzzy variable structure dynamic Bayesian network model is the degree of influence, and the output of the fuzzy variable structure dynamic Bayesian network model is the stability strength probability.

[0012] The present invention utilizes the trained fuzzy variable structure dynamic Bayesian network model to generate the stability strength probability of multiple black start units more accurately based on the input influence degree. The Bayesian network model has a strong probability reasoning ability. Through learning and training of a large amount of data, it can capture the complex relationship and potential patterns between various observed variables, thereby making a more accurate prediction of the stability strength of the black start unit, providing a reliable basis for the startup decision of the black start unit, and also improving the efficiency of the startup decision of the black start unit.

[0013] In an optional embodiment, scores of multiple black start groups are determined based on the stability strength probability, including: obtaining weights corresponding to a first preset number of stability strength probabilities of each black start group; and summing the products of the first preset number of stability strength probabilities of each black start group and the weight corresponding to each stability strength probability to obtain a score.

[0014] The present invention obtains the weights corresponding to the first preset number of stable strength probabilities of each black start unit, and multiplies the stable strength probability by the weight and sums them up to obtain a score. This method can comprehensively consider multiple influencing factors to evaluate the black start unit, rather than relying solely on a single indicator or probability value. Instead, different situations or influencing factors represented by different probabilities are taken into consideration, making the evaluation of the black start unit more comprehensive and detailed.

[0015] In an optional implementation, a target black start group is selected from multiple black start groups according to the scores for startup, including: selecting the highest score from the scores of each black start group; and selecting the target black start group corresponding to the highest score from multiple black start groups for startup.

[0016] In a second aspect, the present invention provides a startup decision device for a black start unit, comprising: an impact degree determination module, used to divide the range of multiple observed variables that affect the stability strength of multiple black start units to obtain the impact degree corresponding to each observed variable; the impact degree is used to characterize the impact degree of each observed variable on the stability strength of the power system after the multiple black start units are started under different scenarios; a stability strength probability generation module, used to generate the stability strength probability of multiple black start units according to the impact degree; wherein the stability strength probability is the probability of the stability strength of the power system after the multiple black start units are connected to the grid; a black start unit corresponds to a first preset number of stability strength probabilities; a score determination module, used to determine the scores of multiple black start units according to the first preset number of stability strength probabilities corresponding to each black start unit; a target black start unit determination module, used to select a target black start unit from multiple black start units for startup according to the score.

[0017] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the start-up decision method for a black start group of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0018] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the black-start group startup decision method of the first aspect or any corresponding embodiment thereof.

[0019] In a fifth aspect, the present invention provides a computer program product, including computer instructions, which are used to enable a computer to execute the startup decision method for a black start group according to the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the related technologies, the drawings required for use in the specific embodiments or the related technical descriptions will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1is a structural schematic diagram of a wind storage system according to an embodiment of the present invention;

[0022] Figure 2 is a flow chart of a startup decision method for a black start unit according to an embodiment of the present invention;

[0023] Figure 3 is a flow chart of another black start unit startup decision method according to an embodiment of the present invention;

[0024] Figure 4 is a flow chart of another method for making a decision on starting a black start unit according to an embodiment of the present invention;

[0025] Figure 5 is a structural block diagram of a startup decision device for a black start unit according to an embodiment of the present invention;

[0026] Figure 6 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0028] With the large-scale grid connection of new energy sources, the inertia capacity of the power grid has decreased, and the power system faces a greater risk of power outages. Black start is the first step to restore power supply after a major power outage. In order to restore power supply as quickly as possible, more reliable black start power sources are needed. In order to improve the starting capacity of the system, consider the possibility of using wind power generation system as a black start power source, such as Figure 1 The figure shows the structure of the wind storage system, which includes multiple wind turbines. The alternating current generated by the wind turbines is properly processed by the AC (Alternating Current) / AC converter and then connected to the grid to supply power to the load. At the same time, the battery can also supply power to the grid through the DC (Direct Current) / AC converter to meet the needs of the load or provide supplementary power when wind power generation is insufficient.

[0029] The power system is very fragile in the early stage of black start. If the restored path is permanently disconnected again, it will cause another failure of the power system and bring greater economic losses. Therefore, it is necessary to make a decision on the order of black start units.

[0030] At present, with regard to the unit recovery order during the black start phase, related technologies use different objective functions and different optimization algorithms to determine the start-up order of the black start units. For example, if the goal is to minimize the unit recovery time, or to minimize the power shortage of the power system during the recovery period, ant colony algorithms, genetic algorithms, etc. are used to solve the problem and obtain the optimal start-up order of the black start units.

[0031] The methods in the related art do not comprehensively consider the changes in the dynamic environment and system status, which will affect the reliability of the start-up sequence of the black start unit and easily cause the failure of the black start.

[0032] An embodiment of the present invention provides a startup decision method for a black start unit, which determines the startup of a target black start unit by multiple observed variables that affect the stability strength of multiple black start units, so as to improve the reliability of the target black start unit and improve the success rate of black starts.

[0033] According to an embodiment of the present invention, an embodiment of a startup decision method for a black start unit is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0034] In this embodiment, a startup decision method for a black start unit is provided, which can be used for computer equipment. Figure 2 is a flow chart of a startup decision method for a black start unit according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0035] Step S201, divide the range of multiple observed variables that affect the stability strength of multiple black-start units to obtain the influence degree corresponding to each observed variable; the influence degree is used to characterize the influence degree of each observed variable on the stability strength of the power system after the multiple black-start units are started under different scenarios.

[0036] Among them, the stability strength refers to the ability of multiple black-start units to maintain stable operation of the power system after startup; the multiple observation variables are multiple variables that are directly measured during the research process of the black-start units and have an impact on the stability strength of the multiple black-start units. By way of example, the multiple observation variables include: the wind speed of the environment where the black-start units are located, the capacity of the black-start units, the frequency of the grid connection point, and the voltage of the grid connection point, etc.

[0037] In some optional embodiments, before dividing the range of multiple observation variables that affect the stability strength of multiple black-start units, the startup decision method of the black-start unit includes: acquiring time series data of the multiple observation variables, performing anomaly detection on the time series data to obtain abnormal data; and eliminating the abnormal data to obtain the data information.

[0038] In some optional embodiments, anomaly detection is performed on the time series data to obtain abnormal data, including: distinguishing the time series data to obtain first data and second data, calculating the Euclidean distance between the first data and the second data, arranging them in ascending order according to the Euclidean distance, calculating a local outlier factor of the first data, comparing the local outlier factor with a preset threshold, and obtaining the abnormal data based on the comparison result; wherein the collection time corresponding to the first data is less than the collection time corresponding to the second data.

[0039] The preset threshold may be 10, and the local outlier factor is compared with the preset threshold. When the local outlier factor is greater than 10, the outlier factor is regarded as abnormal data.

[0040] In some optional embodiments, multiple observation variables that affect the stability strength of multiple black-start units are divided into ranges to obtain the degree of influence corresponding to each observation variable, including: obtaining membership functions of multiple observation variables; dividing each observation variable into a range according to the observed values ​​of the multiple observation variables and the membership functions corresponding to the multiple observation variables, to obtain a second preset number of degrees of influence corresponding to each observation variable.

[0041] Among them, the observed value is substituted into the membership function corresponding to each observed variable to divide the range of each observed variable to obtain the influence degree of the second preset number corresponding to each observed variable. Exemplarily, the second preset number can be 3.

[0042] In the embodiment of the present invention, when the membership function is used for the first time, it is necessary to construct membership functions of multiple observed variables respectively; wherein one observed variable corresponds to a second preset number of membership functions.

[0043] Among them, one observed variable corresponds to a second preset number of membership functions. Exemplarily, the observed variable "wind speed" corresponds to three membership functions, which are the membership function corresponding to high wind speed, the membership function corresponding to medium wind speed, and the membership function corresponding to high wind speed; the observed variable "capacity" corresponds to three membership functions, which are the membership function corresponding to large capacity, the membership function corresponding to medium capacity, and the membership function corresponding to small capacity; the observed variable "grid-connected frequency" corresponds to three membership functions, which are the membership function corresponding to high frequency, the membership function corresponding to medium frequency, and the membership function corresponding to low frequency; the observed variable "voltage at the grid-connected point" corresponds to three membership functions, which are the membership function corresponding to high voltage, the membership function corresponding to medium voltage, and the membership function corresponding to low voltage.

[0044] In some optional implementations, membership functions of multiple observation variables are constructed separately, including: determining target ranges and membership function types corresponding to the multiple observation variables respectively based on the multiple observation variables obtained; obtaining function parameters corresponding to the membership function type, and constructing membership functions of the multiple observation variables based on the target range, membership function type and function parameters.

[0045] Among them, the corresponding target range is selected according to different observed variables. For each observed variable, it is necessary to determine its reasonable value range. For example, for the observed variable "high wind speed", the corresponding target range may be within the first wind speed range, the influence degree is the first influence degree, within the second wind speed range, the influence degree is the second influence degree, and within the third wind speed range, the influence degree is the third influence degree, wherein the first wind speed range, the second wind speed range and the third wind speed range are the target ranges.

[0046] In some optional implementations, the membership function types include: triangular membership function, trapezoidal membership function, Gaussian membership function, etc. In the embodiment of the present invention, a suitable membership function type is selected according to the observed variable. For example, for the observed variable "wind speed", a triangular membership function is selected.

[0047] In some optional implementations, different membership function types require different function parameters to determine their specific shapes and characteristics. Taking the triangle membership function as an example, three parameters need to be determined, corresponding to the coordinate values ​​of the three vertices of the triangle. In the embodiment of the present invention, the function parameters are determined according to the target range.

[0048] For example, for the observed variable "wind speed", triangular membership functions corresponding to high wind speed, medium wind speed and low wind speed of the environment where the black start unit is located are constructed respectively, and the expression of the triangular membership function corresponding to the high wind speed is:

[0049]

[0050] Among them, x represents the observed variable wind speed, a1 is the first starting point of the triangular membership function corresponding to high wind speed, b1 is the first peak value of the triangular membership function corresponding to high wind speed, c1 is the first end point of the triangular membership function corresponding to high wind speed, and μ1(x) is the expression of the triangular membership function corresponding to high wind speed.

[0051] The expression of the triangle membership function corresponding to the medium wind speed is:

[0052]

[0053] Among them, x represents the observed variable wind speed, a2 is the second starting point of the triangular membership function corresponding to the medium wind speed, b2 is the second peak value of the triangular membership function corresponding to the medium wind speed, c2 is the second end point of the triangular membership function corresponding to the medium wind speed, and μ2(x) is the expression of the triangular membership function corresponding to the medium wind speed.

[0054] The expression of the triangle membership function corresponding to low wind speed is:

[0055]

[0056] Among them, x represents the observed variable wind speed, a3 is the third starting point of the triangular membership function corresponding to low wind speed, b3 is the third peak value of the triangular membership function corresponding to low wind speed, c3 is the third end point of the triangular membership function corresponding to low wind speed, and μ3(x) is the expression of the triangular membership function corresponding to low wind speed.

[0057] In an embodiment of the present invention, the observed wind speed value corresponding to the observed variable wind speed is substituted into the triangle membership function corresponding to high wind speed, the triangle membership function corresponding to medium wind speed, and the triangle membership function corresponding to low wind speed, respectively, and each triangle membership function obtains a membership value, and the three triangle membership functions obtain three membership values, wherein the meaning of the membership value is the degree of influence of the embodiment of the present invention.

[0058] Step S202, generating stability strength probabilities of multiple black start units according to the degree of impact; wherein the stability strength probability is the probability of the stability strength of the power system after the multiple black start units are connected to the grid; one black start unit corresponds to a first preset number of stability strength probabilities.

[0059] In some optional embodiments, stable strength probabilities of multiple black-start units are generated according to the degree of influence, including: inputting the degree of influence into a trained fuzzy variable structure dynamic Bayesian network model to obtain stable strength probabilities of multiple black-start units; wherein the input of the fuzzy variable structure dynamic Bayesian network model is the degree of influence, and the output of the fuzzy variable structure dynamic Bayesian network model is the stable strength probability.

[0060] Among them, one black start unit corresponds to a first preset number of stability strength probabilities, and the first preset number may be 3, that is, one black start unit corresponds to 3 stability strength probabilities. Exemplarily, the stability strengths corresponding to the 3 stability strength probabilities may be strong stability, medium stability, and low stability.

[0061] Step S203: Determine the scores of the plurality of black start units according to the first preset number of stable strength probabilities corresponding to each black start unit.

[0062] In some optional embodiments, scores of multiple black start groups are determined based on a first preset number of stability strength probabilities corresponding to each black start group, including: obtaining weights corresponding to the first preset number of stability strength probabilities of each black start group; and summing the products of the first preset number of stability strength probabilities of each black start group and the weight corresponding to each stability strength probability to obtain a score.

[0063] Among them, the weights of each level can be obtained according to the 1-5 scaling method, as shown in Table 1, which is the weights of each level determined by the 1-5 scaling method.

[0064] Table 1: shows the weights of each level determined by the 1-5 scale.

[0065] index Strong stability Medium Stable Low stability Score Weight Strong stability 1 3 5 9 0.61 Medium Stable 1 / 3 1 3 13 / 3 0.29 Low stability 1 / 5 1 / 3 1 23 / 15 0.1

[0066] Among them, the weights in the last column are the weights obtained in the embodiment of the present invention. The weight corresponding to strong stability is 0.61, the weight corresponding to medium stability is 0.29, and the weight corresponding to low weight is 0.1.

[0067] In an embodiment of the present invention, exemplarily, when the first preset number of stability strength probabilities of a black start group are: the stability strength probability corresponding to strong stability is 0.2, the stability strength probability corresponding to medium stability is 0.3, and the stability strength probability corresponding to low stability is 0.5, then the score of the black start group is: 0.2*0.61+0.3*0.29+0.5*0.1=0.259.

[0068] In some optional embodiments, the scores of multiple black start groups are determined according to a first preset number of stable strength probabilities corresponding to each black start group, and the method also includes: analyzing the distribution of the stable strength probability of each black start group to obtain multiple distribution characteristics, constructing a scoring function according to the multiple distribution characteristics, and determining the scores of the multiple black start groups according to the scoring function.

[0069] The specific form of the scoring function depends on the requirements for unit performance and the understanding of the characteristics of probability distribution. For example, the scoring function can be designed as: mean minus variance multiplied by the first empirical coefficient, plus skewness multiplied by the second empirical coefficient to obtain the score.

[0070] For example, the mean of the stability strength probability distribution of a black start unit is calculated to be 0.65, the variance is 0.05, and the skewness is 0.2. Assuming that the first empirical coefficient is 0.1 and the second empirical coefficient is 0.5, according to the scoring function, the score is: 0.65-0.05×0.1+0.2×0.5=0.65-0.005+0.1=0.745.

[0071] Step S204: selecting a target black-start unit from a plurality of black-start units for starting according to the scores.

[0072] In some optional implementations, a target black start group is selected from multiple black start groups according to the scores for startup, including: selecting the highest score from the scores of each black start group; and selecting the target black start group corresponding to the highest score from multiple black start groups for startup.

[0073] In the embodiment of the present invention, after a target black start unit is selected from a plurality of black start units for startup, the target black start unit is removed and the process is performed again. Figure 2 Steps S201 to S204 are performed until all black start units are started.

[0074] The startup decision method of the black start unit provided in this embodiment divides the range of multiple observation variables that affect the stability strength of multiple black start units to obtain the degree of influence of each observation variable on the stability strength of the power system after the multiple black start units are started in different scenarios, and generates the stability strength probability of multiple black start units according to the degree of influence. The embodiment of the present invention comprehensively considers multiple observation variables that affect the stability strength of the black start unit, and more accurately evaluates the effects of various observation variables on the black start unit and the stability strength of the power system after grid connection. The embodiment of the present invention determines the scores of multiple black start units according to the stability strength probabilities of the first preset number corresponding to each black start unit, and selects the target black start unit from the multiple black start units for startup according to the scores. The present invention provides clear quantitative indicators and data support for the startup of the black start unit in the power system by quantitatively representing the observation variables, avoids the limitations of considering a single influencing factor in the related technology, makes the startup decision of the black start unit based on a more scientific basis, improves the accuracy and reliability of the startup decision of the black start unit, and helps to restore the power supply of the power system more efficiently.

[0075] In this embodiment, a startup decision method for a black start unit is provided, which can be used for computer equipment. Figure 3 FIG. 4 is a flow chart of another method for starting a black start unit according to an embodiment of the present invention. Figure 3 As shown, the process includes the following steps:

[0076] Step S301, divide the range of multiple observed variables that affect the stability strength of multiple black start units to obtain the influence degree corresponding to each observed variable; the influence degree is used to characterize the influence degree of each observed variable on the stability strength of the power system after the multiple black start units are started under different scenarios. For details, please refer to Figure 1 Step S201 of the illustrated embodiment will not be described in detail here.

[0077] Specifically, the above step S301 includes:

[0078] Step S3011, constructing membership functions of multiple observed variables respectively; wherein one observed variable corresponds to a second preset number of membership functions.

[0079] Step S3012, according to the observed values ​​of the multiple observed variables and the membership functions corresponding to the multiple observed variables, each observed variable is divided into a range to obtain the influence degree of the second preset quantity corresponding to each observed variable.

[0080] In some optional implementations, the above step S3011 includes:

[0081] Step a1: Determine the target ranges and membership function types corresponding to the multiple observed variables respectively according to the multiple observed variables obtained.

[0082] Step a2, obtaining function parameters corresponding to the membership function type, and constructing membership functions of multiple observation variables according to the target range, the membership function type and the function parameters.

[0083] In some optional implementations, the above step S3012 includes:

[0084] Step b1, substituting the observed value into the membership function corresponding to each observed variable to divide the range of each observed variable to obtain the influence degree of the second preset quantity corresponding to each observed variable.

[0085] Step S302, generating stability strength probabilities of multiple black start units according to the degree of impact; wherein the stability strength probability is the probability of the stability strength of the power system after the multiple black start units are connected to the grid; one black start unit corresponds to a first preset number of stability strength probabilities.

[0086] Specifically, the above step S302 includes:

[0087] Step S3021, input the influence degree into the trained fuzzy variable structure dynamic Bayesian network model to obtain the stability strength probability of multiple black start units; wherein, the input of the fuzzy variable structure dynamic Bayesian network model is the influence degree, and the output of the fuzzy variable structure dynamic Bayesian network model is the stability strength probability.

[0088] In some optional embodiments, the startup decision method for a black-start unit also includes a training process for a fuzzy variable structure dynamic Bayesian network model. The training process for the fuzzy variable structure dynamic Bayesian network model includes: inputting multiple historical impact degrees and the historical stability intensity probability corresponding to each historical impact degree into the fuzzy variable structure dynamic Bayesian network model, and training the fuzzy variable structure dynamic Bayesian network model.

[0089] Exemplarily, a training data set is constructed, which includes 100 groups of samples, each sample contains 4 observed variables and three influence levels corresponding to each observed variable, and each sample corresponds to 3 stability strength probabilities of the power system after grid connection. The training data set is input into the fuzzy variable structure dynamic Bayesian network model to train the fuzzy variable structure dynamic Bayesian network model. The training includes two steps. The first step is to obtain the expectation of the likelihood function L(θ) after obtaining the existing stability strength probability and giving a model parameter:

[0090] Q(θ;X,θ i )=E(L(θ;X,Y))

[0091] Among them, θ is the model parameter, X is the stability intensity probability, Y is the observed variable, and θ i is the model parameter of the i-th stable intensity probability.

[0092] The second step is to substitute the given model parameters into the above formula to obtain Q(θ; X,θ i ), and then iterate the result until Q(θ; X,θ i ) converges to a constant. The purpose of the second step is to obtain Q(θ; X,θ i ), thereby obtaining the model parameter value at the maximum value, and substituting the model parameter value into the fuzzy variable structure dynamic Bayesian network model to complete the training of the fuzzy variable structure dynamic Bayesian network model.

[0093] Step S303: Determine the scores of the plurality of black start units according to the first preset number of stable strength probabilities corresponding to each black start unit.

[0094] Specifically, the above step S303 includes:

[0095] Step S3031, obtaining the weights corresponding to the first preset number of stability strength probabilities of each black start unit.

[0096] Step S3032: sum the product of the first preset number of stable strength probabilities of each black start unit and the weight corresponding to each stable strength probability to obtain a score.

[0097] Step S304: selecting a target black start unit from a plurality of black start units according to the scores for starting.

[0098] Specifically, the above step S304 includes:

[0099] Step S3041, selecting the highest score from the scores of each black start unit.

[0100] Step S3042: Select a target black start unit corresponding to the highest score from among multiple black start units for startup.

[0101] The startup decision method of the black start unit provided in this embodiment uses the trained fuzzy variable structure dynamic Bayesian network model to generate the stability strength probability of multiple black start units more accurately based on the input influence degree. The Bayesian network model has a strong probability reasoning ability. Through learning and training a large amount of data, it can capture the complex relationship and potential patterns between various observation variables, so as to make a more accurate prediction of the stability strength of the black start unit, provide a reliable basis for the startup decision of the black start unit, and improve the efficiency of the startup decision of the black start unit. The embodiment of the present invention obtains the weights corresponding to the first preset number of stability strength probabilities of each black start unit, and multiplies the stability strength probability by the weight to obtain a score. This method can comprehensively consider the influencing factors of multiple aspects to evaluate the black start unit, instead of relying on a single indicator or probability value, but taking into account the different situations or influencing factors represented by different probabilities, so that the evaluation of the black start unit is more comprehensive and more detailed.

[0102] In this embodiment, a startup decision method for a black start unit is provided, which can be used for computer equipment. Figure 4 FIG. 4 is a flowchart of another method for starting a black start unit according to an embodiment of the present invention. Figure 4 As shown, the process includes:

[0103] Select the initial black start unit, determine the unit to be started according to the dynamic Bayesian network, start the unit to be started, and determine whether there is an abnormality in the current startup. If there is an abnormality, re-determine the unit to be started according to the dynamic Bayesian network. If there is no abnormality, determine whether all wind turbines have been started. If the startup is completed, end the task. If the startup is not completed, continue to determine the unit to be started according to the dynamic Bayesian network until all wind turbines are started.

[0104] The startup decision method for the black start unit provided in this embodiment utilizes a fuzzy variable structure dynamic Bayesian network, comprehensively considers the dynamic environment and system status, and dynamically decides the order of the black start of the wind storage system, making the black start of the wind storage system more stable and reliable.

[0105] In this embodiment, a startup decision device for a black start unit is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0106] This embodiment provides a startup decision device for a black start unit, such as Figure 5 As shown, including:

[0107] The impact degree determination module 501 is used to divide the range of multiple observed variables that affect the stability strength of multiple black-start units to obtain the impact degree corresponding to each observed variable; the impact degree is used to characterize the impact degree of each observed variable on the stability strength of the power system after the start-up of multiple black-start units under different scenarios.

[0108] The stability strength probability generation module 502 is used to generate the stability strength probability of multiple black start units according to the degree of influence; wherein the stability strength probability is the probability of the stability strength of the power system after the multiple black start units are connected to the grid; one black start unit corresponds to the first preset number of stability strength probabilities.

[0109] The score determination module 503 is used to determine the scores of multiple black start groups according to a first preset number of stable strength probabilities corresponding to each black start group.

[0110] The target black-start unit determination module 504 is used to select a target black-start unit from multiple black-start units for startup according to the scores.

[0111] In some optional implementations, the impact degree determination module 501 includes:

[0112] The membership function construction unit is used to respectively construct membership functions of multiple observed variables; wherein one observed variable corresponds to a second preset number of membership functions.

[0113] The influence degree determination unit is used to divide each observation variable into a range according to the observation values ​​of multiple observation variables and the membership functions corresponding to the multiple observation variables, so as to obtain the influence degree of a second preset number corresponding to each observation variable.

[0114] In some optional implementations, the membership function construction unit includes:

[0115] The function type determination subunit is used to determine the target ranges and membership function types corresponding to the multiple observation variables respectively according to the multiple observation variables obtained.

[0116] The function construction subunit is used to obtain function parameters corresponding to the membership function type, and to construct membership functions of multiple observation variables according to the target range, membership function type and function parameters.

[0117] In some optional implementations, the impact degree determination unit includes:

[0118] The influence degree determination subunit is used to substitute the observed value into the membership function corresponding to each observed variable to divide the range of each observed variable to obtain the influence degree of the second preset number corresponding to each observed variable.

[0119] In some optional implementations, the stable intensity probability generation module 502 includes:

[0120] The stability strength probability generating unit is used to input the influence degree into the trained fuzzy variable structure dynamic Bayesian network model to obtain the stability strength probability of multiple black start units; wherein, the input of the fuzzy variable structure dynamic Bayesian network model is the influence degree, and the output of the fuzzy variable structure dynamic Bayesian network model is the stability strength probability.

[0121] In some optional implementations, the score determination module 503 includes:

[0122] The weight acquisition unit is used to obtain the weights corresponding to the first preset number of stable strength probabilities of each black start unit.

[0123] The score determination unit is used to sum the product of the first preset number of stable strength probabilities of each black start unit and the weight corresponding to each stable strength probability to obtain a score.

[0124] In some optional implementations, the target black-start unit determination module 504 includes:

[0125] The highest score selection unit is used to select the highest score among the scores of each black start unit.

[0126] The target black start unit determination unit is used to select the target black start unit corresponding to the highest score from multiple black start units for startup.

[0127] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0128] The startup decision device of the black start group in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0129] The embodiment of the present invention also provides a computer device having the above Figure 5 The starting decision device of the black start unit is shown.

[0130] See also Figure 6 , Figure 6 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 6As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 6 A processor 10 is taken as an example.

[0131] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0132] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0133] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0134] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0135] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0136] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0137] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0138] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A startup decision method for a black start unit, characterized in that: The method comprises: Divide the range of multiple observed variables that affect the stability strength of multiple black-start units to obtain the influence degree corresponding to each observed variable; the influence degree is used to characterize the influence degree of each observed variable on the stability strength of the power system after the multiple black-start units are started under different scenarios; According to the degree of influence, the stability strength probability of the multiple black start units is generated; wherein the stability strength probability is the probability of the stability strength of the power system of the multiple black start units after grid connection; one black start unit corresponds to a first preset number of stability strength probabilities; Determine the scores of the plurality of black start units according to the first preset number of stability strength probabilities corresponding to each black start unit; A target black-start unit is selected from the plurality of black-start units according to the score for startup.

2. The method according to claim 1, characterized in that The multiple observed variables affecting the stability strength of the multiple black start units are divided into ranges to obtain the influence degree corresponding to each observed variable, including: Constructing membership functions of the plurality of observed variables respectively; wherein one observed variable corresponds to a second preset number of membership functions; According to the observed values ​​of the multiple observed variables and the membership functions respectively corresponding to the multiple observed variables, each observed variable is divided into a range to obtain the influence degree of the second preset number corresponding to each observed variable.

3. The method according to claim 2, characterized in that The respectively constructing the membership functions of the plurality of observed variables; dividing each observed variable into a range according to the observed values ​​of the plurality of observed variables and the membership functions respectively corresponding to the plurality of observed variables to obtain the influence degree of the second preset quantity corresponding to each observed variable, comprises: Determining target ranges and membership function types corresponding to the plurality of observed variables respectively according to the plurality of observed variables obtained; Acquire function parameters corresponding to the membership function type, and construct the membership function of the multiple observed variables according to the target range, the membership function type and the function parameters; Substitute the observed value into the membership function corresponding to each observed variable to divide the range of each observed variable, and obtain the influence degree of the second preset quantity corresponding to each observed variable.

4. The method according to any one of claims 1 to 3, characterized in that Generating the stability strength probabilities of the plurality of black start units according to the impact degree includes: The degree of influence is input into the trained fuzzy variable structure dynamic Bayesian network model to obtain the stability strength probability of the multiple black start units; wherein the input of the fuzzy variable structure dynamic Bayesian network model is the degree of influence, and the output of the fuzzy variable structure dynamic Bayesian network model is the stability strength probability.

5. The method according to any one of claims 1 to 3, characterized in that Determining the scores of the plurality of black start units according to the stability strength probability includes: Obtain the weights corresponding to the first preset number of the stability strength probabilities of each black start unit; The score is obtained by summing the product of the first preset number of stability strength probabilities of each black start group and the weight corresponding to each stability strength probability.

6. The method according to any one of claims 1 to 3, characterized in that The step of selecting a target black start unit from the plurality of black start units for starting according to the score comprises: Selecting the highest score among the scores of each black start unit; A target black start unit corresponding to the highest score is selected from the multiple black start units for startup.

7. A startup decision device for a black start unit, characterized in that: The device comprises: An impact degree determination module is used to divide the multiple observed variables that affect the stability strength of multiple black start units into ranges to obtain the impact degree corresponding to each observed variable; the impact degree is used to characterize the impact degree of each observed variable on the stability strength of the power system after the multiple black start units are started under different scenarios; A stability strength probability generation module is used to generate the stability strength probability of the multiple black start units according to the impact degree; wherein the stability strength probability is the probability of the stability strength of the power system of the multiple black start units after grid connection; one black start unit corresponds to a first preset number of stability strength probabilities; A score determination module, configured to determine the scores of the plurality of black start units according to a first preset number of stable strength probabilities corresponding to each black start unit; The target black-start unit determination module is used to select a target black-start unit from the multiple black-start units for startup according to the score.

8. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the startup decision method for a black start unit according to any one of claims 1 to 6 by executing the computer instructions.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the black-start unit startup decision method according to any one of claims 1 to 6.

10. A computer program product, characterized in that It comprises computer instructions, and the computer instructions are used to enable a computer to execute the startup decision method of the black start group according to any one of claims 1 to 6.

Images