Electric power system optimization scheduling method, device and equipment based on static voltage-power angle dual stability constraint and medium

Abstract

The invention discloses a static voltage-power angle dual stability constraint-based power system optimization scheduling method, device and equipment and a medium, and relates to the technical field of power systems and automation thereof, and the method comprises the steps: carrying out the pre-solving of a preset power system optimal power flow model under a preset constraint condition; searching a target feasible solution of the optimal power flow model of the power system from a first neighborhood of the pre-solving result; generating a sample set based on a second neighborhood of the target feasible solution, classifying samples, and determining a stability constraint type according to a classification result; using a preset support vector machine technology to segment the sample according to the classification result so as to generate an optimized stability constraint condition; and optimizing the optimal power flow model of the power system by using the optimized stability constraint condition, and performing optimal scheduling of the power system based on the optimized optimal power flow model of the power system. Therefore, various stability constraints can be efficiently embedded into the power system optimization model to provide a more reliable optimization scheduling scheme for the operation of the power system.

Description

Technical Field

[0001] The present invention relates to the field of power systems and automation technologies thereof, and in particular to a method, device, equipment and medium for optimizing and dispatching a power system based on static voltage-power angle dual stability constraints. Background Art

[0002] After the access of large-scale renewable energy, the operation characteristics of the power system will change significantly, and the uncertainty of power fluctuation and operation mode will increase significantly, which is very likely to cause a variety of stability problems, which will not only affect the normal operation of the power grid, but also may cause serious cascading failures, posing a threat to the safety of the power system. In order to embed various stability constraints into the power grid operation optimization model, existing studies have attempted to analyze the stability constraints through sensitivity analysis or data-driven methods, so that the operation of the power system gradually approaches the corresponding stability requirements. Among them, the sensitivity analysis method linearizes the implicit function of stability so that the operation of the power system gradually approaches the stability requirements, but it requires multiple iterations of the optimization model, and the optimization scheduling efficiency of the power system is low; the data-driven method constructs the mapping relationship between the operating state and stability through large-scale sample data, but the modeling complexity of the nonlinear mapping relationship is high, and the linearization process will reduce the accuracy and generalization performance of the constraints, making it difficult to achieve efficient power system optimization scheduling.

[0003] In summary, how to efficiently embed multiple stability constraints into the power system optimization model to provide a more reliable optimization scheduling solution for the power system operation is an urgent problem to be solved. Summary of the invention

[0004] In view of this, the purpose of the present invention is to provide a method, device, equipment and medium for optimizing and dispatching a power system based on static voltage-power angle dual stability constraints, which can efficiently embed multiple stability constraints into the power system optimization model to provide a more reliable optimization and dispatching scheme for the power system operation. The specific scheme is as follows:

[0005] In a first aspect, the present application provides a method for optimizing the dispatching of a power system based on a static voltage-power angle dual stability constraint, comprising:

[0006] Pre-solving a preset power system optimal power flow model under preset constraint conditions to obtain a pre-solved result;

[0007] Searching for a target feasible solution of the power system optimal power flow model from a first neighborhood of the pre-solved result; the target feasible solution is a solution that satisfies initial stability constraints of static voltage and static power angle;

[0008] Generate a corresponding sample set based on the second neighborhood of the target feasible solution, classify the samples in the sample set, and determine the type of stability constraint to be performed on key local modeling according to the obtained classification result; the stability constraint type includes a static voltage stability constraint and a static power angle stability constraint;

[0009] Using a preset support vector machine technology and the classification results to segment the samples in the sample set, so as to perform the key local modeling and generate optimized stable constraint conditions corresponding to the stable constraint type;

[0010] The optimized stability constraint condition is used to optimize the optimal power flow model of the power system, and the optimal dispatch of the power system is performed based on the optimized optimal power flow model of the power system.

[0011] Optionally, the preset constraints include power flow balance constraints, line power upper and lower limit constraints, and voltage amplitude upper and lower limit constraints; the optimal power flow model of the power system includes the objective function, the preset constraints and the initial stability constraints, and the initial stability constraints include initial static voltage stability constraints and initial static power angle stability constraints; the optimized optimal power flow model of the power system includes the objective function, the preset constraints and the optimized stability constraints, and the optimized stability constraints include optimized static voltage stability constraints and optimized static power angle stability constraints.

[0012] Optionally, searching for a target feasible solution of the power system optimal power flow model from a first neighborhood of the pre-solved result includes:

[0013] The first neighborhood of the pre-solved result is searched to calculate the preset optimization function based on the Newton-Raphson method and the numerical method using the optimization variables in the first neighborhood, and the target feasible solution of the optimal power flow model of the power system is determined from the first neighborhood according to the calculation result; wherein the preset optimization function is a nonlinear equation.

[0014] Optionally, generating a corresponding sample set based on the second neighborhood of the target feasible solution and classifying samples in the sample set includes:

[0015] Taking the target feasible solution as the center, performing random sampling in a second neighborhood of the target feasible solution, so as to generate a corresponding sample set using the sampled solution;

[0016] Determining whether the samples in the sample set satisfy the first initial stability constraint condition of the static voltage and the second initial stability constraint condition of the static power angle, so as to classify the samples;

[0017] Among them, if the sample satisfies the first initial stability constraint and the second initial stability constraint, the sample is determined to be the first type; if the sample satisfies the first initial stability constraint but does not satisfy the second initial stability constraint, the sample is determined to be the second type; if the sample satisfies the second initial stability constraint but does not satisfy the first initial stability constraint, the sample is determined to be the third type; if the sample does not satisfy the first initial stability constraint and the second initial stability constraint, the sample is determined to be the fourth type.

[0018] Optionally, determining the type of stability constraint to be used for key local modeling according to the obtained classification result includes:

[0019] If the obtained classification result indicates that the sample set contains samples of the first preset type, determining that the stability constraint type to be subjected to key local modeling is the static voltage stability constraint;

[0020] If the obtained classification result indicates that the sample set contains samples of the second preset type, determining that the stability constraint type is the static power angle stability constraint;

[0021] If the obtained classification result indicates that the sample set contains samples of the third preset type, determining that the stability constraint type is the static voltage stability constraint and the static power angle stability constraint;

[0022] Among them, the first preset type includes the first type and the third type; the second preset type includes the first type and the second type; the third preset type includes any one or a combination of the first type, the second type, the third type and the fourth type except the first preset type and the second preset type.

[0023] Optionally, the using of a preset support vector machine technology and the classification result to segment the samples in the sample set to perform the key local modeling and generate an optimized stable constraint condition corresponding to the stable constraint type includes:

[0024] The corresponding analytical expressions are generated using soft-margin support vector machine technology;

[0025] Segmenting the samples in the sample set based on the classification result and the analytical expression, and in the process of segmenting the samples, using the slack variables and penalty factors in the analytical expression to penalize the samples that violate the constraints of the analytical expression, so as to obtain the parameters to be determined in the analytical expression;

[0026] The key local modeling is performed using the parameters to be determined to generate optimized stability constraint conditions corresponding to the stability constraint type.

[0027] Optionally, after optimizing the optimal power flow model of the power system by using the optimized stability constraint condition and performing optimal dispatch of the power system based on the optimized optimal power flow model of the power system, the method further includes:

[0028] Monitoring the optimization result of the optimization scheduling;

[0029] When it is detected that the optimization result does not satisfy the stability constraint corresponding to the stability constraint type, the optimization result is added to the sample set, and the weight of the optimization result in the sample set is increased to obtain an updated sample set;

[0030] The optimized stable constraint condition is iteratively corrected by using the updated sample set, so as to obtain an optimization result satisfying the stable constraint corresponding to the stable constraint type by using the corrected stable constraint condition.

[0031] In a second aspect, the present application provides a power system optimization dispatching device based on static voltage-power angle dual stability constraints, comprising:

[0032] A pre-solution module is used to pre-solve a preset power system optimal power flow model under preset constraints to obtain a pre-solution result;

[0033] A feasible solution search module, used to search for a target feasible solution of the power system optimal power flow model from a first neighborhood of the pre-solution result; the target feasible solution is a solution that satisfies initial stability constraints of static voltage and static power angle;

[0034] A type determination module, used to generate a corresponding sample set based on the second neighborhood of the target feasible solution, classify the samples in the sample set, and determine the type of stability constraint to be performed on key local modeling according to the classification result; the stability constraint type includes a static voltage stability constraint and a static power angle stability constraint;

[0035] A sample segmentation module, used to segment the samples in the sample set by using a preset support vector machine technology and the classification result, so as to perform the key local modeling and generate optimized stable constraint conditions corresponding to the stable constraint type;

[0036] The optimization scheduling module is used to optimize the optimal power flow model of the power system by using the optimized stability constraint conditions, and to perform optimal scheduling of the power system based on the optimized optimal power flow model of the power system.

[0037] In a third aspect, the present application provides an electronic device, including:

[0038] Memory, used to store computer programs;

[0039] A processor is used to execute the computer program to implement the aforementioned power system optimization scheduling method based on static voltage-power angle dual stability constraints.

[0040] In a fourth aspect, the present application provides a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the aforementioned power system optimization scheduling method based on the static voltage-power angle dual stability constraint is implemented.

[0041] In this embodiment, a preset optimal power flow model of the power system is pre-solved under preset constraints to obtain a pre-solved result; a target feasible solution of the optimal power flow model of the power system is searched from a first neighborhood of the pre-solved result; the target feasible solution is a solution that satisfies the initial stability constraints of static voltage and static power angle; a corresponding sample set is generated based on a second neighborhood of the target feasible solution, the samples in the sample set are classified, and the type of stability constraint to be performed on key local modeling is determined based on the obtained classification results; the stability constraint type includes static voltage stability constraint and static power angle stability constraint; the samples in the sample set are segmented using a preset support vector machine technology and the classification results to perform the key local modeling, and optimized stability constraint conditions corresponding to the stability constraint type are generated, and the optimized stability constraint conditions and the optimal power flow model of the power system are used to perform optimal scheduling of the power system. As can be seen from the above, the present application first pre-solves the optimal power flow model of the power system under preset constraints to obtain a pre-solved result, searches for the target feasible solution of the optimal power flow model of the power system from the first neighborhood of the pre-solved result, generates a corresponding sample set based on the second neighborhood of the target feasible solution, and determines the stability constraint type according to the classification result of the samples in the sample set, and uses the preset support vector machine technology and the classification result to segment the samples in the sample set to generate the optimized stability constraint conditions corresponding to the stability constraint type, and uses the optimized stability constraint conditions and the optimal power flow model of the power system to optimize the scheduling of the power system. In this way, through the above process of the present application, the optimized stability constraint conditions corresponding to the stability constraint type are constructed by using the key local modeling method, which can reduce the complexity of global modeling and significantly improve the efficiency of optimization scheduling. At the same time, the two stability constraints of static voltage-power angle are considered in the optimization scheduling of the power system, which improves the stability and reliability of the scheduling scheme, and then efficiently embeds multiple stability constraints into the power system optimization model to provide a more reliable optimization scheduling scheme for the operation of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0043] Figure 1 A flow chart of a method for optimizing dispatching of a power system based on static voltage-power angle dual stability constraints disclosed in this application;

[0044] Figure 2 A voltage stability margin comparison schematic diagram disclosed in this application;

[0045] Figure 3 A schematic diagram of a power angle stability damping ratio comparison disclosed in this application;

[0046] Figure 4 This is a schematic diagram of operating cost comparison disclosed in this application;

[0047] Figure 5 A schematic diagram showing the comparison of the number of constraint equivalent modeling disclosed in this application;

[0048] Figure 6 This is a schematic diagram of optimization cost comparison when setting different stability thresholds disclosed in this application;

[0049] Figure 7 A schematic diagram of the structure of a power system optimization dispatching device based on static voltage-power angle dual stability constraints disclosed in this application;

[0050] Figure 8 This is a structural diagram of an electronic device disclosed in this application. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] In order to embed multiple stability constraints into the power grid operation optimization model, existing studies have attempted to analyze the stability constraints through sensitivity analysis or data-driven methods, so that the operation of the power system gradually approaches the corresponding stability requirements. Among them, the sensitivity analysis method linearizes the implicit function of stability so that the operation of the power system gradually approaches the stability requirements, but it requires multiple iterations of the optimization model, and the optimization scheduling efficiency of the power system is low; the data-driven method constructs the mapping relationship between the operating state and stability through large-scale sample data, but the modeling complexity of the nonlinear mapping relationship is high, and the linearization process will reduce the accuracy and generalization performance of the constraints, making it difficult to achieve efficient power system optimization scheduling.

[0053] In order to overcome the above technical problems, the present application provides a power system optimization scheduling method based on static voltage-power angle dual stability constraints, so as to efficiently embed multiple stability constraints into the power system optimization model to provide a more reliable optimization scheduling scheme for the power system operation.

[0054] See also Figure 1 As shown, the embodiment of the present invention discloses a method for optimizing and dispatching a power system based on a static voltage-power angle dual stability constraint, including:

[0055] Step S11 : pre-solve a preset power system optimal power flow model under preset constraint conditions to obtain a pre-solved result.

[0056] In this embodiment, under preset constraints, the preset optimal power flow model (i.e., Optimal power flow, OPF) of the power system is pre-solved to obtain the corresponding pre-solved results. Wherein, the preset constraints include power flow power balance constraints, line power upper and lower limit constraints, and voltage amplitude upper and lower limit constraints; the optimal power flow model of the power system includes an objective function, the preset constraints, and the initial stability constraints, and the initial stability constraints include initial static voltage stability constraints and initial static power angle stability constraints; the pre-solved result is the economic optimal solution obtained without considering the static voltage-power angle stability constraints. That is, the optimization model constructed by the power system optimization dispatching method based on the static voltage-power angle dual stability constraints of the present application is based on the traditional optimal power flow model of the power system, and is expanded by adding static voltage and power angle stability constraints. The optimal power flow model adopts a decoupled linear power flow method for calculation, and the optimization goal is to minimize the power generation cost. Wherein, the expression formula of the objective function can be as follows:

[0057] ;

[0058] in, and They represent the active and reactive cost coefficients of the generators, N represents the total number of generators, , Represent the active power and reactive power of the generator and renewable energy, respectively, and min represents the minimum value of the function. The power flow balance constraint, that is, the decoupled linear power flow constraint considering voltage, can be expressed as follows:

[0059] ;

[0060] in, , denote the net active and reactive injection of the node, respectively, , They represent the active and reactive power of the load, G and B represent the conductance and susceptance, respectively. and denote the conductance and susceptance excluding the grounding branch respectively; and Respectively represent the phase angle and amplitude of the node voltage. The expression formula of the upper and lower limit constraints of the line power can be as follows:

[0061] ;

[0062] ;

[0063] ;

[0064] ;

[0065] ;

[0066] ;

[0067] in, and Indicates the active and reactive power of the branch. , , and Both represent the power transfer factor from node to branch, Indicates the lower limit corresponding to the sign, The upper and lower limits of the voltage amplitude can be expressed as follows:

[0068] ;

[0069] The expression formula of the initial static power angle stability constraint condition can be as follows:

[0070] ;

[0071] in, is the minimum threshold of damping ratio, represents the damping ratio function under the static power angle stability constraint condition, and the initial static power angle stability constraint condition is determined by the small disturbance method. The expression formula of the initial static voltage stability constraint condition can be as follows:

[0072] ;

[0073] in, Indicates the voltage stability threshold, represents the static voltage function under the static voltage stability constraint condition, and the initial static voltage stability constraint condition is determined by the voltage stability margin. Therefore, the pre-solved result represents In this way, after constructing the optimal power flow model of the power system, this embodiment first pre-solves the optimal power flow model of the power system under preset constraints, that is, without considering the static voltage-power angle stability constraint, to obtain the economically optimal solution, that is, the initial solution, so as to search for the target feasible solution that satisfies all the constraints of the optimal power flow model of the power system based on the initial solution, and pave the way for the subsequent equivalent modeling considering the static voltage-power angle dual stability constraint.

[0074] Step S12: searching for a target feasible solution of the optimal power flow model of the power system from a first neighborhood of the pre-solution result; the target feasible solution is a solution that satisfies initial stability constraints of static voltage and static power angle.

[0075] In this embodiment, since the pre-solution result may not satisfy the stability requirements of the static voltage and the static power angle at the same time, that is, the initial stability constraint condition, after obtaining the pre-solution result, it is necessary to determine the first neighborhood of the pre-solution result, and search for the target feasible solution of the power system optimal power flow model from the first neighborhood. Among them, the target feasible solution is a solution that satisfies the initial stability constraint conditions of the static voltage and the static power angle, which represents Therefore, in the process of searching for the target feasible solution, the expression formula of the power flow balance constraint can be calculated to obtain value.

[0076] It is understandable that this embodiment can use the pre-solved result as the initial solution and further optimize it in its neighborhood, aiming to comprehensively consider economy and stability, and find a feasible solution that satisfies all constraints, that is, satisfies the preset constraints and the initial stability constraints. In order to determine whether a given solution in the first neighborhood of the pre-solved result satisfies the initial stability constraints, the requirements for static voltage and power angle stability can be expressed as a stable boundary of a nonlinear hyperplane, which is composed of the boundary of the intersection of the voltage stability region and the power angle stability region, and its expression formula can be as follows:

[0077] ;

[0078] in, Represents the boundary mapping function. However, due to the complexity of the stability boundary, it is difficult to explicitly model it in the global space, but considering that the optimization solution does not need to traverse the global space for modeling, it is only necessary to focus on the key local area under the guidance of the objective function. Therefore, the present application proposes a key local focusing method, which further searches in the first neighborhood of the initial solution to achieve the optimization goal while meeting the requirements of static voltage and power angle stability. The processing flow is as follows: the first neighborhood of the pre-solution result is searched to calculate the preset optimization function based on the Newton-Raphson method and the numerical method using the optimization variables in the first neighborhood, and the target feasible solution of the optimal power flow model of the power system is determined from the first neighborhood according to the calculation results; wherein the preset optimization function is a nonlinear equation. That is, the first neighborhood of the pre-solution result is searched to calculate the preset optimization function based on the Newton-Raphson method and the numerical method using the optimization variables in the first neighborhood, and the target feasible solution of the optimal power flow model of the power system is determined from the first neighborhood according to the obtained calculation results. It should be pointed out that in order to determine whether a given solution satisfies all the constraints of the optimal power flow model of the power system, a constraint determination formula as follows can be constructed:

[0079] ;

[0080] Wherein, each term of the constraint determination formula represents the inequality constraint, the equality constraint, the initial static power angle stability constraint, and the initial static voltage stability constraint of the OPF model, respectively. The weights of each item correspond to each item respectively; the inequality constraint and the equality constraint correspond to the inequality and equality in the preset constraint conditions respectively; h represents the inequality constraint, represents the equality constraint. The following is the proof analysis of the constraint judgment formula: when given is the objective feasible solution of the OPF model, The inequality constraint, the equality constraint, the initial static power angle stability constraint and the initial static voltage stability constraint of the OPF model are satisfied. At this time, the first to fourth terms of the constraint judgment formula are 0, and the sum is also 0. On the contrary, when the given The constraint determination formula is satisfied, that is, the sum of the first to fourth terms of the constraint determination formula is 0. Since each term is non-negative, the first to fourth terms of the constraint determination formula are all 0, that is, The target feasible solution satisfies all the constraints of the OPF model. Therefore, the constraint judgment formula is established. It should be further pointed out that, considering the strong nonlinear characteristics of the constraint judgment formula and the difficulty of direct analytical solution, this embodiment can use the Newton-Raphson method for iterative solution, and in order to improve the calculation efficiency, only the variables with the highest sensitivity and the variables with similar sensitivity orders of magnitude are selected as optimization variables during the optimization process, that is, . Specific optimization function The expression formula can be as follows:

[0081] ;

[0082] It should be noted that, considering the possibility that the gradient may not be explicitly expressed, this embodiment may use the numerical method for calculation, and its expression formula may be as follows:

[0083] ;

[0084] That is, the optimization function is derived, represents the independent variable, Represents the increment of the independent variable. Therefore, the preset optimization function is composed of the optimization function and the expression formula calculated by the numerical method. In this way, this embodiment uses the pre-solved result as the initial solution, takes the initial solution as the center, searches for the target feasible solution of the optimal power flow model of the power system in its neighborhood, and effectively focuses on the key local area of ​​the stability boundary in the form of key local modeling. While reducing the calculation complexity, it takes into account both economy and static stability, and provides an efficient solution for power system operation optimization.

[0085] Step S13, generating a corresponding sample set based on the second neighborhood of the target feasible solution, classifying the samples in the sample set, and determining the type of stability constraint to be performed on key local modeling according to the classification results; the stability constraint type includes a static voltage stability constraint and a static power angle stability constraint.

[0086] In this embodiment, after obtaining the target feasible solution, a corresponding sample set is generated using the second neighborhood of the target feasible solution, and the samples in the sample set are classified to obtain a corresponding classification result, and the stability constraint type to be modeled for key local areas is determined according to the classification result. The stability constraint type includes a static voltage stability constraint and a static power angle stability constraint.

[0087] It should be noted that the processing flow of generating the sample set using the second neighborhood and classifying the samples in the sample set is as follows: taking the target feasible solution as the center, performing random sampling in the second neighborhood of the target feasible solution, so as to generate a corresponding sample set using the sampled solution; judging whether the samples in the sample set satisfy the first initial stability constraint of the static voltage and the second initial stability constraint of the static power angle, so as to classify the samples; wherein, if the sample satisfies the first initial stability constraint and the second initial stability constraint, the sample is determined to be of the first type; if the sample satisfies the first initial stability constraint but does not satisfy the second initial stability constraint, the sample is determined to be of the second type; if the sample satisfies the second initial stability constraint but does not satisfy the first initial stability constraint, the sample is determined to be of the third type; if the sample does not satisfy the first initial stability constraint and the second initial stability constraint, the sample is determined to be of the fourth type. That is, with the target feasible solution as the center, random sampling is performed within its second neighborhood to form the sampled solutions into a sample set, and the samples are divided into the following four categories according to whether the samples satisfy the initial static voltage stability constraint and the initial static power angle stability constraint: Set A: positive samples that simultaneously satisfy the initial stability constraint; Set B: negative samples that satisfy the initial static voltage stability constraint but do not satisfy the initial static power angle stability constraint; Set C: negative samples that satisfy the initial static power angle stability constraint but do not satisfy the initial static voltage stability constraint; Set D: negative samples that do not simultaneously satisfy the initial stability constraint.

[0088] It should be further pointed out that after obtaining the corresponding classification results, this embodiment needs to determine the type of stability constraint to be used for key local modeling according to the position of the samples in the sample set, and the processing flow is as follows: if the obtained classification result indicates that the sample set contains samples of the first preset type, then the type of stability constraint to be used for key local modeling is determined to be the static voltage stability constraint; if the obtained classification result indicates that the sample set contains samples of the second preset type, then the type of stability constraint is determined to be the static power angle stability constraint; if the obtained classification result indicates that the sample set contains samples of the third preset type, then the type of stability constraint is determined to be the static voltage stability constraint and the static power angle stability constraint; wherein, the first preset type includes the first type and the third type; the second preset type includes the first type and the second type; the third preset type includes any one or a combination of the first type, the second type, the third type and the fourth type except the first preset type and the second preset type. That is, if the samples in the sample set only exist in set A and set C, it is necessary to model the static voltage stability constraint; if the samples in the sample set only exist in set A and set B, it is necessary to model the static power angle stability constraint; and if the samples in the sample set exist not only in set A and set C, or only in set A and set B, it is necessary to model both the static voltage stability constraint and the static power angle stability constraint. In this way, this embodiment determines the type of stability constraint that needs to be modeled locally by determining the location classification of the neighborhood samples of the target feasible solution, determines the location classification according to whether it meets the initial static power angle stability constraint condition and the initial static voltage stability constraint condition, constructs the static voltage stability constraint when there are samples that do not meet the initial static voltage stability constraint condition, and constructs the static power angle stability constraint when there are samples that do not meet the initial static power angle stability constraint condition, so as to constrain the relevant conditions, significantly improve the efficiency of the optimization scheduling, and provide a more reliable optimization scheduling scheme for the operation of the power system.

[0089] Step S14: using a preset support vector machine technology and the classification result to segment the samples in the sample set to perform the key local modeling and generate optimized stability constraint conditions corresponding to the stability constraint type.

[0090] In this embodiment, after determining the type of stable constraint that needs to be modeled locally, it is necessary to segment the samples in the sample set using a preset support vector machine technology (i.e., Support Vector Machine, SVM) and the classification result for the constraint that needs to be modeled, so as to perform the key local modeling and generate optimized stable constraint conditions corresponding to the stable constraint type. The preset support vector machine technology may be a soft margin support vector machine technology.

[0091] It should be noted that, in this embodiment, the parameters to be sought for the key local modeling are obtained by using the preset support vector machine technology, and the processing flow is as follows: the corresponding analytical expression is generated by using the soft margin support vector machine technology; the samples in the sample set are segmented based on the classification result and the analytical expression, and in the process of segmenting the samples, the slack variables and penalty factors in the analytical expression are used to punish the samples that violate the constraints of the analytical expression to obtain the parameters to be sought in the analytical expression; the key local modeling is performed using the parameters to be sought to generate the optimized stable constraint conditions corresponding to the stable constraint type. That is, the corresponding analytical expression is generated by using the soft margin support vector machine technology, the positive and negative samples in the sample set are segmented by using the classification result and the analytical expression, and in the process of segmenting the samples, the slack variables and penalty factors in the analytical expression are used to punish the samples that violate the constraints of the analytical expression to obtain the parameters to be sought in the analytical expression, so as to perform the key local modeling using the parameters to be sought to generate the optimized stable constraint conditions corresponding to the stable constraint type. Among them, for the traditional support vector machine technology, the hard margin support vector machine technology is usually used, and the linear kernel function is used to construct a hyperplane to maximize the interval segmentation of positive samples and negative samples. The traditional analytical expression and traditional constraints can be as follows:

[0092] ;

[0093] Wherein, w, b represent the parameters to be determined of SVM; y represents the sample label, wherein the positive sample is 1 and the negative sample is 0 (when the constraint to be modeled is the static voltage stability constraint, the positive samples are sets A and B, and the negative samples are sets C and D; when the constraint to be modeled is the static power angle stability constraint, the positive samples are sets A and C, and the negative samples are sets B and D); x represents the sample. The analytical expression is to maximize the distance between the positive and negative hyperplanes, and the traditional constraints need to ensure that all positive and negative samples are correctly separated to both sides of the positive and negative hyperplanes. However, considering that the samples may not be completely linearly separable, this embodiment adopts the soft margin support vector machine technology, and by introducing the slack variables and the penalty factors, the samples that violate the constraints are penalized. The expression formula can be as follows:

[0094] ;

[0095] in, In this embodiment, the parameters to be determined in the analytical expression are obtained by using the above formula, and the parameters to be determined are brought into the general expression of the static voltage stability constraint or the static power angle stability constraint to obtain the optimized stability constraint condition, wherein the expression formula of the optimized stability constraint condition can be as follows:

[0096] ;

[0097] Among them, T represents the inversion operation, and x represents . It should be noted that if the stability constraint types that require key local modeling include both static voltage stability constraints and static power angle stability constraints, the above key local modeling operation is performed twice to construct the static voltage stability constraints and the static power angle stability constraints respectively. In this way, this embodiment uses the soft margin support vector machine technology and the classification results to segment the samples in the sample set, and can also perform key local modeling when the samples are not completely linearly separable. It innovatively combines key local focusing and data-driven technology to construct efficient and analytical stability constraint expressions, providing reliable technical support for power system operation optimization.

[0098] Step S15: Optimizing the optimal power flow model of the power system using the optimized stability constraint condition, and performing optimal dispatching of the power system based on the optimized optimal power flow model of the power system.

[0099] In this embodiment, after the optimized stability constraint condition is generated, the optimal power flow model of the power system is optimized using the optimized stability constraint condition, and the optimal dispatch of the power system is performed based on the optimized optimal power flow model of the power system. The optimized optimal power flow model of the power system includes the objective function, the preset constraint condition and the optimized stability constraint condition, and the optimized stability constraint condition includes the optimized static voltage stability constraint condition and the optimized static power angle stability constraint condition.

[0100] It can be understood that the optimized stability constraint condition may include the optimized static voltage stability constraint condition and the optimized static power angle stability constraint condition, or may be the optimized static voltage stability constraint condition or the optimized static power angle stability constraint condition. Among them, if the generated optimized stability constraint condition only includes the optimized static voltage stability constraint condition, the optimized static voltage stability constraint condition is used to replace the initial static voltage stability constraint condition in the optimal power flow model of the power system to obtain the optimized optimal power flow model of the power system, so as to use it for optimal scheduling of the power system; if the generated optimized stability constraint condition only includes the optimized static power angle stability constraint condition, the optimized static power angle stability constraint condition is used to replace the initial static power angle stability constraint condition in the optimal power flow model of the power system to obtain the optimized optimal power flow model of the power system, so as to use it for optimal scheduling of the power system; if the generated optimized stability constraint condition includes the optimized static voltage stability constraint condition and the optimized static power angle stability constraint condition, the optimized static voltage stability constraint condition and the optimized static power angle stability constraint condition are used to replace the initial static voltage stability constraint condition and the initial static power angle stability constraint condition in the optimal power flow model of the power system respectively to obtain the optimized optimal power flow model of the power system, so as to use it for optimal scheduling of the power system.

[0101] It should be pointed out that, in the process of optimization scheduling, in order to ensure that the final scheduling result satisfies the static voltage-power angle stability constraint, this embodiment can continuously monitor the optimization result of the optimization scheduling after the optimization scheduling of the power system, and perform corresponding iterative correction operations. The processing flow is as follows: monitor the optimization result of the optimization scheduling; when it is monitored that the optimization result does not satisfy the stability constraint corresponding to the stability constraint type, add the optimization result to the sample set, and increase the weight of the optimization result in the sample set to obtain an updated sample set; use the updated sample set to iteratively correct the optimized stability constraint condition, so as to use the corrected stability constraint condition to obtain the optimization result that satisfies the stability constraint corresponding to the stability constraint type. That is, the optimization result of the optimization scheduling is monitored, and when it is detected that the optimization result does not satisfy the stability constraint corresponding to the stability constraint type, the optimization result is re-incorporated into the sample set and assigned a greater weight to obtain an updated sample set, so as to cause these samples to have a greater impact on the model in subsequent optimization, and then the updated sample set is used to iteratively correct the optimized stability constraint conditions, so as to obtain the optimization result that satisfies the stability constraint corresponding to the stability constraint type using the corrected stability constraint conditions. Among them, in the traditional SVM technology, the objective function realizes the classification of samples by minimizing the distance between positive and negative hyperplanes, and in this embodiment, in order to correct the optimization result more accurately, the objective function of SVM is corrected before iterative correction, and the expression formula of the corrected objective function can be as follows:

[0102] ;

[0103] in, Represents the weight of sample i, given Large weights can make Approaches 0, forcing sample i not to be misclassified. In this way, this embodiment uses the above-mentioned modified objective function expression formula to iteratively correct the optimized stable constraint condition, so that the optimized scheduling result gradually approaches the optimal solution that satisfies the stable constraint, avoiding the local instability problem that may exist in the traditional method, and improving the stability and reliability of the scheduling solution; at the same time, when the optimization result is re-incorporated into the sample set, it is given a greater weight to promote it to have a greater impact on the model in the subsequent optimization process, avoid the sample from being misclassified, and improve the reliability of the stable constraint equivalent modeling.

[0104] As can be seen from the above, the embodiment of the present application first pre-solves the optimal power flow model of the power system under preset constraints to obtain a pre-solution result, searches for a target feasible solution of the optimal power flow model of the power system from a first neighborhood of the pre-solution result, generates a corresponding sample set based on a second neighborhood of the target feasible solution, and determines the stability constraint type according to the classification result of the samples in the sample set, segments the samples in the sample set using a preset support vector machine technology and the classification result to generate optimized stability constraint conditions corresponding to the stability constraint type, and uses the optimized stability constraint conditions and the optimal power flow model of the power system to perform optimal scheduling of the power system. In this way, through the above process of the embodiment of the present application, on the one hand, the optimal power flow model of the power system is pre-solved without considering the static voltage-power angle stability constraint to obtain an initial solution, so as to search for a target feasible solution that satisfies all the constraints of the optimal power flow model of the power system based on the initial solution, and pave the way for subsequent equivalent modeling considering the dual stability constraints of static voltage-power angle; on the one hand, with the initial solution as the center, the target feasible solution is searched in its neighborhood, and the key local area of ​​the stability boundary is effectively focused on in the form of key local modeling, while reducing the computational complexity, taking into account both economy and static stability, and providing an efficient solution for the optimization of power system operation; on the one hand, the type of stability constraint that needs to be modeled key locally is determined by classifying the locations of the neighborhood samples of the target feasible solution, so as to constrain the relevant conditions, significantly improve the efficiency of optimal scheduling, and provide a more reliable optimal scheduling scheme for the operation of the power system; on the one hand, soft interval support is used Vector machine technology and the classification results are used to segment the samples in the sample set. When the samples are not completely linearly separable, key local modeling can also be performed. The key local focus and data-driven technology are innovatively combined to construct an efficient and analytical stability constraint expression, providing reliable technical support for the optimization of power system operation; on the one hand, the optimized stability constraint condition is iteratively corrected using the corrected objective function expression formula, so that the optimized scheduling result gradually approaches the optimal solution that satisfies the stability constraint, avoiding the local instability problem that may exist in the traditional method and improving the stability and reliability of the scheduling scheme; on the other hand, when the optimization result is re-incorporated into the sample set, a greater weight is given to it to promote it to have a greater impact on the model in the subsequent optimization process, avoid the sample from being misclassified, and improve the reliability of the stability constraint equivalent modeling, thereby efficiently embedding a variety of stability constraints into the power system optimization model to provide a more reliable optimization scheduling scheme for the power system operation.

[0105] The following is an explanation of the technical solution in this application by taking the modified IEEE 39-node (a model commonly used in power system engineering) example.

[0106] The technical solution in this application is implemented in the Python 3.4 environment. The power angle small disturbance stability index and static voltage stability index involved in the calculation process are calculated using DIgSILENT (a power system simulation software) / PowerFactory (a power system simulation software) and PyPower (a power system analysis toolkit). In the experiment, the versatility and adaptability of the technical solution in this application are further verified by simulating 24-hour load changes and modifying the threshold of the stability index.

[0107] In order to verify the advantages of the technical solution in this application, this experiment set up three comparative methods for performance evaluation:

[0108] M1: initial scheduling result without considering stability constraints;

[0109] M2: The technical solution in this application without considering iterative correction;

[0110] M3: The technical solution in this application (including iterative correction strategy).

[0111] Specifically, the load level is adjusted to simulate the 24-hour load change, where the calculation results of the solution process are as follows: Figures 2 to 5 As shown in the figure, they are the voltage stability margin comparison diagram, the power angle stability damping ratio comparison diagram, the operation cost comparison diagram, and the constraint equivalent modeling number comparison diagram. Figure 2 and Figure 3 From the analysis, it can be observed that: at 22:00 and 23:00, the initial scheduling results met the voltage and power angle stability requirements, so there is no need to additionally construct static voltage-power angle stability constraints. In other time periods, the initial optimization results did not fully meet a certain stability requirement in voltage or power angle. When the technical solution in this application without considering iterative correction was introduced, 7 of the 22 time periods failed to fully meet the voltage or power angle stability requirements, but the optimization results were close to the set stability threshold target. On the contrary, when the iterative correction strategy was adopted, all scheduling results successfully met the voltage and power angle stability requirements; Figure 4 The economic efficiency of the three methods is shown. It can be seen that based on the initial scheduling results without considering the stability constraints, the total cost of the technical solution of this application is only increased by 3.88%. This result shows that under the premise of increasing a small amount of economic cost, the technical solution of this application can ensure that the optimization results meet the stability requirements of voltage and power angle; Figure 5 The figure shows the number of constraints required for a single optimization run. The data in the figure reflects the differences in the key local position characteristics of the stability boundary in different scenarios. Therefore, it can be seen that it is necessary to predetermine the number of constraints before building stability constraints.

[0112] It is understandable that increasing the threshold of the stability index will lead to a reduction in the feasible domain of the optimization result. This embodiment can verify the adaptability of the technical solution of the present application to stability changes by increasing the safety threshold of the power angle and voltage stability index. Figure 6 Shown is a schematic diagram of the optimization cost comparison when different stability thresholds are set provided by the present application. It can be seen that the power angle stability damping ratio of the initial scheduling result is 5.2%, and the voltage stability margin is 43%. When the safety thresholds of the power angle and voltage stability indicators are changed, the technical solution of the present application can still ensure that the optimization results meet the stability requirements. At the same time, with the increase of the stability threshold, the cost required for operation optimization gradually increases, but the increase is stable, indicating that the technical solution of the present application has good adaptability to changes in the stability threshold. By comparing the optimization results under different threshold settings, it can be seen that the technical solution of the present application can still maintain a relatively stable balance between system stability and economy under high threshold requirements.

[0113] In summary, this embodiment describes in detail the experimental environment, comparison method, load change simulation, and impact of threshold changes, ensuring the applicability and stability of the technical solution of the present application in different scenarios.

[0114] Accordingly, see Figure 7 As shown, the embodiment of the present application also provides a power system optimization dispatching device based on static voltage-power angle dual stability constraints, including:

[0115] A pre-solving module 11 is used to pre-solve a preset power system optimal power flow model under preset constraints to obtain a pre-solving result;

[0116] A feasible solution search module 12 is used to search for a target feasible solution of the power system optimal power flow model from the first neighborhood of the pre-solution result; the target feasible solution is a solution that satisfies the initial stability constraint conditions of the static voltage and the static power angle;

[0117] A type determination module 13 is used to generate a corresponding sample set based on the second neighborhood of the target feasible solution, classify the samples in the sample set, and determine the type of stability constraint to be modeled for key local areas according to the classification results; the stability constraint type includes a static voltage stability constraint and a static power angle stability constraint;

[0118] A sample segmentation module 14, configured to segment the samples in the sample set by using a preset support vector machine technology and the classification result, so as to perform the key local modeling and generate optimized stable constraint conditions corresponding to the stable constraint type;

[0119] The optimization scheduling module 15 is used to optimize the optimal power flow model of the power system by using the optimized stability constraint condition, and perform optimal scheduling of the power system based on the optimized optimal power flow model of the power system.

[0120] As can be seen from the above, the embodiment of the present application first pre-solves the optimal power flow model of the power system under the preset constraint conditions to obtain the pre-solved result, searches for the target feasible solution of the optimal power flow model of the power system from the first neighborhood of the pre-solved result, generates a corresponding sample set based on the second neighborhood of the target feasible solution, and determines the stability constraint type according to the classification result of the samples in the sample set, and uses the preset support vector machine technology and the classification result to segment the samples in the sample set to generate the optimized stability constraint conditions corresponding to the stability constraint type, and uses the optimized stability constraint conditions and the optimal power flow model of the power system to optimize the scheduling of the power system. In this way, through the above process of the embodiment of the present application, the optimized stability constraint conditions corresponding to the stability constraint type are constructed by using the key local modeling method, which can reduce the complexity of global modeling and significantly improve the efficiency of optimization scheduling. At the same time, the two stability constraints of static voltage-power angle are considered in the optimization scheduling of the power system, which improves the stability and reliability of the scheduling scheme, and then efficiently embeds multiple stability constraints into the power system optimization model to provide a more reliable optimization scheduling scheme for the operation of the power system.

[0121] In some specific embodiments, the preset constraints include power flow balance constraints, line power upper and lower limit constraints, and voltage amplitude upper and lower limit constraints; the optimal power flow model of the power system includes an objective function, the preset constraints and the initial stability constraints, and the initial stability constraints include initial static voltage stability constraints and initial static power angle stability constraints; the optimized optimal power flow model of the power system includes the objective function, the preset constraints and the optimized stability constraints, and the optimized stability constraints include optimized static voltage stability constraints and optimized static power angle stability constraints.

[0122] In some specific implementations, the feasible solution search module 12 may specifically include:

[0123] A neighborhood search unit is used to search the first neighborhood of the pre-solved result, so as to calculate the preset optimization function using the optimization variables in the first neighborhood based on the Newton-Raphson method and the numerical method, and determine the target feasible solution of the optimal power flow model of the power system from the first neighborhood according to the calculation result; wherein the preset optimization function is a nonlinear equation.

[0124] In some specific implementations, the type determination module 13 may specifically include:

[0125] A random sampling unit, used to perform random sampling in a second neighborhood of the target feasible solution with the target feasible solution as the center, so as to generate a corresponding sample set using the solution obtained by sampling;

[0126] a condition judgment unit, used for judging whether the samples in the sample set satisfy the first initial stability constraint condition of the static voltage and the second initial stability constraint condition of the static power angle, so as to classify the samples;

[0127] Among them, if the sample satisfies the first initial stability constraint and the second initial stability constraint, the sample is determined to be the first type; if the sample satisfies the first initial stability constraint but does not satisfy the second initial stability constraint, the sample is determined to be the second type; if the sample satisfies the second initial stability constraint but does not satisfy the first initial stability constraint, the sample is determined to be the third type; if the sample does not satisfy the first initial stability constraint and the second initial stability constraint, the sample is determined to be the fourth type.

[0128] In some specific implementations, the type determination module 13 may specifically include:

[0129] A first type determination unit, configured to determine that the stability constraint type to be subjected to key local modeling is the static voltage stability constraint if the obtained classification result indicates that the sample set contains samples of the first preset type;

[0130] A second type determination unit, configured to determine that the stability constraint type is the static power angle stability constraint if the obtained classification result indicates that the sample set contains samples of a second preset type;

[0131] A third type determination unit, configured to determine that the stability constraint type is the static voltage stability constraint and the static power angle stability constraint if the obtained classification result indicates that the sample set contains samples of a third preset type;

[0132] Among them, the first preset type includes the first type and the third type; the second preset type includes the first type and the second type; the third preset type includes any one or a combination of the first type, the second type, the third type and the fourth type except the first preset type and the second preset type.

[0133] In some specific implementations, the sample segmentation module 14 may specifically include:

[0134] An expression generation unit, used for generating corresponding analytical expressions by using soft margin support vector machine technology;

[0135] A sample penalty unit, configured to segment the samples in the sample set based on the classification result and the analytical expression, and in the process of segmenting the samples, use the slack variables and penalty factors in the analytical expression to penalize the samples that violate the constraints of the analytical expression, so as to obtain the parameters to be determined in the analytical expression;

[0136] The local modeling unit is used to perform the key local modeling using the parameters to be determined, so as to generate optimized stability constraint conditions corresponding to the stability constraint type.

[0137] In some specific implementations, the power system optimization dispatching device based on static voltage-power angle dual stability constraints may also include:

[0138] A result monitoring unit, used to monitor the optimization result of the optimization scheduling;

[0139] a weight adding unit, configured to add the optimization result to the sample set and increase the weight of the optimization result in the sample set when it is detected that the optimization result does not satisfy the stability constraint corresponding to the stability constraint type, so as to obtain an updated sample set;

[0140] The iterative correction unit is used to iteratively correct the optimized stable constraint condition by using the updated sample set, so as to obtain an optimization result that satisfies the stable constraint corresponding to the stable constraint type by using the corrected stable constraint condition.

[0141] Furthermore, the present application also discloses an electronic device. Figure 8 It is a structural diagram of an electronic device 20 shown according to an exemplary embodiment, and the content in the figure cannot be regarded as any limitation on the scope of use of this application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25 and a communication bus 26. Among them, the memory 22 is used to store a computer program, and the computer program is loaded and executed by the processor 21 to implement the relevant steps in the power system optimization scheduling method based on the static voltage-power angle dual stability constraint disclosed in any of the aforementioned embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0142] In this embodiment, the power supply 23 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0143] In addition, the memory 22 as a carrier for storing resources may be a read-only memory, a random access memory, a disk or an optical disk, etc. The resources stored thereon may include an operating system 221, a computer program 222, etc., and the storage method may be temporary storage or permanent storage.

[0144] The operating system 221 is used to manage and control the hardware devices and computer program 222 on the electronic device 20, which can be Windows Server, Netware, Unix, Linux, etc. In addition to including a computer program that can be used to complete the power system optimization scheduling method based on static voltage-power angle dual stability constraints performed by the electronic device 20 disclosed in any of the aforementioned embodiments, the computer program 222 can further include a computer program that can be used to complete other specific tasks.

[0145] Furthermore, the present application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the above-disclosed power system optimization dispatching method based on static voltage-power angle dual stability constraints is implemented. For the specific steps of the method, reference may be made to the corresponding contents disclosed in the above-mentioned embodiments, and no further description will be given here.

[0146] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0147] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0148] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0149] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0150] The technical solution provided by the present application is introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for general technicians in this field, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for optimizing the dispatch of a power system based on static voltage-power angle dual stability constraints, characterized in that: include: Pre-solving a preset power system optimal power flow model under preset constraint conditions to obtain a pre-solved result; Searching for a target feasible solution of the power system optimal power flow model from a first neighborhood of the pre-solved result; The target feasible solution is a solution that satisfies the initial stability constraint conditions of static voltage and static power angle; Generate a corresponding sample set based on the second neighborhood of the target feasible solution, classify the samples in the sample set, and determine the type of stability constraint to be performed on key local modeling according to the obtained classification result; the stability constraint type includes a static voltage stability constraint and a static power angle stability constraint; Using a preset support vector machine technology and the classification results to segment the samples in the sample set, so as to perform the key local modeling and generate optimized stable constraint conditions corresponding to the stable constraint type; The optimized stability constraint condition is used to optimize the optimal power flow model of the power system, and the optimal dispatch of the power system is performed based on the optimized optimal power flow model of the power system.

2. The power system optimization dispatching method based on static voltage-power angle dual stability constraint according to claim 1 is characterized in that: The preset constraints include power flow balance constraints, line power upper and lower limit constraints, and voltage amplitude upper and lower limit constraints; the optimal power flow model of the power system includes the objective function, the preset constraints and the initial stability constraints, and the initial stability constraints include the initial static voltage stability constraints and the initial static power angle stability constraints; the optimized optimal power flow model of the power system includes the objective function, the preset constraints and the optimized stability constraints, and the optimized stability constraints include the optimized static voltage stability constraints and the optimized static power angle stability constraints.

3. The power system optimization dispatching method based on static voltage-power angle dual stability constraint according to claim 1 is characterized in that: The step of searching for a target feasible solution of the power system optimal power flow model from a first neighborhood of the pre-solved result comprises: The first neighborhood of the pre-solved result is searched to calculate the preset optimization function based on the Newton-Raphson method and the numerical method using the optimization variables in the first neighborhood, and the target feasible solution of the optimal power flow model of the power system is determined from the first neighborhood according to the calculation result; wherein the preset optimization function is a nonlinear equation.

4. The power system optimization dispatching method based on static voltage-power angle dual stability constraint according to claim 1 is characterized in that: The step of generating a corresponding sample set based on the second neighborhood of the target feasible solution and classifying the samples in the sample set includes: Taking the target feasible solution as the center, performing random sampling in a second neighborhood of the target feasible solution, so as to generate a corresponding sample set using the sampled solution; Determining whether the samples in the sample set satisfy the first initial stability constraint condition of the static voltage and the second initial stability constraint condition of the static power angle, so as to classify the samples; Among them, if the sample satisfies the first initial stability constraint and the second initial stability constraint, the sample is determined to be the first type; if the sample satisfies the first initial stability constraint but does not satisfy the second initial stability constraint, the sample is determined to be the second type; if the sample satisfies the second initial stability constraint but does not satisfy the first initial stability constraint, the sample is determined to be the third type; if the sample does not satisfy the first initial stability constraint and the second initial stability constraint, the sample is determined to be the fourth type.

5. The power system optimization dispatching method based on static voltage-power angle dual stability constraint according to claim 4 is characterized in that: Determining the type of stability constraint to be modeled for key local areas according to the obtained classification results includes: If the obtained classification result indicates that the sample set contains samples of the first preset type, determining that the stability constraint type to be subjected to key local modeling is the static voltage stability constraint; If the obtained classification result indicates that the sample set contains samples of the second preset type, determining that the stability constraint type is the static power angle stability constraint; If the obtained classification result indicates that the sample set contains samples of the third preset type, determining that the stability constraint type is the static voltage stability constraint and the static power angle stability constraint; Among them, the first preset type includes the first type and the third type; the second preset type includes the first type and the second type; the third preset type includes any one or a combination of the first type, the second type, the third type and the fourth type except the first preset type and the second preset type.

6. The power system optimization dispatching method based on static voltage-power angle dual stability constraint according to claim 1 is characterized in that: The using of the preset support vector machine technology and the classification results to segment the samples in the sample set to perform the key local modeling and generate optimized stable constraint conditions corresponding to the stable constraint type includes: The corresponding analytical expressions are generated using soft-margin support vector machine technology; Segmenting the samples in the sample set based on the classification result and the analytical expression, and in the process of segmenting the samples, using the slack variables and penalty factors in the analytical expression to penalize the samples that violate the constraints of the analytical expression, so as to obtain the parameters to be determined in the analytical expression; The key local modeling is performed using the parameters to be determined to generate optimized stability constraint conditions corresponding to the stability constraint type.

7. The power system optimization dispatching method based on static voltage-power angle dual stability constraint according to any one of claims 1 to 6, characterized in that: After optimizing the optimal power flow model of the power system by using the optimized stability constraint condition and optimizing the power system based on the optimized optimal power flow model of the power system, the method further includes: Monitoring the optimization result of the optimization scheduling; When it is detected that the optimization result does not satisfy the stability constraint corresponding to the stability constraint type, the optimization result is added to the sample set, and the weight of the optimization result in the sample set is increased to obtain an updated sample set; The optimized stable constraint condition is iteratively corrected by using the updated sample set, so as to obtain an optimization result satisfying the stable constraint corresponding to the stable constraint type by using the corrected stable constraint condition.

8. A power system optimization dispatching device, characterized in that: include: A pre-solution module is used to pre-solve a preset power system optimal power flow model under preset constraints to obtain a pre-solution result; A feasible solution search module, used for searching a target feasible solution of the optimal power flow model of the power system from a first neighborhood of the pre-solution result; The target feasible solution is a solution that satisfies the initial stability constraint conditions of static voltage and static power angle; A type determination module, used to generate a corresponding sample set based on the second neighborhood of the target feasible solution, classify the samples in the sample set, and determine the type of stability constraint to be performed on the key local modeling according to the obtained classification result; the stability constraint type includes a static voltage stability constraint and a static power angle stability constraint; A sample segmentation module, used to segment the samples in the sample set by using a preset support vector machine technology and the classification result, so as to perform the key local modeling and generate optimized stable constraint conditions corresponding to the stable constraint type; The optimization scheduling module is used to optimize the optimal power flow model of the power system by using the optimized stability constraint conditions, and to perform optimal scheduling of the power system based on the optimized optimal power flow model of the power system.

9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the power system optimization scheduling method based on static voltage-power angle dual stability constraints as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Used to store computer programs; wherein, when the computer program is executed by a processor, it implements the power system optimization scheduling method based on static voltage-power angle dual stability constraints as described in any one of claims 1 to 7.

Images