Method for regulating and controlling static voltage stability risk of high-proportion new energy power system

By obtaining and analyzing the historical output data of new energy equipment, training the static voltage stability risk model, the efficiency and accuracy of static voltage stability risk assessment and regulation in high-proportion new energy power systems are solved, and real-time risk assessment of the power system is realized and regulation improves the safety of the power system.

CN119070402APending Publication Date: 2024-12-03CGN YUXI YUANJIANG WIND POWER CO LTD +2
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411200617.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-29
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

The existing technology cannot effectively evaluate and regulate the static voltage stability risks in high proportion new energy power systems, and traditional methods cannot meet the current efficiency and accuracy requirements for voltage stability risk assessment and regulation.

Method used

By obtaining the historical output data of new energy equipment, analyzing and training the static voltage stability risk model, and using asymmetric spline regression and Latin hypercube sampling, a static voltage stability regulation model is constructed to realize real-time risk assessment of the power system and Regulation.

Benefits of technology

It improves the accuracy and efficiency of static voltage stability risk assessment, can quickly respond to changes in the output data of new energy equipment, and provides important references to ensure the safe operation of the power system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119070402A_ABST
    Figure CN119070402A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of electric power, in particular to a static voltage stability risk regulation and control method for a high-proportion new energy electric power system. Comprising the following steps: acquiring historical output data of new energy equipment in a power system at each historical moment; analyzing the historical output data at each historical moment to obtain a static voltage stability index corresponding to each historical output data; according to the historical output data at each historical moment and the static voltage stability index corresponding to each historical output data, training the initial model to obtain a static voltage stability risk model; wherein the static voltage stability risk model is used for determining a static voltage stability index corresponding to the current output data according to the current output data at the current moment.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of electric power technology, and in particular to a method for controlling static voltage stability risks in a high-proportion new energy power system. Background Art

[0002] In the context of power system construction, the proportion of new energy installed capacity is increasing, the operation of the power system is closer to the boundary of the safe and stable domain, the risk of voltage collapse is significantly increased, and the research on static voltage stability risk assessment and regulation is becoming increasingly important.

[0003] Static voltage stability risk assessment refers to the process of evaluating and analyzing the ability of the voltage in the power system to maintain stability under load changes or faults. This assessment focuses on the change of voltage after a disturbance and predicts whether it can be maintained within a reasonable range to avoid serious problems such as voltage collapse.

[0004] At present, with the high penetration rate of new energy making the operating status of the power system highly diversified, traditional methods can no longer meet the current efficiency and accuracy requirements of voltage stability risk assessment and regulation.

[0005] Therefore, improvement is urgently needed. Summary of the invention

[0006] Based on this, it is necessary to provide a static voltage stability risk assessment method that can improve the accuracy of static voltage stability risk assessment in response to the above technical problems.

[0007] In the first aspect, the present application provides a method for controlling static voltage stability risk of a high-proportion new energy power system, including:

[0008] Obtain historical output data of new energy equipment in the power system at each historical moment;

[0009] Analyze the historical output data at each historical moment to obtain the static voltage stability index corresponding to each historical output data;

[0010] The initial model is trained according to the historical output data at each historical moment and the static voltage stability index corresponding to each historical output data to obtain a static voltage stability risk model; wherein the static voltage stability risk model is used to determine the static voltage stability index corresponding to the current output data according to the current output data at the current moment.

[0011] In one embodiment, obtaining historical output data of new energy equipment in the power system at each historical moment includes:

[0012] Determine a typical scenario set for the power system based on the historical output data of new energy equipment in the power system at various historical moments;

[0013] For any typical scenario set, determine the sample output data corresponding to the typical scenario set according to the historical output data and predicted output data corresponding to the typical scenario set;

[0014] The sample output data corresponding to each typical scenario set are analyzed to obtain the static voltage stability index corresponding to each historical output data.

[0015] In one embodiment, determining the sample output data corresponding to the typical scene set according to the historical output data and the predicted output data corresponding to the typical scene set includes:

[0016] Determine prediction error data based on historical output data and predicted output data corresponding to the typical scenario set;

[0017] The asymmetric spline regression model is used to fit the prediction error data to obtain the error sample set;

[0018] Latin hypercube sampling is used to sample the error sample set to obtain the sample output data corresponding to the typical scenario set.

[0019] In one embodiment, the sample output data corresponding to each typical scenario set is analyzed to obtain a static voltage stability index corresponding to each historical output data, including:

[0020] The continuous power flow method is used to analyze the sample output data corresponding to each typical scenario set, and the static voltage stability index corresponding to each historical output data is obtained.

[0021] In one embodiment, a typical scenario set of the power system is determined based on historical output data at historical moments, including:

[0022] The time series clustering method is used to analyze the historical output data at historical moments to obtain a set of typical scenarios of the power system.

[0023] In one embodiment, the method further comprises:

[0024] According to the output results of the static voltage stability risk model, a static voltage stability control model is constructed;

[0025] Among them, the objective function of the static voltage stability control model is the control cost function, and the control cost includes the cost of the whole generator output control measures, the cost of changing the network topology control measures and the cost of switching capacitor control measures.

[0026] In a second aspect, the present application also provides a static voltage stability risk assessment device, comprising:

[0027] An acquisition module is used to obtain historical output data of renewable energy in the power system at various historical moments;

[0028] An analysis module is used to analyze the historical output data at each historical moment to obtain the static voltage stability index corresponding to each historical output data;

[0029] The evaluation module is used to train the initial model according to the historical output data at each historical moment and the static voltage stability index corresponding to each historical output data to obtain a static voltage stability risk model; wherein the static voltage stability risk model is used to determine the static voltage stability index corresponding to the current output data according to the current output data at the current moment.

[0030] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0031] Obtain historical output data of new energy equipment in the power system at each historical moment;

[0032] Analyze the historical output data at each historical moment to obtain the static voltage stability index corresponding to each historical output data;

[0033] The initial model is trained according to the historical output data at each historical moment and the static voltage stability index corresponding to each historical output data to obtain a static voltage stability risk model; wherein the static voltage stability risk model is used to determine the static voltage stability index corresponding to the current output data according to the current output data at the current moment.

[0034] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the following steps are implemented:

[0035] Obtain historical output data of new energy equipment in the power system at each historical moment;

[0036] Analyze the historical output data at each historical moment to obtain the static voltage stability index corresponding to each historical output data;

[0037] According to the historical output data at each historical moment and the static voltage stability index corresponding to each historical output data, the initial model is trained to obtain a static voltage stability risk model; wherein the static voltage stability risk model is used to determine the static voltage stability index corresponding to the current output data according to the current output data at the current moment.

[0038] Voltage stability indicator.

[0039] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0040] Obtain historical output data of new energy equipment in the power system at each historical moment;

[0041] Analyze the historical output data at each historical moment to obtain the static voltage stability index corresponding to each historical output data;

[0042] The initial model is trained according to the historical output data at each historical moment and the static voltage stability index corresponding to each historical output data to obtain a static voltage stability risk model; wherein the static voltage stability risk model is used to determine the static voltage stability index corresponding to the current output data according to the current output data at the current moment.

[0043] After the training of the above static voltage stability risk assessment method is completed, the static voltage stability risk model obtained can be used to assess the static voltage stability risk of the power system in real time. When the output data of the new energy equipment changes, the model can quickly give the static voltage stability index corresponding to the current output data, thereby providing an important reference for the safe operation of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0045] Figure 1 It is a flow chart of a method for controlling static voltage stability risk of a high-proportion new energy power system in one embodiment;

[0046] Figure 2 A schematic diagram of a flow chart of steps for obtaining historical output data of new energy equipment in a power system at each historical moment in an embodiment;

[0047] Figure 3 is a structural block diagram of a static voltage stability risk assessment device in one embodiment;

[0048] Figure 4 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only

[0050] It is used to explain the present application but not to limit the present application.

[0051] In an exemplary embodiment, Figure 2 As shown, a static voltage stability risk control method for a high-proportion new energy power system is provided, and the method is applied to a computer device as an example for explanation, including the following steps 101 to 103. Among them:

[0052] Step 101, obtaining historical output data of new energy equipment in the power system at each historical moment.

[0053] Among them, it is necessary to collect the output data of new energy equipment (such as wind farms, photovoltaic power stations, etc.) at various historical moments from the historical records of the power system. These data may include the output value at each moment, the output change rate, etc. These data are the basis for training the model, so its accuracy and completeness need to be ensured.

[0054] Step 102: Analyze the historical output data at each historical moment to obtain a static voltage stability index corresponding to each historical output data.

[0055] In this step, it is necessary to use power system analysis tools or simulation software to perform static voltage stability analysis on the output data at each historical moment. Static voltage stability indicators can include voltage stability margin, sensitivity index, etc. These indicators can reflect the voltage stability performance of the system under the current output conditions. The results of the analysis will be used as label data for model training.

[0056] Step 103 , training the initial model according to the historical output data at each historical moment and the static voltage stability index corresponding to each historical output data, to obtain a static voltage stability risk model.

[0057] Among them, the static voltage stability risk model is used to determine the static voltage stability index corresponding to the current output data according to the current output data at the current moment.

[0058] Optionally, a machine learning algorithm (such as deep learning, support vector machine, etc.) is needed to train a model that can predict the static voltage stability index based on the output data of new energy equipment. During the training process, historical output data is used as input features, and the corresponding static voltage stability index is used as the target output. Through continuous iteration and optimization, the model can learn the complex relationship between output data and static voltage stability index.

[0059] After the training of the above static voltage stability risk assessment method is completed, the static voltage stability risk model obtained can be used to assess the static voltage stability risk of the power system in real time. When the output data of the new energy equipment changes, the model can quickly give the static voltage stability index corresponding to the current output data, thereby providing an important reference for the safe operation of the power system.

[0060] In an exemplary embodiment, Figure 2 As shown, step 101, obtaining historical output data of new energy equipment in the power system at each historical moment, includes:

[0061] Step 201 , determining a typical scenario set of the power system according to the historical output data of new energy equipment in the power system at each historical moment.

[0062] Specifically, the time series clustering method is used to analyze the historical output data at historical moments to obtain a set of typical scenarios of the power system.

[0063] First, based on the historical output data, the dynamic time warping algorithm is used to compare the historical output data in pairs, calculate the minimum distance between each wind power output time series, and store it in the matrix M. For any two wind power output samples P i and P j , create a distance matrix D of size N×N ij , the distance matrix D ij The elements in are calculated as follows:

[0064] D ij (m,n)=|P i,m -P j,n |+min{D ij (m-1,n),D ij (m,n-1),D ij (m-1,n-1)}

[0065] P i = {P i,1 ,…,P i,t ,…,P i,N}

[0066] P j = {P j,1 ,…,P j,t ,…,P j,N}

[0067] Where N represents the length of the wind power output sample.

[0068] According to the above formula, complete the distance matrix D ij After all the elements in the distance matrix D are calculated based on the following rules ij Find a line starting at D ij (N i -1,N j -1) End at D ij The path with the minimum distance value len={len1,…,len k ,…,lenK}, K∈[N,2N-1].

[0069] If k =D ij (m,n), then w k+1 =min{D ij (m-1,n),D ij (m,n-1),D ij (m-1,n-1)}

[0070] Furthermore, the shortest cumulative distance DTW (P i ,P j ):

[0071]

[0072] For the existing historical data, create a matrix M of size S×S, compare each historical output data pairwise, calculate their shortest cumulative distances respectively, and fill the matrix M according to the following formula:

[0073] M(i,j)=DTW(P i ,P j )

[0074] Wherein, S represents the number of historical output data to be clustered.

[0075] After that, the generated matrix is ​​subjected to multidimensional scaling analysis, the corresponding pressure function is constructed, and the ladder descent method is used for optimization and solution to find the best configuration of the projection points in the low-dimensional space to minimize the stress function, and then the projection point set is clustered. The matrix M reflecting the differences between the historical output data is input into the multidimensional scaling analysis algorithm, and the following pressure function is used for calculation:

[0076]

[0077] Where E(X) represents the pressure function to be optimized; w ij represents the weight associated with the difference between samples i and j; d ij represents the raw difference between samples i and j; Represents the projection point of the sample in the low-dimensional space and The Euclidean distance between .

[0078] After that, the gradient descent method is used for optimization. The pressure function is minimized by finding the optimal configuration of the projection points in the low-dimensional space, and the difference matrix M generated by dynamic time warping is scaled to the projection points in the Euclidean space.

[0079] For the obtained projection point set The K-means algorithm is used for clustering to divide the typical scene sets.

[0080] Step 202: for any typical scenario set, determine the sample output data corresponding to the typical scenario set based on the historical output data and predicted output data corresponding to the typical scenario set.

[0081] Specifically, according to the historical output data and the predicted output data corresponding to the typical scenario set, the sample output data corresponding to the typical scenario set is determined, including: according to the historical output data and the predicted output data corresponding to the typical scenario set, the prediction error data is determined; an asymmetric spline regression model is used to fit the prediction error data to obtain an error sample set; and Latin hypercube sampling is used to sample the error sample set to obtain the sample output data corresponding to the typical scenario set.

[0082] First, in this embodiment, the new energy output prediction error ΔP in each typical scenario is calculated according to the following formula: i :

[0083] ΔP i =P i -P i '

[0084] Among them, P i and P' i Represent the historical output data and predicted output data of new energy sources respectively. Use variables x and y to represent the actual output data P and prediction error ΔP of new energy sources respectively, and use the sample set {x, y} as the input of the asymmetric spline regression algorithm. In the asymmetric spline regression model, the sample {x i ,y i The spline regression model of} can be expressed as:

[0085] y i =z i τ+ξ i

[0086]

[0087] in, represents the regression error; τ is the regression coefficient vector; z i represents the quantity related to the spline basis function; η is the augmented knot sequence; a represents the order of the spline basis. In general, assuming that the random variable ξ obeys a mixed asymmetric Gaussian distribution, its probability density function p MoAG It can be expressed as:

[0088]

[0089] Where K represents the number of asymmetric Gaussian distributions; pAG (·) represents the probability density function of asymmetric Gaussian distribution; σ 2 and 2 σ 2 are two variances; ω=[ω1,...,ω K ] represents the weight of each asymmetric Gaussian distribution in the mixed distribution. Based on the maximum likelihood estimation, the objective function of the asymmetric Gaussian mixture distribution spline regression is to maximize the log-likelihood function L(θ), that is:

[0090]

[0091] Where θ={π,σ 2 ,r,τ} represents the parameter set. Further, the expectation maximization method is used to adjust the parameter θ. At this time, the original objective function can be rewritten as:

[0092]

[0093] Among them, I ik represents the unobserved indicator variable in expectation-maximization.

[0094] Secondly, randomly initialize τ and update the parameter set θ according to τ. For each sample in the sample set {x, y}, its corresponding I is calculated by the following formula ik value:

[0095]

[0096] Among them, E(·) represents the conditional expectation. The remaining parameters in the parameter set θ s k and ω k It can be updated by the following formula:

[0097]

[0098] Update based on the above formula and k After that, the update formula of τ can be easily obtained through the iterative weighted least squares algorithm:

[0099] τ=(Z T A-Z) -1 Z T AY

[0100]

[0101] Where A is a diagonal matrix; Y = [y1,...,y N ] T .

[0102] After that, the above calculation process is repeated and the parameter set θ is updated until the maximum number of iterations is reached or convergence fails. The parameters are brought back to the function p MoAG The probability density function of new energy prediction error can be obtained.

[0103] Finally, determine the number of samples to be sampled, divide the sampling space into equal number of sub-intervals, and first uniformly sample to generate samples of power system state variables, such as conventional generator output P G , node voltage V, load active power P L Etc., and then according to the probability density function p of the new energy output prediction error MoAG Sampling is performed. The predicted value of renewable energy power is superimposed on the prediction error to obtain the corrected renewable energy output sample. The generated samples can effectively simulate the uncertainty of renewable energy output, increase the diversity of training samples, and supplement the samples of renewable energy output scenarios with low probability.

[0104] Step 203 , analyzing the sample output data corresponding to each typical scenario set to obtain a static voltage stability index corresponding to each historical output data.

[0105] Specifically, the continuous power flow method is used to analyze the sample output data corresponding to each typical scenario set to obtain the static voltage stability index corresponding to each historical output data.

[0106] The load margin index is selected as the quantitative representation of the static voltage stability of the power system, and the calculation expression of the load margin index is as follows:

[0107]

[0108] Among them, λ is the load growth rate; μ Gi , μ PLi and μ QLi They represent the growth direction of the generator output, load active power and reactive power of node i respectively; h(·) represents the inequality constraint of the power system; u represents the state variable of the power system.

[0109] Afterwards, the continuous power flow method is used to calculate the load margin index of the sample, that is, the power system power flow is repeatedly calculated by gradually increasing the load growth rate λ until the Jacobian matrix of the power flow is singular. At this time, the load margin λ of the power system is cr It is the system static voltage stability risk assessment index.

[0110] Considering that the continuous power flow method is sensitive to the scale of the power system and has a high computational cost, an alternative model of the continuous power flow method is constructed based on the deep belief network to achieve a rapid assessment of static voltage stability risk. Assuming the sample set is [u,γ], the mathematical model of the l-layer deep belief network can be simplified as:

[0111]

[0112] where O(·) is the output function of the fully connected layer, and M(·) is the activation function of the hidden layer; ρ and b represent the weight and bias of the deep belief network. The loss function of the deep belief network can be defined as the weighted sum of the estimation error and the L2 norm:

[0113]

[0114] Finally, the above equation is solved by training and fine-tuning the deep belief network model. After training, the calculation of the static voltage stability risk assessment index of the power system will be transformed into the following equation:

[0115]

[0116] Here, χ represents the hyperparameter in the deep belief network.

[0117] In an exemplary embodiment, the method further includes: constructing a static voltage stability control model according to an output result of the static voltage stability risk model.

[0118] Among them, the objective function of the static voltage stability control model is the control cost function, and the control cost includes the cost of the whole generator output control measures, the cost of changing the network topology control measures and the cost of switching capacitor control measures.

[0119] Optionally, a static voltage stability control model for the power system is constructed and the trained deep belief network is embedded, specifically:

[0120] The goal of static voltage stability risk control in power systems is to minimize the cost required to control the voltage stability risk assessment index to the set margin. Therefore, its objective function is expressed as:

[0121] min f=∑c Pi (P Gi )+∑c cn (Q cn )

[0122]

[0123] c cn (Q cn )=c s Q cn / P s

[0124] Where f represents the control objective function; P Gi is the active output of the generator at node i; Qcn is the reactive power compensation of node n; c Pi (·) and c cn (·) represent the cost functions of generator and reactive power compensation respectively; α 1,i , α 2,i and α 3,i is the active output cost coefficient of generator i; c s P is the average cost of a single reactive power compensation switching operation; s The power input by a single reactive power compensation device.

[0125] The constraints include the following parts:

[0126] (1) Power flow equality constraint

[0127]

[0128] Among them, P Li and Q Li represents the active and reactive power of the load at node i; V i is the voltage amplitude of node i; δ ij is the phase angle difference between nodes i and j; Q Gi is the reactive power of generator i; G ij and B ij are the conductance and susceptance between nodes i and j respectively.

[0129] (2) Equipment operation constraints

[0130]

[0131] The max and min subscripts on the upper right of the variable represent the maximum and minimum values ​​of the variable respectively; ij Represents the power flow on line ij; Tr ij Represents the transformer ratio on line ij.

[0132] (3) Static voltage stability constraints

[0133]

[0134] Among them, λ th Indicates the set static voltage stability risk indicator margin.

[0135] Furthermore, the structural expression of the deep belief network is analyzed, its control gradient is derived, and the interior point method is introduced to solve the constructed static voltage stability control model, specifically:

[0136] The constructed static voltage stability control model can be simplified as follows:

[0137]

[0138] Here, g(·) represents the equality constraint of the power system.

[0139] The interior point method is used to solve the problem. First, add the slack variable r = [r1, ..., r n ] T and q=[q1,...,q n ] T Convert h(u) into an equality constraint and introduce the perturbation factor ζ to construct the perturbation function. Use the Lagrange multiplier method to construct the Lagrangian function F L :

[0140]

[0141] Among them, β1, β2 and β3 are Lagrange multipliers. Further, the disturbance factor ζ is calculated by the following formula:

[0142]

[0143] Among them, κ is the central parameter.

[0144] After that, considering the KKT condition and using Newton's method, the matrix form of the modified equation can be derived as:

[0145]

[0146] Among them, FL u , FL β2 , FL β3 , FL ζ r and FL ζ q are the partial derivatives of FL with respect to u, β2, β3, r and q respectively; I represents the identity matrix. The modified values ​​of β2, β3, r and q in each iteration are calculated by the following formula:

[0147]

[0148] As for the static voltage stability constraint, since its risk assessment model is a trained deep belief network, it is impossible to directly calculate the gradient of the inequality constraint with respect to the state variable, and its Jacobian matrix and Hessian matrix need to be analytically derived. As an inequality constraint, the first-order derivative of the static voltage stability constraint is expressed as follows according to the chain derivation rule:

[0149]

[0150] To simplify the formula, define the function Γ l :

[0151]

[0152] in, It can be derived from the following matrix formula:

[0153]

[0154] Therefore, the Jacobian matrix can be simplified as:

[0155]

[0156] Similarly, the Hessian matrix can be simplified as:

[0157]

[0158] Finally, the calculated correction value updates the variable in the following way:

[0159]

[0160] Among them, ε p and ε d Indicates the step size of each update. In addition, the above variables are updated repeatedly until the convergence condition is met, that is, (r T β2-q T β3) is less than the set threshold, the state variable u is output. At this time, the output state variable u is the control result of the static voltage stability.

[0161] The static voltage stability risk assessment method in this embodiment is intended to solve the uncertainty problem in the power system with high penetration rate of new energy and improve the efficiency and accuracy of static voltage stability risk assessment.

[0162] 1) Dealing with the uncertainty of renewable energy output Using improved time series clustering methods, renewable energy output data is classified and aggregated to more accurately capture its output pattern. Asymmetric spline regression technology is used to predict and model renewable energy output to deal with its nonlinear characteristics. Latin hypercube sampling technology is used to generate representative sample sets to fully consider the uncertainty of renewable energy output.

[0163] 2) Construct a fast static voltage stability risk evaluator: A fast static voltage stability risk evaluator is constructed based on a deep belief network (DBN). DBN can learn and simulate complex nonlinear relationships, so it is suitable for predicting static voltage stability risks. By training the DBN model, it can quickly and accurately predict the static voltage stability risk assessment indicators based on the output data of new energy sources.

[0164] 3) Analytically derive the control gradient of the evaluator: Considering the "black box" characteristics of the DBN model, its control gradient, that is, the derivative of the evaluation index with respect to the control variable, is derived by analytical methods. This enables the DBN model to be directly embedded in the static voltage stability optimization model, thereby achieving a tight coupling of mechanism modeling and data modeling.

[0165] 4) Propose a static voltage stability optimization model coupled with the interior point method: Combine the derived control gradient and the interior point method to construct a static voltage stability optimization model. The interior point method is an efficient optimization algorithm suitable for solving optimization problems with constraints, such as voltage stability constraints, generator output constraints, etc. Through the optimization model, the static voltage stability risk of the power system can be minimized while meeting various operation constraints.

[0166] 5) Improve the efficiency of assessment and control: The proposed method realizes the rapid assessment and control of the static voltage stability risk of a high proportion of renewable energy power systems, providing powerful auxiliary opinions and decision-making support for dispatchers. Through the automated and intelligent assessment and control process, work efficiency is improved and labor costs are reduced.

[0167] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0168] Based on the same inventive concept, the embodiment of the present application also provides a static voltage stability risk assessment device for implementing the static voltage stability risk control method of the high-proportion new energy power system involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more static voltage stability risk assessment device embodiments provided below can refer to the limitations of the static voltage stability risk assessment method above, and will not be repeated here.

[0169] In an exemplary embodiment, Figure 3 As shown, a static voltage stability risk assessment device is provided, comprising: an acquisition module 11, an analysis module 12 and an assessment module 14, wherein:

[0170] An acquisition module 11 is used to acquire historical output data of renewable energy sources in the power system at various historical moments;

[0171] An analysis module 12 is used to analyze the historical output data at each historical moment to obtain a static voltage stability index corresponding to each historical output data;

[0172] The evaluation module 13 is used to train the initial model according to the historical output data at each historical moment and the static voltage stability index corresponding to each historical output data to obtain a static voltage stability risk model; wherein the static voltage stability risk model is used to determine the static voltage stability index corresponding to the current output data according to the current output data at the current moment.

[0173] Each module in the above-mentioned static voltage stability risk assessment device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0174] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 4 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a static voltage stability risk control method for a high-proportion new energy power system is implemented.

[0175] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0176] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0177] Obtain historical output data of new energy equipment in the power system at each historical moment;

[0178] Analyze the historical output data at each historical moment to obtain the static voltage stability index corresponding to each historical output data;

[0179] The initial model is trained according to the historical output data at each historical moment and the static voltage stability index corresponding to each historical output data to obtain a static voltage stability risk model; wherein the static voltage stability risk model is used to determine the static voltage stability index corresponding to the current output data according to the current output data at the current moment.

[0180] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0181] Obtain historical output data of new energy equipment in the power system at each historical moment;

[0182] Analyze the historical output data at each historical moment to obtain the static voltage stability index corresponding to each historical output data;

[0183] The initial model is trained according to the historical output data at each historical moment and the static voltage stability index corresponding to each historical output data to obtain a static voltage stability risk model; wherein the static voltage stability risk model is used to determine the static voltage stability index corresponding to the current output data according to the current output data at the current moment.

[0184] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0185] Obtain historical output data of new energy equipment in the power system at each historical moment;

[0186] Analyze the historical output data at each historical moment to obtain the static voltage stability index corresponding to each historical output data;

[0187] The initial model is trained according to the historical output data at each historical moment and the static voltage stability index corresponding to each historical output data to obtain a static voltage stability risk model; wherein the static voltage stability risk model is used to determine the static voltage stability index corresponding to the current output data according to the current output data at the current moment.

[0188] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0189] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0190] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for controlling static voltage stability risk of a high proportion of new energy power system, characterized in that: The method comprises: Obtain historical output data of new energy equipment in the power system at each historical moment; Analyze the historical output data at each historical moment to obtain the static voltage stability index corresponding to each historical output data; The initial model is trained according to the historical output data at each historical moment and the static voltage stability index corresponding to each historical output data to obtain a static voltage stability risk model; wherein the static voltage stability risk model is used to determine the static voltage stability index corresponding to the current output data according to the current output data at the current moment.

2. The method according to claim 1, characterized in that The obtaining of historical output data of new energy equipment in the power system at each historical moment includes: Determine a typical scenario set of the power system according to historical output data of new energy equipment in the power system at various historical moments; For any typical scenario set, determine the sample output data corresponding to the typical scenario set according to the historical output data and predicted output data corresponding to the typical scenario set; The sample output data corresponding to each typical scenario set are analyzed to obtain the static voltage stability index corresponding to each historical output data.

3. The method according to claim 2, characterized in that Determining the sample output data corresponding to the typical scene set according to the historical output data and the predicted output data corresponding to the typical scene set includes: Determine prediction error data based on historical output data and predicted output data corresponding to the typical scenario set; The asymmetric spline regression model is used to fit the prediction error data to obtain the error sample set; Latin hypercube sampling is used to sample the error sample set to obtain sample output data corresponding to the typical scenario set.

4. The method according to claim 2, characterized in that: The sample output data corresponding to each typical scenario set is analyzed to obtain the static voltage stability index corresponding to each historical output data, including: The continuous power flow method is used to analyze the sample output data corresponding to each typical scenario set, and the static voltage stability index corresponding to each historical output data is obtained.

5. The method according to claim 2, characterized in that: Determining a typical scenario set of the power system according to the historical output data at historical moments includes: The time series clustering method is used to analyze the historical output data at historical moments to obtain a typical scenario set of the power system.

6. The method according to claim 1, characterized in that The method further comprises: Constructing a static voltage stability control model according to the output result of the static voltage stability risk model; Among them, the objective function of the static voltage stability control model is a control cost function, and the control cost includes the cost of the whole generator output control measure, the cost of the network topology change control measure and the cost of the capacitor switching control measure.