Voltage stability assessment method, system and electronic equipment based on wind-solar complementary characteristics

Abstract

The present invention discloses a voltage stability assessment method, system and electronic device based on the complementary characteristics of wind and solar. The method includes: generating correlation samples of wind and solar output through a pre-constructed Bayesian network model, the Bayesian network model is constructed based on the historical wind and solar load data of the power system, and is used to characterize the correlation between wind power information and photovoltaic information; using Latin hypercube sampling technology to select target samples from the correlation samples; inputting the target samples into a pre-constructed voltage stability analysis model to obtain the corresponding load margin; determining the voltage stability assessment result according to the load margin; wherein the voltage stability analysis model is used to fit the relationship between wind and solar output and load margin according to the random response surface method. The above method can realize efficient probabilistic voltage stability assessment based on complex correlation between wind and solar power by combining Bayesian network and random response surface method, and the obtained voltage stability assessment result is more accurate.

Description

Technical Field

[0001] The present invention relates to the field of power safety technology, and in particular to a voltage stability assessment method, system and electronic equipment based on wind-solar complementary characteristics. Background Art

[0002] In recent years, the deterministic voltage stability assessment system has become mature, but there are still many random factors in the actual operation of the power grid. With the grid connection of new energy units such as wind power and photovoltaic power, which have strong randomness, volatility and intermittency, deterministic research can no longer meet the requirements of random changes in the system.

[0003] Since distributed power sources such as wind power and solar power generation are easily affected by complex factors such as temperature and weather, their impact on the static voltage stability of the power system is often random, uncertain and complexly correlated. However, the existing deterministic voltage stability calculation methods usually only consider the randomness of uncertainty sources such as wind power and photovoltaics, and ignore the complex correlation between uncertainty sources, resulting in large errors in the obtained voltage stability assessment results. Summary of the invention

[0004] In response to the above technical problems, the present invention provides a voltage stability assessment method, system and electronic equipment based on the complementary characteristics of wind and solar power. By combining the Bayesian network with the random response surface method, efficient probabilistic voltage stability assessment based on the complex correlation between wind and solar power is achieved, and the obtained voltage stability assessment results are more accurate.

[0005] In a first aspect, the present invention provides a voltage stability assessment method based on wind-solar complementary characteristics, comprising:

[0006] Generate correlation samples of wind and solar power output through a pre-built Bayesian network model, where the Bayesian network model is built based on historical wind and solar load data of the power system and is used to characterize the correlation between wind power information and photovoltaic information;

[0007] Selecting a target sample from the correlation samples using Latin hypercube sampling technology;

[0008] The target sample is input into a pre-built voltage stability analysis model to obtain a corresponding load margin; a voltage stability assessment result is determined according to the load margin; wherein,

[0009] The voltage stability analysis model is used to fit the relationship between wind and solar power output and load margin according to the random response surface method.

[0010] Optionally, the Bayesian network model is constructed in the following manner:

[0011] Acquire historical wind and solar load data of the power system, wherein the historical wind and solar load data includes wind speed, light intensity and load;

[0012] Determine the cumulative distribution function corresponding to wind speed, light intensity and load by kernel density estimation method, generate uniformly distributed probability values ​​according to the cumulative distribution function, and discretize the probability values;

[0013] The Bayesian network model is constructed using the K2 algorithm according to the probability value after discretization, as well as the preset initial node sequence and the maximum number of parent nodes.

[0014] Optionally, the generation of the wind and solar power output correlation sample by using the pre-built Bayesian network model is specifically as follows:

[0015] Sampling the network nodes of the Bayesian network model to obtain a discrete value matrix;

[0016] Performing an equal-width discretization inverse transformation on the discrete value matrix to obtain a probability value matrix;

[0017] The probability value matrix is ​​calculated using the inverse function of the cumulative distribution function corresponding to the wind speed, light intensity and load to generate a correlation sample of wind and solar power output.

[0018] Optionally, the voltage stability analysis model is constructed in the following manner:

[0019] Establishing the objective function of the voltage stability analysis model based on multi-order Hermite chaotic polynomials, wherein the objective function includes several undetermined parameters;

[0020] The historical wind and solar load data of the power system are sampled through Latin hypercube sampling technology, and the sampling results are converted into wind and solar output data;

[0021] Calculate the maximum load margin corresponding to the wind and solar power output data using the continuous power flow method;

[0022] The objective function is fitted using the wind and solar power output data and the corresponding maximum load margin to determine each of the undetermined parameters in the objective function.

[0023] Optionally, the multi-order Hermite chaotic polynomial is specifically a second-order Hermite chaotic polynomial.

[0024] In a second aspect, the present invention further provides a voltage stability assessment system based on wind-solar complementary characteristics, comprising:

[0025] A target sample generating unit, used to generate a correlation sample of wind and solar power output through a pre-built Bayesian network model, wherein the Bayesian network model is built based on historical wind and solar load data of the power system and is used to characterize the correlation between wind power information and photovoltaic information;

[0026] Selecting a target sample from the correlation samples using Latin hypercube sampling technology;

[0027] A voltage stability evaluation unit is used to input the target sample into a pre-built voltage stability analysis model to obtain a corresponding load margin; and determine a voltage stability evaluation result according to the load margin; wherein,

[0028] The voltage stability analysis model is used to fit the relationship between wind and solar power output and load margin according to the random response surface method.

[0029] Optionally, the Bayesian network model is constructed in the following manner:

[0030] Acquire historical wind and solar load data of the power system, wherein the historical wind and solar load data includes wind speed, light intensity and load;

[0031] Determine the cumulative distribution function corresponding to wind speed, light intensity and load by kernel density estimation method, generate uniformly distributed probability values ​​according to the cumulative distribution function, and discretize the probability values;

[0032] The Bayesian network model is constructed using the K2 algorithm according to the probability value after discretization, as well as the preset initial node sequence and the maximum number of parent nodes.

[0033] Optionally, the voltage stability analysis model is constructed in the following manner:

[0034] Establishing the objective function of the voltage stability analysis model based on multi-order Hermite chaotic polynomials, wherein the objective function includes several undetermined parameters;

[0035] The historical wind and solar load data of the power system are sampled through Latin hypercube sampling technology, and the sampling results are converted into wind and solar output data;

[0036] Calculate the maximum load margin corresponding to the wind and solar power output data using the continuous power flow method;

[0037] The objective function is fitted using the wind and solar power output data and the corresponding maximum load margin to determine each of the undetermined parameters in the objective function.

[0038] In a third aspect, the present invention also provides an electronic device, comprising one or more processors; a memory coupled to the processor, for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the voltage stability assessment method based on the wind-solar complementary characteristics as described in the first aspect.

[0039] Compared with the prior art, the present invention has the following beneficial effects:

[0040] The voltage stability assessment method based on the complementary characteristics of wind and solar power provided by the present invention utilizes multi-dimensional wind and solar power load historical data to construct a Bayesian network model that can accurately and comprehensively characterize the complex correlation of multi-dimensional random variables, so as to generate wind and solar power output simulation samples that conform to the correlation characterization; at the same time, the complex relationship between wind and solar power output and the load margin of the power system is fitted through the random response surface method, so as to obtain the corresponding load margin according to the wind and solar power output simulation samples.

[0041] The above method can not only effectively improve the efficiency of voltage stability calculation, but also obtain more accurate voltage stability evaluation results. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solution of the present invention, the drawings required for use in the implementation mode will be briefly introduced below. Obviously, the drawings described below are only some implementation modes of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0043] Figure 1 It is a flow chart of a voltage stability assessment method based on wind-solar complementary characteristics provided by an embodiment of the present invention;

[0044] Figure 2 It is a structural schematic diagram of a voltage stability assessment system based on wind-solar complementary characteristics provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0045] 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.

[0046] See also Figure 1 In a first aspect, an embodiment of the present invention provides a voltage stability assessment method based on wind-solar complementary characteristics, which specifically includes the following steps.

[0047] S1: Generate correlation samples of wind and solar power output through a pre-built Bayesian network model, where the Bayesian network model is built based on historical wind and solar load data of the power system and is used to characterize the correlation between wind power information and photovoltaic information; select target samples from the correlation samples using Latin hypercube sampling technology.

[0048] In power systems, random sources such as wind power and photovoltaic power often have certain correlations. Accurately simulating the relevant random sources in actual power systems is of great significance for probabilistic voltage stability analysis.

[0049] In this embodiment, the correlation of multi-dimensional random variables is processed by a Bayesian network (BN) to obtain the joint probability distribution of the random variables, and then a Bayesian network model that can characterize the correlation between wind and solar power is established.

[0050] S2: Input the target sample into a pre-built voltage stability analysis model to obtain the corresponding load margin; determine the voltage stability assessment result according to the load margin; wherein the voltage stability analysis model is used to fit the relationship between wind and solar power output and load margin according to the random response surface method.

[0051] In this embodiment, the complex relationship between the input variable (wind and solar power output) and the output variable (load margin) in the voltage stability analysis model is fitted by using the stochastic response surface method (SRSM) using an analytical chaotic polynomial, which can avoid large-scale iterative solution calculations and significantly improve the efficiency of probabilistic voltage stability analysis.

[0052] It can be understood that load margin refers to the total amount of load increase required for the load to increase in a given direction until the voltage collapse point, and can be used to characterize the voltage stability of the power system.

[0053] Voltage stability analysis is an important means to quantify the voltage stability level of the system. Specifically, it refers to the ability of all buses in the power system to continuously maintain an acceptable voltage under rated operating conditions and after disturbances. It can generally be divided into dynamic and static analysis.

[0054] Among them, static voltage stability refers to the ability of the system voltage to maintain or recover to the allowable range without voltage collapse after the system is subjected to a small disturbance. It is mainly used to define the voltage stability reserve under normal system operation and post-accident operation, and is usually evaluated by load margin.

[0055] In the static voltage stability analysis of the power system, the nose point of the PV curve represents the maximum load margin that the system can withstand, also known as the voltage collapse critical point. When the current load margin of the power system exceeds the maximum load margin, the system voltage is in an unstable state.

[0056] The static voltage stability analysis method is based on the system power flow equation. The critical point of voltage stability refers to the point where the system reaches the maximum transmission power in physics, and refers to the question of whether there is a feasible solution to the system power flow in mathematics. The continuous power flow method is usually used for calculation.

[0057] In this embodiment, it is first necessary to establish a Bayesian network model capable of characterizing the wind-solar correlation based on historical wind-solar load data to generate a correlation sample of wind-solar output.

[0058] The construction process of the Bayesian network model is specifically as follows: obtaining historical wind and solar load data of the power system, the historical wind and solar load data including wind speed, light intensity and load. Determining the cumulative distribution function corresponding to wind speed, light intensity and load by kernel density estimation method, generating uniformly distributed probability values ​​according to the cumulative distribution function, and discretizing the probability values.

[0059] Specifically, the cumulative distribution function is expressed as F i (x i ), according to the cumulative distribution function, we can get the probability value u of uniform distribution i , the specific calculation is shown as follows:

[0060]

[0061] Furthermore, the Bayesian network model is constructed by the K2 algorithm according to the probability value after discretization, as well as the preset initial node sequence and the maximum number of parent nodes.

[0062] In this embodiment, the maximum information coefficient (MIC) may be used to determine the quantized correlation values ​​between two random variables, and then determine the initial node order of the BN.

[0063] Since continuous input variables need to obey a specific distribution before they can be input into the Bayesian network, considering that the historical wind and solar load data obtained in this embodiment obeys multiple different complex distributions, it is necessary to calculate the continuous probability value u i Discretization processing is performed.

[0064] Specifically, each probability value u can be discretized by the equal width method. i (l) Convert to discrete values Where l represents the amount of data of the random variable.

[0065] Furthermore, the discrete value As the input data of the Bayesian network, the initial node sequence and the maximum number of parent nodes are given, and the structure is learned through the K2 algorithm. After the DAG structure is obtained, the maximum likelihood estimation method is used for parameter learning to establish a Bayesian network model that includes wind-solar correlation.

[0066] It can be understood that the present embodiment uses the Bayesian network technology to obtain a correlation network of multi-dimensional random variables, and then obtain a joint probability distribution of the multi-dimensional random variables. The modeling process is not only highly accurate, but also faster.

[0067] After completing the construction of the Bayesian network model, the Bayesian network model is used to generate correlation samples that obey the joint probability distribution of multi-dimensional random variables.

[0068] Specifically, the network nodes of the Bayesian network model can be sampled to obtain a discrete value matrix, and then the discrete value matrix can be inversely transformed into an equal-width discretization matrix to obtain a probability value matrix; finally, the probability value matrix can be calculated using the inverse function of the cumulative distribution function corresponding to the wind speed, light intensity and load to generate a correlation sample of wind and solar output.

[0069] In this embodiment, the parent nodes of the Bayesian network model are first sampled, and the child node samples are obtained by linear combination of the parent nodes to obtain a discrete value matrix of the probability of the multidimensional random variable The specific expression is:

[0070] In the above formula, D i represents the number of sampling times, i represents the number of network nodes, Indicates that the i-th node passes through D i The discrete value vector obtained after sampling is express The kth element in Indicates that n nodes pass through D i The discrete value matrix after subsampling.

[0071] Determine the discrete value vector of the i-th node After that, the continuous probability value is obtained by the inverse transformation of equal width discretization Then we get the probability value matrix of m×n dimension Expressed as

[0072] Get the probability value matrix Then, using the cumulative distribution function F i (x i ) Generate correlation samples of wind and solar power outputs that obey the joint probability distribution of multi-dimensional random variables The specific calculation is shown in the following formula:

[0073]

[0074] In this embodiment, the correlation sample of wind and solar power output is obtained through the Bayesian network model. Then, the correlation samples are analyzed based on the Latin hypercube algorithm. Sampling is performed, and the sampled target samples are input into a voltage stability analysis model to perform a probabilistic voltage stability analysis.

[0075] It should be noted that the traditional voltage stability analysis model needs to be repeatedly iterated to obtain the maximum load margin of the power system, which makes the voltage stability analysis process too time-consuming. Therefore, this embodiment uses the random response surface method to construct the voltage stability analysis model, so that the constructed model can avoid large-scale iterative solution calculations, thereby significantly improving the efficiency of probabilistic analysis.

[0076] Specifically, the objective function of the voltage stability analysis model can be established based on the multi-order Hermite chaotic polynomial, and the objective function is expressed as:

[0077]

[0078] The above formula uses the random variable ξ that obeys the standard normal distribution as the standard random variable, where n represents the number of random variables, a0, etc. respectively represent the unknown parameters of the multi-order Hermite chaotic polynomials, H m (ξ1,ξ2,...ξ m ) represents the m-order Hermite polynomial of ξ.

[0079] It should be noted that, when the polynomial order is larger, the fitting accuracy is higher, but there are more parameters to be determined, and the amount of calculation is often greater. This embodiment considers both the calculation efficiency and the fitting accuracy, and sets the second-order Hermite chaos polynomial as the objective function of the voltage stability analysis model, which is specifically expressed as:

[0080]

[0081] In order to determine the objective function of the voltage stability analysis model, it is necessary to solve the unknown parameters a0, a ii and a ij .

[0082] In this embodiment, considering that the random source wind speed and light intensity in the power system obey Weibull distribution and Beta distribution, the conversion relationship between the probability distribution of the random source and the standard random variable distribution can be expressed as:

[0083] X=F -1 (Φ(ξ))

[0084] Among them, F -1 is the inverse function of the cumulative probability distribution function of X, and Φ is the standard normal distribution function.

[0085] Furthermore, in order to solve the unknown parameters in the objective function, the historical wind and solar load data of the power system can be sampled using Latin hypercube sampling technology, and the sampling results can be converted into wind and solar output data. The maximum load margin corresponding to the wind and solar output data is then calculated using continuous power flow, and the objective function is then fitted using the wind and solar output data and the corresponding maximum load margin to estimate the unknown coefficients in the objective function.

[0086] Specifically, since the historical wind and solar load data are wind speed, light intensity and other values, they need to be converted into wind and solar output in the following way, that is, wind power output P W and photovoltaic output P S .

[0087]

[0088] In the above formula, v is the real-time wind speed, v in is the cut-in wind speed, v out is the cut-out wind speed, v N is the rated wind speed, P N is the rated power of the fan, P r is the rated power of the photovoltaic, S and S r They are real-time light intensity and rated light intensity respectively.

[0089] Furthermore, based on the continuation power flow method, the load margin ε can be calculated by the following formula:

[0090]

[0091] Among them, P Li0 and Q Li0 Represent active reference load and reactive reference load respectively, P Gi0 and Q Gi0 The reference quantity representing the active and reactive output of a traditional generator, P Ri and Q Ri Respectively represent the active and reactive power of wind power output and photovoltaic output, K Gi and K Li They represent the multiplier coefficients of load and traditional generator output respectively. The above formula can be solved iteratively by the prediction correction method.

[0092] The maximum value of the load margin ε is expressed as the maximum load margin ε nose , when ε=ε nose The power system is in a critical stable state.

[0093] Furthermore, this embodiment uses the least squares fitting method to estimate the undetermined parameters in the objective function polynomial.

[0094] Specifically, the input-output relationship of the voltage stability analysis model is assumed to be yi =y(X)+δ, and we hope that the residual value δ is infinitely close to zero. Assuming there are n sets of input and output values, the undetermined parameters of the K+1 chaotic polynomial expansions are expressed as β=(β0,β1,...,β K ) T .

[0095] The undetermined parameters can be solved by the following formula:

[0096]

[0097] The optimal solution of the above formula is Where H is represented by:

[0098]

[0099] In this embodiment, after completing the construction of the voltage stability analysis model by determining the various pending parameters, the Latin hypercube algorithm is used to sample the target samples obtained by the Bayesian network model, and the sampling results are input into the constructed voltage stability analysis model to obtain the corresponding load margin, and then the voltage stability evaluation result is determined according to the load margin.

[0100] The above-mentioned embodiment of the present invention utilizes multi-dimensional wind and solar load historical data to construct a Bayesian network model that can accurately and comprehensively characterize the complex correlation of multi-dimensional random variables, so as to generate wind and solar output simulation samples that conform to the correlation characterization; at the same time, the complex relationship between wind and solar output and the load margin of the power system is fitted by the random response surface method, so as to obtain the corresponding load margin according to the wind and solar output simulation samples.

[0101] Compared with the existing technology, the above method can not only effectively improve the efficiency of voltage stability calculation, but also obtain more accurate voltage stability evaluation results.

[0102] See also Figure 2 In a second aspect, another embodiment of the present invention provides a voltage stability assessment system based on wind-solar complementary characteristics, including a target sample generating unit 101 and a voltage stability assessment unit 102 .

[0103] The target sample generation unit 101 is used to generate correlation samples of wind and solar power output through a pre-constructed Bayesian network model. The Bayesian network model is constructed based on historical wind and solar load data of the power system and is used to characterize the correlation between wind power information and photovoltaic information; and Latin hypercube sampling technology is used to select target samples from the correlation samples.

[0104] The voltage stability assessment unit 102 is used to input the target sample into a pre-built voltage stability analysis model to obtain the corresponding load margin; determine the voltage stability assessment result according to the load margin; wherein the voltage stability analysis model is used to fit the relationship between wind and solar power output and load margin according to the random response surface method.

[0105] The information interaction, execution process, etc. between the units in the above-mentioned system are based on the same concept as the embodiment of the voltage stability assessment method based on the wind-solar complementary characteristics of the first aspect of the present invention. The specific contents can be found in the description of the embodiment of the method of the present invention and will not be repeated here.

[0106] In a third aspect, an embodiment of the present invention further provides an electronic device, which may include: one or more processors, and a memory. The memory is coupled to the processor and is used to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the voltage stability assessment method based on the wind-solar complementary characteristics as described in any of the above embodiments, and achieve the technical effect consistent with the above method.

[0107] The processor is used to control the overall operation of the electronic device to complete all or part of the steps of the voltage stability assessment method based on the complementary characteristics of wind and solar. The memory is used to store various types of data to support the operation of the electronic device, and these data may include, for example, instructions for any application or method used to operate on the electronic device, as well as application-related data. The memory can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, disk or optical disk.

[0108] In an exemplary embodiment, the electronic device may be implemented by one or more application specific integrated circuits (Application Specific Integrated Circuit, ASC), digital signal processors (Digital Signal Processor, DSP), digital signal processing devices (Digital Signal Processing Device, DSPD), programmable logic devices (Programmable Logic Device, PLD), field programmable gate arrays (Field Programmable Gate Array, FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned voltage stability assessment method based on wind-solar complementary characteristics and achieve the same technical effect as the above-mentioned method.

[0109] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned voltage stability assessment method based on wind-solar complementary characteristics are implemented. For example, the computer-readable storage medium can be the above-mentioned memory including program instructions, and the above-mentioned program instructions can be executed by a processor of an electronic device to complete the above-mentioned voltage stability assessment method based on wind-solar complementary characteristics, and achieve the same technical effect as the above-mentioned method.

[0110] It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. The terms "first", "second", etc. in the present invention are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "include" and "have" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device comprising a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or devices.

[0111] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0112] The above description is only an implementation mode of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A voltage stability assessment method based on wind-solar complementary characteristics, characterized in that: include: Generate a correlation sample of wind and solar power output through a pre-constructed Bayesian network model, the Bayesian network model is constructed based on the historical wind and solar load data of the power system, and is used to characterize the correlation between wind power information and photovoltaic information; wherein, the generation of the correlation sample of wind and solar power output through the pre-constructed Bayesian network model is specifically as follows: sampling the network nodes of the Bayesian network model to obtain a discrete value matrix; performing an equal-width discretization inverse transformation on the discrete value matrix to obtain a probability value matrix; using the inverse function of the cumulative distribution function corresponding to wind speed, light intensity and load to calculate the probability value matrix, and generate a correlation sample of wind and solar power output; Selecting a target sample from the correlation samples using Latin hypercube sampling technology; The target sample is input into a pre-built voltage stability analysis model to obtain a corresponding load margin; a voltage stability assessment result is determined according to the load margin; wherein, The voltage stability analysis model is used to fit the relationship between wind and solar power output and load margin according to the random response surface method; The Bayesian network model is constructed in the following way: Acquire historical wind and solar load data of the power system, wherein the historical wind and solar load data includes wind speed, light intensity and load; determine the cumulative distribution function corresponding to the wind speed, light intensity and load by the kernel density estimation method, generate uniformly distributed probability values ​​according to the cumulative distribution function, and discretize the probability values; construct the Bayesian network model by the K2 algorithm according to the probability values ​​after discretization, as well as the preset initial node sequence and the maximum number of parent nodes; The voltage stability analysis model is constructed in the following way: The objective function of the voltage stability analysis model is established based on multi-order Hermite chaotic polynomials, and the objective function includes several undetermined parameters; the historical wind and solar load data of the power system are sampled by Latin hypercube sampling technology, and the sampling results are converted into wind and solar output data; the maximum load margin corresponding to the wind and solar output data is calculated by continuous power flow method; the objective function is fitted by using the wind and solar output data and the corresponding maximum load margin to determine each of the undetermined parameters in the objective function.

2. The voltage stability assessment method based on wind-solar complementary characteristics according to claim 1 is characterized in that: The multi-order Hermite chaotic polynomial is specifically a second-order Hermite chaotic polynomial.

3. A voltage stability assessment system based on wind-solar complementary characteristics, characterized in that: include: A target sample generation unit is used to generate correlation samples of wind and solar power outputs through a pre-constructed Bayesian network model, wherein the Bayesian network model is constructed based on historical wind and solar load data of the power system and is used to characterize the correlation between wind power information and photovoltaic information; wherein the generation of correlation samples of wind and solar power outputs through the pre-constructed Bayesian network model is specifically as follows: sampling the network nodes of the Bayesian network model to obtain a discrete value matrix; performing an equal-width discretization inverse transformation on the discrete value matrix to obtain a probability value matrix; calculating the probability value matrix using the inverse function of the cumulative distribution function corresponding to wind speed, light intensity and load to generate correlation samples of wind and solar power outputs; Selecting a target sample from the correlation samples using Latin hypercube sampling technology; A voltage stability evaluation unit is used to input the target sample into a pre-built voltage stability analysis model to obtain a corresponding load margin; and determine a voltage stability evaluation result according to the load margin; wherein, The voltage stability analysis model is used to fit the relationship between wind and solar power output and load margin according to the random response surface method; The Bayesian network model is constructed in the following way: Acquire historical wind and solar load data of the power system, wherein the historical wind and solar load data includes wind speed, light intensity and load; determine the cumulative distribution function corresponding to the wind speed, light intensity and load by the kernel density estimation method, generate uniformly distributed probability values ​​according to the cumulative distribution function, and discretize the probability values; construct the Bayesian network model by the K2 algorithm according to the probability values ​​after discretization, as well as the preset initial node sequence and the maximum number of parent nodes; The voltage stability analysis model is constructed in the following way: The objective function of the voltage stability analysis model is established based on multi-order Hermite chaotic polynomials, and the objective function includes several undetermined parameters; the historical wind and solar load data of the power system are sampled by Latin hypercube sampling technology, and the sampling results are converted into wind and solar output data; the maximum load margin corresponding to the wind and solar output data is calculated by continuous power flow method; the objective function is fitted by using the wind and solar output data and the corresponding maximum load margin to determine each of the undetermined parameters in the objective function.

4. The voltage stability assessment system based on wind-solar complementary characteristics according to claim 3 is characterized in that: The multi-order Hermite chaotic polynomial is specifically a second-order Hermite chaotic polynomial.

5. An electronic device, characterized in that: include, one or more processors; A memory, coupled to the processor, for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the voltage stability assessment method based on wind-solar complementary characteristics as described in any one of claims 1 to 2.

Images