Power system control method and device based on extreme event uncertainty, computer equipment, readable storage medium and program product

Abstract

The invention relates to a power system control method and device based on extreme event uncertainty, computer equipment, a readable storage medium and a program product. The method comprises the following steps: acquiring historical data of an extreme event, and determining an initial uncertainty set according to the historical data; in the ith round, obtaining a sample generation amount, and selecting a predicted value corresponding to the uncertainty variable from the initial uncertainty set according to the sample generation amount to obtain a plurality of sample points; selecting a plurality of target sample points from the plurality of sample points based on a preset percentage threshold, and obtaining an intermediate uncertainty set based on predicted values corresponding to the plurality of target sample points; performing performance evaluation on the intermediate uncertainty set, and if a first preset condition is met, taking the intermediate uncertainty set as an uncertainty set; and using the uncertainty set to control the operation of the power system. By adopting the method, load uncertainty and unit operation uncertainty caused by extreme events in a power system can be solved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device, computer equipment, readable storage medium and program product for controlling a power system based on uncertainty of extreme events. Background Art

[0002] Among the challenges facing the current global power system, in addition to the uncertainty and volatility brought about by the rapid integration of renewable energy, extreme events such as fires also pose additional uncertainties to the load and unit operation of the power system. These extreme events not only increase the complexity of power system management and optimization, but also pose new challenges to traditional optimal power flow methods.

[0003] In traditional technologies, although scenario optimization methods can cope with uncertainty by presetting multiple scenarios, their high computational cost and insufficient coverage of extreme events limit their practical application. Although the chance-constrained optimization method provides a certain degree of flexibility, it relies on specific probability distribution assumptions and cannot accurately reflect the actual impact of extreme events such as fires. Although existing robust optimization methods have advantages in computational efficiency, their overly conservative characteristics may lead to unnecessary conservative measures in the face of extreme events such as fires, affecting the performance of the power system.

[0004] Therefore, it is urgent to propose a method that can solve the load uncertainty and unit operation uncertainty caused by extreme events in the power system. Summary of the invention

[0005] Based on this, it is necessary to provide a power system control method, device, computer equipment, readable storage medium and program product based on extreme event uncertainty, which can solve the load uncertainty and unit operation uncertainty caused by extreme events in the power system in response to the above technical problems.

[0006] In a first aspect, the present application provides a power system control method based on extreme event uncertainty, the method comprising:

[0007] Obtain historical data of extreme events, and determine an initial uncertainty set based on the historical data; wherein the predicted values ​​corresponding to the uncertainty variables in the initial uncertainty set form a geometric figure;

[0008] In the i-th round, the sample generation amount is obtained, and the prediction value corresponding to the uncertainty variable is selected from the initial uncertainty set according to the sample generation amount to obtain multiple sample points; wherein i is greater than or equal to 1;

[0009] Selecting a plurality of target sample points from the plurality of sample points based on a preset percentage threshold, and obtaining an intermediate uncertainty set based on prediction values ​​corresponding to the plurality of target sample points;

[0010] The performance of the intermediate uncertainty set is evaluated. If the first preset condition is met, the intermediate uncertainty set is used as the uncertainty set. If the first preset condition is not met, the step of returning to re-execute the step of obtaining the sample generation amount and selecting the predicted value corresponding to the uncertainty variable from the initial uncertainty set according to the sample generation amount to obtain multiple sample points is performed until the intermediate uncertainty set meets the first preset condition.

[0011] Controlling the operation of power systems using uncertainty sets.

[0012] In one embodiment, selecting a plurality of target sample points from a plurality of sample points based on a preset percentage threshold comprises:

[0013] Calculate the center point of the geometric figure composed of multiple sample points to obtain the sample center point;

[0014] Calculate the distance from each sample point to the sample center point;

[0015] Based on a preset percentage threshold and the distance between each sample point and the sample center point, multiple target sample points are selected from the multiple sample points.

[0016] In one embodiment, based on a preset percentage threshold and the distance between each sample point and the sample center point, a plurality of target sample points are selected from a plurality of sample points, including:

[0017] Sort multiple sample points based on the distance from each sample point to the sample center point;

[0018] Calculate the product of the number of sample points and the preset percentage threshold to obtain a first sample total;

[0019] Select sample points with smaller distances and the same number as the total number of the first samples from the sorting results as multiple target sample points.

[0020] In one embodiment, obtaining the sample generation amount includes:

[0021] Determining the second sample population based on statistical parameters; the statistical parameters include a confidence level and a tolerance for violation of the optimization condition;

[0022] Determine a plurality of initial sample generation quantities that meet a second preset condition based on the second sample total quantity;

[0023] The minimum value is selected from multiple initial sample generation amounts as the sample generation amount.

[0024] In one embodiment, the performance evaluation of the intermediate uncertainty set includes:

[0025] Obtaining a first objective function value based on the intermediate uncertainty set, and obtaining a second objective function value based on the initial uncertainty set;

[0026] Determine the performance indicator range based on the intermediate uncertainty set and the initial uncertainty set;

[0027] The ratio of the first objective function value to the second objective function value is used as a competition ratio;

[0028] If the competition ratio is within the performance index range, the first preset condition is met;

[0029] If the contention ratio is outside the performance index range, the first preset condition is not met.

[0030] In one embodiment, for each uncertainty variable, when the value range of the uncertainty variable in the intermediate uncertainty set is less than or equal to the value range in the initial uncertainty set, and the product of the maximum predicted value of the uncertainty variable in the intermediate uncertainty set and the maximum predicted value of the uncertainty variable in the initial uncertainty set is greater than zero, the performance indicator range is determined based on the intermediate uncertainty set and the initial uncertainty set, including:

[0031] When the minimum predicted value of the uncertainty variable in the initial uncertainty set is less than zero, for each uncertainty variable, the ratio of the maximum predicted value of the uncertainty variable in the intermediate uncertainty set to the maximum predicted value in the initial uncertainty set is calculated to obtain a first ratio corresponding to the uncertainty variable, and the ratio of the minimum predicted value of the uncertainty variable in the intermediate uncertainty set to the minimum predicted value in the initial uncertainty set is calculated to obtain a second ratio corresponding to the uncertainty variable;

[0032] Selecting a maximum value from the first ratios corresponding to the plurality of uncertainty variables and the second ratios corresponding to the plurality of uncertainty variables as an upper bound of the performance indicator;

[0033] When the minimum predicted value of the uncertainty variable in the initial uncertainty set is greater than or equal to zero, for each uncertainty variable, the ratio of the maximum predicted value of the uncertainty variable in the intermediate uncertainty set to the maximum predicted value in the initial uncertainty set is calculated to obtain a first ratio corresponding to the uncertainty variable; the maximum ratio is selected from the first ratios corresponding to the multiple uncertainty variables as the upper bound of the performance indicator;

[0034] The result obtained by multiplying the predicted value in the initial uncertainty set belongs to the value of the intermediate uncertainty set and is used as the lower bound of the initial performance indicator; when there are multiple lower bounds of the initial performance indicator, the maximum value is selected from the multiple lower bounds of the initial performance indicator as the lower bound of the performance indicator; when there is only one lower bound of the initial performance indicator, the lower bound of the initial performance indicator is used as the lower bound of the performance indicator;

[0035] According to the upper bound and the lower bound of the performance indicator, the performance indicator range is obtained.

[0036] In a second aspect, the present application further provides a power system control device based on extreme event uncertainty, the device comprising:

[0037] A first determination module is used to obtain historical data of extreme events and determine an initial uncertainty set based on the historical data; wherein the predicted values ​​corresponding to the uncertainty variables in the initial uncertainty set form a geometric figure;

[0038] A selection module is used to obtain the sample generation amount in the i-th round, and select the prediction value corresponding to the uncertainty variable from the initial uncertainty set according to the sample generation amount to obtain multiple sample points; wherein i is greater than or equal to 1;

[0039] A second determination module is used to select a plurality of target sample points from the plurality of sample points based on a preset percentage threshold, and obtain an intermediate uncertainty set based on the prediction values ​​corresponding to the plurality of target sample points;

[0040] A performance evaluation module is used to perform performance evaluation on the intermediate uncertainty set. If the first preset condition is met, the intermediate uncertainty set is used as the uncertainty set; if the first preset condition is not met, the module returns to re-execute the steps of obtaining the sample generation amount and selecting the predicted value corresponding to the uncertainty variable from the initial uncertainty set according to the sample generation amount to obtain multiple sample points, until the intermediate uncertainty set meets the first preset condition;

[0041] A control module is used to control the operation of the power system using the uncertainty set.

[0042] In one of the embodiments, the second determination module is specifically used to calculate the center point of a geometric figure formed by multiple sample points to obtain a sample center point; calculate the distance from each sample point to the sample center point; and select multiple target sample points from multiple sample points based on a preset percentage threshold and the distance from each sample point to the sample center point.

[0043] In one embodiment, the second determination module is specifically used to sort multiple sample points based on the distance from each sample point to the sample center point; calculate the product of the number of sample points and a preset percentage threshold to obtain a first total sample amount; and select sample points with a smaller distance and the same number as the first total sample amount from the sorting results as multiple target sample points.

[0044] In one embodiment, the selection module is specifically used to determine the second sample total amount based on statistical parameters; the statistical parameters include confidence level and optimization condition violation tolerance; based on the second sample total amount, determine multiple initial sample generation amounts that meet the second preset condition; and select the minimum value from the multiple initial sample generation amounts as the sample generation amount.

[0045] In one embodiment, the performance evaluation module is specifically used to obtain a first objective function value based on an intermediate uncertainty set, and to obtain a second objective function value based on an initial uncertainty set; to determine a performance indicator range based on the intermediate uncertainty set and the initial uncertainty set; to use a ratio of the first objective function value to the second objective function value as a competition ratio; if the competition ratio is within the performance indicator range, the first preset condition is met; if the competition ratio is outside the performance indicator range, the first preset condition is not met.

[0046] In one of the embodiments, for each uncertainty variable, when the value range of the uncertainty variable in the intermediate uncertainty set is less than or equal to the value range in the initial uncertainty set, and the product of the maximum predicted value of the uncertainty variable in the intermediate uncertainty set and the maximum predicted value of the uncertainty variable in the initial uncertainty set is greater than zero, the performance evaluation module is specifically used to calculate, for each uncertainty variable, the ratio of the maximum predicted value of the uncertainty variable in the intermediate uncertainty set to the maximum predicted value in the initial uncertainty set when the minimum predicted value of the uncertainty variable in the initial uncertainty set is less than zero, to obtain a first ratio corresponding to the uncertainty variable, and calculate the ratio of the minimum predicted value of the uncertainty variable in the intermediate uncertainty set to the minimum predicted value in the initial uncertainty set to obtain a second ratio corresponding to the uncertainty variable; from the first ratios and The maximum value is selected from the second ratios corresponding to multiple uncertainty variables as the upper bound of the performance indicator; when the minimum predicted value of the uncertainty variable in the initial uncertainty set is greater than or equal to zero, for each uncertainty variable, the ratio of the maximum predicted value of the uncertainty variable in the intermediate uncertainty set to the maximum predicted value in the initial uncertainty set is calculated to obtain the first ratio corresponding to the uncertainty variable; the maximum ratio is selected from the first ratios corresponding to multiple uncertainty variables as the upper bound of the performance indicator; the result of multiplying the predicted value in the initial uncertainty set belongs to the value of the intermediate uncertainty set, which is used as the lower bound of the initial performance indicator; when there are multiple lower bounds of the initial performance indicator, the maximum value is selected from the multiple initial performance indicator lower bounds as the lower bound of the performance indicator; when there is one initial performance indicator lower bound, the initial performance indicator lower bound is used as the lower bound of the performance indicator; according to the upper bound and the lower bound of the performance indicator, the performance indicator range is obtained.

[0047] In a third aspect, the present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the methods described in the first aspect when executing the computer program.

[0048] 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 steps of any one of the methods described in the first aspect are implemented.

[0049] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of any one of the methods described in the first aspect.

[0050] The above-mentioned power system control method, device, computer equipment, readable storage medium and program product based on extreme event uncertainty obtain historical data of extreme events and determine an initial uncertainty set based on the historical data; wherein the predicted values ​​corresponding to the uncertainty variables in the initial uncertainty set constitute a geometric figure; in the i-th round, obtain the sample generation amount, and select the predicted values ​​corresponding to the uncertainty variables from the initial uncertainty set according to the sample generation amount to obtain multiple sample points; wherein i is greater than or equal to 1; select multiple target sample points from the multiple sample points based on a preset percentage threshold, and obtain an intermediate uncertainty set based on the predicted values ​​corresponding to the multiple target sample points; perform performance evaluation on the intermediate uncertainty set, and if the first preset condition is met, use the intermediate uncertainty set as the uncertainty set; if the first preset condition is not met, return to re-execute the steps of obtaining the sample generation amount, and select the predicted values ​​corresponding to the uncertainty variables from the initial uncertainty set according to the sample generation amount to obtain multiple sample points, until the obtained intermediate uncertainty set meets the first preset condition; use the uncertainty set to control the operation of the power system. In this way, based on the method of selecting multiple target sample points from multiple sample points based on a preset percentage threshold and then obtaining the uncertainty set, it is achieved that the uncertainty set only retains part of the historical data. Compared with the method of taking all historical data as the uncertainty set, it can not only effectively deal with uncertainty, but also avoid over-protection, thereby solving the problems of load uncertainty and unit operation uncertainty caused by extreme events in the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] 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.

[0052] FIG1 is an application environment diagram of a power system control method based on extreme event uncertainty in one embodiment;

[0053] FIG2 is a flow chart of a power system control method based on uncertainty of extreme events in one embodiment;

[0054] FIG3 is a schematic diagram of a flow chart of a method for acquiring target sample points in one embodiment;

[0055] FIG4 is a schematic diagram of a flow chart of a method for obtaining a sample generation amount in one embodiment;

[0056] FIG5 is a schematic diagram of a flow chart of a method for performing performance evaluation on an intermediate uncertainty set in one embodiment;

[0057] FIG6 is a structural block diagram of a power system control device based on extreme event uncertainty in one embodiment;

[0058] FIG. 7 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0059] 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 herein are only used to explain the present application and are not used to limit the present application.

[0060] Before introducing the specific embodiments of the present application, the professional terms involved in the present application are explained first:

[0061] Optimal power flow: is a mathematical programming problem whose goal is to optimize one or more objective functions while satisfying the physical and operational constraints of the power system. These objective functions usually include minimizing the cost of power generation, improving system reliability, reducing losses, etc. Optimal power flow takes into account various constraints in the power system, such as: output limitations of generators, capacity limitations of transmission lines, stability of node voltages, minimization of system losses, and other operational constraints.

[0062] Robust optimization: Robust optimization is a mathematical programming method that seeks an optimal solution or strategy that works in the worst case when faced with uncertainty and variability. This method takes into account the range of possible parameter variations and, unlike classical optimization methods, does not assume that all parameters are certain. Robust optimization defines an uncertainty set that encompasses all possible parameter variations and evaluates the objective function in the worst case, usually a minimization problem, such as minimizing the maximum cost or maximizing the minimum benefit. It attempts to find a balance between conservatism (ensuring that it works in all cases) and efficiency (getting as close to the optimal solution as possible when uncertainty is small). Robust optimization has applications in many fields, including financial investment, supply chain management, and energy system planning. In particular, in decision-making problems that are sensitive to uncertainty, it provides a protective strategy that maintains the effectiveness of the solution even when uncertainty occurs. Compared with stochastic optimization, robust optimization does not rely on probabilistic models, but ensures the robustness of the solution by considering the worst case of uncertainty.

[0063] Uncertainty set: In robust optimization, the uncertainty set is a core concept that defines the range of all parameter variations that may affect the results of the optimization problem, including uncertain factors such as cost, demand, and resource availability. The design of this uncertainty set must be based on reality and conservative enough to ensure the feasibility of the solution under any circumstances. It needs to be of moderate size to avoid excessive computational complexity while ensuring that the problem is solvable. In addition, the uncertainty set should be flexible, able to adapt to different types of uncertainty, and designed to be flexible enough to adjust based on new information or feedback. The goal of robust optimization is to find a solution under the worst-case objective of all possible situations within the uncertainty set, and to meet performance requirements even in the most unfavorable situations, thereby providing a protection strategy to deal with the risks brought by uncertainty.

[0064] Among the challenges facing the current global power system, in addition to the uncertainty and volatility brought about by the rapid integration of renewable energy, extreme events such as fires also pose additional uncertainties to the load and unit operation of the power system. These extreme events not only increase the complexity of power system management and optimization, but also pose new challenges to traditional optimal power flow methods, as these methods are usually based on the assumption that energy supply is relatively stable and predictable.

[0065] In order to deal with various sources of uncertainty, including fire, the power industry is actively researching and developing new optimization technologies. These technologies need to be able to quickly adapt and maintain system stability and efficiency in the face of emergencies. Although methods such as scenario optimization, chance-constrained optimization, and robust optimization have made some progress in dealing with the uncertainty of renewable energy, they are still insufficient in dealing with extreme events such as fire.

[0066] Among them, although the scenario optimization method can cope with uncertainty by presetting multiple scenarios, its high computational cost and insufficient coverage of extreme events limit its application in practice. Although the chance-constrained optimization method provides a certain degree of flexibility, it relies on specific probability distribution assumptions and cannot accurately reflect the actual impact of extreme events such as fires. Although the existing robust optimization methods have advantages in computational efficiency, their overly conservative characteristics may lead to unnecessary conservative measures in the face of extreme events such as fires, affecting the performance of the power system.

[0067] Therefore, it is urgent to propose a method that can solve the load uncertainty and unit operation uncertainty caused by extreme events in the power system. The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0068] It should be noted that the beneficial effects brought about by the embodiments of the present application or the technical problems solved are not limited to this one, but may also include other implicit or related problems. For details, please refer to the description of the following embodiments.

[0069] The power system control method based on extreme event uncertainty provided in the embodiment of the present application can be applied in the application environment shown in FIG1 . The terminal 102 communicates with the server 104 through a network. The data storage system can store data that the server 104 needs to process. The data storage system can be integrated on the server 104, or placed on the cloud or other network servers. Server 104 obtains historical data of extreme events, and determines an initial uncertainty set based on the historical data; wherein the predicted values ​​corresponding to the uncertainty variables in the initial uncertainty set form a geometric figure; in the i-th round, the sample generation amount is obtained, and the predicted values ​​corresponding to the uncertainty variables are selected from the initial uncertainty set according to the sample generation amount to obtain multiple sample points; wherein i is greater than or equal to 1; multiple target sample points are selected from the multiple sample points based on a preset percentage threshold, and an intermediate uncertainty set is obtained based on the predicted values ​​corresponding to the multiple target sample points; the performance of the intermediate uncertainty set is evaluated, and if the first preset condition is met, the intermediate uncertainty set is used as the uncertainty set; if the first preset condition is not met, the step of returning to re-execute the step of obtaining the sample generation amount, and selecting the predicted values ​​corresponding to the uncertainty variables from the initial uncertainty set according to the sample generation amount to obtain multiple sample points, until the intermediate uncertainty set obtained meets the first preset condition; and the uncertainty set is used to control the operation of the power system.

[0070] The terminal 102 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart car devices, projection devices, etc. Portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. Head-mounted devices may be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. The server 104 may be an independent physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides cloud computing services.

[0071] In an exemplary embodiment, as shown in FIG2 , a power system control method based on extreme event uncertainty is provided, which is described by taking the method applied to the server in FIG1 as an example, and includes the following steps:

[0072] Step 201, obtain historical data of extreme events, and determine an initial uncertainty set based on the historical data; wherein the predicted values ​​corresponding to the uncertainty variables in the initial uncertainty set form a geometric figure.

[0073] The extreme event may be a fire event. In the case where the extreme event is a fire event, the historical data refers to historical data related to the fire, such as the speed of fire development, the area that may be affected, and the location of key infrastructure.

[0074] Optionally, the server receives historical data of extreme events sent by the terminal, processes the historical data, and obtains the value ranges of different uncertainty variables, that is, obtains the changes of different uncertainty variables. For each uncertainty variable, each value within the value range of the uncertainty variable is used as the predicted value of the uncertainty variable. All predicted values ​​of all uncertainty variables constitute the initial uncertainty set. It should be noted that uncertainty variables can be, for example, the speed of fire development, the area that may be affected, and the location of critical infrastructure.

[0075] Coordinates are assigned to each predicted value of each uncertainty variable using preset rules, so that all predicted values ​​in the initial uncertainty set can form a geometric figure, which can be three-dimensional or two-dimensional, depending on the type of coordinates assigned to the predicted values.

[0076] Step 202, in the i-th round, obtain the sample generation amount, and select the predicted value corresponding to the uncertainty variable from the initial uncertainty set according to the sample generation amount to obtain multiple sample points; wherein i is greater than or equal to 1.

[0077] The sample generation amount refers to the number of prediction values ​​selected from the initial uncertainty set. The sample generation amount can be sent by the terminal to the server, that is, specified, or calculated by the server based on statistical parameters.

[0078] Optionally, after obtaining the sample generation amount, multiple prediction values ​​are randomly selected from the initial uncertainty set, and the number of the selected prediction values ​​is the sample generation amount. Since each prediction value is assigned a corresponding coordinate, the coordinates corresponding to the selected prediction values ​​can be regarded as sample points.

[0079] Step 203 , selecting a plurality of target sample points from the plurality of sample points based on a preset percentage threshold, and obtaining an intermediate uncertainty set based on the prediction values ​​corresponding to the plurality of target sample points.

[0080] The preset percentage threshold refers to a preset fixed value, such as 98%.

[0081] Optionally, the product of the number of sample points and the preset percentage threshold is calculated to obtain the first total sample amount, and the first total sample amount sample points can be randomly selected from multiple sample points, and the first total sample amount sample points randomly selected are used as multiple target sample points, or the first total sample amount sample points can be selected from multiple sample points according to a preset rule, and the first total sample amount sample points selected according to the preset rule are used as multiple target sample points. Then, the predicted values ​​corresponding to all target sample points are directly used as elements in the intermediate uncertainty set.

[0082] Step 204, perform performance evaluation on the intermediate uncertainty set. If the first preset condition is met, the intermediate uncertainty set is used as the uncertainty set. If the first preset condition is not met, return to re-execute the step of obtaining the sample generation amount, and select the predicted value corresponding to the uncertainty variable from the initial uncertainty set according to the sample generation amount to obtain multiple sample points, until the intermediate uncertainty set meets the first preset condition.

[0083] Optionally, a first objective function value is obtained based on an intermediate uncertainty set, and a second objective function value is obtained based on an initial uncertainty set; a performance index range is determined based on the intermediate uncertainty set and the initial uncertainty set; a ratio of the first objective function value to the second objective function value is used as a competition ratio; if the competition ratio is within the performance index range, the first preset condition is satisfied; if the competition ratio is outside the performance index range, the first preset condition is not satisfied. It can be understood that the first preset condition refers to the competition ratio being within the performance index range.

[0084] When the first preset condition is met, the intermediate uncertainty set is directly used as the uncertainty set. When the first preset condition is not met, the process returns to step 202 until the obtained intermediate uncertainty set meets the first preset condition.

[0085] In addition, in each of the above rounds, the server also calculates the gradient information corresponding to the uncertainty variables, thereby updating parameters such as weights in the objective function.

[0086] Step 205: Control the operation of the power system using the uncertainty set.

[0087] Optionally, the predicted values ​​in the uncertainty set are input into the objective function to obtain the objective function value, and the operation of the power system is controlled based on the objective function value.

[0088] The above-mentioned power system control method based on extreme event uncertainty obtains historical data of extreme events and determines an initial uncertainty set based on the historical data; wherein the predicted values ​​corresponding to the uncertainty variables in the initial uncertainty set constitute a geometric figure; in the i-th round, the sample generation amount is obtained, and the predicted values ​​corresponding to the uncertainty variables are selected from the initial uncertainty set according to the sample generation amount to obtain multiple sample points; wherein i is greater than or equal to 1; multiple target sample points are selected from the multiple sample points based on a preset percentage threshold, and an intermediate uncertainty set is obtained based on the predicted values ​​corresponding to the multiple target sample points; the performance of the intermediate uncertainty set is evaluated, and if the first preset condition is met, the intermediate uncertainty set is used as the uncertainty set; if the first preset condition is not met, the step of returning to re-execute the step of obtaining the sample generation amount, and selecting the predicted values ​​corresponding to the uncertainty variables from the initial uncertainty set according to the sample generation amount to obtain multiple sample points, until the obtained intermediate uncertainty set meets the first preset condition; and the uncertainty set is used to control the operation of the power system. In this way, based on the method of selecting multiple target sample points from multiple sample points based on a preset percentage threshold and then obtaining the uncertainty set, it is achieved that the uncertainty set only retains part of the historical data. Compared with the method of taking all historical data as the uncertainty set, it can not only effectively deal with uncertainty, but also avoid over-protection, thereby solving the problems of load uncertainty and unit operation uncertainty caused by extreme events in the power system.

[0089] In an exemplary embodiment, as shown in FIG3 , a method for acquiring a target sample point is provided, wherein a plurality of target sample points are selected from a plurality of sample points based on a preset percentage threshold, and the method comprises:

[0090] Step 301, calculate the center point of a geometric figure formed by multiple sample points to obtain a sample center point.

[0091] From the above, we can know that the sample points are coordinates, so multiple sample points can form a geometric figure. Then, by calculating the center point of the geometric figure, we can get the sample center point.

[0092] Step 302, calculating the distance from each sample point to the sample center point.

[0093] The method for calculating the distance between two points is well known and will not be described in detail here.

[0094] Step 303 : Select multiple target sample points from the multiple sample points based on a preset percentage threshold and the distance between each sample point and the sample center point.

[0095] Optionally, multiple sample points are sorted based on the distance from each sample point to the sample center point; the product of the number of sample points and a preset percentage threshold is calculated to obtain a first total sample amount; and sample points with a smaller distance and the same number as the first total sample amount are selected from the sorting results as multiple target sample points.

[0096] For example, the preset percentage threshold is 50%, the number of sample points is 6, the distance from sample point 1 to the sample center point is 7, the distance from sample point 2 to the sample center point is 5, the distance from sample point 3 to the sample center point is 9, the distance from sample point 4 to the sample center point is 1, the distance from sample point 5 to the sample center point is 10, and the distance from sample point 6 to the sample center point is 6. The sorting result of multiple sample points is: sample point 5>sample point 3>sample point 1>sample point 6>sample point 2>sample point 4. Then the selected target sample points are sample point 6, sample point 2, and sample point 4.

[0097] In an exemplary embodiment, as shown in FIG4 , a method for obtaining a sample generation amount is provided, and obtaining the sample generation amount includes:

[0098] Step 401, determining the second sample population based on statistical parameters; the statistical parameters include a confidence level and an optimization condition violation tolerance.

[0099] Among them, the confidence level and the tolerance for violation of the optimization condition are both pre-given fixed values.

[0100] The calculation formula for determining the second sample size based on statistical parameters is as follows:

[0101]

[0102] in, represents the total amount of the second sample; Indicates the confidence level; The calculation formula for determining the total number of the second sample ensures that, even in the most unfavorable case, the uncertainty set obtained by the sample estimation can be at least 1- The probability of accurately reflects the true uncertainty distribution.

[0103] Step 402: Determine a plurality of initial sample generation quantities that meet a second preset condition based on the second sample total quantity.

[0104] Step 403: Select a minimum value from multiple initial sample generation amounts as the sample generation amount.

[0105] The expression for determining the amount of sample generation is as follows:

[0106]

[0107] in, represents the sample generation amount; r represents the initial sample generation amount, Indicates from The expression for determining the number of samples generated is an inequality based on the binomial distribution, which takes into account the The probability that there will be at least r-1 "successes" (i.e., the frequency of occurrence of a specific uncertainty) in independent trials.

[0108] In this embodiment, by determining the calculation formula of the second total sample amount and the expression for determining the sample generation amount, it is achieved to determine the appropriate second total sample amount and sample generation amount while taking into account the uncertainty and variability of the data, ensuring that the uncertainty set can cover the real uncertainty with a high probability and ensuring the statistical feasibility of the solution to the optimization problem. This method allows for effective quantification and control of uncertainty under limited sample data, thereby improving the reliability and robustness of decision-making.

[0109] In an exemplary embodiment, as shown in FIG5 , a method for performing performance evaluation on an intermediate uncertainty set is provided, and the method for performing performance evaluation on the intermediate uncertainty set includes:

[0110] Step 501, obtaining a first objective function value based on an intermediate uncertainty set, and obtaining a second objective function value based on an initial uncertainty set.

[0111] Optionally, based on the intermediate uncertainty set and the objective function, an optimal objective function value corresponding to the intermediate uncertainty set is obtained, and the optimal objective function value corresponding to the intermediate uncertainty set is used as the first objective function value.

[0112] Based on the initial uncertainty set and the objective function, an optimal objective function value corresponding to the initial uncertainty set is obtained, and the optimal objective function value corresponding to the initial uncertainty set is used as the second objective function value.

[0113] Step 502: Determine a performance indicator range based on the intermediate uncertainty set and the initial uncertainty set.

[0114] Optionally, for each uncertainty variable, when the value range of the uncertainty variable in the intermediate uncertainty set is less than or equal to the value range in the initial uncertainty set, and the product of the maximum predicted value of the uncertainty variable in the intermediate uncertainty set and the maximum predicted value of the uncertainty variable in the initial uncertainty set is greater than zero, the performance indicator range is determined based on the intermediate uncertainty set and the initial uncertainty set, including:

[0115] When the minimum predicted value of the uncertainty variable in the initial uncertainty set is less than zero, for each uncertainty variable, the ratio of the maximum predicted value of the uncertainty variable in the intermediate uncertainty set to the maximum predicted value in the initial uncertainty set is calculated to obtain a first ratio corresponding to the uncertainty variable, and the ratio of the minimum predicted value of the uncertainty variable in the intermediate uncertainty set to the minimum predicted value in the initial uncertainty set is calculated to obtain a second ratio corresponding to the uncertainty variable;

[0116] Selecting a maximum value from the first ratios corresponding to the plurality of uncertainty variables and the second ratios corresponding to the plurality of uncertainty variables as an upper bound of the performance indicator;

[0117] When the minimum predicted value of the uncertainty variable in the initial uncertainty set is greater than or equal to zero, for each uncertainty variable, the ratio of the maximum predicted value of the uncertainty variable in the intermediate uncertainty set to the maximum predicted value in the initial uncertainty set is calculated to obtain a first ratio corresponding to the uncertainty variable; the maximum ratio is selected from the first ratios corresponding to the multiple uncertainty variables as the upper bound of the performance indicator;

[0118] The result obtained by multiplying the predicted value in the initial uncertainty set belongs to the value of the intermediate uncertainty set and is used as the lower bound of the initial performance indicator; when there are multiple lower bounds of the initial performance indicator, the maximum value is selected from the multiple lower bounds of the initial performance indicator as the lower bound of the performance indicator; when there is only one lower bound of the initial performance indicator, the lower bound of the initial performance indicator is used as the lower bound of the performance indicator;

[0119] According to the upper bound and the lower bound of the performance indicator, the performance indicator range is obtained.

[0120] For ease of understanding, the above performance index range process is expressed in mathematical language as follows:

[0121] (1) Characterization of the upper bound of performance indicators

[0122] The upper bound of the performance index is The initial uncertainty set is represented by U and the intermediate uncertainty set is represented by Us Indicates that U and U s are all convex sets, and satisfy the following conditions for all uncertain variables:

[0123] , , and

[0124] when hour, For all and The maximum value in .

[0125] when hour, For all The maximum value in .

[0126] in, represents the uncertainty variable i in the initial uncertainty set, represents the uncertainty variable i in the intermediate uncertainty set, and They represent the minimum and maximum predicted values ​​of the uncertainty variable i in the initial uncertainty set, respectively. and They represent the minimum predicted value and the maximum predicted value of the uncertainty variable i in the intermediate uncertainty set respectively.

[0127] The calculation of this upper bound on the performance metric provides us with a quantitative measure of the maximum potential for performance improvement when considering a set of coupled uncertainties.

[0128] (2) Characterization of the lower bound of performance indicators

[0129] The performance index is lower bounded by express, The following conditions must be met:

[0130]

[0131] in, Represents a positive natural number.

[0132] The performance metric lower bound may be close to zero. By deactivating some constraints, we can obtain a "relaxed" lower bound, where The conditions to be satisfied are proposed under the assumption that the first objective function value and the second objective function value represent the optimal values ​​of the relaxed optimization problem under the corresponding uncertainty sets.

[0133] A reduction in the upper bound of a performance metric reflects an improvement in the minimum performance gain, while a reduction in the "relaxed" lower bound suggests an improvement in the maximum gain from relaxing the problem. Therefore, we can use these bounds as a baseline to optimize the uncertainty set from the data to improve performance gain.

[0134] Step 503: Taking the ratio of the first objective function value to the second objective function value as the competition ratio.

[0135] The competition ratio can be expressed as ,in, represents the first objective function value, Represents the value of the second objective function.

[0136] Step 504: If the contention ratio is within the performance index range, the first preset condition is satisfied; if the contention ratio is outside the performance index range, the first preset condition is not satisfied.

[0137] A lower contention ratio means that the intermediate uncertainty set achieves a better objective function value in the optimization problem, showing potential performance improvement compared to the initial uncertainty set. Specifically, this performance improvement is manifested in that when considering uncertainty, by optimizing the intermediate uncertainty set, a lower objective function value can be obtained, thereby achieving more efficient and robust system operation.

[0138] This approach not only verifies the effectiveness of the proposed algorithm, but also allows us to intuitively demonstrate how fine-tuning the shape and size of the uncertainty set can improve system performance in practical applications. This choice of performance metric provides us with a way to quantify and evaluate the effectiveness and value of optimization strategies when dealing with uncertainty problems.

[0139] In addition, robust optimization plays a vital role in power dispatching under fire conditions, especially in ensuring the stability and reliability of the power system. In emergency situations such as fires, power dispatching faces great challenges, including damage to power facilities, interruption of transmission lines, and drastic changes in load demand. Robust optimization can help the power system maintain efficient and stable operation under such uncertainty. The following are several specific application examples:

[0140] Preventive dispatch: Robust optimization can be applied in preventive dispatch to take into account the impact of possible fires on the power system. By predicting the possible failure of transmission lines or reduction in power generation capacity caused by fires, the power system can adjust the generation plan and transmission path in advance to reduce the possible losses caused by fires.

[0141] Real-time dispatch optimization: When a fire occurs, the real-time dispatch system needs to respond quickly to cope with the sudden imbalance between power supply and demand. Robust optimization algorithms can help find the best combination of power generation and transmission, ensuring the stability and reliability of the power system even when some grid components fail.

[0142] Reserve capacity configuration: Robust optimization can be used to optimize the configuration of reserve capacity to ensure that in emergency situations such as fire, there is sufficient reserve generation capacity to compensate for the power generation or transmission losses caused by the fire, thereby maintaining the normal operation of the power system.

[0143] Network Reconfiguration: Fires may render some transmission lines unavailable. Robust optimization can help grid operators reconfigure the grid in emergency situations by adjusting transmission lines and switch states to find the best path to maintain power supply while taking into account safety constraints of system operation.

[0144] Demand-side management: In situations where fires limit electricity supply, robust optimization can be used to implement demand-side management strategies such as demand response and load shedding to reduce system load and mitigate the risk of supply-demand imbalances.

[0145] Restoration planning: After a fire, the power system needs to be restored to normal operation as quickly as possible. Robust optimization can be applied to restoration planning to speed up the restoration of the power system and reduce economic losses by optimizing resource allocation and scheduling.

[0146] Through these applications, robust optimization provides an effective tool for power dispatching to cope with uncertainties and challenges in extreme situations such as fires, ensuring stable and reliable operation of the power system.

[0147] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned 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 does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can 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 to be 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.

[0148] Based on the same inventive concept, the embodiment of the present application also provides a power system control device based on extreme event uncertainty for implementing the power system control method based on extreme event uncertainty 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 embodiments of the power system control device based on extreme event uncertainty provided below can refer to the limitations of the power system control method based on extreme event uncertainty above, and will not be repeated here.

[0149] In an exemplary embodiment, as shown in FIG6 , a power system control device based on extreme event uncertainty is provided. The power system control device 600 includes: a first determination module 601, a selection module 602, a second determination module 603, a performance evaluation module 604 and a control module 605, wherein:

[0150] The first determination module 601 is used to obtain historical data of extreme events and determine an initial uncertainty set based on the historical data; wherein the predicted values ​​corresponding to the uncertainty variables in the initial uncertainty set form a geometric figure;

[0151] A selection module 602 is used to obtain the sample generation amount in the i-th round, and select the prediction value corresponding to the uncertainty variable from the initial uncertainty set according to the sample generation amount to obtain multiple sample points; wherein i is greater than or equal to 1;

[0152] A second determination module 603 is used to select a plurality of target sample points from the plurality of sample points based on a preset percentage threshold, and obtain an intermediate uncertainty set based on the prediction values ​​corresponding to the plurality of target sample points;

[0153] The performance evaluation module 604 is used to perform a performance evaluation on the intermediate uncertainty set. If the first preset condition is met, the intermediate uncertainty set is used as the uncertainty set; if the first preset condition is not met, the module returns to re-execute the steps of obtaining the sample generation amount and selecting the prediction value corresponding to the uncertainty variable from the initial uncertainty set according to the sample generation amount to obtain multiple sample points, until the intermediate uncertainty set meets the first preset condition.

[0154] The control module 605 is used to control the operation of the power system using the uncertainty set.

[0155] In one embodiment, the second determination module 603 is specifically used to calculate the center point of a geometric figure formed by multiple sample points to obtain a sample center point; calculate the distance from each sample point to the sample center point; and select multiple target sample points from multiple sample points based on a preset percentage threshold and the distance from each sample point to the sample center point.

[0156] In one embodiment, the second determination module 603 is specifically used to sort multiple sample points based on the distance from each sample point to the sample center point; calculate the product of the number of sample points and a preset percentage threshold to obtain a first total sample amount; and select sample points with a smaller distance and the same number as the first total sample amount from the sorting results as multiple target sample points.

[0157] In one embodiment, the selection module 602 is specifically used to determine the second sample total amount based on statistical parameters; the statistical parameters include confidence level and optimization condition violation tolerance; determine multiple initial sample generation amounts that meet the second preset condition based on the second sample total amount; and select the minimum value from the multiple initial sample generation amounts as the sample generation amount.

[0158] In one embodiment, the performance evaluation module 604 is specifically used to obtain a first objective function value based on an intermediate uncertainty set, and to obtain a second objective function value based on an initial uncertainty set; to determine a performance indicator range based on the intermediate uncertainty set and the initial uncertainty set; to use a ratio of the first objective function value to the second objective function value as a competition ratio; if the competition ratio is within the performance indicator range, the first preset condition is met; if the competition ratio is outside the performance indicator range, the first preset condition is not met.

[0159] In one of the embodiments, for each uncertainty variable, when the value range of the uncertainty variable in the intermediate uncertainty set is less than or equal to the value range in the initial uncertainty set, and the product of the maximum predicted value of the uncertainty variable in the intermediate uncertainty set and the maximum predicted value of the uncertainty variable in the initial uncertainty set is greater than zero, the performance evaluation module 604 is specifically used to calculate, for each uncertainty variable, the ratio of the maximum predicted value of the uncertainty variable in the intermediate uncertainty set to the maximum predicted value in the initial uncertainty set when the minimum predicted value of the uncertainty variable in the initial uncertainty set is less than zero, to obtain a first ratio corresponding to the uncertainty variable, and calculate the ratio of the minimum predicted value of the uncertainty variable in the intermediate uncertainty set to the minimum predicted value in the initial uncertainty set to obtain a second ratio corresponding to the uncertainty variable; from the first ratios corresponding to the multiple uncertainty variables The maximum value is selected from the second ratios corresponding to the multiple uncertainty variables as the upper bound of the performance indicator; when the minimum predicted value of the uncertainty variable in the initial uncertainty set is greater than or equal to zero, for each uncertainty variable, the ratio of the maximum predicted value of the uncertainty variable in the intermediate uncertainty set to the maximum predicted value in the initial uncertainty set is calculated to obtain the first ratio corresponding to the uncertainty variable; the maximum ratio is selected from the first ratios corresponding to the multiple uncertainty variables as the upper bound of the performance indicator; the result of multiplying the predicted value in the initial uncertainty set belongs to the value of the intermediate uncertainty set, which is used as the initial performance indicator lower bound; when there are multiple initial performance indicator lower bounds, the maximum value is selected from the multiple initial performance indicator lower bounds as the performance indicator lower bound; when there is one initial performance indicator lower bound, the initial performance indicator lower bound is used as the performance indicator lower bound; according to the performance indicator upper bound and the performance indicator lower bound, the performance indicator range is obtained.

[0160] Each module in the above-mentioned power system control device based on uncertainty of extreme events can be implemented in whole or in part by software, hardware and their combination. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0161] In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in FIG7. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. 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. 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 such as historical data, an initial uncertainty set, an intermediate uncertainty set and an uncertainty set. 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 power system control method based on extreme event uncertainty is implemented.

[0162] Those skilled in the art will understand that the structure shown in FIG. 7 is merely a block diagram of a partial 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 shown in the figure, or combine certain components, or have a different arrangement of components.

[0163] 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 steps of the method described in any one of the above method embodiments are implemented.

[0164] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method described in any one of the above method embodiments are implemented.

[0165] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the steps of the method described in any one of the above method embodiments.

[0166] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0167] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method 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.

[0168] 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.

[0169] 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 power system control method based on uncertainty of extreme events, characterized in that: The method comprises: Obtaining historical data of extreme events, and determining an initial uncertainty set based on the historical data; wherein the predicted values ​​corresponding to the uncertainty variables in the initial uncertainty set form a geometric figure; In the i-th round, a sample generation amount is obtained, and a prediction value corresponding to an uncertainty variable is selected from the initial uncertainty set according to the sample generation amount to obtain a plurality of sample points; wherein i is greater than or equal to 1; Selecting a plurality of target sample points from the plurality of sample points based on a preset percentage threshold, and obtaining an intermediate uncertainty set based on the prediction values ​​corresponding to the plurality of target sample points; Performing a performance evaluation on the intermediate uncertainty set, and if the first preset condition is met, taking the intermediate uncertainty set as the uncertainty set; if the first preset condition is not met, returning to re-execute the step of obtaining the sample generation amount, and selecting the predicted value corresponding to the uncertainty variable from the initial uncertainty set according to the sample generation amount to obtain a plurality of sample points, until the intermediate uncertainty set obtained meets the first preset condition; The uncertainty set is utilized to control operation of the power system.

2. The method according to claim 1, characterized in that The selecting a plurality of target sample points from the plurality of sample points based on a preset percentage threshold comprises: Calculate the center point of a geometric figure formed by a plurality of the sample points to obtain a sample center point; Calculating the distance from each of the sample points to the sample center point; Based on a preset percentage threshold and the distance between each of the sample points and the sample center point, a plurality of target sample points are selected from the plurality of sample points.

3. The method according to claim 2, characterized in that The selecting a plurality of target sample points from the plurality of sample points based on a preset percentage threshold and a distance from each of the sample points to the sample center point comprises: Sorting the plurality of sample points based on the distance from each sample point to the sample center point; Calculate the product of the number of sample points and the preset percentage threshold to obtain a first sample total amount; Select sample points with a smaller distance and the same number as the first total sample amount from the sorting results as the multiple target sample points.

4. The method according to claim 1, characterized in that: The obtaining of sample generation amount comprises: Determining a second sample population based on statistical parameters; the statistical parameters include a confidence level and an optimization condition violation tolerance; Determine a plurality of initial sample generation quantities that meet a second preset condition based on the second sample total quantity; A minimum value is selected from the multiple initial sample generation amounts as the sample generation amount.

5. The method according to claim 1, characterized in that The performing performance evaluation on the intermediate uncertainty set comprises: Obtain a first objective function value based on the intermediate uncertainty set, and obtain a second objective function value based on the initial uncertainty set; Determining a performance indicator range based on the intermediate uncertainty set and the initial uncertainty set; taking the ratio of the first objective function value to the second objective function value as a competition ratio; If the competition ratio is within the performance index range, the first preset condition is met; If the competition ratio is outside the performance indicator range, the first preset condition is not met.

6. The method according to claim 5, characterized in that For each of the uncertainty variables, when the value range of the uncertainty variable in the intermediate uncertainty set is less than or equal to the value range in the initial uncertainty set, and the product of the maximum predicted value of the uncertainty variable in the intermediate uncertainty set and the maximum predicted value of the uncertainty variable in the initial uncertainty set is greater than zero, determining the performance indicator range based on the intermediate uncertainty set and the initial uncertainty set includes: When the minimum predicted value of the uncertainty variable in the initial uncertainty set is less than zero, for each uncertainty variable, the ratio of the maximum predicted value of the uncertainty variable in the intermediate uncertainty set to the maximum predicted value in the initial uncertainty set is calculated to obtain a first ratio corresponding to the uncertainty variable, and the ratio of the minimum predicted value of the uncertainty variable in the intermediate uncertainty set to the minimum predicted value in the initial uncertainty set is calculated to obtain a second ratio corresponding to the uncertainty variable; Selecting a maximum value from the first ratios corresponding to the plurality of uncertainty variables and the second ratios corresponding to the plurality of uncertainty variables as an upper bound of the performance indicator; When the minimum predicted value of the uncertainty variable in the initial uncertainty set is greater than or equal to zero, for each uncertainty variable, the ratio of the maximum predicted value of the uncertainty variable in the intermediate uncertainty set to the maximum predicted value in the initial uncertainty set is calculated to obtain a first ratio corresponding to the uncertainty variable; and the maximum ratio is selected from the first ratios corresponding to the plurality of uncertainty variables as the upper bound of the performance indicator; The result obtained by multiplying the predicted value in the initial uncertainty set belongs to the value of the intermediate uncertainty set, and is used as the initial performance indicator lower bound; when there are multiple initial performance indicator lower bounds, the maximum value is selected from the multiple initial performance indicator lower bounds as the performance indicator lower bound; when there is only one initial performance indicator lower bound, the initial performance indicator lower bound is used as the performance indicator lower bound; The performance indicator range is obtained according to the performance indicator upper bound and the performance indicator lower bound.

7. A power system control device based on uncertainty of extreme events, characterized in that: The device comprises: A first determination module is used to obtain historical data of extreme events and determine an initial uncertainty set based on the historical data; wherein the predicted values ​​corresponding to the uncertainty variables in the initial uncertainty set form a geometric figure; A selection module, used for obtaining a sample generation amount in the i-th round, and selecting a prediction value corresponding to an uncertainty variable from the initial uncertainty set according to the sample generation amount to obtain a plurality of sample points; wherein i is greater than or equal to 1; A second determination module, configured to select a plurality of target sample points from the plurality of sample points based on a preset percentage threshold, and obtain an intermediate uncertainty set based on the prediction values ​​corresponding to the plurality of target sample points; A performance evaluation module is used to perform a performance evaluation on the intermediate uncertainty set. If the first preset condition is met, the intermediate uncertainty set is used as the uncertainty set; if the first preset condition is not met, the module returns to re-execute the steps of obtaining the sample generation amount and selecting the predicted value corresponding to the uncertainty variable from the initial uncertainty set according to the sample generation amount to obtain a plurality of sample points, until the intermediate uncertainty set obtained meets the first preset condition; A control module is used to control the operation of the power system using the uncertainty set.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images