Electric power system operation scene reduction method, system and device and storage medium

Abstract

The invention belongs to the field of electric power automation, and discloses an electric power system operation scene reduction method, system and device and a storage medium, and the method comprises the steps: obtaining a plurality of basic operation scenes of an electric power system; based on the Wasserstein distance between every two basic operation scenes, the basic operation scene with the lowest typicality in the multiple basic operation scenes is deleted one by one till the number of the basic operation scenes reaches a preset number; and based on the Wasserstein distance between every two basic operation scenes, in combination with a fast search and density peak discovery algorithm, identifying extreme scenes in the preset number of basic operation scenes. The Wasserstein distance is adopted to screen typical scenes, so that the representativeness of the scenes after reduction can be enhanced, and redundant scenes are reduced. Meanwhile, the method for identifying the extreme scene in combination with a rapid search and density peak discovery algorithm can reduce misjudgment and missed judgment of important scenes, and can provide an intelligent auxiliary decision-making means for dispatching production personnel, thereby ensuring safe and stable operation of a power system.

Description

Technical Field

[0001] The present invention belongs to the field of electric power automation and relates to a method, system, device and storage medium for reducing operation scenarios of an electric power system. Background Art

[0002] In the process of building a new power system, the gradual increase in the proportion of new energy is an important feature. New energy power generation has strong randomness and uncontrollable characteristics. At the same time, the randomness of load fluctuations is superimposed, resulting in strong randomness and a large number of power system operation scenarios. It is difficult to cope with the challenges of power system dispatching and optimization decision-making under the strong randomness of both the source and the load by relying solely on manual experience. Therefore, in order to ensure the safe and stable operation of the power system under the increasing uncertainty of both the source and the load, it is necessary to study and analyze these uncertain scenarios.

[0003] As an effective tool for describing uncertainty, scenario analysis has been used in recent years to study the uncertainty of power system operation scenarios. It can help decision makers evaluate the risks in power system dispatch and improve the safety of system operation by simulating and analyzing various states or events that may occur in the future. The construction of power system operation scenarios includes three steps: uncertainty modeling, scenario sampling, and scenario reduction. Among them, scenario reduction is an important link in the construction of operation scenarios. By reducing the number of scenarios, the complexity of problem analysis can be effectively reduced. In the process of scenario reduction, the selection of typical scenarios and extreme scenarios is very important. Among them, typical scenarios describe the main operating status of power systems under normal conditions, which helps to understand the normal behavior patterns of power systems. Extreme scenarios describe the operating status of the system under extreme conditions, such as extreme weather or failures, which is crucial for evaluating the robustness and emergency response capabilities of power systems.

[0004] At present, common scene reduction methods include k-means clustering method, simplification method and hierarchical clustering method. However, when using k-means clustering to reduce the initial scene, it is easy to lose the temporal features, and the representativeness of the reduced scene is insufficient; although the simplification method improves the representativeness of the scene, it still does not fully cover all key features; and although the hierarchical clustering method enhances the feature retention effect, it still has the problem of insufficient feature extraction accuracy in complex scenes. The existing methods still have certain defects in ensuring the representativeness of the scene. Summary of the invention

[0005] The purpose of the present invention is to overcome the shortcomings of the above-mentioned prior art and provide a method, system, device and storage medium for reducing power system operation scenarios.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions: In a first aspect, the present invention provides a method for reducing operation scenarios of an electric power system, comprising: obtaining a number of basic operation scenarios of the electric power system; based on the Wasserstein distance between the basic operation scenarios pairwise, deleting the basic operation scenarios with the lowest typicality among the basic operation scenarios one by one until the number of basic operation scenarios reaches a preset number; based on the Wasserstein distance between the basic operation scenarios pairwise, combining a fast search and a density peak discovery algorithm, identifying extreme scenarios among the preset number of basic operation scenarios.

[0007] Optionally, the obtaining of several basic operating scenarios of the power system includes: obtaining several basic operating scenarios of the power system by using a Latin hypercube sampling method.

[0008] Optionally, based on the Wasserstein distance between each pair of basic operating scenarios, deleting the basic operating scenarios with the lowest typicality among several basic operating scenarios one by one until the number of basic operating scenarios reaches a preset number includes: repeating the following reduction steps until the number of basic operating scenarios reaches a preset number; wherein, the reduction step includes: calculating the average Wasserstein distance between each basic operating scenario and the remaining basic operating scenarios based on the Wasserstein distance between each pair of basic operating scenarios among the current several basic operating scenarios, obtaining the typicality of each basic operating scenario, deleting the basic operating scenario with the lowest typicality, and assigning the probability of the deleted basic operating scenario to the remaining basic operating scenarios.

[0009] Optionally, allocating the probability of the deleted basic operation scenario to the remaining current basic operation scenarios includes: evenly allocating the probability of the deleted basic operation scenario to the remaining current basic operation scenarios.

[0010] Optionally, the present algorithm identifies extreme scenarios among a preset number of basic operating scenarios, including: obtaining the local density of each basic operating scenario; wherein the local density is the number of basic operating scenarios whose Wasserstein distance between the current basic operating scenario and the remaining basic operating scenarios is less than a preset cutoff distance; obtaining the degree of separation of each basic operating scenario; wherein, for the basic operating scenario with the largest local density, the degree of separation is the maximum value of the Wasserstein distance between the basic operating scenario and the remaining basic operating scenarios; for the basic operating scenario with a local density not as large as the largest, the degree of separation is the minimum value of the Wasserstein distance between the basic operating scenario and a basic operating scenario with a local density greater than that of the basic operating scenario; based on the local density and degree of separation of each basic operating scenario, a basic operating scenario with a local density lower than a preset local density threshold and a degree of separation higher than a preset degree of separation threshold is selected as the extreme scenario among the preset number of basic operating scenarios.

[0011] Optionally, the method of selecting, according to the local density and degree of separation of each basic operating scenario, a basic operating scenario with a local density lower than a preset local density threshold and a degree of separation higher than a preset degree of separation threshold as an extreme scenario among a preset number of basic operating scenarios includes: according to the local density and degree of separation of each basic operating scenario, using the local density and the degree of separation as the horizontal axis coordinate and the vertical axis coordinate, respectively, to construct an extreme scenario clustering decision diagram; and according to the extreme scenario clustering decision diagram, selecting a basic operating scenario with a local density lower than a preset local density threshold and a degree of separation higher than a preset degree of separation threshold as an extreme scenario among a preset number of basic operating scenarios.

[0012] Optionally, the preset cutoff distance is a preset percentile of the distance distribution of the Wasserstein distance between any two basic operating scenarios.

[0013] According to a second aspect of the present invention, there is provided a system for reducing operation scenarios of an electric power system, comprising: a scenario acquisition module for acquiring a number of basic operation scenarios of an electric power system; a typical scenario screening module for deleting the basic operation scenarios with the lowest typicality from among a number of basic operation scenarios one by one based on the Wasserstein distance between any two basic operation scenarios, until the number of basic operation scenarios reaches a preset number; and an extreme scenario identification module for identifying extreme scenarios from among a preset number of basic operation scenarios based on the Wasserstein distance between any two basic operation scenarios, in combination with a fast search and density peak discovery algorithm.

[0014] According to a third aspect of the present invention, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned power system operation scenario reduction method when executing the computer program.

[0015] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned power system operation scenario reduction method are implemented.

[0016] Compared with the prior art, the present invention has the following beneficial effects: The method for reducing the operation scenarios of the power system of the present invention first deletes the basic operation scenarios with the lowest typicality in a number of basic operation scenarios one by one based on the Wasserstein distance between the basic operation scenarios in pairs, until the number of basic operation scenarios reaches a preset number, and the typical scenarios are screened by using the Wasserstein distance to enhance the representativeness of the scenarios after reduction and reduce redundant scenarios. Then, based on the Wasserstein distance between the basic operation scenarios in pairs, combined with the fast search and density peak discovery algorithms, the extreme scenarios in the preset number of basic operation scenarios are identified, and the extreme scenarios are identified by combining the fast search and density peak discovery algorithms to reduce the misjudgment and omission of important scenarios. It can provide intelligent auxiliary decision-making means for dispatching production personnel, screen the numerous power system operation scenarios caused by the strong uncertainty on both the source and load sides, so as to obtain a limited number of typical scenarios and extreme scenarios, facilitate the decision-making of dispatching production personnel, support intelligent dispatching under the strong uncertainty of the source and load, and thus ensure the safe and stable operation of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a flow chart of a method for reducing power system operation scenarios according to an embodiment of the present invention.

[0018] Figure 2 This is an extreme scenario clustering decision diagram of an embodiment of the present invention.

[0019] Figure 3 This is a structural block diagram of a power system operation scenario reduction system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0020] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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 should fall within the scope of protection of the present invention.

[0021] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0022] The present invention is further described in detail below in conjunction with the accompanying drawings: See also Figure 1 In one embodiment of the present invention, a method for reducing power system operation scenarios is provided, which uses Wasserstein distance to screen typical scenarios, enhances the representativeness of the scenarios after reduction and reduces redundancy; combines fast search with density peak discovery algorithm to identify extreme scenarios, and reduces misjudgment and omission of important scenarios.

[0023] Specifically, the present invention, the method for reducing power system operation scenarios includes the following steps: S1: Obtain several basic operating scenarios of the power system.

[0024] S2: Based on the Wasserstein distance between the basic operating scenarios, the basic operating scenarios with the lowest typicality among several basic operating scenarios are deleted one by one until the number of basic operating scenarios reaches a preset number.

[0025] S3: Based on the Wasserstein distance between two basic operating scenarios, combined with fast search and density peak discovery algorithms, extreme scenarios in a preset number of basic operating scenarios are identified.

[0026] The method for reducing the operation scenarios of the power system of the present invention first deletes the basic operation scenarios with the lowest typicality in a number of basic operation scenarios one by one based on the Wasserstein distance between the basic operation scenarios in pairs, until the number of basic operation scenarios reaches a preset number, and the typical scenarios are screened by using the Wasserstein distance to enhance the representativeness of the scenarios after reduction and reduce redundant scenarios. Then, based on the Wasserstein distance between the basic operation scenarios in pairs, combined with the fast search and density peak discovery algorithms, the extreme scenarios in the preset number of basic operation scenarios are identified, and the extreme scenarios are identified by combining the fast search and density peak discovery algorithms to reduce the misjudgment and omission of important scenarios. It can provide intelligent auxiliary decision-making means for dispatching production personnel, screen the numerous power system operation scenarios caused by the strong uncertainty on both the source and load sides, so as to obtain a limited number of typical scenarios and extreme scenarios, facilitate the decision-making of dispatching production personnel, support intelligent dispatching under the strong uncertainty of the source and load, and thus ensure the safe and stable operation of the power system.

[0027] In a possible implementation manner, the acquiring several basic operation scenarios of the power system includes: acquiring several basic operation scenarios of the power system by using a Latin hypercube sampling method.

[0028] Specifically, after Latin hypercube sampling of the probability models of wind, solar and load, hourly sample data can be obtained, and then the uncertain sample data can be combined to generate a large number of complete basic operating scenarios and obtain the probability of each basic operating scenario.

[0029] In a possible implementation, based on the Wasserstein distance between the basic operating scenarios pairwise, deleting the basic operating scenarios with the lowest typicality among several basic operating scenarios one by one until the number of basic operating scenarios reaches a preset number includes: repeating the following reduction steps until the number of basic operating scenarios reaches a preset number; wherein, the reduction step includes: calculating the average Wasserstein distance between each basic operating scenario and the remaining basic operating scenarios based on the Wasserstein distance between the basic operating scenarios pairwise among the current several basic operating scenarios, obtaining the typicality of each basic operating scenario, deleting the basic operating scenario with the lowest typicality, and assigning the probability of the deleted basic operating scenario to the remaining basic operating scenarios.

[0030] Specifically, Wasserstein distance (also known as earth transport distance) is a method for measuring the distance between two probability distributions. In this embodiment, Wasserstein distance is used to measure the similarity between two basic operation scenarios. Wasserstein distance is used to screen typical scenarios, enhance the representativeness of the reduced scenarios, and reduce redundant scenarios. Among them, the expression of Wasserstein distance is:

[0031] in, represents the set of joint distributions of all basic operating scenarios, and their marginal distributions are and , representing the distribution of two different basic operating scenarios, random variables and Respectively represent the distribution and Assume there are two basic operating scenarios and , they correspond to two different distributions, so the basic operation scenario And basic operation scenarios Wasserstein distance: , indicating the basic operation scenario Distributed conversion to basic operation scenario The minimum amount of "work" required to distribute.

[0032] The screening of typical scenarios basically includes two parts: Wasserstein distance matrix calculation and gradual scenario reduction.

[0033] The Wasserstein distance matrix calculation is to calculate the Wasserstein distance between all basic running scenarios, which can be represented by a symmetric Wasserstein distance matrix:

[0034] in, , and the diagonal elements , Indicates the basic operation scenario And basic operation scenarios The Wasserstein distance.

[0035] The scenario reduction is to gradually remove the least typical basic operation scenarios according to the calculated Wasserstein distance matrix to reduce the number of basic operation scenarios. Specifically, it includes: 1. Average distance calculation. For each basic operation scenario , calculate the average distance between it and all other basic running scenarios , the expression is:

[0036] 2. Delete scene selection. According to the average distance, mark the basic running scene with the smallest average distance as the deletion target. The basis for selecting the basic operation scenario is:

[0037] 3. Update the scenario set. After deleting the selected basic operation scenario, assign its probability to the remaining basic operation scenarios to ensure that the total probability sums to 1, and repeat this process until the number of basic operation scenarios reaches the preset number.

[0038] Optionally, allocating the probability of the deleted basic operation scenario to the remaining current basic operation scenarios includes: evenly allocating the probability of the deleted basic operation scenario to the remaining current basic operation scenarios.

[0039] In a possible implementation, the method of identifying extreme scenarios among a preset number of basic operating scenarios based on the Wasserstein distance between each pair of basic operating scenarios, combined with a fast search and density peak discovery algorithm, includes: obtaining the local density of each basic operating scenario; obtaining the degree of separation of each basic operating scenario; and according to the local density and degree of separation of each basic operating scenario, selecting a basic operating scenario whose local density is lower than a preset local density threshold and whose degree of separation is higher than a preset degree of separation threshold as an extreme scenario among the preset number of basic operating scenarios.

[0040] The local density is the number of basic operation scenarios whose Wasserstein distance between the current basic operation scenario and the remaining basic operation scenarios is less than a preset cutoff distance.

[0041] Among them, for the basic operation scenario with the largest local density, the degree of separation is the maximum Wasserstein distance between the basic operation scenario and the other basic operation scenarios; for the basic operation scenario with non-largest local density, the degree of separation is the minimum Wasserstein distance between the basic operation scenario and the basic operation scenario with a local density greater than that of the basic operation scenario.

[0042] In this implementation, by combining fast search with density peak discovery algorithm to perform extreme scene recognition, misjudgment and missed judgment of important scenes are reduced.

[0043] Specifically, obtaining the local density of each basic operation scenario includes: for each basic operation scenario , calculate its local density Here, the local density is defined as the Wasserstein distance between the base running scenes. Less than the cutoff distance Number of scenes:

[0044] in, is an indicator function, when hour ,otherwise ; and the cutoff distance is the distance threshold used to determine which base run scenarios are taken into account in the local density calculation.

[0045] Optionally, the preset cutoff distance is a preset percentile of the distance distribution of the Wasserstein distance between two basic operation scenarios. The cutoff distance is used to determine the distance threshold of which basic operation scenarios are taken into account in the local density calculation. Usually, this distance threshold can be expressed as a certain percentile of the distance distribution, that is, a certain number of the Wasserstein distance between the basic operation scenarios is taken as the cutoff distance.

[0046] Specifically, obtaining the degree of separation of each basic operation scenario is mainly divided into the following two situations: 1. Calculate each basic operation scenario The minimum distance to all base running scenarios with a density greater than its local density is taken as the separation degree For each base run scenario , find the set of all base running scenarios with local density greater than it . Computing basic operation scenarios The Wasserstein distance to these denser base operating scenarios , and select the smallest one from these Wasserstein distances as The value of, that is:

[0047] 2. For the basic operation scenario with the largest local density, since there is no basic operation scenario with a larger local density than it, It is defined as the maximum distance to all other basic operation scenarios. That is, for the basic operation scenario with the largest local density , calculate its Wasserstein distance to all other base run scenarios , and select the largest one from these distances as The value of, that is:

[0048] Obviously, It reflects the degree of separation of the most dense basic operation scenario from the entire data set.

[0049] In a possible implementation, the selecting, according to the local density and degree of separation of each basic operating scenario, a basic operating scenario with a local density lower than a preset local density threshold and a degree of separation higher than a preset degree of separation threshold as an extreme scenario among a preset number of basic operating scenarios includes: according to the local density and degree of separation of each basic operating scenario, using the local density and the degree of separation as the horizontal axis coordinate and the vertical axis coordinate, respectively, to construct an extreme scenario clustering decision diagram; and according to the extreme scenario clustering decision diagram, selecting a basic operating scenario with a local density lower than a preset local density threshold and a degree of separation higher than a preset degree of separation threshold as an extreme scenario among a preset number of basic operating scenarios.

[0050] Specifically, by generating an extreme scenario clustering decision diagram, the important representative scenarios and extreme scenarios in the scenario set can be intuitively identified. The local density and separation degree values ​​of all basic operation scenarios are used as the horizontal axis coordinate and the vertical axis coordinate, respectively. Figure 2 , a scatter plot can be drawn in a two-dimensional coordinate system.

[0051] According to the values ​​of local density and separation degree, the basic operation scenario with low local density and high separation degree is selected as the extreme scenario. Specifically, the points on the upper left side of the extreme scenario clustering decision diagram are selected as extreme scenarios, which have a small probability of occurrence but a large impact.

[0052] The present invention uses Wasserstein distance to screen typical scenes, which can enhance the representativeness of the scenes after reduction and reduce redundant scenes. At the same time, the method of combining fast search with density peak discovery algorithm to identify extreme scenes can reduce misjudgment and omission of important scenes.

[0053] The following are device embodiments of the present invention, which can be used to implement the method embodiments of the present invention. For details not disclosed in the device embodiments, please refer to the method embodiments of the present invention.

[0054] See also Figure 3 In another embodiment of the present invention, a power system operation scenario reduction system is provided, which can be used to implement the above-mentioned power system operation scenario reduction method. Specifically, the power system operation scenario reduction system includes a scenario acquisition module, a typical scenario screening module and an extreme scenario recognition module.

[0055] Among them, the scenario acquisition module is used to obtain several basic operating scenarios of the power system; the typical scenario screening module is used to delete the basic operating scenarios with the lowest typicality among several basic operating scenarios one by one based on the Wasserstein distance between the basic operating scenarios, until the number of basic operating scenarios reaches a preset number; the extreme scenario identification module is used to identify extreme scenarios among a preset number of basic operating scenarios based on the Wasserstein distance between the basic operating scenarios, combined with fast search and density peak discovery algorithms.

[0056] All relevant contents of each step involved in the embodiment of the aforementioned power system operation scenario reduction method can be referred to the functional description of the functional modules corresponding to the power system operation scenario reduction system in the embodiment of the present invention, and will not be repeated here.

[0057] The division of modules in the embodiments of the present invention is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional module in each embodiment of the present invention may be integrated into one processor, or may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated modules may be implemented in the form of hardware or in the form of software functional modules.

[0058] In another embodiment of the present invention, a computer device is provided, the computer device including a processor and a memory, the memory is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc., which are the computing core and control core of the terminal, which are suitable for implementing one or more instructions, and are specifically suitable for loading and executing one or more instructions in the computer storage medium to implement the corresponding method flow or corresponding function; the processor described in the embodiment of the present invention can be used for the operation of the power system operation scenario reduction method.

[0059] In another embodiment of the present invention, the present invention further provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device for storing programs and data. It is understandable that the computer-readable storage medium here can include both built-in storage media in a computer device and, of course, extended storage media supported by the computer device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by a processor are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the method for reducing power system operation scenarios in the above embodiment.

[0060] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0061] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0062] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0063] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0064] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for reducing power system operation scenarios, characterized in that: include: Obtain several basic operating scenarios of the power system; Based on the Wasserstein distance between two basic operation scenarios, the basic operation scenarios with the lowest typicality among several basic operation scenarios are deleted one by one until the number of basic operation scenarios reaches a preset number; Based on the Wasserstein distance between two basic operating scenarios, combined with fast search and density peak discovery algorithms, extreme scenarios in a preset number of basic operating scenarios are identified.

2. The method for reducing power system operation scenarios according to claim 1, characterized in that: Several basic operation scenarios of the power acquisition system include: Several basic operating scenarios of the power system are obtained through the Latin hypercube sampling method.

3. The method for reducing power system operation scenarios according to claim 1, characterized in that: The method of deleting the least typical basic operation scenarios from among a number of basic operation scenarios based on the Wasserstein distance between the two basic operation scenarios one by one until the number of basic operation scenarios reaches a preset number includes: Repeat the following reduction steps until the number of basic operating scenarios reaches a preset number; wherein, the reduction step: according to the Wasserstein distance between each basic operating scenario in the current basic operating scenarios, calculate the average Wasserstein distance between each basic operating scenario and the remaining basic operating scenarios, obtain the typicality of each basic operating scenario, delete the basic operating scenario with the lowest typicality, and assign the probability of the deleted basic operating scenario to the remaining basic operating scenarios.

4. The method for reducing power system operation scenarios according to claim 1, characterized in that: The step of allocating the probability of the deleted basic operation scenario to the remaining current basic operation scenarios includes: The probability of the deleted basic operation scenario is evenly distributed to the remaining current basic operation scenarios.

5. The method for reducing power system operation scenarios according to claim 1, characterized in that: The method of identifying extreme scenarios in a preset number of basic operating scenarios based on the Wasserstein distance between two basic operating scenarios, combined with the fast search and density peak discovery algorithm, includes: Obtaining the local density of each basic operation scenario; wherein the local density is the number of basic operation scenarios whose Wasserstein distance between the current basic operation scenario and the remaining basic operation scenarios is less than a preset cutoff distance; Obtain the degree of separation of each basic operation scenario; wherein, for the basic operation scenario with the largest local density, the degree of separation is the maximum Wasserstein distance between the basic operation scenario and the remaining basic operation scenarios; for the basic operation scenario with a non-maximum local density, the degree of separation is the minimum Wasserstein distance between the basic operation scenario and the basic operation scenario with a local density greater than that of the basic operation scenario; According to the local density and separation degree of each basic operation scenario, a basic operation scenario with a local density lower than a preset local density threshold and a separation degree higher than a preset separation degree threshold is selected as an extreme scenario among a preset number of basic operation scenarios.

6. The method for reducing power system operation scenarios according to claim 5, characterized in that: According to the local density and separation degree of each basic operation scenario, the basic operation scenario with a local density lower than a preset local density threshold and a separation degree higher than a preset separation degree threshold is selected as the extreme scenario in the preset number of basic operation scenarios, including: According to the local density and separation degree of each basic operating scenario, the local density and separation degree are used as the horizontal axis and the vertical axis respectively to construct an extreme scenario clustering decision diagram; and according to the extreme scenario clustering decision diagram, the basic operating scenarios with local density lower than the preset local density threshold and separation degree higher than the preset separation degree threshold are selected as the extreme scenarios among the preset number of basic operating scenarios.

7. The method for reducing power system operation scenarios according to claim 5, characterized in that: The preset cutoff distance is a preset percentile of the distance distribution of the Wasserstein distance between any two basic operating scenarios.

8. A power system operation scenario reduction system, characterized in that: include: A scenario acquisition module is used to acquire several basic operation scenarios of the power system; A typical scenario screening module is used to delete the least typical basic operation scenarios from a number of basic operation scenarios one by one based on the Wasserstein distance between the basic operation scenarios, until the number of basic operation scenarios reaches a preset number; The extreme scenario identification module is used to identify extreme scenarios in a preset number of basic operating scenarios based on the Wasserstein distance between two basic operating scenarios, combined with fast search and density peak discovery algorithms.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the power system operation scenario reduction method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for reducing power system operation scenarios as described in any one of claims 1 to 7 are implemented.

Images