Scene generation method and device considering space-time correlation

Abstract

The invention belongs to the technical field of power systems, and particularly discloses a scene generation method and device considering spatial-temporal correlation. According to the method, the time correlation and the space correlation in the renewable energy historical data (such as wind speed, illumination radiation intensity and runoff) are fully considered, and the improved particle swarm algorithm is adopted to perform time sequence reconstruction on the initial scene set for representing the space correlation in the renewable energy historical data; and the space-time correlation in the renewable energy historical data can be effectively captured. Considering that renewable energy has randomness and volatility and is relatively high in dimensionality and difficult to process when multiple possible scenes are generated, the method comprises the following steps: capturing space-time correlation in renewable energy historical data, mapping the high-dimensional renewable energy historical data to a low-dimensional space, and obtaining the high-dimensional renewable energy historical data; the challenge that a complementary system (such as a water-wind-light complementary system) generates a high-dimensional uncertainty scene is effectively dealt with, and short-term scheduling of the complementary system is better guided.

Description

Technical Field

[0001] This application belongs to the technical field of power systems, and more specifically, relates to a scenario generation method and device considering spatio-temporal correlation. Background Art

[0002] Renewable energy dominated by hydropower, wind power, and solar energy has achieved unprecedented development in recent years. However, the randomness and uncertainty of renewable energy affect the robustness and stability of complementary systems (such as hydropower-wind-solar complementary systems).

[0003] The scenario generation method is an effective way to analyze the uncertainty of renewable energy. This method highly depends on probability distributions and can solve various practical problems in engineering through various assumptions. However, traditional probability modeling methods do not fully consider various correlations and uncertainties in renewable energy.

[0004] Runoff, wind speed, and light radiation intensity show autocorrelation in their respective time series, and also show spatial correlation between the series. However, due to the lack of in-depth research on the uncertainty and spatio-temporal correlation of hydropower, wind power, and solar energy in existing research, there are certain difficulties in the short-term scheduling of complementary systems. Summary of the Invention

[0005] Aiming at the defects of the existing technology, the purpose of this application is to provide a scenario generation method and device considering spatio-temporal correlation, aiming to solve the problem that the existing research on the uncertainty and spatio-temporal correlation of hydropower, wind power, and solar energy is not deep enough, resulting in certain difficulties in the short-term scheduling of complementary systems.

[0006] To achieve the above purpose, in the first aspect, this application provides a scenario generation method considering spatio-temporal correlation, including: Obtain an initial scenario set used to characterize the spatial correlation in the historical data of renewable energy; Considering the time correlation in the historical data of renewable energy, based on an improved particle swarm algorithm, perform temporal reconstruction on the initial scenario set to generate a target scenario set used to characterize the spatio-temporal correlation in the historical data of renewable energy.

[0007] In some embodiments, considering the time correlation in the historical data of renewable energy, based on an improved particle swarm algorithm, performing temporal reconstruction on the initial scenario set to generate a target scenario set used to characterize the spatio-temporal correlation in the historical data of renewable energy includes: Generate a benchmark fluctuation sequence used to characterize the time correlation in the historical data of renewable energy; Based on the improved particle swarm optimization algorithm, the particles in the initial population are optimized to determine the globally optimal particle with the minimum mean absolute error between the benchmark fluctuation sequence, where the particles are composed of renewable energy data for each time period in each scenario. According to the globally optimal particle, the initial scenario set is reconstructed in time sequence to generate the target scenario set.

[0008] In some embodiments, based on the improved particle swarm optimization algorithm, optimizing the particles in the initial population to determine the globally optimal particle with the minimum mean absolute error between the benchmark fluctuation sequence includes: According to the fitness value of each particle in the initial population, the individual optimal particle and the globally optimal particle are determined, where the fitness value is determined according to the mean absolute error between the particle and the benchmark fluctuation sequence; Update the positions of the renewable energy data for the same time period in any scenario in each particle; Based on the renewable energy data in the globally optimal particle, update the renewable energy data in each updated particle; Update the positions of the renewable energy data for the same time period in any scenario in each updated particle; Based on the fitness value of each updated particle, update the individual optimal particle and the globally optimal particle, return to execute updating the positions of the renewable energy data for the same time period in any scenario in each particle until the termination condition is met, and use the globally optimal particle after the last update as the globally optimal particle with the minimum mean absolute error between the benchmark fluctuation sequence.

[0009] In some embodiments, generating the benchmark fluctuation sequence for characterizing the temporal correlation in the historical renewable energy data includes: Using the stochastic differential equation to capture the temporal correlation in the historical renewable energy data and generate the benchmark fluctuation sequence.

[0010] In some embodiments, obtaining the initial scenario set for characterizing the spatial correlation in the historical renewable energy data includes: When the historical renewable energy data includes historical wind speed, historical solar irradiance intensity, and historical runoff, in the time period when the historical solar irradiance intensity is 0, calculate the first joint probability distribution function of the historical wind speed and the historical runoff based on the two-dimensional Copula method; In the time period when the historical solar irradiance intensity is not 0, calculate the second joint probability distribution function of the historical wind speed, the historical solar irradiance intensity, and the historical runoff based on the three-dimensional Copula method; Generate the initial scenario set according to the first joint probability distribution function and the second joint probability distribution function.

[0011] In some embodiments, the method further includes: Evaluating the target scenario set according to an evaluation system composed of a spatial correlation index, a coverage rate, and a temporal correlation index.

[0012] In a second aspect, the present application provides a scenario generation device considering spatio-temporal correlation, including: An acquisition module for acquiring an initial scenario set for characterizing the spatial correlation in the historical data of renewable energy; A generation module for considering the temporal correlation in the historical data of renewable energy and performing temporal reconstruction on the initial scenario set based on an improved particle swarm algorithm to generate a target scenario set for characterizing the spatio-temporal correlation in the historical data of renewable energy.

[0013] In a third aspect, the present application provides an electronic device, including: at least one memory for storing a program; at least one processor for executing the program stored in the memory, and when the program stored in the memory is executed, the processor is used to execute the method described in the first aspect or any of the embodiments of the first aspect.

[0014] In a fourth aspect, the present application provides a computer-readable storage medium storing a computer program, and when the computer program runs on a processor, the processor is caused to execute the method described in the first aspect or any of the embodiments of the first aspect.

[0015] In a fifth aspect, the present application provides a computer program product, and when the computer program product runs on a processor, the processor is caused to execute the method described in the first aspect or any of the embodiments of the first aspect.

[0016] Generally speaking, compared with the prior art, the above technical solution conceived by the present application has the following beneficial effects: The scenario generation method and device considering spatio-temporal correlation provided by the present application fully consider the temporal correlation and spatial correlation in the historical data of renewable energy (such as wind speed, light radiation intensity, and runoff), and use an improved particle swarm algorithm to perform temporal reconstruction on the initial scenario set for characterizing the spatial correlation in the historical data of renewable energy, effectively capturing the spatio-temporal correlation in the historical data of renewable energy. Considering that renewable energy has randomness and volatility, when generating multiple possible scenarios, the dimension is relatively high and difficult to process. By capturing the spatio-temporal correlation in the historical data of renewable energy, the present application maps the high-dimensional historical data of renewable energy to a low-dimensional space, effectively coping with the challenge of generating high-dimensional uncertain scenarios in complementary systems (such as water-wind-solar complementary systems), and better guiding the short-term scheduling of complementary systems. Description of the Drawings

[0017] Figure 1It is a flowchart of a scenario generation method considering spatio-temporal correlation provided by an embodiment of the present application; Figure 2 It is a structural diagram of a scenario generation device considering spatio-temporal correlation provided by an embodiment of the present application; Figure 3 It is a structural diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0018] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, rather than to limit the present application.

[0019] The term "and / or" in this article is a correlation relationship describing associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. The symbol " / " in this article represents an "or" relationship between associated objects. For example, A / B represents A or B.

[0020] The terms "first" and "second" in the description and claims of this article are used to distinguish different objects, rather than to describe a specific order of objects. For example, the first joint probability distribution function and the second joint probability distribution function are used to distinguish different joint probability distribution functions, rather than to describe the specific order of the joint probability distribution functions.

[0021] In the embodiments of the present application, words such as "exemplary" or "for example" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as "exemplary" or "for example" in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly speaking, using words such as "exemplary" or "for example" aims to present relevant concepts in a specific manner.

[0022] In the description of the embodiments of the present application, unless otherwise specified, the meaning of "a plurality" refers to two or more.

[0023] The embodiments of the present application will be described below with reference to the accompanying drawings in the embodiments of the present application.

[0024] Please refer to Figure 1 , an embodiment of the present application provides a scenario generation method considering spatio-temporal correlation, including: step 110 and step 120.

[0025] Step 110 obtains an initial scenario set for characterizing the spatial correlation in the historical data of renewable energy; Step 120 considers the temporal correlation in the historical renewable energy data and performs temporal reconstruction on the initial scenario set based on the improved particle swarm optimization algorithm to generate a target scenario set for characterizing the spatio-temporal correlation in the historical renewable energy data.

[0026] In the embodiments of the present application, the historical renewable energy data may specifically be historical wind speed, historical solar irradiance intensity, and historical runoff. Correspondingly, in the embodiments of the present application, the initial scenario set is specifically a water-wind-solar scenario set. Among them, water, wind, and solar respectively correspond to runoff, wind speed, and solar irradiance intensity.

[0027] In specific implementation, a hybrid-dimensional Copula method can be used to calculate the spatial correlation between each pair of the historical renewable energy data, such as historical wind speed, historical solar irradiance intensity, and historical runoff.

[0028] According to the calculated spatial correlation above, an initial scenario set including historical wind speed, historical solar irradiance intensity, and historical runoff is obtained.

[0029] In the embodiments of the present application, the temporal correlation of a single renewable energy in the renewable energy data is considered, and the improved particle swarm optimization algorithm is used to perform temporal reconstruction on the above initial scenario set to generate a target scenario set. The target scenario set can be used to characterize the spatio-temporal correlation (including temporal correlation and spatial correlation) among wind speed, solar irradiance intensity, and runoff in the historical renewable energy data.

[0030] The scenario generation method considering spatio-temporal correlation provided by the embodiments of the present application fully considers the temporal correlation and spatial correlation in the historical renewable energy data (such as wind speed, solar irradiance intensity, and runoff), and uses the improved particle swarm optimization algorithm to perform temporal reconstruction on the initial scenario set for characterizing the spatial correlation in the historical renewable energy data, effectively capturing the spatio-temporal correlation in the historical renewable energy data. Considering that renewable energy has randomness and volatility, when generating multiple possible scenarios, the dimension is relatively high and difficult to process. By capturing the spatio-temporal correlation in the historical renewable energy data, the present application maps the high-dimensional historical renewable energy data to a low-dimensional space, effectively coping with the challenge of generating high-dimensional uncertain scenarios in complementary systems (such as water-wind-solar complementary systems), and better guiding the short-term scheduling of complementary systems.

[0031] Further, in some embodiments, considering the temporal correlation in the historical renewable energy data, based on the improved particle swarm optimization algorithm, performing temporal reconstruction on the initial scenario set to generate a target scenario set for characterizing the spatio-temporal correlation in the historical renewable energy data includes: Generating a benchmark fluctuation sequence for characterizing the temporal correlation in the historical renewable energy data; Based on the improved particle swarm optimization algorithm, the particles in the initial population are optimized to determine the globally optimal particle with the minimum mean absolute error between the reconstructed fluctuation sequence and the benchmark fluctuation sequence. The particle is composed of renewable energy data in each time period of each scenario. According to the globally optimal particle, the initial scenario set is reconstructed in time series to generate the target scenario set.

[0032] In the embodiments of the present application, the benchmark fluctuation sequence can be used to characterize the time-correlation characteristics of historical renewable energy data (including historical runoff, historical wind speed, and historical solar irradiance intensity).

[0033] In specific implementation, time series models, stochastic differential equations, Copula methods, etc. can be used to generate the benchmark fluctuation sequences corresponding to historical runoff, historical wind speed, and historical solar irradiance intensity respectively.

[0034] The criterion for reconstruction using the improved particle swarm optimization algorithm is to minimize the mean absolute error between the reconstructed fluctuation sequence and the benchmark fluctuation sequence. Based on this, in the embodiments of the present application, with the goal of minimizing the mean absolute error between the reconstructed fluctuation sequence and the benchmark fluctuation sequence, the objective function is constructed as follows:

[0035] Wherein, represents the objective function, is the total number of generated scenarios, is the reconstructed fluctuation sequence, is the benchmark fluctuation sequence, represents the th scenario in the generated target scenario set.

[0036] In the embodiments of the present application, the particles in the randomly initialized initial population are used as the initial values, and each particle in the initial population is respectively substituted into the above objective function to obtain the fitness value corresponding to each particle. Among them, the particle is a matrix ( represents the total number of time periods), which is used to represent the renewable energy data in each time period of each scenario. Each row element in the matrix represents the renewable energy data of a scenario in each time period, each column element in the matrix represents the renewable energy data of each scenario in the same time period, and each element represents the renewable energy data of any scenario in any time period.

[0037] The improved particle algorithm is adopted, combined with the fitness values of the particles, to optimize the particles in the initial population to obtain the globally optimal particle with the minimum mean absolute error between the reconstructed fluctuation sequence and the benchmark fluctuation sequence.

[0038] Based on the group-optimal particle with the smallest mean absolute error from the above-obtained reference fluctuation sequence, perform a time-series reconstruction on the generated initial scene set to generate a target scene set for characterizing the spatio-temporal correlation in the historical data of renewable energy.

[0039] In some embodiments, generating a reference fluctuation sequence for characterizing the temporal correlation in the historical data of renewable energy includes: Using a stochastic differential equation to capture the temporal correlation in the historical data of renewable energy and generate a reference fluctuation sequence.

[0040] In the embodiments of the present application, a stochastic differential equation is used to obtain the temporal correlation in the historical data of renewable energy to generate a reference fluctuation sequence, where the stochastic differential equation is as follows:

[0041] Where, is the time period, , , is the reference fluctuation sequence, is a variable. In the embodiments of the present application, is specifically the central time series corresponding to the mean value of any one of the historical data of renewable energy, such as historical wind speed, historical irradiance intensity, and historical runoff. is a stationary sequence used to simulate the intra-day fluctuations of the time series. , represents a standard Wiener process, , and are constants greater than 0, is the noise parameter of the diffusion term.

[0042] Furthermore, in some embodiments, based on an improved particle swarm optimization algorithm, optimizing the particles in the initial population to determine the group-optimal particle with the smallest mean absolute error from the reference fluctuation sequence includes: Determine the individual-optimal particle and the group-optimal particle according to the fitness value of each particle in the initial population, where the fitness value is determined according to the mean absolute error between the particle and the reference fluctuation sequence; Update the positions of the renewable energy data at the same time period in any scene in each particle; Update the renewable energy data in each updated particle based on the renewable energy data in the group-optimal particle; Update the positions of the renewable energy data at the same time period in any scene in each updated particle; Based on the updated fitness values of each particle, update the individual best particle and the global best particle, and return to perform the update on the positions of the renewable energy data in the same time period in any scenario of each particle until the termination condition is met. Then, take the global best particle after the last update as the global best particle with the minimum mean absolute error between the benchmark fluctuation sequence.

[0043] In the embodiments of the present application, according to the above objective function, calculate the objective function value of each particle and use it as the fitness value corresponding to the particle.

[0044] According to the calculated fitness values of each particle, find the individual best particle corresponding to each particle in the initial population and the global best particle in the initial population.

[0045] In the embodiments of the present application, the initial value of the individual best particle is itself, and the global best particle is the particle with the minimum fitness value.

[0046] Update the positions of the renewable energy data (which can be any one of wind speed, light radiation intensity, and runoff) in the same time period in any scenario of each particle.

[0047] In specific implementation, it can be achieved by randomly exchanging the positions of the renewable energy data in the same time period in each scenario to update the positions of the renewable energy data in the same time period in any scenario of each particle.

[0048] In specific implementation, it can be achieved by using the data in any row and any column of the global best particle to update the data in the corresponding row and column of each particle, so as to update the renewable energy data in each updated particle.

[0049] Update the positions of the renewable energy data in the same time period in any scenario of the particles after the above update again, and the update method is still to randomly exchange the positions of the renewable energy data in the same time period in each scenario.

[0050] Based on the updated particles, recalculate their corresponding fitness values respectively, and based on the fitness values corresponding to each updated particle, update the individual best particle and the global best particle. If the fitness value corresponding to the updated particle is less than the fitness value corresponding to the individual best particle, then take the updated particle as the individual best particle; otherwise, do not update the individual best particle. If the minimum value among the fitness values of the updated particles is less than the global best particle, then take the updated particle corresponding to the minimum fitness value as the global best particle; otherwise, do not update the global best particle.

[0051] Determine whether the termination condition is satisfied. If not, return to execute the update of the positions of the renewable energy data in the same time period in any scenario of each particle until the termination condition is satisfied, and use the population-optimal particle after the last update as the population-optimal particle with the smallest mean absolute error between the benchmark fluctuation sequence.

[0052] In the embodiments of the present application, the termination condition may be reaching a preset maximum number of optimization times.

[0053] Determine whether the positions of the renewable energy data in each time period of each scenario in the population-optimal particle after the last update have changed compared to the positions of the renewable energy in each time period of each scenario in the population-optimal particle in the initial situation. If so, perform a temporal reconstruction of the initial scenario set by correspondingly adjusting the historical renewable energy data in each time period of each scenario in the initial scenario set.

[0054] Exemplarily, if the position of the renewable energy data in the first time period of scenario one in the population-optimal particle after the last update has changed compared to the position of the renewable energy data in the first time period of scenario one in the population-optimal particle in the initial situation, then correspondingly adjust the position of the historical renewable energy data in the first time period of scenario one in the initial scenario set.

[0055] The scenario generation method considering spatio-temporal correlation provided by the embodiments of the present application uses an improved particle swarm algorithm, abandons the method of updating particle positions by tracking extreme values in the traditional particle swarm algorithm, and introduces the crossover and mutation operations in the genetic algorithm to avoid particles falling into local optimal solutions, which is beneficial to generating multiple sets of water-wind-light scenarios that conform to the actual time correlation during temporal reconstruction.

[0056] Furthermore, in some embodiments, obtaining the initial scenario set for characterizing the spatial correlation in the historical renewable energy data includes: When the historical renewable energy data includes historical wind speed, historical solar irradiance intensity, and historical runoff, in the time period when the historical solar irradiance intensity is 0, calculate the first joint probability distribution function of the historical wind speed and historical runoff based on the two-dimensional Copula method; In the time period when the historical solar irradiance intensity is not 0, calculate the second joint probability distribution function of the historical wind speed, historical solar irradiance intensity, and historical runoff based on the three-dimensional Copula method; Generate the initial scenario set according to the first joint probability distribution function and the second joint probability distribution function.

[0057] In the embodiments of the present application, based on the historical wind speed, historical solar irradiance intensity, and historical runoff, in different seasons, it can be divided into 24 time periods with a daily cycle and an hourly interval.

[0058] During the time period when the historical light radiation intensity is 0, the two-dimensional Copula method can be used to consider the spatial correlation between the historical wind speed and the historical runoff. In the specific implementation, the two-dimensional Copula method is used to calculate the joint probability distribution function of the historical wind speed and the historical runoff, that is, the first joint probability distribution function. The functional expression of the Copula method is as follows:

[0059] Among them, is the joint probability distribution function of n variables. During the time period when the historical light radiation intensity is 0, , and correspond to the historical wind speed and the historical runoff respectively, is the marginal distribution function of a single variable , is the Copula connection function.

[0060] During the time period when the historical light radiation intensity is not 0, the three-dimensional Copula method is used to consider the spatial correlation among the historical runoff, the historical light radiation intensity and the historical wind speed. In the specific implementation, a three-dimensional Copula method such as the R-vine Copula function or the C-vine Copula function can be used to calculate the joint probability distribution function between any two of the historical wind speed, the historical light radiation intensity and the historical runoff, that is, the second joint probability distribution function.

[0061] Inverse sampling is performed on the above-obtained first joint probability distribution function and second joint probability distribution function, and according to the sampling results and the joint probability distribution functions (including the first joint probability distribution function and the second joint probability distribution function), inverse transformation is performed to obtain the initial scenario set corresponding to the historical wind speed, the historical light radiation intensity and the historical runoff for each time period.

[0062] In some embodiments, the above method further includes: Evaluating the target scenario set according to an evaluation system composed of a spatial correlation index, a coverage rate and a time correlation index.

[0063] In the embodiments of the present application, the evaluation system includes a spatial correlation index, a coverage rate and a time correlation index.

[0064] Among them, the spatial correlation index is the absolute error of the average Kendall correlation coefficient, and the expression is as shown in the following formula:

[0065] In the formula, is the absolute error of the average Kendall correlation coefficient, is the Kendall correlation coefficient of the th scenario in the target scenario set, is the average Kendall correlation coefficient of the historical scenarios.

[0066] The expression of the coverage rate is as follows:

[0067] In the formula, is the total number of time periods. In the embodiments of the present application, , is the coverage rate, is the total number of historical scenarios, is the historical renewable energy data of the historical scenario , is the generated target scenario set.

[0068] The time correlation index is the average absolute error between the autocorrelation coefficient of the scenario time lag of in the generated target scenario set and the autocorrelation coefficient of the scenario time lag of in the historical scenario set. The expression is as follows:

[0069] In the formula, is the maximum time interval selected by the research, that is, the maximum time lag number, is the value of the scenario in the target scenario set at the time period, is the value of the scenario in the target scenario set at the time period, is the average value of the scenarios in the target scenario set at each time period, is the value of the scenario in the historical scenario set at the time period, is the value of the scenario in the historical scenario set at the time period, is the average value of the scenarios in the historical scenario set at each time period, is the average absolute error between the autocorrelation coefficient of the scenario time lag of in the generated target scenario set and the autocorrelation coefficient of the scenario time lag of in the historical scenario set, is the autocorrelation coefficient of the th scenario time lag of in the generated target scenario set, is the autocorrelation coefficient of the historical scenario time lag of .

[0070] It should be noted that The smaller the value of , the more the scenes in the generated target scene set can describe the spatial correlation characteristics among water, wind, and light; The larger the value of

[0071] Table 1: Spatial correlation evaluation index

[0072] Table 2: Coverage rate

[0073] Table 3: Time correlation evaluation index

[0074] It can be seen from Tables 1-3 that the present application does not destroy the spatial correlation of the target scene set generated based on the multi-dimensional Copula method. In addition, after considering the spatio-temporal correlation, the generated target scene set can more effectively capture the time correlation of the scene set and can effectively reflect the historical situation of the water, wind, and light time series.

[0075] Next, a spatio-temporal correlation-aware scene generation device provided by the present application will be described. The spatio-temporal correlation-aware scene generation device described below can be mutually referred to the spatio-temporal correlation-aware scene generation method described above.

[0076] Please refer to Figure 2 , an embodiment of the present application provides a spatio-temporal correlation-aware scene generation device, including: an acquisition module 210 and a generation module 220.

[0077] The acquisition module 210 is configured to acquire an initial scene set for characterizing the spatial correlation in the historical data of renewable energy; The generation module 220 is configured to consider the time correlation in the historical data of renewable energy and perform time series reconstruction on the initial scene set based on an improved particle swarm algorithm to generate a target scene set for characterizing the spatio-temporal correlation in the historical data of renewable energy.

[0078] The scenario generation device considering spatio-temporal correlation provided by the embodiments of the present application fully considers the temporal correlation and spatial correlation in the historical data of renewable energy (such as wind speed, solar radiation intensity, and runoff), and uses an improved particle swarm algorithm to perform temporal reconstruction on the initial scenario set used to characterize the spatial correlation in the historical data of renewable energy, effectively capturing the spatio-temporal correlation in the historical data of renewable energy. Considering that renewable energy has randomness and volatility, when generating multiple possible scenarios, the dimension is relatively high and difficult to process. By capturing the spatio-temporal correlation in the historical data of renewable energy, the present application maps the high-dimensional historical data of renewable energy to a low-dimensional space, effectively addressing the challenge of generating high-dimensional uncertain scenarios in complementary systems (such as the water-wind-solar complementary system), and better guiding the short-term scheduling of complementary systems.

[0079] It can be understood that the detailed functional implementation of each of the above units / modules can be referred to the introduction in the foregoing method embodiments, and will not be elaborated herein.

[0080] It should be understood that the above device is used to execute the method in the above embodiments. For the corresponding program modules in the device, their implementation principles and technical effects are similar to those described in the above method. The working process of the device can refer to the corresponding process in the above method, and will not be elaborated herein.

[0081] Based on the method in the above embodiments, the embodiments of the present application provide an electronic device. Please refer to Figure 3 The electronic device may include: a processor 310, a communications interface 320, a memory 330, and a communication bus 340. Among them, the processor 310, the communications interface 320, and the memory 330 communicate with each other through the communication bus 340. The processor 310 can call the logical instructions in the memory 330 to execute the method in the above embodiments.

[0082] In addition, when the logical instructions in the above memory 330 are implemented in the form of software functional units and sold or used as an independent product, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application.

[0083] Based on the method in the above embodiments, an embodiment of the present application provides a computer-readable storage medium storing a computer program, which, when running on a processor, causes the processor to execute the method in the above embodiments.

[0084] Based on the method in the above embodiments, an embodiment of the present application provides a computer program product, which, when running on a processor, causes the processor to execute the method in the above embodiments.

[0085] It can be understood that the processor in the embodiments of the present application may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.

[0086] The method steps in the embodiments of the present application may be implemented in a hardware manner or by a processor executing software instructions. The software instructions may be composed of corresponding software modules, and the software modules may be stored in a random access memory (RAM), flash memory, read-only memory (ROM), programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), registers, hard disk, removable hard disk, CD-ROM, or any other form of storage medium well known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium may also be a component of the processor. The processor and the storage medium may be located in an ASIC.

[0087] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired manner (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or a wireless manner (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that includes one or more integrated available media. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)), etc.

[0088] It can be understood that the various numerical numbers involved in the embodiments of the present application are only for the convenience of description and are not used to limit the scope of the embodiments of the present application.

[0089] It is easy for those skilled in the art to understand that the above is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, and improvements made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A scene generation method considering spatiotemporal correlation, characterized in that: include: Obtaining an initial set of scenarios for characterizing spatial correlations in historical renewable energy data; Taking into account the temporal correlation in the renewable energy historical data, based on the improved particle swarm algorithm, the initial scene set is time-series reconstructed to generate a target scene set for characterizing the spatiotemporal correlation in the renewable energy historical data.

2. The scene generation method considering time and space correlation as claimed in claim 1, characterized in that: The step of considering the temporal correlation in the renewable energy historical data and reconstructing the initial scene set in time series based on an improved particle swarm algorithm to generate a target scene set for characterizing the temporal and spatial correlation in the renewable energy historical data comprises: generating a benchmark fluctuation series for characterizing the time correlation in the renewable energy historical data; Based on the improved particle swarm algorithm, the particles in the initial population are optimized to determine the optimal particle in the population with the smallest mean absolute error with the benchmark fluctuation sequence, wherein the particle is composed of renewable energy data in each time period in each scenario; The initial scene set is reconstructed in time sequence according to the optimal particle of the group to generate the target scene set.

3. The scene generation method considering time and space correlation as claimed in claim 2, characterized in that: The step of optimizing the particles in the initial population based on the improved particle swarm algorithm to determine the optimal particle in the population with the smallest mean absolute error with the benchmark fluctuation sequence includes: Determine an individual optimal particle and a group optimal particle according to the fitness value of each particle in the initial population, wherein the fitness value is determined according to the mean absolute error between the particle and a reference fluctuation sequence; Update the position of renewable energy data in the same time period in any scenario in each particle; Based on the renewable energy data in the optimal particle of the group, updating the renewable energy data in each updated particle; The position of the renewable energy data in the same time period in any scenario in each updated particle is updated; Based on the updated fitness value of each particle, the individual optimal particle and the group optimal particle are updated, and the position of the renewable energy data in the same time period in any scene in each particle is updated again until the termination condition is met, and the group optimal particle after the last update is used as the group optimal particle with the smallest mean absolute error with the benchmark fluctuation sequence.

4. The scene generation method considering time and space correlation as claimed in claim 2, characterized in that: The generating of a reference fluctuation sequence for characterizing the time correlation in the renewable energy historical data comprises: Stochastic differential equations are used to capture the time correlation in the renewable energy historical data and generate the benchmark fluctuation series.

5. The scene generation method considering time and space correlation as claimed in claim 1, characterized in that: The method of obtaining an initial scene set for characterizing spatial correlation in renewable energy historical data includes: When the renewable energy historical data includes historical wind speed, historical light radiation intensity and historical runoff, in a time period when the historical light radiation intensity is 0, a first joint probability distribution function of the historical wind speed and the historical runoff is calculated based on a two-dimensional Copula method; In the time period when the historical light radiation intensity is not 0, a second joint probability distribution function of the historical wind speed, the historical light radiation intensity and the historical runoff is calculated based on the three-dimensional Copula method; The initial scene set is generated according to the first joint probability distribution function and the second joint probability distribution function.

6. The scene generation method considering time and space correlation according to any one of claims 1 to 5, characterized in that: The method further comprises: The target scene set is evaluated according to an evaluation system consisting of a spatial correlation index, a coverage rate, and a temporal correlation index.

7. A scene generation device considering time and space correlation, characterized in that: include: An acquisition module for acquiring an initial set of scenarios for characterizing spatial correlations in renewable energy historical data; A generation module is used to consider the time correlation in the renewable energy historical data, and based on the improved particle swarm algorithm, perform time series reconstruction on the initial scene set to generate a target scene set for characterizing the spatiotemporal correlation in the renewable energy historical data.

8. An electronic device, characterized in that: include: at least one memory for storing a computer program; At least one processor is used to execute the program stored in the memory. When the program stored in the memory is executed, the processor is used to execute the method according to any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program runs on a processor, the processor is caused to execute the method according to any one of claims 1 to 6.

10. A computer program product, characterized in that When the computer program product runs on a processor, the processor is caused to execute the method according to any one of claims 1 to 6.

Images