Wind power uncertainty set modeling method, system, medium and equipment

Abstract

The invention discloses a wind power uncertainty set modeling method and system, a medium and equipment, and relates to the technical field of electrical engineering, and the method comprises the steps: obtaining historical actually-measured wind power output data of different wind power plants and historical predicted wind power output data obtained through prediction according to the historical actually-measured wind power output data; grouping the wind power plants based on the spatial correlation strength of the historical actually measured wind power output data, taking the historical actually measured wind power output data corresponding to each wind power plant group as a fractal, and modeling the spatial correlation of the wind power uncertainty set based on each fractal; modeling the time correlation of the wind power uncertainty set by using an e index method and a probability distribution method based on historical predicted wind power output data; and utilizing Gibbs sampling to correlate time and space correlation of the wind power uncertainty set to obtain a wind power uncertainty set with space-time correlation. The method is adaptive to the distribution shape of historical data.

Description

Technical Field

[0001] The present invention relates to the field of electrical engineering technology, and in particular to a wind power uncertainty set modeling method, system, medium and equipment. Background Art

[0002] Generating electricity through renewable energy is a key means to achieve the "dual carbon" goal, and wind power generation is an important part of it. However, due to the significant uncertainty of wind power and the difficulty in accurately describing it, it affects the flexibility requirements of the system. Under the condition of inaccurate description of wind power characteristics, the decisions made by dispatching and operation will deviate from the optimal operating point, resulting in reduced economic efficiency of the decision.

[0003] Robust optimization is one of the mainstream methods for dealing with wind power uncertainty. It has the advantage of ensuring the reliability of the dispatch plan and is consistent with the requirement of energy dispatch to put safety first, but it is relatively conservative in terms of decision-making economy. Robust optimization mainly uses box sets to describe wind power uncertainty and focuses on the safety of dispatch. However, it fails to envelop historical data with the smallest area or space, resulting in the flexible reserve capacity reserved by robust optimization for real-time operation exceeding the actual requirement, reducing the decision-making economy, and thus being very conservative in terms of decision-making economy. In order to improve the economy of robust optimization decisions, some studies use polyhedral uncertainty sets considering budget sets to describe wind power uncertainty. However, when considering the polyhedral set of budget sets to reduce conservatism, it does not consider the distribution shape of wind power historical data, and therefore cannot fully guarantee the safety of the dispatch plan. In order to improve the decision-making economy, some studies consider establishing a more refined uncertainty set, that is, an uncertainty set that can fully approximate the distribution shape of historical data. The distribution shape of historical data is a reflection of the spatial correlation and temporal correlation of the uncertainty set. For example, the use of nonlinear ellipsoid equations to establish spatiotemporal correlation models, the minimum elliptical convex hull to establish spatial correlation models, and the diamond convex hull to establish spatial correlation models are mostly based on specific geometric shapes to describe the distribution of historical data. The method is applicable only when the distribution of historical data is similar to the selected geometric shape. However, the wind power output of different systems and the wind power output of the same system in different seasons may present different data distribution characteristics, and most of them are irregular shapes. Using only a specific shape to describe the correlation of the uncertainty set is not adaptive. Summary of the invention

[0004] The purpose of the present invention is to solve the problem that the correlation of an uncertainty set described by only a certain shape is not adaptive, and to propose a wind power uncertainty set modeling method, comprising the following steps: S1. Obtain historical output data of different wind farms, including historical measured wind power output data and historical predicted wind power output data predicted based on historical measured wind power output data; S2. Grouping wind farms based on the spatial correlation strength of historical measured wind power output data, taking the historical measured wind power output data corresponding to each wind farm group as a fractal, and modeling the spatial correlation of the wind power uncertainty set based on each fractal; S3. Based on the historical measured wind power output data and the historical predicted wind power output data, the time correlation of the wind power uncertainty set is modeled using the e-index method and the probability distribution method; S4. Use Gibbs sampling to correlate the time correlation and spatial correlation of the wind power uncertainty set to obtain a wind power uncertainty set with time and space correlation.

[0005] Furthermore, each fractal is segmented to obtain a set of subsets, and the boundary subsets that do not contain historical measured wind power output data are removed to obtain irregular polyhedrons. The scene set composed of the boundary points of the irregular polyhedrons is used to characterize the spatial correlation of the wind power uncertainty set.

[0006] Furthermore, the historical measured wind power output data of irregular-shaped polyhedrons are divided into two subsets containing boundary points and excluding boundary points, and the vertices belonging only to the subset containing boundary points are used as elements describing the boundary of the uncertainty set.

[0007] Furthermore, S3 is specifically: S31. wind farms, and construct the time covariance matrix of historical measured wind power output data in different time periods : (1), Covariance matrix The elements in are calculated as follows: (2), in, , For any two time periods, , , is the number of wind farms in , The covariance between time periods, Used to control the time correlation intensity of the j-th wind farm; S32. Each wind farm generates a joint distribution of A Gaussian random sequence, is the number of scenarios in the wind power uncertainty set, for dimensional zero vector; is the covariance matrix; S33, calculate the cumulative distribution function value of each random variable of the Gaussian random sequence in step S32 , is the Gaussian cumulative distribution function, represents the value of the Gaussian random sequence of the j-th wind farm in each time period under the s-th scenario of the wind power uncertainty set in the t-th period, It is the random data about the j-th wind farm in the t-th period under the s-th scenario of the wind power uncertainty set that follows the uniform distribution of [0,1]; S34, using the segmented mapping method, Converted into historical forecast wind power output data Given Range The uncertainty set of wind power in each period Scenes , complete the time correlation modeling of wind power uncertainty set, where represents the historical forecast wind power output data for the tth period, represents the wind farm capacity, Indicates the width of the range taken, Represents the time correlation of the wind power uncertainty set in the sth scenario and time period t.

[0008] Furthermore, step S4 is specifically as follows: S41. Based on the boundary points of the irregularly shaped polyhedron, the conditional cumulative distribution function of the actual wind power output of the wind farm is calculated, which is expressed as: (3), (4), in, Indicates The wind farm is in the wind power uncertainty set In this scenario The conditional joint probability density function of the time period, Indicates The wind farm is in the wind power uncertainty set In this scenario The actual output value of each period, The lower boundary point of the irregular-shaped polyhedron in the first period, The lower boundary point of the irregularly shaped polyhedron representing the 24th period, The upper boundary point of the irregularly shaped polyhedron in the first period, The upper boundary point of the irregular polyhedron in the 24th period, P represents conditional probability; make (5) in, Indicates the first scenario of the wind power uncertainty set for n wind farms. The sequence of actual output values ​​in each period, Indicates the number of wind farms n A sequence of historical measured wind power output data for a period of time; S42, combined with the time correlation of the wind power uncertainty set, the conditional cumulative distribution function Perform discretization sampling to obtain the The wind farm is in the wind power uncertainty set In this scenario Cumulative probability of time period ; S43, using inverse transformation right Make updates; S44. Implement steps S41-S43 for each time period and each scenario, discard the scenarios during the running-in period, and finally obtain a set of wind power uncertainties with spatiotemporal correlation.

[0009] Furthermore, combined with the time correlation of the wind power uncertainty set, the conditional cumulative distribution function Discretized sampling is expressed as: (6) in, represents the length of the vector, means rounding up to the nearest integer. Express Sampling the values ​​of the indexes in brackets.

[0010] The present invention also proposes a wind power uncertainty ensemble modeling system, comprising: A data acquisition module is used to acquire historical output data of different wind farms, including historical measured wind power output data and historical predicted wind power output data predicted based on historical measured wind power output data; A wind power uncertainty set spatial correlation modeling module is used to group wind farms based on the spatial correlation strength of historical measured wind power output data, take the historical measured wind power output data corresponding to each wind farm group as a fractal, and model the spatial correlation of the wind power uncertainty set based on each fractal; Wind power uncertainty set time correlation modeling module, which is used to model the time correlation of wind power uncertainty set based on historical measured wind power output data and historical predicted wind power output data using the e-index method and probability distribution method; The module for obtaining a wind power uncertainty set with spatiotemporal correlation is used to utilize the time correlation and spatial correlation of the wind power uncertainty set by Gibbs sampling to obtain a wind power uncertainty set with spatiotemporal correlation.

[0011] The present invention further proposes a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned wind power uncertainty set modeling method is implemented.

[0012] The present invention also proposes an electronic device, comprising a processor and a memory, wherein the processor and the memory are interconnected, wherein the memory is used to store a computer program, the computer program comprises computer-readable instructions, and the processor is configured to call the computer-readable instructions to execute the above-mentioned wind power uncertainty set modeling method.

[0013] The beneficial effects brought by the technical solution provided by the present invention are: The present invention proposes a method for constructing a wind power uncertainty set based on a fractal method. First, the spatial correlation of the wind power uncertainty set is modeled based on a fractal body, and the temporal correlation of the wind power uncertainty set is modeled. The temporal correlation and spatial correlation of the two modelings are associated to obtain the spatiotemporal correlation wind power uncertainty modeling. The present invention is adaptive to the distribution shape of historical data. By incorporating probability distribution technology into the modeling process, the decoupled modeling of the spatiotemporal correlation of the uncertainty set is achieved, and the dimensionality curse problem of the joint modeling of spatiotemporal correlation is avoided. The advantages of the fractal method can be retained to improve the economic efficiency of decision-making, while taking into account the computational tractability of the optimization method. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 is a flow chart of a wind power uncertainty ensemble modeling method according to an embodiment of the present invention; Figure 2 is an example diagram of an irregularly shaped polyhedron according to an embodiment of the present invention; Figure 3 It is a block diagram of an electronic device in an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0015] To make the objectives, technical solutions and advantages of the present invention more clear, the embodiments of the present invention will be further described below with reference to the accompanying drawings.

[0016] Embodiment 1: A flow chart of the wind power uncertainty ensemble modeling method according to an embodiment of the present invention is as follows Figure 1 , specifically including the following steps: S1. Obtain historical output data of different wind farms, including historical measured wind power output data and historical predicted wind power output data predicted based on historical measured wind power output data.

[0017] In a preferred embodiment of the present invention, the wind power output data is measured once every hour. For example, the historical measured wind power output data includes the first Days, a total of n days of 24-hour historical measured data per day, of which the 24-hour historical measured data on the dth day is expressed as: The historical forecast wind power output data includes the 24-hour historical forecast for the dth day: , the predicted data is obtained based on the data of n-1 days before the d day.

[0018] S2. Wind farms are grouped based on the spatial correlation strength of historical measured wind power output data, the historical measured wind power output data corresponding to each wind farm group is used as a fractal, and the spatial correlation of the wind power uncertainty set is modeled based on each fractal.

[0019] In a preferred embodiment of the present invention, firstly, based on the historical output data of different wind farms, the spatial correlation strength of the outputs of different wind farms is counted, and the wind farms are grouped in order of the size of the correlation strength, such as: wind farm group 1, wind farm group 2, wind farm group 3, etc., and the historical output data corresponding to the wind farm groupings are used as fractals, such as: fractal 1 is the historical output data of wind farm group 1, fractal 1 constitutes hypercube 1, fractal 2 is the historical output data of wind farm group 2, and fractal 2 constitutes hypercube 2.

[0020] Each fractal body is segmented to obtain a set of subsets, and the boundary subsets without historical output data are cut off to obtain an irregular polyhedron. The example diagram of the irregular polyhedron in the embodiment of the present invention is shown in FIG. Figure 2 According to the principle that the worst scenario of robust optimization is located at the vertex of the convex hull, the scenario set composed of the boundary points of the irregular polyhedron and its spatial distribution are used to characterize the spatial correlation of the uncertainty set. This scenario-based description form is used to transform the subsequent robust optimization problem into an equivalent deterministic optimization problem, thereby facilitating the application of distributed optimization methods. The historical measured wind power output data of the irregular polyhedron is divided into two subsets: those with boundary points and those without boundary points. Figure 2 The two types of subsets containing and not containing boundary points are compared to obtain the feature differences between the two. Based on the above method, the boundary subset is identified, and the vertices that only belong to the subset containing boundary points are selected as elements describing the boundary of the uncertainty set.

[0021] S3. Based on the historical measured wind power output data and the historical predicted wind power output data, the time correlation of the wind power uncertainty set is modeled using the e-index method and the probability distribution method.

[0022] In the preferred embodiment of the present invention, specifically: S31. wind farms, and construct the time covariance matrix of historical measured wind power output data in different time periods : (1), Covariance matrix The elements in are calculated as follows: (2), in, , For any two time periods, , , is the number of wind farms in , The covariance between time periods, Used to control the time correlation strength of the j-th wind farm.

[0023] S32. Each wind farm generates a joint distribution of A Gaussian random sequence, is the number of scenarios in the wind power uncertainty set, for dimensional zero vector; is the covariance matrix.

[0024] S33, calculate the cumulative distribution function (CDF) value of each random variable of the Gaussian random sequence in step S32 , represents the value of the Gaussian random sequence of the j-th wind farm in each time period under the s-th scenario of the wind power uncertainty set in the t-th period. The Gaussian random sequence of the j-th wind farm in different time periods under the s-th scenario of the wind power uncertainty set is expressed as: ( ), ; is the Gaussian cumulative distribution function, It is the random data about the j-th wind farm in the t-th period under the s-th scenario of the wind power uncertainty set that follows the uniform distribution between [0,1].

[0025] S34, using the segmented mapping method, Converted into historical forecast wind power output data Given Range The uncertainty set of wind power in different periods of time Scenes , complete the time correlation modeling of wind power uncertainty set, where represents the historical forecast wind power output data for the tth period, represents the wind farm capacity, Indicates the width of the range taken, Represents the time correlation of the wind power uncertainty set in the sth scenario and time period t.

[0026] S4. Use Gibbs sampling to correlate the time correlation and spatial correlation of the wind power uncertainty set to obtain a wind power uncertainty set with time and space correlation.

[0027] In the preferred embodiment of the present invention, specifically: S41, based on the boundary points of irregularly shaped polyhedra, e.g. Figure 2 The uncertainty set boundary points in the irregular shape are taken as the upper boundary points, and the points below the irregular shape are taken as the lower boundary points. The conditional cumulative distribution function of the actual wind power output of the wind farm is calculated, which is expressed as: (3), (4), in, Indicates The wind farm is in the wind power uncertainty set In this scenario The conditional joint probability density function of the time period, Indicates The wind farm is in the wind power uncertainty set In this scenario The actual output value of each period, The lower boundary point of the irregular-shaped polyhedron in the first period, The lower boundary point of the irregularly shaped polyhedron representing the 24th period, The upper boundary point of the irregularly shaped polyhedron in the first period, The upper boundary point of the irregular polyhedron in the 24th period, P represents conditional probability.

[0028] Determine the initial value of Gibbs sampling, let: (5) in, Indicates the first scenario of the wind power uncertainty set for n wind farms. The sequence of actual output values ​​in each period, Indicates the number of wind farms n The sequence of historical measured wind power output data for a period of time.

[0029] S42, combined with the time correlation of the wind power uncertainty set, the conditional cumulative distribution function Perform discretization sampling to obtain the The wind farm is in the wind power uncertainty set In this scenario Cumulative probability of time period .

[0030] It is expressed as: (6) in, represents the length of the vector, means rounding up to the nearest integer. Express Sampling of the index values ​​in brackets.

[0031] S43, using inverse transformation right to update.

[0032] S44. Implement steps S41-S43 for each time period and each scenario, discard the scenarios during the running-in period, and finally obtain a set of wind power uncertainties with spatiotemporal correlation.

[0033] Embodiment 2: The present invention also proposes a wind power uncertainty ensemble modeling system, comprising: A data acquisition module is used to acquire historical output data of different wind farms, including historical measured wind power output data and historical predicted wind power output data predicted based on historical measured wind power output data; A wind power uncertainty set spatial correlation modeling module is used to group wind farms based on the spatial correlation strength of historical measured wind power output data, take the historical measured wind power output data corresponding to each wind farm group as a fractal, and model the spatial correlation of the wind power uncertainty set based on each fractal; Wind power uncertainty set time correlation modeling module, which is used to model the time correlation of wind power uncertainty set based on historical measured wind power output data and historical predicted wind power output data using the e-index method and probability distribution method; The module for obtaining a wind power uncertainty set with spatiotemporal correlation is used to utilize the time correlation and spatial correlation of the wind power uncertainty set by Gibbs sampling to obtain a wind power uncertainty set with spatiotemporal correlation.

[0034] Embodiment 3: In an exemplary embodiment, a computer-readable storage medium is included, the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned wind power uncertainty set modeling method is implemented.

[0035] Example 4: Please refer to Figure 3 In an exemplary embodiment, an electronic device is also included, including at least one processor, at least one memory, and at least one communication bus.

[0036] A computer program is stored in the memory, and the computer program includes computer-readable instructions. The processor calls the computer-readable instructions stored in the memory through a communication bus to execute the above-mentioned wind power uncertainty set modeling method.

[0037] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A wind power uncertainty ensemble modeling method, characterized in that: The following steps are involved: S1. Obtain historical output data of different wind farms, including historical measured wind power output data and historical predicted wind power output data predicted based on historical measured wind power output data; S2. Grouping wind farms based on the spatial correlation strength of historical measured wind power output data, taking the historical measured wind power output data corresponding to each wind farm group as a fractal, and modeling the spatial correlation of the wind power uncertainty set based on each fractal; S3. Based on the historical measured wind power output data and the historical predicted wind power output data, the time correlation of the wind power uncertainty set is modeled using the e-index method and the probability distribution method; S4. Use Gibbs sampling to correlate the time correlation and spatial correlation of the wind power uncertainty set to obtain a wind power uncertainty set with time and space correlation.

2. A wind power uncertainty ensemble modeling method according to claim 1, characterized in that: Each fractal is segmented to obtain a set of subsets, and the boundary subsets that do not contain historical measured wind power output data are cut off to obtain irregular polyhedrons. The scene set composed of the boundary points of the irregular polyhedrons is used to characterize the spatial correlation of the wind power uncertainty set.

3. A wind power uncertainty ensemble modeling method according to claim 2, characterized in that: The historical measured wind power output data of irregular-shaped polyhedrons are divided into two subsets with boundary points and without boundary points. The vertices belonging only to the subset containing boundary points are used as elements to describe the boundary of the uncertainty set.

4. A wind power uncertainty ensemble modeling method according to claim 3, characterized in that: S3 is specifically: S31. wind farms, and construct the time covariance matrix of historical measured wind power output data in different time periods : （1）， Covariance matrix The elements in are calculated as follows: （2）， in, , For any two time periods, , , is the number of wind farms in , The covariance between time periods, Used to control the time correlation intensity of the j-th wind farm; S32. Each wind farm generates a joint distribution of A Gaussian random sequence, is the number of scenarios in the wind power uncertainty set, for dimensional zero vector; is the covariance matrix; S33, calculate the cumulative distribution function value of each random variable of the Gaussian random sequence in step S32 , is the Gaussian cumulative distribution function, represents the value of the Gaussian random sequence of the j-th wind farm in different time periods under the s-th scenario of the wind power uncertainty set in the t-th period, represents the random data about the j-th wind farm in the t-th period under the s-th scenario of the wind power uncertainty set that follows the uniform distribution of [0,1]; S34, using the segmented mapping method, Converted into historical forecast wind power output data Given Range The uncertainty set of wind power in each period Scenes , complete the time correlation modeling of wind power uncertainty set, where represents the historical forecast wind power output data for the tth period, represents the wind farm capacity, Indicates the width of the range taken, Represents the time correlation of the wind power uncertainty set in the sth scenario and time period t.

5. A wind power uncertainty ensemble modeling method according to claim 4, characterized in that: Step S4 is specifically as follows: S41. Based on the boundary points of the irregularly shaped polyhedron, the conditional cumulative distribution function of the actual wind power output of the wind farm is calculated, which is expressed as: （3）， （4）， in, Indicates The wind farm is in the wind power uncertainty set In this scenario The conditional joint probability density function of the time period, Indicates The wind farm is in the wind power uncertainty set In this scenario The actual output value of each period, The lower boundary point of the irregular-shaped polyhedron in the first period, The lower boundary point of the irregularly shaped polyhedron representing the 24th period, The upper boundary point of the irregularly shaped polyhedron in the first period, The upper boundary point of the irregular polyhedron in the 24th period, P represents conditional probability; make (5), in, Indicates the first scenario of the wind power uncertainty set for n wind farms. The sequence of actual output values ​​in each period, Indicates the number of wind farms n A sequence of historical measured wind power output data for a period of time; S42, combined with the time correlation of the wind power uncertainty set, the conditional cumulative distribution function Perform discretization sampling to obtain the The wind farm is in the wind power uncertainty set In this scenario Cumulative probability of time period ; S43, using inverse transformation right Make updates; S44. Implement steps S41-S43 for each time period and each scenario, discard the scenarios during the running-in period, and finally obtain a set of wind power uncertainties with spatiotemporal correlation.

6. A wind power uncertainty ensemble modeling method according to claim 5, characterized in that: Combined with the time correlation of wind power uncertainty set, the conditional cumulative distribution function Discretized sampling is expressed as: （6）， in, represents the length of the vector, means rounding up to the nearest integer. Express Sampling the values ​​of the indexes in the brackets.

7. A wind power uncertainty ensemble modeling system, characterized in that: include: A data acquisition module is used to acquire historical output data of different wind farms, including historical measured wind power output data and historical predicted wind power output data predicted based on historical measured wind power output data; A wind power uncertainty set spatial correlation modeling module is used to group wind farms based on the spatial correlation strength of historical measured wind power output data, take the historical measured wind power output data corresponding to each wind farm group as a fractal, and model the spatial correlation of the wind power uncertainty set based on each fractal; Wind power uncertainty set time correlation modeling module, which is used to model the time correlation of wind power uncertainty set based on historical measured wind power output data and historical predicted wind power output data using the e-index method and probability distribution method; The module for obtaining a wind power uncertainty set with spatiotemporal correlation is used to utilize the time correlation and spatial correlation of the wind power uncertainty set by Gibbs sampling to obtain a wind power uncertainty set with spatiotemporal correlation.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the processor and the memory are interconnected, wherein the memory is used to store a computer program, the computer program comprises computer-readable instructions, and the processor is configured to call the computer-readable instructions to execute the method according to any one of claims 1 to 6.

Images