Renewable energy grid-connected adjusting method and system

Abstract

The invention relates to the technical field of renewable energy sources, and particularly discloses a renewable energy source grid-connected adjustment method and system, and the method comprises the steps: obtaining historical power generation scene data, carrying out the clustering of the historical power generation scene data, and screening out a typical power generation scene of the historical power generation scene according to a clustering result; obtaining current power generation scene data, and determining a current power generation power change curve according to a typical power generation scene corresponding to the current power generation scene data; and determining a system stability level according to the current generated power change curve, and making a renewable energy power generation plan according to the current generated power change curve and the system stability level. According to the method, the stability level of the system can be predicted, the optimal power generation plan of the renewable energy is formulated based on the prediction result, and the stability of grid-connected operation of the renewable energy is ensured.

Description

Technical Field

[0001] The present application relates to the field of renewable energy technology, and more specifically, to a renewable energy grid-connected regulation method and system. Background Art

[0002] Renewable Energy refers to energy that can be continuously regenerated and used sustainably in nature, and is harmless or minimally harmful to the environment. It mainly includes non-chemical energy such as wind energy, solar energy, hydropower, biomass energy, geothermal energy, and ocean energy. Renewable Energy refers to resources that can be continuously regenerated and used sustainably in nature, and are inexhaustible and inexhaustible. It is harmless or minimally harmful to the environment, and the resources are widely distributed and suitable for local development and utilization. It mainly includes non-chemical energy such as wind energy, solar energy, hydropower, biomass energy, geothermal energy, and ocean energy.

[0003] In the existing technology, the grid-connected dispatching and management of renewable energy need to take into account the instability and intermittency of renewable energy. Compared with traditional thermal power generation, the power generation of renewable energy will be affected by factors such as weather conditions, resulting in unstable power supply. Therefore, how to formulate a stable renewable energy power generation plan has become a technical problem that needs to be solved urgently in this field. Summary of the invention

[0004] The present invention provides a renewable energy grid-connected regulation method and system to solve the problem that a relatively stable renewable energy power generation plan cannot be formulated in the prior art, including: Acquire historical power generation scenario data, cluster the historical power generation scenario data, and screen out typical power generation scenarios of the historical power generation scenarios based on the clustering results; Acquire current power generation scenario data, and determine the current power generation change curve according to the typical power generation scenario corresponding to the current power generation scenario data; Determine the system stability level based on the current power generation change curve, and formulate a renewable energy power generation plan based on the current power generation change curve and the system stability level.

[0005] Furthermore, clustering the historical power generation scenario data includes: A power generation feature data set is established based on historical power generation scenario data, and k initial clustering centers of the historical power generation scenario data set are randomly selected; Calculate the Euclidean distance between the sample data in the power generation characteristic data set and the initial cluster center, and divide each sample data into a corresponding cluster cluster according to the Euclidean distance between the sample data in the power generation characteristic data set and the initial cluster center; Calculate the average value of the sample data in each cluster, and re-determine the cluster center based on the average value of the sample data in each cluster; Repeat the above steps until the cluster center no longer changes or the number of iterations reaches the preset iteration threshold, and obtain k final cluster centers.

[0006] Furthermore, the typical power generation scenarios of the historical power generation scenarios are screened out according to the clustering results, including: Determine the distance between each historical power generation scenario and the final cluster center according to the clustering result of the historical power generation scenario data, and set the weight value of each historical power generation scenario according to the distance between each historical power generation scenario and the final cluster center; Obtain the probability value of each historical power generation scenario, and correct the corresponding probability value according to the weight value of each historical power generation scenario; The historical power generation scenarios with probability values ​​greater than a first preset threshold are screened out, and the historical power generation scenarios with probability values ​​greater than the first preset threshold are set as typical power generation scenarios of the cluster.

[0007] Further, the determining of the current power generation change curve according to the typical power generation scenario corresponding to the current power generation scenario data includes: Obtain the cluster to which the current power generation scenario belongs, and determine the typical power generation scenario corresponding to the cluster according to the cluster to which the current power generation scenario belongs; Calculate the correlation coefficient between each typical power generation scenario and the current power generation scenario, and determine the target typical power generation scenario according to the correlation coefficient between each typical power generation scenario and the current power generation scenario; The power generation change curve corresponding to the target typical power generation scenario is obtained, and the power generation change curve is corrected according to the correlation coefficient to obtain the power generation change curve of the current power generation scenario.

[0008] Furthermore, the correction of the power generation change curve according to the correlation coefficient includes: The power generation in the power generation change curve is corrected according to the power generation correction formula. The power generation correction formula is specifically as follows:

[0009] in, is the corrected power generation, is the power generation in the power generation curve, is the correlation coefficient between the typical power generation scenario and the current power generation scenario, is the preset standard correlation coefficient, is the preset range factor.

[0010] Further, determining the system stability level according to the current power generation change curve includes: Obtaining a preset sliding time window, and dividing the power generation change curve according to the preset sliding time window to obtain a plurality of sub-power generation change curves; Calculate the average value of each sub-generation power change curve, and select the sub-generation power change curve whose average value is greater than the second preset threshold as a high-power curve; The sub-generation power change curves whose average value is less than the third preset threshold are screened out as low-power curves, and the current system stability index is determined according to the high-power curve and the low-power curve.

[0011] Further, determining the current system stability index according to the high power curve and the low power curve includes: In the power generation curve, the midpoints of the high power curve and the low power curve are sequentially connected, and the absolute values ​​of the slopes of the midpoints of the adjacent high power curve and the low power curve are calculated; The sub-stability index is determined according to the absolute value of the slope of the midpoint of the adjacent high-power curve and the low-power curve, and the sum of all sub-stability indexes in the power generation change curve is calculated to obtain the current system stability index.

[0012] Further, determining the system stability level according to the current system stability index includes: Calculating the difference between the current system stability index and the preset standard stability index, and determining whether the difference between the current system stability index and the preset standard stability index is greater than a fourth preset threshold; If the difference between the current system stability index and the preset standard stability index is greater than a fourth preset threshold, setting the preset first level as the system stability level; If the difference between the current system stability index and the preset standard stability index is less than or equal to the fourth preset threshold, determining whether the difference between the current system stability index and the preset standard stability index is greater than the fifth preset threshold; If the difference between the current system stability index and the preset standard stability index is greater than a fifth preset threshold, the preset second level is set as the system stability level; If the difference between the current system stability index and the preset standard stability index is less than or equal to the fifth preset threshold, the preset third level is set as the system stability level.

[0013] Furthermore, formulating a renewable energy power generation plan according to the current power generation change curve and the system stability level includes: Obtain historical power generation data, and determine the power generation plan corresponding to the historical power generation change curve and system stability level based on the historical power generation data; Establish a training sample set according to the power generation plan corresponding to the historical power generation change curve and the system stability level, establish an initial power generation plan model according to the training sample set, and train the initial power generation plan model to obtain a trained power generation plan model; The current power generation change curve and system stability level are input into the trained power generation plan model to obtain the power generation plan.

[0014] In order to achieve the above object, the present invention also provides a renewable energy grid-connected regulation system, comprising: The first module is used to obtain historical power generation scenario data, cluster the historical power generation scenario data, and screen out typical power generation scenarios of the historical power generation scenarios according to the clustering results; The second module is used to obtain the current power generation scenario data and determine the current power generation change curve according to the typical power generation scenario corresponding to the current power generation scenario data; The third module is used to determine the system stability level according to the current power generation change curve, and formulate a renewable energy power generation plan according to the current power generation change curve and the system stability level.

[0015] The beneficial effects of the present invention are: By applying the above technical scheme, the present invention screens out typical power generation scenarios of renewable energy grid connection through a clustering algorithm, and can generate accurate and reliable typical power generation scenarios of renewable energy, and then realize accurate prediction of the power generation change curve through the typical power generation scenario, and obtain the system stability level based on the prediction result, so as to generate the corresponding renewable energy power generation plan in combination with the power generation change curve, effectively ensuring the stability of the grid-connected operation of renewable energy. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 The overall flow chart of a renewable energy grid-connected regulation method proposed in an embodiment of the present invention is shown; Figure 2 A schematic structural diagram of a renewable energy grid-connected regulation system proposed in an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0019] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0020] The present application embodiment provides a renewable energy grid-connected regulation method, such as Figure 1 As shown, the method includes: S101, acquiring historical power generation scenario data, clustering the historical power generation scenario data, and screening out typical power generation scenarios of the historical power generation scenarios according to the clustering results; In some embodiments of the present application, the clustering of historical power generation scenario data includes: establishing a power generation feature data set based on the historical power generation scenario data, randomly selecting k initial clustering centers of the historical power generation scenario data set; calculating the Euclidean distance from the sample data in the power generation feature data set to the initial clustering center, and dividing each sample data into a corresponding cluster cluster according to the Euclidean distance from the sample data in the power generation feature data set to the initial clustering center; calculating the average value of the sample data in each cluster cluster, and re-determining the cluster center according to the average value of the sample data in each cluster cluster; repeatedly iterating the above steps until the cluster center no longer changes or the number of iterations reaches a preset iteration threshold, and obtaining k final cluster centers.

[0021] In this embodiment, the power generation scenario data specifically includes meteorological characteristic data such as wind conditions and light conditions. The historical power generation scenario data is clustered using a k-means clustering algorithm, thereby screening out typical power generation scenarios within each cluster based on the clustering results.

[0022] In some embodiments of the present application, the method of screening out typical power generation scenarios of historical power generation scenarios based on clustering results includes: determining the distance between each historical power generation scenario and the final clustering center based on the clustering results of the historical power generation scenario data, and setting the weight value of each historical power generation scenario based on the distance between each historical power generation scenario and the final clustering center; obtaining the probability value of occurrence of each historical power generation scenario, and correcting the corresponding probability value based on the weight value of each historical power generation scenario; screening out historical power generation scenarios with probability values ​​greater than a first preset threshold, and setting the historical power generation scenarios with a probability of occurrence greater than the first preset threshold as typical power generation scenarios of the clustering cluster.

[0023] In this embodiment, the weight value of each historical power generation scenario is set according to the distance between each historical power generation scenario and the final cluster center. The closer the distance, the higher the corresponding weight value. The weight value of the cluster center is set to 1. The probability value of the occurrence of each historical power generation scenario is obtained by calculating the ratio of the number of times the historical power generation scenario appears in the historical power generation scenario to the number of times all power generation scenarios appear in the cluster cluster. The typical power generation scenario corresponding to each cluster cluster is screened out by combining the probability value of the occurrence of each historical power generation scenario with the corresponding weight value.

[0024] S102, obtaining current power generation scenario data, and determining a current power generation change curve according to a typical power generation scenario corresponding to the current power generation scenario data; In some embodiments of the present application, determining the current power generation change curve according to the typical power generation scenario corresponding to the current power generation scenario data includes: obtaining the cluster cluster to which the current power generation scenario belongs, and determining the typical power generation scenario corresponding to the cluster cluster according to the cluster cluster to which the current power generation scenario belongs; calculating the correlation coefficient between each typical power generation scenario and the current power generation scenario, and determining the target typical power generation scenario according to the correlation coefficient between each typical power generation scenario and the current power generation scenario; obtaining the power generation change curve corresponding to the target typical power generation scenario, and correcting the power generation change curve according to the correlation coefficient to obtain the power generation change curve of the current power generation scenario.

[0025] In some embodiments of the present application, the correction of the power generation change curve according to the correlation coefficient includes: correcting the power generation in the power generation change curve according to a power generation correction formula, and the power generation correction formula is specifically:

[0026] in, is the corrected power generation, is the power generation in the power generation curve, is the correlation coefficient between the typical power generation scenario and the current power generation scenario, is the preset standard correlation coefficient, is the preset range factor.

[0027] In this embodiment, the correlation coefficients of the current power generation scenario and multiple typical power generation scenarios in the corresponding cluster are calculated respectively. The range of the correlation coefficient is between -1 and 1, where 1 indicates a completely positive correlation, -1 indicates a completely negative correlation, and 0 indicates no correlation. The typical power generation scenario with the largest correlation coefficient is screened out to obtain the target typical power generation scenario. Each typical power generation scenario corresponds to a power generation change curve. The power generation change curve corresponding to the target typical power generation scenario is corrected according to the correlation coefficient to obtain the power generation change curve of the current power generation scenario.

[0028] S103, determining the system stability level according to the current power generation change curve, and formulating a power generation plan for renewable energy according to the current power generation change curve and the system stability level.

[0029] In some embodiments of the present application, determining the system stability level based on the current power generation change curve includes: obtaining a preset sliding time window, dividing the power generation change curve according to the preset sliding time window, and obtaining a plurality of sub-power generation change curves; calculating the average value of each sub-power generation change curve, and screening out the sub-power generation change curves with an average value greater than a second preset threshold as high-power curves; screening out the sub-power generation change curves with an average value less than a third preset threshold as low-power curves, and determining the current system stability index based on the high-power curve and the low-power curve.

[0030] In some embodiments of the present application, determining the current system stability index based on the high power curve and the low power curve includes: connecting the midpoints of the high power curve and the low power curve in sequence in the power generation change curve, and calculating the absolute values ​​of the slopes of the midpoints of adjacent high power curves and low power curves; determining a sub-stability index based on the absolute values ​​of the slopes of the midpoints of adjacent high power curves and low power curves, calculating the sum of all sub-stability indicators in the power generation change curve, and obtaining the current system stability index.

[0031] In this embodiment, the fluctuation of the power generation change curve is calculated by the changes of the high power curve and the low power curve in the power generation change curve, and the system stability index is calculated by the fluctuation of the power generation change curve. The larger the system stability index, the higher the fluctuation of the power generation change curve.

[0032] In some embodiments of the present application, determining the system stability based on the power generation prediction result includes: calculating the difference between the current system stability index and the preset standard stability index, and judging whether the difference between the current system stability index and the preset standard stability index is greater than a fourth preset threshold; if the difference between the current system stability index and the preset standard stability index is greater than the fourth preset threshold, setting the preset first level as the system stability level; if the difference between the current system stability index and the preset standard stability index is less than or equal to the fourth preset threshold, judging whether the difference between the current system stability index and the preset standard stability index is greater than a fifth preset threshold; if the difference between the current system stability index and the preset standard stability index is greater than the fifth preset threshold, setting the preset second level as the system stability level; if the difference between the current system stability index and the preset standard stability index is less than or equal to the fifth preset threshold, setting the preset third level as the system stability level.

[0033] In this embodiment, the system stability level of the current renewable energy grid connection is set by the difference between the current system stability index and the preset standard stability index. The larger the difference, the higher the corresponding system stability level.

[0034] In some embodiments of the present application, formulating a power generation plan according to system stability includes: Obtain historical power generation data, and determine the power generation plan corresponding to the historical power generation change curve and the system stability level according to the historical power generation data; establish a training sample set according to the power generation plan corresponding to the historical power generation change curve and the system stability level, establish an initial power generation plan model according to the training sample set and train the initial power generation plan model to obtain a trained power generation plan model; input the current power generation change curve and the system stability level into the trained power generation plan model to obtain a power generation plan.

[0035] In this embodiment, the historical power generation change curve and system stability level are determined based on the deep learning neural network model combined with historical power generation data to formulate the current renewable energy power generation plan, which can effectively ensure the stability of renewable energy grid-connected operation.

[0036] Based on the same technical concept, such as Figure 2 As shown, the present invention also provides a renewable energy grid-connected regulation system, including: a first module, used to obtain historical power generation scenario data, cluster the historical power generation scenario data, and screen out typical power generation scenarios of the historical power generation scenarios according to the clustering results; a second module, used to obtain current power generation scenario data, and determine a current power generation power change curve according to the typical power generation scenario corresponding to the current power generation scenario data; a third module, used to determine a system stability level according to the current power generation power change curve, and formulate a renewable energy power generation plan according to the current power generation power change curve and the system stability level.

[0037] By applying the above technical solutions, the present invention obtains historical power generation scenario data, clusters the historical power generation scenario data, and screens out typical power generation scenarios of historical power generation scenarios according to the clustering results; obtains current power generation scenario data, and determines the current power generation change curve according to the typical power generation scenario corresponding to the current power generation scenario data; determines the system stability level according to the current power generation change curve, and formulates a power generation plan for renewable energy according to the current power generation change curve and the system stability level. The present invention can predict the system stability level, and formulate the optimal power generation plan for renewable energy based on the prediction results, so as to ensure the stability of the grid-connected operation of renewable energy.

[0038] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present invention can be implemented by hardware, or by software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each implementation scenario of the present invention.

[0039] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A renewable energy grid-connected regulation method, characterized in that: The method comprises: Acquire historical power generation scenario data, cluster the historical power generation scenario data, and screen out typical power generation scenarios of the historical power generation scenarios based on the clustering results; Acquire current power generation scenario data, and determine the current power generation change curve according to the typical power generation scenario corresponding to the current power generation scenario data; Determine the system stability level based on the current power generation change curve, and formulate a renewable energy power generation plan based on the current power generation change curve and the system stability level.

2. The renewable energy grid-connected regulation method according to claim 1, characterized in that: The clustering of historical power generation scenario data includes: A power generation feature data set is established based on historical power generation scenario data, and k initial clustering centers of the historical power generation scenario data set are randomly selected; Calculate the Euclidean distance between the sample data in the power generation characteristic data set and the initial cluster center, and divide each sample data into a corresponding cluster cluster according to the Euclidean distance between the sample data in the power generation characteristic data set and the initial cluster center; Calculate the average value of the sample data in each cluster, and re-determine the cluster center based on the average value of the sample data in each cluster; Repeat the above steps until the cluster center no longer changes or the number of iterations reaches the preset iteration threshold, and obtain k final cluster centers.

3. The renewable energy grid-connected regulation method according to claim 2, characterized in that: The typical power generation scenarios of the historical power generation scenarios are screened out according to the clustering results, including: Determine the distance between each historical power generation scenario and the final cluster center according to the clustering result of the historical power generation scenario data, and set the weight value of each historical power generation scenario according to the distance between each historical power generation scenario and the final cluster center; Obtain the probability value of each historical power generation scenario, and correct the corresponding probability value according to the weight value of each historical power generation scenario; The historical power generation scenarios with probability values ​​greater than a first preset threshold are screened out, and the historical power generation scenarios with probability values ​​greater than the first preset threshold are set as typical power generation scenarios of the cluster.

4. The renewable energy grid-connected regulation method according to claim 3, characterized in that: The determining of the current power generation change curve according to the typical power generation scenario corresponding to the current power generation scenario data includes: Obtain the cluster to which the current power generation scenario belongs, and determine the typical power generation scenario corresponding to the cluster according to the cluster to which the current power generation scenario belongs; Calculate the correlation coefficient between each typical power generation scenario and the current power generation scenario, and determine the target typical power generation scenario according to the correlation coefficient between each typical power generation scenario and the current power generation scenario; The power generation change curve corresponding to the target typical power generation scenario is obtained, and the power generation change curve is corrected according to the correlation coefficient to obtain the power generation change curve of the current power generation scenario.

5. The renewable energy grid-connected regulation method according to claim 4, characterized in that: The step of correcting the power generation change curve according to the correlation coefficient includes: The power generation in the power generation change curve is corrected according to the power generation correction formula. The power generation correction formula is specifically as follows: in, is the corrected power generation, is the power generation in the power generation curve, is the correlation coefficient between the typical power generation scenario and the current power generation scenario, is the preset standard correlation coefficient, is the preset range factor.

6. The renewable energy grid-connected regulation method according to claim 5, characterized in that: Determining the system stability level according to the current power generation change curve includes: Obtaining a preset sliding time window, and dividing the power generation change curve according to the preset sliding time window to obtain a plurality of sub-power generation change curves; Calculate the average value of each sub-generation power change curve, and select the sub-generation power change curve whose average value is greater than the second preset threshold as a high-power curve; The sub-generation power change curve whose average value is less than the third preset threshold is screened out as the low power curve, the current system stability index is determined according to the high power curve and the low power curve, and the system stability level is determined according to the current system stability index.

7. The renewable energy grid-connected regulation method according to claim 6, characterized in that: Determining the current system stability index according to the high power curve and the low power curve includes: In the power generation curve, the midpoints of the high power curve and the low power curve are sequentially connected, and the absolute values ​​of the slopes of the midpoints of the adjacent high power curve and the low power curve are calculated; The sub-stability index is determined according to the absolute value of the slope of the midpoint of the adjacent high-power curve and the low-power curve, and the sum of all sub-stability indexes in the power generation change curve is calculated to obtain the current system stability index.

8. The renewable energy grid-connected regulation method according to claim 7, characterized in that: Determining the system stability level according to the current system stability index includes: Calculating the difference between the current system stability index and the preset standard stability index, and determining whether the difference between the current system stability index and the preset standard stability index is greater than a fourth preset threshold; If the difference between the current system stability index and the preset standard stability index is greater than a fourth preset threshold, setting the preset first level as the system stability level; If the difference between the current system stability index and the preset standard stability index is less than or equal to the fourth preset threshold, determining whether the difference between the current system stability index and the preset standard stability index is greater than the fifth preset threshold; If the difference between the current system stability index and the preset standard stability index is greater than a fifth preset threshold, the preset second level is set as the system stability level; If the difference between the current system stability index and the preset standard stability index is less than or equal to the fifth preset threshold, the preset third level is set as the system stability level.

9. The renewable energy grid-connected regulation method according to claim 8, characterized in that: The method of formulating a renewable energy power generation plan according to the current power generation change curve and the system stability level includes: Obtain historical power generation data, and determine the power generation plan corresponding to the historical power generation change curve and system stability level based on the historical power generation data; Establish a training sample set according to the power generation plan corresponding to the historical power generation change curve and the system stability level, establish an initial power generation plan model according to the training sample set, and train the initial power generation plan model to obtain a trained power generation plan model; The current power generation change curve and system stability level are input into the trained power generation plan model to obtain the power generation plan.

10. A renewable energy grid-connected regulation system, characterized in that: include: The first module is used to obtain historical power generation scenario data, cluster the historical power generation scenario data, and screen out typical power generation scenarios of the historical power generation scenarios according to the clustering results; The second module is used to obtain the current power generation scenario data and determine the current power generation change curve according to the typical power generation scenario corresponding to the current power generation scenario data; The third module is used to determine the system stability level according to the current power generation change curve, and formulate a renewable energy power generation plan according to the current power generation change curve and the system stability level.

Images