Energy storage siting method

Abstract

The application provides a kind of energy storage site selection method, belongs to energy storage site selection technical field, in the application, energy storage candidate site image is shot by unmanned aerial vehicle, and according to the texture features on energy storage candidate site image, find the flat area on energy storage candidate site image, then combine the flatness of each flat area and transmission distance, select the optimal energy storage location, realize a kind of site selection method based on topographic features and transmission distance, improve site selection accuracy, avoid artificial subjective factor interference, the application solves the problem that the existing energy storage site selection method by artificial is difficult to realize accurate energy storage site selection.

Description

Technical Field

[0001] This invention relates to the field of energy storage site selection technology, and more specifically, to an energy storage site selection method. Background Technology

[0002] Energy storage locations vary depending on the region and application scenario. Current key factors considered in energy storage site selection include: geographical location, topography, meteorological conditions, grid connection conditions, and market demand. Among these, geographical location and topography are the most important factors, directly affecting the construction cost of energy storage equipment.

[0003] Current methods for assessing geographical location and topography involve on-site investigations, where technical personnel traverse every area of ​​potential energy storage sites to find the optimal location. However, existing energy storage site selection methods rely heavily on the experience of technical personnel, which varies from person to person, making it difficult to achieve accurate site selection. Summary of the Invention

[0004] The purpose of this invention is to provide an energy storage location method that solves the problem that existing energy storage location methods are difficult to achieve accurate energy storage location.

[0005] The embodiments of the present invention are achieved through the following technical solution: an energy storage site selection method, comprising the following steps:

[0006] S1. Take images of potential energy storage sites using drones;

[0007] S2. Based on the texture features on the energy storage candidate site image, find the flat areas on the energy storage candidate site image;

[0008] S3. Based on the flatness of each flat area and the transmission distance, establish the site selection objective function and find the optimal energy storage site.

[0009] Furthermore, step S2 includes the following sub-steps:

[0010] S21. Perform grayscale processing on the image of the energy storage candidate site to obtain a grayscale image;

[0011] S22. Select texture pixels from the grayscale image and construct a texture map;

[0012] S23. Set the energy storage location window and use the energy storage location window to traverse the texture map until the texture map is completely traversed.

[0013] S24. Extract the texture lines under the energy storage location window in the texture map during each traversal;

[0014] S25. Extract the texture features of each texture line;

[0015] S26. Based on the texture features of all texture lines under the energy storage location window in the texture map, calculate the flatness of the image region corresponding to the energy storage location window during the current traversal.

[0016] S27. Select image regions with flatness greater than the flatness threshold as flat regions.

[0017] The beneficial effects of the above-mentioned further solution are as follows: In this invention, the image of the energy storage candidate site is processed into a grayscale image, and then texture pixels are selected based on the brightness values ​​of different contour images on the grayscale image to construct a texture map. The energy storage location window is traversed on the texture map. During each traversal, the texture lines under the energy storage location window in the texture map are extracted. The flatness of the image area corresponding to the energy storage location window is evaluated through the texture features on all texture lines. Only some flat areas can be retained as temporary candidate sites for energy storage.

[0018] Furthermore, step S22 includes the following sub-steps:

[0019] S221. Calculate the brightness change value of each pixel in each 3*3 region of the grayscale image;

[0020] S222. Select the center pixels of the 3*3 region where the brightness change value is greater than the change threshold, and mark them as texture pixels. All texture pixels constitute a texture map.

[0021] Furthermore, the formula for calculating the brightness change value in S221 is as follows:

[0022]

[0023] Among them, L f L represents the brightness variation value over a 3x3 area. o L is the brightness value of the center pixel. i Let be the brightness value of the i-th pixel in the 3x3 region excluding the center pixel, where i is the pixel number and e is a natural constant.

[0024] The beneficial effects of the above-mentioned further solution are as follows: changes in brightness values ​​indicate changes in the contours of the image. In this invention, the difference between the brightness values ​​of the center pixel and the brightness values ​​of the surrounding pixels reflects the distance between the center pixel and the surrounding pixels. In this way, texture pixels that can reflect the contours of the image are selected.

[0025] Furthermore, step S25 includes the following sub-steps:

[0026] S251. Divide each texture line into multiple lines to obtain multiple texture sub-lines;

[0027] S252. Take one pixel at each end of each texture sub-line and calculate the tilt angle of each texture sub-line.

[0028] S253. The tilt angle of each texture sub-line constitutes the texture feature of a texture line.

[0029] The beneficial effects of the above-mentioned further solution are as follows: In this invention, the texture lines under the energy storage position window in the texture map are extracted during each traversal, that is, the area under the energy storage position window in the texture map is processed separately during each traversal, each texture line is divided into multiple lines, one pixel is taken at each end of each texture sub-line, and the tilt angle of a short texture sub-line is calculated. Multiple tilt angles constitute texture features.

[0030] Furthermore, the formula for calculating the tilt angle of each texture sub-line in S252 is as follows:

[0031]

[0032] Where θ is the tilt angle of each texture sub-line, arctan is the arctangent operation, and y f x is the ordinate of a pixel at one end. f Let y be the x-coordinate of a pixel at one end. a x is the ordinate of the pixel at the other end. a This is the x-coordinate of the pixel at the other end.

[0033] Furthermore, step S26 includes the following sub-steps:

[0034] S261. Calculate the tortuosity of each texture line based on the texture characteristics of each texture line under the energy storage location window in the texture map;

[0035] S262. Calculate the flatness of the image region corresponding to the energy storage location window during the current traversal based on the tortuosity of each texture line.

[0036] Furthermore, the formula for calculating the tortuosity of each texture line in S261 is as follows:

[0037]

[0038] Among them, T n，O Let θ be the tortuosity of the nth texture line. n，k Let K be the tilt angle of the k-th sub-texture line in the texture feature of the n-th texture line, where K is the number of tilt angles in the texture feature, e is a natural constant, k is the sub-texture line number, and n is the texture line number.

[0039] The beneficial effect of the above-mentioned further solution is that: in this invention, all tilt angles in the texture features of each texture line are added together and an exponential function is set to enhance the distinguishability between the tortuosity of each texture line.

[0040] Furthermore, the formula for calculating the flatness of the image region corresponding to the energy storage location window during the current traversal in S262 is as follows:

[0041]

[0042] Where E is the flatness of the image region corresponding to the energy storage location window, and T n，O θ represents the tortuosity of the nth texture line, N represents the number of texture lines in the image region corresponding to the energy storage location window, n represents the texture line number, θ represents the scaling factor, and max represents the maximum value.

[0043] The beneficial effects of the above-mentioned further solution are as follows: In this invention, the flatness of the corresponding image region is evaluated based on the tortuosity of all texture lines in the image region corresponding to the energy storage location window, and when calculating the flatness, the maximum tortuosity is extracted to filter out the flat region to the greatest extent.

[0044] Furthermore, the addressing objective function in S3 is:

[0045] target = min{w E E m +w s L m，s +w d L m，d , m=1,...,M}

[0046] Where target is the minimum value obtained by the location objective function, E m Let w be the flatness of the m-th flat region. E The flatness E of the m-th flat region m The weight, L m，s Let L be the power generation and transmission distance in the m-th flat region. m，d Let w be the power transmission distance for the m-th flat region. s The power transmission distance L in the m-th flat region m，s The weight, w d Let L be the power transmission distance for the m-th flat area. m，d The weights are: min = minimum value, M = number of flat regions, and m = number of flat regions.

[0047] The beneficial effects of the above-mentioned further solutions are as follows: the present invention considers the flatness of each flat area, as well as the power transmission distance and power generation transmission distance in each flat area, and ensures that the construction cost of energy storage is minimized based on geographical location and topography.

[0048] The technical solution of this invention has at least the following advantages and beneficial effects: In this invention, images of potential energy storage sites are captured by drones, and flat areas are found on the images based on texture features. Then, the optimal energy storage location is selected by combining the flatness of each flat area with the transmission distance. This realizes a site selection method based on topographic features and transmission distance, which improves the site selection accuracy and avoids interference from subjective human factors. This invention solves the problem that existing methods for manually selecting energy storage sites are difficult to achieve accurate site selection. Attached Figure Description

[0049] Figure 1 This is a flowchart of an energy storage site selection method. Detailed Implementation

[0050] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0051] like Figure 1 As shown, an energy storage site selection method includes the following steps:

[0052] S1. Take images of potential energy storage sites using drones;

[0053] S2. Based on the texture features on the energy storage candidate site image, find the flat areas on the energy storage candidate site image;

[0054] S3. Based on the flatness of each flat area and the transmission distance, establish the site selection objective function and find the optimal energy storage site.

[0055] S2 includes the following steps:

[0056] S21. Perform grayscale processing on the image of the energy storage candidate site to obtain a grayscale image;

[0057] S22. Select texture pixels from the grayscale image and construct a texture map;

[0058] S23. Set the energy storage location window and use the energy storage location window to traverse the texture map until the texture map is completely traversed.

[0059] S24. Extract the texture lines under the energy storage location window in the texture map during each traversal;

[0060] S25. Extract the texture features of each texture line;

[0061] S26. Based on the texture features of all texture lines under the energy storage location window in the texture map, calculate the flatness of the image region corresponding to the energy storage location window during the current traversal.

[0062] S27. Select image regions with flatness greater than the flatness threshold as flat regions.

[0063] In this embodiment, the size of the energy storage location window is the same as the area of ​​the energy storage region on the image, and the specific size can be set based on experience.

[0064] In this embodiment, the flatness threshold is set based on experience.

[0065] In this invention, the image of the energy storage candidate site is processed into a grayscale image. Based on the brightness values ​​of different contour images on the grayscale image, texture pixels are selected to construct a texture map. The energy storage location window is traversed on the texture map. During each traversal, the texture lines under the energy storage location window in the texture map are extracted. The flatness of the image area corresponding to the energy storage location window is evaluated by the texture features on all texture lines. Only a portion of the flat area is retained as a temporary candidate site for energy storage.

[0066] In this embodiment, when the energy storage location window traverses the texture map in step S23, it can move forward one row or one column each time it traverses, thereby changing the area of ​​the texture map covered by the energy storage location window.

[0067] S22 includes the following sub-steps:

[0068] S221. Calculate the brightness change value of each pixel in each 3*3 region of the grayscale image;

[0069] S222. Select the center pixels of the 3*3 region where the brightness change value is greater than the change threshold, and mark them as texture pixels. All texture pixels constitute a texture map.

[0070] In this embodiment, in step S221, each pixel on the grayscale image is taken as the center pixel, and the center pixel and its 3*3 neighborhood range is a 3*3 region.

[0071] In this embodiment, the change threshold is set based on experience.

[0072] The formula for calculating the brightness change value in S221 is as follows:

[0073]

[0074] Among them, L f L represents the brightness variation value over a 3x3 area. o L is the brightness value of the center pixel. i Let be the brightness value of the i-th pixel in the 3x3 region excluding the center pixel, where i is the pixel number and e is a natural constant.

[0075] Changes in brightness value indicate changes in the contour of an image. In this invention, the difference between the brightness value of the center pixel and the brightness values ​​of the surrounding pixels reflects the distance between the center pixel and the surrounding pixels. This method is used to select texture pixels that can represent the contour of the image.

[0076] In this invention, since the texture pixels that represent the image outline are filtered out in step S22, the texture map is a line map composed of each texture pixel. Therefore, each texture line can be processed.

[0077] S25 includes the following sub-steps:

[0078] S251. Divide each texture line into multiple lines to obtain multiple texture sub-lines;

[0079] S252. Take one pixel at each end of each texture sub-line and calculate the tilt angle of each texture sub-line.

[0080] S253. The tilt angle of each texture sub-line constitutes the texture feature of a texture line.

[0081] In this invention, the texture lines under the energy storage position window in the texture map are extracted during each traversal. That is, the area under the energy storage position window in the texture map is processed separately during each traversal. Each texture line is divided into multiple lines, and one pixel is taken at each end of each texture sub-line. The tilt angle of a short texture sub-line is calculated, and multiple tilt angles constitute texture features.

[0082] The formula for calculating the tilt angle of each texture sub-line in S252 is as follows:

[0083]

[0084] Where θ is the tilt angle of each texture sub-line, arctan is the arctangent operation, and y f x is the ordinate of a pixel at one end. f Let y be the x-coordinate of a pixel at one end. a x is the ordinate of the pixel at the other end. a This is the x-coordinate of the pixel at the other end.

[0085] S26 includes the following sub-steps:

[0086] S261. Calculate the tortuosity of each texture line based on the texture characteristics of each texture line under the energy storage location window in the texture map;

[0087] S262. Calculate the flatness of the image region corresponding to the energy storage location window during the current traversal based on the tortuosity of each texture line.

[0088] The formula for calculating the tortuosity of each texture line in S261 is as follows:

[0089]

[0090] Among them, T n，O Let θ be the tortuosity of the nth texture line. n，k Let K be the tilt angle of the k-th sub-texture line in the texture feature of the n-th texture line, where K is the number of tilt angles in the texture feature, e is a natural constant, k is the sub-texture line number, and n is the texture line number.

[0091] In this invention, all tilt angles in the texture features of each texture line are summed, and an exponential function is set to enhance the distinguishability between the tortuosity of each texture line.

[0092] The formula for calculating the flatness of the image region corresponding to the energy storage location window during the current traversal in S262 is as follows:

[0093]

[0094] Where E is the flatness of the image region corresponding to the energy storage location window, and T n，O θ represents the tortuosity of the nth texture line, N represents the number of texture lines in the image region corresponding to the energy storage location window, n represents the texture line number, θ represents the scaling factor, and max represents the maximum value.

[0095] In this invention, the flatness of the corresponding image region is evaluated based on the tortuosity of all texture lines in the image region corresponding to the energy storage location window. When calculating the flatness, the maximum tortuosity is extracted to filter out the flat regions to the greatest extent.

[0096] The addressing objective function in S3 is:

[0097] target = min{w E E m +w s L m，s +w d L m，d , m=1,...,M}

[0098] Where target is the minimum value obtained by the location objective function, E mLet w be the flatness of the m-th flat region. E The flatness E of the m-th flat region m The weight, L m，s Let L be the power generation and transmission distance in the m-th flat region. m，d Let w be the power transmission distance for the m-th flat region. s The power transmission distance L in the m-th flat region m，s The weight, w d Let L be the power transmission distance for the m-th flat area. m，d The weights are: min = minimum value, M = number of flat regions, and m = number of flat regions.

[0099] This invention considers the flatness of each flat area, as well as the power transmission distance and power generation distance in each flat area, to ensure that the construction cost of energy storage is minimized based on geographical location and topography.

[0100] This invention uses drones to capture images of potential energy storage sites. Based on the texture features of these images, flat areas are identified. Then, by combining the flatness of each flat area with the transmission distance, the optimal energy storage location is selected. This invention provides a site selection method based on topographic features and transmission distance, improving site selection accuracy and avoiding interference from subjective human factors. This invention solves the problem that existing methods for manually selecting energy storage sites are difficult to achieve accurate site selection.

[0101] The above are merely preferred embodiments of the present invention and are not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for energy storage site selection, characterized in that, Includes the following steps: S1. Take images of potential energy storage sites using drones; S2. Based on the texture features on the energy storage candidate site image, find the flat areas on the energy storage candidate site image; It includes the following steps: S21. Perform grayscale processing on the image of the energy storage candidate site to obtain a grayscale image; S22. Select texture pixels from the grayscale image and construct a texture map; S23. Set the energy storage location window and use the energy storage location window to traverse the texture map until the texture map is completely traversed. S24. Extract the texture lines under the energy storage location window in the texture map during each traversal; S25. Extract the texture features of each texture line; S26. Based on the texture features of all texture lines under the energy storage location window in the texture map, calculate the flatness of the image region corresponding to the energy storage location window during the current traversal. It includes the following steps: S261. Based on the texture characteristics of each texture line under the energy storage location window in the texture map, calculate the tortuosity of each texture line; the formula for calculating the tortuosity of the texture line is: in, For the first The curvature of the striped lines, For the first The texture features of the striped lines The tilt angle of the striped sub-lines. This represents the number of tilt angles in the texture features. It is a natural constant. For the sub-line number of the texture, The numbering of the texture lines; S262. Based on the tortuosity of each texture line, calculate the flatness of the image region corresponding to the energy storage location window during the current traversal; the formula for calculating the flatness is: in, The flatness of the image region corresponding to the energy storage location window. For the first The curvature of the striped lines, This represents the number of texture lines in the image region corresponding to the energy storage location window. The numbering of the texture lines. This is the proportionality coefficient. To obtain the maximum value; S27. Select image regions with flatness greater than the flatness threshold as flat regions; S3. Based on the flatness and transmission distance of each flat area, establish a site selection objective function to find the optimal energy storage site; the site selection objective function is: in, The minimum value obtained for the location objective function. For the first The flatness of a flat area For the first Flatness of a flat area The weight, For the first The power generation and transmission distance in a flat area For the first The power transmission distance for a flat area For the first Power transmission distance in a flat area The weight, For the first Power transmission distance in a flat area The weight, To obtain the minimum value, The number of flat areas. This refers to the numbering of the flat regions.

2. The energy storage site selection method according to claim 1, characterized in that, S22 includes the following steps: S221, Calculate each 3 on the grayscale image. The brightness variation of pixels in region 3; S222, Filter out 3 values ​​whose brightness change value is greater than the change threshold. The center pixel of the 3 regions is marked as the texture pixel, and all texture pixels constitute the texture map.

3. The energy storage site selection method according to claim 2, characterized in that, The formula for calculating the brightness change value in S221 is as follows: in, 3 Brightness variation values ​​in region 3 The brightness value of the center pixel. 3 The third region excluding the center pixel The brightness value of each pixel. The pixel number, It is a natural constant.

4. The energy storage site selection method according to claim 1, characterized in that, S25 includes the following sub-steps: S251. Divide each texture line into multiple lines to obtain multiple texture sub-lines; S252. Take one pixel at each end of each texture sub-line and calculate the tilt angle of each texture sub-line. S253. The tilt angle of each texture sub-line constitutes the texture feature of a texture line.

5. The energy storage site selection method according to claim 4, characterized in that, The formula for calculating the tilt angle of each texture sub-line in S252 is as follows: in, The tilt angle of each texture sub-line, For arctangent operation, The y-coordinate of the pixel at one end. Let x be the x-coordinate of the pixel at one end. Let be the ordinate of the pixel at the other end. This is the x-coordinate of the pixel at the other end.

Images