Virtual power plant resource combination optimization method

Abstract

The invention discloses a virtual power plant resource combination optimization method, and relates to the technical field of virtual power plants, and the method comprises the steps: dividing a line section set into four facing surfaces of a ground facing surface, a left side wall facing surface, an underground facing surface, and a right side wall facing surface, and according to the abnormal environment temperature values of the four facing surfaces, determining the abnormal environment temperature values of the four facing surfaces; predicting a temperature loss energy consumption prediction value of each line section in the line section set caused by the influence of the environment temperature, and counting the crack length of the crack section and the crack direction of the crack section; and predicting a first energy consumption prediction value generated when each line section in the line section set is influenced by the crack length and a second energy consumption prediction value generated when each line section in the line section set is influenced by cracks with different gradients, and reasonably distributing the energy distribution quantity required by the transmission line according to the three energy consumption prediction values. According to the virtual power plant resource combination optimization method provided by the invention, the resource allocation reasonability can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of virtual power plants, and in particular to a method for optimizing resource combinations of virtual power plants. Background Art

[0002] A virtual power plant (VPP) is a power system that leverages advanced information and communication technologies and software systems to optimize and centrally control distributed energy resources (such as solar energy, wind energy, energy storage equipment, and adjustable loads). Resource optimization is a key component of VPP operations. It aims to improve energy efficiency and reduce operating costs by rationally allocating various energy resources, while ensuring stable and reliable power supply.

[0003] In traditional technologies, resource allocation is often configured based on the demand of the demander, without further analysis of the energy loss generated during the energy transmission process on the line. As a result, the actual resource allocation amount received by the final demander is insufficient, thereby reducing the efficiency of resource allocation. Summary of the Invention

[0004] In order to overcome the above-mentioned deficiencies of the prior art, the present application provides a virtual power plant resource combination optimization method.

[0005] This application provides a virtual power plant resource combination optimization method, the method comprising: Step S1: obtaining a transmission line buried in an underground space for energy transmission, dividing the transmission line into a number of equal segments to obtain a line segment set, dividing each line segment in the line segment set based on an orientation surface to obtain four orientation surfaces, calculating a weighted ratio of energy consumption influence of each of the four orientation surfaces based on the four orientation surfaces, and calculating a first correlation coefficient between historical ambient temperature data and historical line energy consumption values based on the acquired historical detection feature data, wherein the four orientation surfaces are a surface facing the ground, a surface facing the left wall, a surface facing the underground, and a surface facing the right wall; Step S2: detecting the current temperature value of the first facing surface among the four facing surfaces of each line section in the line section set, and predicting an abnormal ambient temperature value based on the distance of the first facing surface of the line section from the ground and the distance of the third facing surface from the ground; and predicting a temperature loss energy consumption prediction value caused by the ambient temperature for each line section in the line section set based on the abnormal ambient temperature value, the energy consumption influence weight ratio, and the first correlation coefficient; Step S3: perform image detection on the line section set to extract crack sections with cracks, count the crack lengths of each line section in the crack section and the crack directions of each line section in the crack section, so as to predict a first energy consumption prediction value generated by the influence of the crack length on each line section in the line section set and a second energy consumption prediction value generated by the influence of cracks of different inclinations on each line section in the line section set; reasonably allocate the energy required for the transmission line based on the temperature loss energy consumption prediction value, the first energy consumption prediction value and the second energy consumption prediction value, and output the actual energy distribution amount.

[0006] Preferably, a transmission line buried in an underground space for energy transmission is obtained, and the transmission line is divided into a number of equal sections to obtain a line section set, wherein each line section in the line section set is equidistant; The line sections are concentrated and each line section is divided into four orientation surfaces, and four orientation surfaces are output. The surface areas of the four orientation surfaces are equal. Among the four orientation surfaces, orientation surface one is a surface of the line facing the ground part, orientation surface two is a surface of the line facing the left side wall part of the underground space, orientation surface three is a surface of the line facing the underground part, and orientation surface four is a surface of the line facing the right side wall part of the underground space.

[0007] Preferably, the ratio of the surface area of each of the four facing surfaces to the total surface area of the four facing surfaces is calculated to obtain the energy consumption degree impact weight ratio; Obtain historical detection feature data, extract historical ambient temperature data of the transmission line and corresponding historical line energy consumption values from the historical detection feature data, calculate the correlation coefficient between the historical ambient temperature data and the historical line energy consumption values, and output a first correlation coefficient.

[0008] Preferably, based on the historical ambient temperature data, the temperature values of the four types of line surfaces at different heights in the underground space and the correlation coefficients between the four types of line surfaces at different heights in the underground space in the historical ambient temperature data are calculated, and the temperature variation characteristic coefficient is output; The detection line section concentrates the current temperature value of each line section toward surface one, outputs the ambient temperature value one, detects the distance of each line section toward surface one from the ground, and the distance toward surface three from the ground, outputs height one and height two.

[0009] Preferably, based on the temperature variation characteristic coefficient, the current temperature value, the height one and the height two, the ambient temperature value of each line section in the line section set facing the surface three is predicted, the ambient temperature value two is output, the ambient temperature value one and the ambient temperature value two are averaged to obtain the ambient temperature value three of each line section in the line section set facing the surface two and the surface four; Obtain the ambient temperature standard value that generates energy consumption, and extract the abnormal ambient temperature value that is greater than or equal to the ambient temperature standard value among ambient temperature value 1, ambient temperature value 2, and ambient temperature value 3; According to the abnormal ambient temperature value, the energy consumption degree influence weight ratio and the first correlation coefficient, the energy consumption value of each line section in the line section set caused by the ambient temperature is predicted, and the temperature loss energy consumption prediction value is output.

[0010] Preferably, image detection is performed on the line section set to obtain a line image set, grayscale image processing is performed on the line image set to obtain a line grayscale image set, and based on the crack conditions present in the line grayscale image set, sections with cracks are extracted from the line section set, and the crack sections are output; Obtaining the current direction of each line section in the line section set, and performing statistics on the crack lengths of each line section in the crack section to obtain the crack length to be measured; Extracting historical energy consumption values and historical crack length data of the transmission route from the historical detection feature data, wherein the historical crack length data is subject to a condition that the crack direction is horizontal to the current direction, extracting a correlation coefficient between the historical energy consumption values and the historical crack length data, and outputting a second correlation coefficient; According to the crack length to be measured and the second correlation coefficient, the energy consumption value of each line section in the line section set affected by the crack length is predicted, and a first energy consumption prediction value is output.

[0011] Preferably, the crack directions of each line section in the crack section are counted to obtain the crack orientation, and the inclination angle formed between the crack orientation and the current direction is counted to obtain the crack inclination angle to be measured; Extracting historical energy consumption values and historical crack inclination angles of the transport route from the historical detection feature data, wherein the condition for the historical crack inclination angle is that the crack length remains unchanged, extracting a correlation coefficient between the historical energy consumption values and the historical crack inclination angles, and outputting a third correlation coefficient; predicting energy consumption values of each line section in the line section set affected by cracks with different inclinations based on the crack inclination angle to be measured and the third correlation coefficient, and outputting a second energy consumption prediction value; Integrating the temperature loss energy consumption prediction value, the first energy consumption prediction value, and the second energy consumption prediction value to obtain comprehensive energy consumption data; The original energy allocation required to be transmitted by the transmission line is obtained, the original energy allocation is scheduled according to the comprehensive energy consumption data, and the actual energy allocation is output.

[0012] Compared with the prior art, the present invention has the following characteristics and beneficial effects: The transmission line is divided into several equal sections, so as to facilitate the statistics of energy consumption values of each line section. The underground depth of each line section is different, and the ambient temperature value in the corresponding underground space is different. In order to avoid the large error caused by the traditional technology of predicting and analyzing the one-time overall energy consumption value of the transmission line, the above-mentioned line segmentation processing is carried out. The line sections obtained by segmentation are concentrated and each line section is divided into four directional surfaces. Under the condition that the ambient temperature of each directional surface of the transmission line in the underground space is affected by different heights, different levels of temperature values exist at different heights of the underground space where the transmission line is located. For example, the smaller the height from the ground, the higher the ambient temperature value. Conversely, the greater the height from the ground, the lower the ambient temperature value. Therefore, the ambient temperature of the four directional surfaces is affected by different heights. The ambient temperature values are detected separately to comprehensively predict the different degrees of energy consumption values actually generated by the four orientation surfaces of each line section in the line section set. Through the above processing method, the large errors caused by general data analysis are reduced and the reliability of the analysis results is improved. The line sections with cracks are extracted from the line section set to facilitate the judgment of the energy consumption status of the crack sections. Because different crack lengths and crack extension directions have different influences on energy consumption when they are inclined with the current direction of the transmission line, separate data feature statistics are performed separately. Finally, the energy consumption values generated by diverse factors in various situations are predicted and comprehensively counted to predict the actual energy consumption value of the transmission line, so as to realize the rational scheduling of the energy distribution of the transmission line, improve the efficiency of resource allocation and effective statistics of the actual utilization rate of resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 This is a flowchart of the steps of a virtual power plant resource combination optimization method mainly embodied in this embodiment. DETAILED DESCRIPTION

[0014] The present invention is further described in detail below with reference to the following examples.

[0015] Reference Figure 1 , a virtual power plant resource combination optimization method, the method comprising the following steps: Step S1, obtain a transmission line buried in an underground space for energy transmission, divide the transmission line into several equal sections to obtain a line section set, divide each line section in the line section set based on the orientation surface to obtain four orientation surfaces, and based on the four orientation surfaces, calculate the energy consumption influence weight ratio of each orientation surface in the four orientation surfaces, and based on the historical detection feature data obtained, calculate the first correlation coefficient between the historical ambient temperature data and the historical line energy consumption value, wherein the four orientation surfaces are the ground surface, the left wall surface, the underground surface, and the right wall surface.

[0016] Step S2: Detect the current temperature value of the first facing surface of the four facing surfaces of each line section in the line section set, and predict the abnormal ambient temperature value based on the distance of the first facing surface of the line section from the ground and the distance of the third facing surface from the ground. According to the abnormal ambient temperature value, the weight ratio of the influence of the energy consumption degree and the first correlation coefficient, predict the temperature loss energy consumption prediction value caused by the influence of the ambient temperature on each line section in the line section set.

[0017] Step S3: perform image detection on the line section set to extract crack sections with cracks, count the crack lengths of each line section in the crack section and the crack directions of each line section in the crack section, so as to predict a first energy consumption prediction value generated by the influence of the crack length on each line section in the line section set and a second energy consumption prediction value generated by the influence of cracks of different inclinations on each line section in the line section set. Based on the temperature loss energy consumption prediction value, the first energy consumption prediction value and the second energy consumption prediction value, reasonably allocate the energy distribution amount required for the transmission line and output the actual energy distribution amount.

[0018] Specifically, the transmission line is divided into several equal sections, so as to facilitate the statistics of energy consumption values of each line section, and each line section belongs to a different underground depth, so the corresponding ambient temperature value in the underground space is different. In order to avoid the large error caused by the traditional technology of predicting and analyzing the one-time overall energy consumption value of the transmission line, the above-mentioned line segmentation processing is carried out, and the line sections obtained by the segmentation are concentrated and each line section is divided into four directional surfaces, so that when the ambient temperature of each directional surface of the transmission line in the underground space is affected by different heights, there are different levels of temperature values at different heights of the underground space where the transmission line is located. For example, the smaller the height from the ground, the higher the ambient temperature value. Conversely, the greater the height from the ground, the lower the ambient temperature value. Therefore, by dividing the four directional surfaces The ambient temperature values are detected separately to comprehensively predict the different degrees of energy consumption values actually generated by the four directions of the surface of each line section in the line section set. Through the above processing method, the large errors caused by general data analysis are reduced and the reliability of the analysis results is improved. The line sections with cracks are extracted from the line section set to facilitate the judgment of the energy consumption status of the crack sections. Because different crack lengths and crack extension directions have different influences on energy consumption when they are inclined with the current direction of the transmission line, separate data feature statistics are performed separately. Finally, the energy consumption values generated by the diverse factors in various situations are predicted and comprehensively counted to predict the actual energy consumption value of the transmission line, so as to realize the rational scheduling of the energy distribution of the transmission line, improve the efficiency of resource allocation and effective statistics of the actual utilization rate of resources.

[0019] The specific step S1 includes the following sub-steps: A transmission line buried in an underground space for energy transmission is obtained, and the transmission line is divided into a number of equal sections to obtain a line section set, wherein each line section in the line section set is equidistant.

[0020] The line sections are concentrated and each line section is divided into four orientation surfaces, and the four orientation surfaces are output. The surface areas of the four orientation surfaces are equal. Among the four orientation surfaces, orientation surface one is a surface of the line facing the ground, orientation surface two is a surface of the line facing the left side wall of the underground space, orientation surface three is a surface of the line facing the underground part, and orientation surface four is a surface of the line facing the right side wall of the underground space.

[0021] Calculating the ratio of the surface area of each of the four facing surfaces to the total surface area of the four facing surfaces to obtain an energy consumption impact weight ratio; Obtain historical detection feature data, extract historical ambient temperature data of the transmission line and corresponding historical line energy consumption values from the historical detection feature data, calculate the correlation coefficient between the historical ambient temperature data and the historical line energy consumption values, and output a first correlation coefficient.

[0022] Specifically, such as the transmission line (one of the lines is taken as an example here, if it is L), the line segment set (if it is l1, l2, l3, l4, l5, all of which are of equal length), four orientation surfaces (such as L is a cylindrical line, L is parallel to the ground, the surface of the middle part of L detected at a top-down angle (vertically perpendicular to L, and the starting point of the viewing angle is the ground) is the orientation surface one, the surface of the middle part of L detected at a left viewing angle (horizontally perpendicular to L) is the orientation surface two, the surface of the middle part of L detected at an angle vertically perpendicular to L, and the starting point of the viewing angle is the bottom of the underground space parallel to the ground) is the orientation surface three, and the surface of the middle part of L detected at a right viewing angle (horizontally perpendicular to L) is the orientation surface four. In the underground space, the ambient temperature values at different heights of L in the underground space will also be different. The deeper the underground space where L is located, the lower the ambient temperature value. Conversely, the shallower the underground space where L is located, the higher the ambient temperature value. Correspondingly, it is inferred that the four facing surfaces of L are located at different heights of the underground space. The depth at facing surface one is h1, the depths at facing surfaces two and four are equal (the ambient temperature values at facing surfaces two and four are the same), the depth at facing surface four is h2, the ambient temperature value at facing surface one is greater than the ambient temperature value at facing surface four, and different ambient temperature values have different effects on the degree of energy consumption. Under high temperature conditions, the higher the temperature value, the greater the energy consumption value. Therefore, the subsequent The temperature values of the four facing surfaces are predicted to facilitate the comprehensive prediction of the energy consumption values caused by the ambient temperature for l1, l2, l3, l4, and l5), the energy consumption influence weight ratio (the coverage area occupied by the four facing surfaces is counted. If the coverage area of facing surface one and facing surface three is s1, and the coverage area of facing surface two and facing surface four is s2, then the energy consumption influence weight ratio of facing surface one and facing surface three is s1 / (2*s1+2*s2) if it is b1, and the energy consumption influence weight ratio of facing surface two and facing surface four is s2 / (2*s1+2*s2) if it is b2), the first correlation coefficient (the historical detection feature data contains the ring of the transmission line in the historical period The ambient temperature value, the energy loss value generated, the spatial height of the four surfaces and the corresponding ambient temperature values, the line crack length, the crack extension direction (inclination angle, with the current direction as the reference object), historical ambient temperature data and historical line energy consumption values (referring to the historical ambient temperature data of each line section in the line section set (such as: w1, w2, w3 to wi) and historical line energy consumption values (such as: n1, n2, n3 to ni), the detection condition is that the line has no other damage conditions), with w as the x-axis and n as the y-axis, draw a correlation curve between w and n, where the curve inclination (excluding the maximum and minimum values of the inclination (to reduce the error), and then calculating the average value) is the first correlation coefficient (if it is R1).

[0023] The specific step S2 includes the following sub-steps: Based on the historical ambient temperature data, the temperature values of the four line surfaces at different heights in the underground space and the correlation coefficients between the four line surfaces at different heights in the underground space are calculated, and the temperature change characteristic coefficient is output.

[0024] The detection line section concentrates the current temperature value of each line section toward surface one, outputs the ambient temperature value one, detects the distance of each line section toward surface one from the ground, and the distance toward surface three from the ground, outputs height one and height two.

[0025] According to the temperature change characteristic coefficient, the current temperature value, height one and height two, the ambient temperature value of each line section in the line section set facing surface three is predicted, and the ambient temperature value two is output. The ambient temperature value one and the ambient temperature value two are averaged to obtain the ambient temperature value three of each line section in the line section set facing surface two and surface four.

[0026] Obtain the ambient temperature standard value that generates energy consumption, and extract abnormal ambient temperature values that are greater than or equal to the ambient temperature standard value among ambient temperature value 1, ambient temperature value 2, and ambient temperature value 3.

[0027] According to the abnormal ambient temperature value, the energy consumption degree influence weight ratio and the first correlation coefficient, the energy consumption value of each line section in the line section set affected by the ambient temperature is predicted, and the temperature loss energy consumption prediction value is output.

[0028] Specifically, the temperature change characteristic coefficient (such as l1 in the historical period: the ambient temperature value toward surface one is d1, the depth is b1, the ambient temperature value toward surface three is d2, the depth is b2, (d1-d2) / (b2-b1) is z1, and so on for l2, l3, l4, l5. If they are z2, z3, z4, z5 respectively, then the average value of z1, z2, z3, z4, z5 is Z, which is the temperature change characteristic coefficient), the current temperature value (if W1, temperature detection can be achieved through existing technologies such as ground source heat pump related temperature measurement equipment: SR1000 recorder: built-in battery, can be used with SCA1000 temperature measurement cable, no other power supply required, can record temperature data for more than 10 days. It is suitable for various environments with low power consumption and long-term temperature data recording, including soil temperature measurement. Height 1 and height 2 (for example, if h1 and h2 are mentioned above, existing technologies such as electromagnetic principle-based equipment: cable path detection system: by ARM STM32F103CET6 and electromagnetic detection module form the core control system, and the external GPS module can detect the location and burial depth of underground cable paths and convert them into longitude and latitude coordinates for storage, display, or communication with the computer. Another example is ground penetrating radar: Ground penetrating radar uses high-frequency electromagnetic wave reflection signals to detect the depth and position of non-metallic pipelines (such as plastic pipes), ambient temperature value two (W1-Z*(h2-h1) if it is W2), ambient temperature value three (i.e. (W1+W2) / 2 if it is W3), ambient temperature standard value (according to the different ambient temperature values in the historical ambient temperature data, whether the transmission line generates energy consumption. When a certain ambient temperature value is reached, if it is D, the transmission line will appear energy consumption, then D is the ambient temperature standard value, that is, the critical ambient temperature threshold for energy consumption), abnormal ambient temperature value (take l1 as an example, if only W1 is greater than or equal to D, then W1 is the abnormal ambient temperature value), temperature loss energy consumption prediction value (then the temperature loss energy consumption prediction value of l1 is b1*W1*R1. If it is H1, the same applies to l2, l3, l4, l5. If they are H2, H3, H4, H5 respectively (it should be noted that the abnormal ambient temperature values of l2, l3, l4, and l5 may be the same or different, because as the path of each line section becomes longer, the ambient temperature value may change), the sum of H1, H2, H3, H4, and H5 is N1).

[0029] The specific step S3 includes the following sub-steps: Image detection is performed on the line section set to obtain a line image set, and grayscale image processing is performed on the line image set to obtain a line grayscale image set. According to the crack conditions existing in the line grayscale image set, the section with cracks is extracted from the line section set, and the crack section is output.

[0030] The current direction of each line section in the line section set is obtained, and the crack length of each line section in the crack section is counted to obtain the crack length to be measured.

[0031] The historical energy consumption values and historical crack length data of the transmission route are extracted from the historical detection feature data. The condition of the historical crack length data is that the crack direction is horizontally related to the current direction. The correlation coefficient between the historical energy consumption values and the historical crack length data is extracted, and the second correlation coefficient is output.

[0032] According to the crack length to be measured and the second correlation coefficient, the energy consumption value of each line section in the line section set affected by the crack length is predicted, and a first energy consumption prediction value is output.

[0033] The crack directions of each line section in the crack section are counted to obtain the crack orientation, and the inclination angle formed between the crack orientation and the current direction is counted to obtain the crack inclination angle to be measured.

[0034] The historical energy consumption value and the historical crack inclination angle of the transmission route are extracted from the historical detection feature data. The condition of the historical crack inclination angle is that the crack length remains unchanged. The correlation coefficient between the historical energy consumption value and the historical crack inclination angle is extracted, and the third correlation coefficient is output.

[0035] According to the inclination angle of the crack to be measured and the third correlation coefficient, the energy consumption value caused by the cracks with different inclinations in each line section in the line section set is predicted, and a second energy consumption prediction value is output.

[0036] The temperature loss energy consumption prediction value, the first energy consumption prediction value and the second energy consumption prediction value are integrated to obtain comprehensive energy consumption data.

[0037] Obtain the original energy allocation required to be transmitted by the transmission line, schedule the original energy allocation based on the comprehensive energy consumption data, and output the actual energy allocation.

[0038] Specifically, such as line image sets (using existing technologies such as pipeline robots to detect line images: a pipeline robot is a device that can crawl inside a pipeline and is equipped with various sensors and cameras. It moves inside the pipeline through a motor-driven walking mechanism such as wheels or tracks, and uses a high-definition camera to take real-time photos of the situation inside the pipeline, and transmits the image data to an external control system for staff to view and analyze), crack segments (through grayscale image processing, in order to distinguish which are real cracks, the color image is converted into a grayscale image. A grayscale image means that each pixel has only one grayscale value (usually between 0 and 255), and this value represents the brightness of the pixel. Grayscaling can simplify image processing because crack features are usually related to brightness changes. If l2, l4, l5 are crack sections), the crack length to be measured (if the crack lengths of l2, l4, l5 are c1, c2, c3 respectively), the second correlation coefficient (historical energy consumption value and historical crack length data (referring to the historical energy consumption values of each line section of the line section set (such as: m1, m2, m3 to mi, the historical energy consumption values here and the historical line energy consumption values in the explanation of the first correlation coefficient can be the same or different, and are illustrated here with distinguishing symbols) and historical crack length data (such as: r1, r2, r3 to ri), the detection conditions are that the ambient temperature value of the line is less than D, and the crack direction of each line section of the line section set is horizontal to the current direction, because the crack direction When there is an inclination between the direction and the current direction, energy loss will also be caused). Therefore, the historical energy consumption values and the corresponding historical crack length data that meet these two conditions are selected from the historical detection feature data. R is used as the x-axis and m is used as the y-axis to draw a correlation curve between r and m, where the inclination of the curve (excluding the maximum and minimum values of the inclination (reducing the error), and then averaging is performed) is the second correlation coefficient (if it is R2), the first energy consumption prediction value (such as the energy consumption prediction value of l2: c1*R2 if it is u1, the energy consumption prediction value of l4: c2*R2 if it is u2, the energy consumption prediction value of l5: c3*R2 if it is u3, the sum of u1, u2, and u3 is the first energy consumption prediction value (if it is N2), the inclination angle of the crack to be measured (if l2, l4, and l5 There is a crack tilt in l4, crack direction: if the crack extends in a curve, then the crack starting position is taken as the origin, the crack ending position is taken as the tail point, and the origin and the tail point are connected by a straight line. If it is L0, it is the crack direction, and the current direction is taken as the horizontal line L1, then the angle formed between L0 and L1 is the crack tilt angle to be measured. If it is J), the third correlation coefficient (historical energy consumption value and historical crack tilt angle (refers to the historical energy consumption value of each line section of the line section set (such as: p1, p2, p3 to pi, the historical energy consumption value here and the historical energy consumption value in the explanation of the second correlation coefficient can be the same or different, and here they are illustrated with distinguishing symbols) and historical crack tilt angle (such as: j1, j2, j3 to ji),The inspection conditions are that the ambient temperature of the line is less than D, and the crack lengths of each line section in the line section set are uniform. Since the length of the crack extension will also cause energy loss, the historical energy consumption values and corresponding historical crack inclination angles that meet these two conditions are selected from the historical inspection feature data. With j as the x-axis and p as the y-axis, a correlation curve is drawn between p and j. The inclination of the curve (excluding the maximum and minimum inclination values (to reduce errors) and then averaging is the third correlation coefficient (if R3), the second energy consumption prediction value (i.e., the energy consumption prediction value of l1: J*R3, if N3), the comprehensive energy consumption data (i.e., summing N1, N2, and N3, if Q), the original energy allocation (if E1, it refers to the energy data required by the demand side), and the actual energy allocation (i.e., Q+E1) are used to achieve rational scheduling of the energy allocation of the transmission line and improve resource allocation efficiency.

[0039] The above are all preferred embodiments of the present application, and are not intended to limit the scope of protection of the present application. Therefore, any equivalent changes made based on the structure, shape, and principle of the present application should be included in the scope of protection of the present application.

Claims

1. A virtual power plant resource combination optimization method, characterized in that: The following steps are involved: Step S1: obtaining a transmission line buried in an underground space for energy transmission, dividing the transmission line into a number of equal segments to obtain a line segment set, dividing each line segment in the line segment set based on an orientation surface to obtain four orientation surfaces, calculating a weighted ratio of energy consumption influence of each of the four orientation surfaces based on the four orientation surfaces, and calculating a first correlation coefficient between historical ambient temperature data and historical line energy consumption values based on the acquired historical detection feature data, wherein the four orientation surfaces are a surface facing the ground, a surface facing the left wall, a surface facing the underground, and a surface facing the right wall; Step S2: detecting the current temperature value of the first facing surface among the four facing surfaces of each line section in the line section set, and predicting an abnormal ambient temperature value based on the distance of the first facing surface of the line section from the ground and the distance of the third facing surface from the ground; and predicting a temperature loss energy consumption prediction value caused by the ambient temperature for each line section in the line section set based on the abnormal ambient temperature value, the energy consumption influence weight ratio, and the first correlation coefficient; Step S3: perform image detection on the line section set to extract crack sections with cracks, count the crack lengths of each line section in the crack section and the crack directions of each line section in the crack section, so as to predict a first energy consumption prediction value generated by the influence of the crack length on each line section in the line section set and a second energy consumption prediction value generated by the influence of cracks of different inclinations on each line section in the line section set; reasonably allocate the energy required for the transmission line based on the temperature loss energy consumption prediction value, the first energy consumption prediction value and the second energy consumption prediction value, and output the actual energy distribution amount.

2. The virtual power plant resource combination optimization method according to claim 1, characterized in that: Step S1 includes: Obtaining a transmission line buried in an underground space for energy transmission, dividing the transmission line into a number of equal segments to obtain a line segment set, wherein each line segment in the line segment set is equidistant; The line sections are concentrated and each line section is divided into four orientation surfaces, and four orientation surfaces are output. The surface areas of the four orientation surfaces are equal. Among the four orientation surfaces, orientation surface one is a surface of the line facing the ground part, orientation surface two is a surface of the line facing the left side wall part of the underground space, orientation surface three is a surface of the line facing the underground part, and orientation surface four is a surface of the line facing the right side wall part of the underground space.

3. The virtual power plant resource combination optimization method according to claim 2, characterized in that: Step S1 further includes: Calculating the ratio of the surface area of each of the four facing surfaces to the total surface area of the four facing surfaces to obtain an energy consumption impact weight ratio; Obtain historical detection feature data, extract historical ambient temperature data of the transmission line and corresponding historical line energy consumption values from the historical detection feature data, calculate the correlation coefficient between the historical ambient temperature data and the historical line energy consumption values, and output a first correlation coefficient.

4. The virtual power plant resource combination optimization method according to claim 3, characterized in that: Step S2 includes: Based on the historical ambient temperature data, calculating the temperature values of the four types of line surfaces at different heights in the underground space and the correlation coefficients between the four types of line surfaces at different heights in the underground space, and outputting the temperature variation characteristic coefficient; The detection line section concentrates the current temperature value of each line section toward surface one, outputs the ambient temperature value one, detects the distance of each line section toward surface one from the ground, and the distance toward surface three from the ground, outputs height one and height two.

5. The virtual power plant resource combination optimization method according to claim 4, characterized in that: Step S2 further includes: Based on the temperature variation characteristic coefficient, the current temperature value, the height 1 and the height 2, the ambient temperature value of each line section in the line section set facing the third surface is predicted, the ambient temperature value 2 is output, and the ambient temperature value 1 and the ambient temperature value 2 are averaged to obtain the ambient temperature value 3 of each line section in the line section set facing the second surface and the fourth surface; Obtain the ambient temperature standard value that generates energy consumption, and extract the abnormal ambient temperature value that is greater than or equal to the ambient temperature standard value among ambient temperature value 1, ambient temperature value 2, and ambient temperature value 3; According to the abnormal ambient temperature value, the energy consumption degree influence weight ratio and the first correlation coefficient, the energy consumption value of each line section in the line section set caused by the ambient temperature is predicted, and the temperature loss energy consumption prediction value is output.

6. The virtual power plant resource combination optimization method according to claim 5, characterized in that: Step S3 includes: Performing image detection on the line section set to obtain a line image set, performing grayscale image processing on the line image set to obtain a line grayscale image set, extracting sections with cracks from the line section set based on crack conditions present in the line grayscale image set, and outputting the crack sections; Obtaining the current direction of each line section in the line section set, and performing statistics on the crack lengths of each line section in the crack section to obtain the crack length to be measured; Extracting historical energy consumption values and historical crack length data of the transmission route from the historical detection feature data, wherein the historical crack length data is subject to a condition that the crack direction is horizontal to the current direction, extracting a correlation coefficient between the historical energy consumption values and the historical crack length data, and outputting a second correlation coefficient; According to the crack length to be measured and the second correlation coefficient, the energy consumption value of each line section in the line section set affected by the crack length is predicted, and a first energy consumption prediction value is output.

7. The virtual power plant resource combination optimization method according to claim 6, characterized in that: Step S3 includes: The crack directions of each line section in the crack section are counted to obtain the crack orientation, and the inclination angle formed between the crack orientation and the current direction is counted to obtain the inclination angle of the crack to be measured; Extracting historical energy consumption values and historical crack inclination angles of the transport route from the historical detection feature data, wherein the condition for the historical crack inclination angle is that the crack length remains unchanged, extracting a correlation coefficient between the historical energy consumption values and the historical crack inclination angles, and outputting a third correlation coefficient; predicting energy consumption values of each line section in the line section set affected by cracks with different inclinations based on the crack inclination angle to be measured and the third correlation coefficient, and outputting a second energy consumption prediction value; Integrating the temperature loss energy consumption prediction value, the first energy consumption prediction value, and the second energy consumption prediction value to obtain comprehensive energy consumption data; The original energy allocation required to be transmitted by the transmission line is obtained, the original energy allocation is scheduled according to the comprehensive energy consumption data, and the actual energy allocation is output.

Images