A photovoltaic deployment planning generation method, device, storage medium and terminal equipment

Abstract

The application discloses a photovoltaic deployment planning generation method, comprising the following steps: acquiring historical energy consumption load data, slope data and power data of a plurality of photovoltaic panels of a to-be-deployed highway domain; inputting the historical energy consumption load data into a pre-constructed radial basis function neural network model, so that the radial basis function neural network model generates predicted load data; determining the to-be-deployed photovoltaic panels corresponding to different slopes and the number of the to-be-deployed photovoltaic panels according to the predicted load data, the slope data and the power data of the photovoltaic panels; and generating a photovoltaic panel deployment planning of the to-be-deployed highway domain according to the to-be-deployed photovoltaic panels and the number of the to-be-deployed photovoltaic panels. The application improves the accuracy of the photovoltaic deployment planning of the highway domain by predicting the future energy consumption load data of the highway domain and planning in combination with the field geographical environment.

Description

Technical Field

[0001] This invention relates to the field of power, and more particularly to a method, apparatus, storage medium, and terminal equipment for generating photovoltaic deployment plans. Background Technology

[0002] Distributed photovoltaic power generation on highways refers to the deployment of solar photovoltaic modules and other equipment on highway slopes, along roadside facilities, and in the surrounding environment to generate electricity. The electricity generated can meet the electricity needs of residents along the route, thereby reducing power loss caused by long-distance power transmission from the power grid.

[0003] However, due to the high price of solar photovoltaic modules and the fact that they are generally installed in areas with relatively harsh geological conditions, making them susceptible to geological disasters such as soil erosion and floods, improper deployment may result in significant waste. Currently, planning is based solely on existing electricity consumption without considering the specific deployment environment or future changes in electricity demand. Therefore, the accuracy of distributed photovoltaic panel deployment cannot be guaranteed. Summary of the Invention

[0004] To overcome the shortcomings of the prior art, this invention proposes a photovoltaic deployment planning generation method, device, storage medium, and terminal equipment. By constructing a radial basis function neural network model, it predicts future energy load data in highway areas and then provides deployment planning suggestions in combination with the on-site geographical environment, which helps to improve the accuracy of photovoltaic deployment.

[0005] This invention provides a method for generating photovoltaic deployment plans, including:

[0006] Obtain historical energy load data, slope data, and power data of several photovoltaic panels for the highway area to be deployed;

[0007] Historical energy load data is input into a pre-built radial basis function neural network model so that the radial basis function neural network model can generate predicted load data;

[0008] Based on the predicted load data, slope data, and power data of each photovoltaic panel, determine the photovoltaic panels to be deployed and the number of photovoltaic panels to be deployed for different slopes.

[0009] Based on the photovoltaic panels to be deployed and their quantity, a photovoltaic panel deployment plan for the highway area to be deployed is generated.

[0010] Furthermore, before inputting historical energy load data into the pre-built radial basis function neural network model, the following steps are also included:

[0011] The following formula is used to iteratively calculate each historical energy load data point. When the difference between two consecutive iterations is less than a preset threshold, the iteration ends, and the result of the next iteration is used as the preprocessed historical energy load data:

[0012] x k+1 =Bx k +f

[0013] Where, x k Given the historical energy load data for the k-th iteration, x k+1 For the (k+1)th iteration, the historical energy load data is given, B is a preset coefficient, and f is a preset constant term.

[0014] Furthermore, the construction of the radial basis function neural network model includes:

[0015] Acquire first and second historical energy load data for several highway areas, where the first and second historical energy load data correspond to different time periods.

[0016] Using the first historical energy load data as input and the second historical energy load data as output, the hidden layer of the initial radial basis function neural network is trained, and the radial basis function neural network model is generated after the training is completed.

[0017] Furthermore, when training the hidden layers of the initial radial basis function neural network, the radial basis function calculation results of the hidden layers are weighted according to the K-means algorithm.

[0018] Furthermore, the slope data includes: slope height, slope angle and area data, and the predicted load data includes: peak predicted load data, flat predicted load data and valley predicted load data;

[0019] The step of determining the number of photovoltaic panels to be deployed for different slopes based on the predicted load data, slope data, and power data of each photovoltaic panel includes:

[0020] Based on the slope height of the highway to be deployed, the slopes are divided into first, second, and third height layers. Then, based on the slope angle, each height layer is further divided into small-angle and large-angle slopes. The slope height of the first height layer is less than that of the second height layer, and the slope height of the second height layer is less than that of the third height layer.

[0021] The valley predicted load data is used as the load data to be allocated corresponding to the first height layer, the difference between the average predicted load data and the valley predicted load data is used as the load data to be allocated corresponding to the second height layer, and the difference between the peak predicted load data and the average predicted load data is used as the load data to be allocated corresponding to the third height layer.

[0022] For each height level, perform a photovoltaic panel determination operation to determine the photovoltaic panels that need to be deployed at each height level and the number of photovoltaic panels;

[0023] The photovoltaic panel determination operation includes:

[0024] Select a photovoltaic panel with a preset power as the first photovoltaic panel;

[0025] Based on the load data to be allocated at each height level and the power of the first photovoltaic panel, the number of first photovoltaic panels to be pre-installed is calculated. Then, based on the number of pre-installed panels and the cross-sectional area of ​​the first photovoltaic panel, the total pre-installed area is calculated.

[0026] The total pre-laid area is compared with the total area of ​​the small-angle slopes in the height layer.

[0027] When the total pre-laid area is less than or equal to the total area of ​​the small-angle slope in the height layer, the first photovoltaic panel is taken as the photovoltaic panel to be deployed on the small-angle slope in the height layer, and the pre-laid quantity is taken as the number of photovoltaic panels to be deployed on the small-angle slope in the height layer.

[0028] When the total pre-laid area is greater than the total area of ​​the small-angle slopes in the height layer, the difference is calculated based on the total pre-laid area and the total area of ​​the small-angle slopes in the height layer, and then compared with the total area of ​​the large-angle slopes in the height layer.

[0029] If the difference is less than the total area of ​​the large-angle slopes in the height layer, then the first laying quantity is calculated based on the total area of ​​the small-angle slopes in the height layer and the cross-sectional area of ​​the first photovoltaic panel, and then the second laying quantity is calculated based on the pre-laid quantity and the first laying quantity.

[0030] The first photovoltaic panel is designated as the photovoltaic panel to be deployed on the small-angle and large-angle slopes in the height layer. The first number of panels laid is designated as the number of photovoltaic panels to be deployed on the small-angle slopes in the height layer. The second number of panels laid is designated as the number of photovoltaic panels to be deployed on the large-angle slopes in the height layer.

[0031] If the difference is greater than the total area of ​​the large-angle slope in the height layer, then the difference load is calculated based on the difference, the cross-sectional area of ​​the first photovoltaic panel, and the power of the first photovoltaic panel;

[0032] Based on the differential load and the total area of ​​the large-angle slopes in the height layer, a second photovoltaic panel is selected and the number of second photovoltaic panels deployed is determined; wherein, the product of the power of the second photovoltaic panel and the number of deployed panels is greater than the differential load, and the product of the cross-sectional area of ​​the second photovoltaic panel and the number of deployed panels is less than the total area of ​​the large-angle slopes in the height layer;

[0033] The first photovoltaic panel is designated as the photovoltaic panel to be deployed on the small-angle slope in the height layer, and the first number of panels laid is designated as the number of photovoltaic panels to be deployed on the small-angle slope in the height layer. The selected second photovoltaic panel is designated as the photovoltaic panel to be deployed on the large-angle slope in the height layer, and the number of the second photovoltaic panel deployed is designated as the number of photovoltaic panels to be deployed on the large-angle slope in the height layer.

[0034] This invention also provides a photovoltaic deployment planning generation device, comprising:

[0035] The data acquisition module is used to acquire historical energy load data, slope data, and power data of several photovoltaic panels in the highway area to be deployed.

[0036] The load forecasting module is used to input historical energy load data into a pre-built radial basis function neural network model so that the radial basis function neural network model can generate predicted load data.

[0037] The analysis module is used to determine the photovoltaic panels to be deployed and the number of photovoltaic panels to be deployed for different slopes based on the predicted load data, slope data and power data of each photovoltaic panel.

[0038] The deployment planning module is used to generate a photovoltaic panel deployment plan for the highway area to be deployed based on the photovoltaic panels to be deployed and the number of photovoltaic panels to be deployed.

[0039] This invention also provides a storage medium comprising a stored computer program; wherein, when the computer program is running, it controls the device containing the storage medium to execute the photovoltaic deployment planning generation method described in any one of this invention.

[0040] This invention also provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the photovoltaic deployment planning generation method according to any one of the present invention when executing the computer program.

[0041] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0042] This invention acquires historical energy load data of the highway area to be deployed, predicts future energy load data based on a constructed radial basis function neural network model, and then calculates the type and quantity of photovoltaic panels to be deployed on different slopes based on the predicted load data, highway slope data, and power data of several photovoltaic panels. Combined with the output deployment planning suggestions, the invention takes into account the on-site environment of the highway area and changes in future energy load during the generation of deployment planning suggestions, which helps to improve the accuracy of photovoltaic deployment in highway areas. Attached Figure Description

[0043] Figure 1 A flowchart illustrating the steps of a photovoltaic deployment planning generation method provided in an embodiment of the present invention;

[0044] Figure 2 This is a schematic diagram of a photovoltaic deployment planning generation device provided in an embodiment of the present invention; Detailed Implementation

[0045] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0046] Please refer to Figure 1 According to one embodiment of the present invention, a method for generating photovoltaic deployment plans is provided, comprising:

[0047] Step S1: Obtain historical energy load data, slope data, and power data of several photovoltaic panels for the highway area to be deployed;

[0048] In a preferred embodiment, after determining the highway section to be deployed, the historical energy load data of the section is obtained from the State Grid. At the same time, the site environment is surveyed, mainly the various slopes where photovoltaic panels can be deployed, and the height, slope angle and area data of various slopes are obtained. In addition, photovoltaic panels with various power values ​​are counted in advance.

[0049] Step S2: Input historical energy load data into a pre-built radial basis function neural network model so that the radial basis function neural network model generates predicted load data;

[0050] Preferably, before inputting historical energy load data into a pre-built radial basis function neural network model, the method further includes:

[0051] The following formula is used to iteratively calculate each historical energy load data point. When the difference between two consecutive iterations is less than a preset threshold, the iteration ends, and the result of the next iteration is used as the preprocessed historical energy load data:

[0052] x k+1 =Bx k +f

[0053] Where, x k Given the historical energy load data for the k-th iteration, x k+1 The historical energy load data for the (k+1)th iteration is used, B is a preset coefficient, and f is a preset constant term. By performing iterative preprocessing on the acquired historical energy load data, the aggregation of the data is improved, making the classification of predicted load data for different scenarios more accurate in the subsequent model analysis process.

[0054] Preferably, the construction of the radial basis function neural network model includes:

[0055] Acquire first and second historical energy load data for several highway areas, where the first and second historical energy load data correspond to different time periods.

[0056] Using the first historical energy load data as input and the second historical energy load data as output, the hidden layer of the initial radial basis function neural network is trained, and the radial basis function neural network model is generated after the training is completed.

[0057] Preferably, when training the hidden layers of the initial radial basis function neural network, the radial basis function calculation results of the hidden layers are weighted according to the K-means algorithm.

[0058] In a preferred embodiment, when training the hidden layers of the initial radial basis function neural network, the radial basis functions are as follows:

[0059]

[0060] Among them, u t With the center point, σ t φ(x) represents the radial basis width, x represents the input of a node during training, and φ(x) represents the output of a node during training. Meanwhile, during the model building process, the hidden layer nodes are optimized using K-means classification, that is, the radial basis function calculation results of the hidden layer are weighted according to the K-means algorithm, thereby achieving higher accuracy prediction of the model.

[0061] Step S3: Based on the predicted load data, slope data, and power data of each photovoltaic panel, determine the photovoltaic panels to be deployed and the number of photovoltaic panels to be deployed for different slopes;

[0062] Preferably, the predicted load data includes: peak predicted load data, average predicted load data, and valley predicted load data;

[0063] Preferably, determining the number of photovoltaic panels to be deployed for different slopes based on the predicted load data, slope data, and power data of each photovoltaic panel includes:

[0064] Based on the slope height of the highway to be deployed, the slopes are divided into first, second, and third height layers. Then, based on the slope angle, each height layer is further divided into small-angle and large-angle slopes. The slope height of the first height layer is less than that of the second height layer, and the slope height of the second height layer is less than that of the third height layer.

[0065] The valley predicted load data is used as the load data to be allocated corresponding to the first height layer, the difference between the average predicted load data and the valley predicted load data is used as the load data to be allocated corresponding to the second height layer, and the difference between the peak predicted load data and the average predicted load data is used as the load data to be allocated corresponding to the third height layer.

[0066] For each height level, perform a photovoltaic panel determination operation to determine the photovoltaic panels that need to be deployed at each height level and the number of photovoltaic panels;

[0067] The photovoltaic panel determination operation includes:

[0068] Select a photovoltaic panel with a preset power as the first photovoltaic panel;

[0069] Based on the load data to be allocated at each height level and the power of the first photovoltaic panel, the number of first photovoltaic panels to be pre-installed is calculated. Then, based on the number of pre-installed panels and the cross-sectional area of ​​the first photovoltaic panel, the total pre-installed area is calculated.

[0070] The total pre-laid area is compared with the total area of ​​the small-angle slopes in the height layer.

[0071] When the total pre-laid area is less than or equal to the total area of ​​the small-angle slope in the height layer, the first photovoltaic panel is taken as the photovoltaic panel to be deployed on the small-angle slope in the height layer, and the pre-laid quantity is taken as the number of photovoltaic panels to be deployed on the small-angle slope in the height layer.

[0072] When the total pre-laid area is greater than the total area of ​​the small-angle slopes in the height layer, the difference is calculated based on the total pre-laid area and the total area of ​​the small-angle slopes in the height layer, and then compared with the total area of ​​the large-angle slopes in the height layer.

[0073] If the difference is less than the total area of ​​the large-angle slopes in the height layer, then the first laying quantity is calculated based on the total area of ​​the small-angle slopes in the height layer and the cross-sectional area of ​​the first photovoltaic panel, and then the second laying quantity is calculated based on the pre-laid quantity and the first laying quantity.

[0074] The first photovoltaic panel is designated as the photovoltaic panel to be deployed on the small-angle and large-angle slopes in the height layer. The first number of panels laid is designated as the number of photovoltaic panels to be deployed on the small-angle slopes in the height layer. The second number of panels laid is designated as the number of photovoltaic panels to be deployed on the large-angle slopes in the height layer.

[0075] If the difference is greater than the total area of ​​the large-angle slope in the height layer, then the difference load is calculated based on the difference, the cross-sectional area of ​​the first photovoltaic panel, and the power of the first photovoltaic panel;

[0076] Based on the differential load and the total area of ​​the large-angle slopes in the height layer, a second photovoltaic panel is selected and the number of second photovoltaic panels deployed is determined; wherein, the product of the power of the second photovoltaic panel and the number of deployed panels is greater than the differential load, and the product of the cross-sectional area of ​​the second photovoltaic panel and the number of deployed panels is less than the total area of ​​the large-angle slopes in the height layer;

[0077] The first photovoltaic panel is designated as the photovoltaic panel to be deployed on the small-angle slope in the height layer, and the first number of panels laid is designated as the number of photovoltaic panels to be deployed on the small-angle slope in the height layer. The selected second photovoltaic panel is designated as the photovoltaic panel to be deployed on the large-angle slope in the height layer, and the number of the second photovoltaic panel deployed is designated as the number of photovoltaic panels to be deployed on the large-angle slope in the height layer.

[0078] In a preferred embodiment, the historical energy load data of the highway section to be deployed is processed by a radial basis function neural network model to output peak predicted load data, flat predicted load data, and valley predicted load data. Considering the diversity of environmental changes, the aforementioned load data are deployed on slopes at different heights and angles. That is, the slopes are divided into three height layers according to height, and each height layer is further divided into two types according to angle. An angle is preset according to the site conditions. Slopes with an angle smaller than this angle are called small-angle slopes, and slopes with an angle larger than this angle are called large-angle slopes. Furthermore, photovoltaic panels corresponding to valley load data are deployed on the lowest slope (i.e., the slope of the first height layer), photovoltaic panels corresponding to flat-valley load difference data are deployed on the second highest slope (i.e., the slope of the second height layer), and photovoltaic panels corresponding to peak-flat load difference data are deployed on the highest slope (i.e., the slope of the third height layer). Since small-angle slopes are easier to deploy and receive better sunlight, they are prioritized when deploying photovoltaic panels. For cost considerations, for each height layer, a common photovoltaic panel is selected as the first photovoltaic panel. Based on the known load data to be allocated and the cross-sectional area of ​​the first photovoltaic panel, it is calculated whether the small-angle slope of that height layer can meet the load deployment requirements. If not, the slope of that height layer is not selected. The first photovoltaic panel is laid on the small-angle slope. Since the small-angle slope can only meet part of the load deployment requirements, the remaining load deployment requirements are considered on the large-angle slope of the same height. If the first photovoltaic panel can meet both the remaining load deployment requirements and the deployment area of ​​the large-angle slope, then the first photovoltaic panel is still laid on the large-angle slope of the same height. If the first photovoltaic panel cannot meet the remaining load deployment requirements and the deployment area of ​​the large-angle slope, then a second photovoltaic panel with a power value greater than that of the first photovoltaic panel is selected and deployed on the large-angle slope of the same height. The power of the second photovoltaic panel is not limited, as long as the second photovoltaic panel can meet both the remaining load deployment requirements and the deployment area of ​​the large-angle slope.

[0079] Step S4: Based on the photovoltaic panels to be deployed and the number of photovoltaic panels to be deployed, generate a photovoltaic panel deployment plan for the highway area to be deployed.

[0080] In a preferred embodiment, given the power type and quantity of the photovoltaic panels to be deployed, the photovoltaic panels and their quantities are sequentially matched with the corresponding slopes. That is, for each height level and each type of slope, which type of photovoltaic panels should be deployed and how many should be deployed, thereby obtaining a specific deployment plan for the photovoltaic panels in the highway area to be deployed.

[0081] In another preferred embodiment, in addition to generating a deployment plan based on the power type and quantity of photovoltaic panels required for different slopes, the weather and temperature of the highway area can also be considered during this process to configure other photovoltaic protection components associated with the photovoltaic panels, so that the photovoltaic panels suffer the least loss under natural conditions. Similarly, the safest construction equipment is selected by combining the type of slope and the type of photovoltaic panels on site. Combining the above multiple scenarios, a complete deployment plan is finally generated.

[0082] Based on the method embodiments of the present invention, corresponding apparatus embodiments are provided:

[0083] Please refer to Figure 2 Another embodiment of the present invention provides a photovoltaic deployment planning generation device, comprising:

[0084] The data acquisition module is used to acquire historical energy load data, slope data, and power data of several photovoltaic panels in the highway area to be deployed.

[0085] The load forecasting module is used to input historical energy load data into a pre-built radial basis function neural network model so that the radial basis function neural network model can generate predicted load data.

[0086] The analysis module is used to determine the photovoltaic panels to be deployed and the number of photovoltaic panels to be deployed for different slopes based on the predicted load data, slope data and power data of each photovoltaic panel.

[0087] The deployment planning module is used to generate a photovoltaic panel deployment plan for the highway area to be deployed based on the photovoltaic panels to be deployed and the number of photovoltaic panels to be deployed.

[0088] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0089] Those skilled in the art will clearly understand that, for convenience and simplicity, the specific working process of the device described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0090] In another embodiment of the present invention described above, a storage medium is provided, the storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to execute a photovoltaic deployment planning generation method according to any one of the method embodiments of the present invention.

[0091] The storage medium is a computer-readable storage medium, and the computer program is stored in the computer-readable storage medium. When executed by a processor, the computer program can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0092] Based on the various embodiments described above, the present invention provides corresponding embodiments for terminal devices.

[0093] One embodiment of the present invention provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements a photovoltaic deployment planning generation method according to any embodiment of the present invention.

[0094] The terminal device may be a desktop computer, laptop, handheld computer, or cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0095] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the terminal device, connecting all parts of the terminal device via various interfaces and lines.

[0096] The memory can be used to store the computer program. The processor implements various functions of the terminal device by running or executing the computer program stored in the memory and calling data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function, etc.; the data storage area may store data created based on the use of the mobile phone, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, RAM, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0097] The embodiments of the present invention have the following beneficial effects:

[0098] This invention acquires historical energy load data of the highway area to be deployed, predicts future energy load data based on a constructed radial basis function neural network model, and then calculates the type and quantity of photovoltaic panels to be deployed on different slopes based on the predicted load data, slope data of the highway area, and power data of several photovoltaic panels. Combined with the output deployment planning suggestions, the invention takes into account the on-site environment of the highway area and changes in future energy load during the generation of deployment planning suggestions, which helps to improve the accuracy of photovoltaic deployment in highway areas.

[0099] The above are preferred embodiments of the present invention. It should be noted that, for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for generating photovoltaic deployment plans, characterized in that, include: Obtain historical energy load data, slope data, and power data of several photovoltaic panels for the highway area to be deployed; Historical energy load data is input into a pre-built radial basis function neural network model so that the radial basis function neural network model can generate predicted load data; Based on the predicted load data, slope data, and power data of each photovoltaic panel, determine the photovoltaic panels to be deployed and the number of photovoltaic panels to be deployed for different slopes. Based on the photovoltaic panels to be deployed and their quantity, a photovoltaic panel deployment plan for the highway area to be deployed is generated. The slope data includes: slope height, slope angle, and area data; The predicted load data includes: peak predicted load data, average predicted load data, and valley predicted load data; The step of determining the number of photovoltaic panels to be deployed for different slopes based on the predicted load data, slope data, and power data of each photovoltaic panel includes: Based on the slope height of the highway to be deployed, the slopes are divided into first, second, and third height layers. Then, based on the slope angle, each height layer is further divided into small-angle and large-angle slopes. The slope height of the first height layer is less than that of the second height layer, and the slope height of the second height layer is less than that of the third height layer. The valley predicted load data is used as the load data to be allocated for the first height layer; the difference between the average predicted load data and the valley predicted load data is used as the load data to be allocated for the second height layer; and the difference between the peak predicted load data and the average predicted load data is used as the load data to be allocated for the third height layer. For each height level, perform a photovoltaic panel determination operation to determine the photovoltaic panels that need to be deployed at each height level and the number of photovoltaic panels; The photovoltaic panel determination operation includes: Select a photovoltaic panel with a preset power as the first photovoltaic panel; Based on the load data to be allocated at each height level and the power of the first photovoltaic panel, the number of first photovoltaic panels to be pre-installed is calculated. Then, based on the number of pre-installed panels and the cross-sectional area of ​​the first photovoltaic panel, the total pre-installed area is calculated. The total pre-laid area is compared with the total area of ​​the small-angle slopes in the height layer. When the total pre-laid area is less than or equal to the total area of ​​the small-angle slope in the height layer, the first photovoltaic panel is taken as the photovoltaic panel to be deployed on the small-angle slope in the height layer, and the pre-laid quantity is taken as the number of photovoltaic panels to be deployed on the small-angle slope in the height layer. When the total pre-laid area is greater than the total area of ​​the small-angle slopes in the height layer, the difference is calculated based on the total pre-laid area and the total area of ​​the small-angle slopes in the height layer, and then compared with the total area of ​​the large-angle slopes in the height layer. If the difference is less than the total area of ​​the large-angle slopes in the height layer, then the first laying quantity is calculated based on the total area of ​​the small-angle slopes in the height layer and the cross-sectional area of ​​the first photovoltaic panel, and then the second laying quantity is calculated based on the pre-laid quantity and the first laying quantity. The first photovoltaic panel is designated as the photovoltaic panel to be deployed on the small-angle slope and the large-angle slope in the height layer. The first number of panels laid is designated as the number of photovoltaic panels to be deployed on the small-angle slope in the height layer. The second number of panels laid is designated as the number of photovoltaic panels to be deployed on the large-angle slope in the height layer. If the difference is greater than the total area of ​​the large-angle slope in the height layer, then the difference load is calculated based on the difference, the cross-sectional area of ​​the first photovoltaic panel, and the power of the first photovoltaic panel; Based on the differential load and the total area of ​​the large-angle slopes in the height layer, a second photovoltaic panel is selected and the number of second photovoltaic panels deployed is determined; wherein, the product of the power of the second photovoltaic panel and the number of deployed panels is greater than the differential load, and the product of the cross-sectional area of ​​the second photovoltaic panel and the number of deployed panels is less than the total area of ​​the large-angle slopes in the height layer; The first photovoltaic panel is designated as the photovoltaic panel to be deployed on the small-angle slope in the height layer, and the first number of panels laid is designated as the number of photovoltaic panels to be deployed on the small-angle slope in the height layer. The selected second photovoltaic panel is designated as the photovoltaic panel to be deployed on the large-angle slope in the height layer, and the number of the second photovoltaic panel deployed is designated as the number of photovoltaic panels to be deployed on the large-angle slope in the height layer.

2. The photovoltaic deployment planning generation method as described in claim 1, characterized in that, Before inputting historical energy load data into a pre-built radial basis function neural network model, the following steps are also included: The following formula is used to iteratively calculate each historical energy load data point. When the difference between two consecutive iterations is less than a preset threshold, the iteration ends, and the result of the next iteration is used as the preprocessed historical energy load data: x k+1 = Bx k + f Where, x k Given the historical energy load data for the k-th iteration, x k+1 For the (k+1)th iteration, the historical energy load data is given, B is a preset coefficient, and f is a preset constant term.

3. The photovoltaic deployment planning generation method as described in claim 1, characterized in that, The construction of the radial basis function neural network model includes: Acquire first and second historical energy load data for several highway areas, where the first and second historical energy load data correspond to different time periods. Using the first historical energy load data as input and the second historical energy load data as output, the hidden layer of the initial radial basis function neural network is trained, and the radial basis function neural network model is generated after the training is completed.

4. The photovoltaic deployment planning generation method as described in claim 3, characterized in that, When training the hidden layers of the initial radial basis function neural network, the radial basis function calculation results of the hidden layers are weighted according to the K-means algorithm.

5. A photovoltaic deployment planning and generation device, characterized in that, include: The data acquisition module is used to acquire historical energy load data, slope data, and power data of several photovoltaic panels in the highway area to be deployed. The load forecasting module is used to input historical energy load data into a pre-built radial basis function neural network model so that the radial basis function neural network model can generate predicted load data. The analysis module is used to determine the photovoltaic panels to be deployed and the number of photovoltaic panels to be deployed for different slopes based on the predicted load data, slope data and power data of each photovoltaic panel. The deployment planning module is used to generate a photovoltaic panel deployment plan for the highway area to be deployed based on the photovoltaic panels to be deployed and the number of photovoltaic panels to be deployed; The slope data includes: slope height, slope angle, and area data; The predicted load data includes: peak predicted load data, average predicted load data, and valley predicted load data; The step of determining the number of photovoltaic panels to be deployed for different slopes based on the predicted load data, slope data, and power data of each photovoltaic panel includes: Based on the slope height of the highway to be deployed, the slopes are divided into first, second, and third height layers. Then, based on the slope angle, each height layer is further divided into small-angle and large-angle slopes. The slope height of the first height layer is less than that of the second height layer, and the slope height of the second height layer is less than that of the third height layer. The valley predicted load data is used as the load data to be allocated for the first height layer; the difference between the average predicted load data and the valley predicted load data is used as the load data to be allocated for the second height layer; and the difference between the peak predicted load data and the average predicted load data is used as the load data to be allocated for the third height layer. For each height level, perform a photovoltaic panel determination operation to determine the photovoltaic panels that need to be deployed at each height level and the number of photovoltaic panels; The photovoltaic panel determination operation includes: Select a photovoltaic panel with a preset power as the first photovoltaic panel; Based on the load data to be allocated at each height level and the power of the first photovoltaic panel, the number of first photovoltaic panels to be pre-installed is calculated. Then, based on the number of pre-installed panels and the cross-sectional area of ​​the first photovoltaic panel, the total pre-installed area is calculated. The total pre-laid area is compared with the total area of ​​the small-angle slopes in the height layer. When the total pre-laid area is less than or equal to the total area of ​​the small-angle slope in the height layer, the first photovoltaic panel is taken as the photovoltaic panel to be deployed on the small-angle slope in the height layer, and the pre-laid quantity is taken as the number of photovoltaic panels to be deployed on the small-angle slope in the height layer. When the total pre-laid area is greater than the total area of ​​the small-angle slopes in the height layer, the difference is calculated based on the total pre-laid area and the total area of ​​the small-angle slopes in the height layer, and then compared with the total area of ​​the large-angle slopes in the height layer. If the difference is less than the total area of ​​the large-angle slopes in the height layer, then the first laying quantity is calculated based on the total area of ​​the small-angle slopes in the height layer and the cross-sectional area of ​​the first photovoltaic panel, and then the second laying quantity is calculated based on the pre-laid quantity and the first laying quantity. The first photovoltaic panel is designated as the photovoltaic panel to be deployed on the small-angle slope and the large-angle slope in the height layer. The first number of panels laid is designated as the number of photovoltaic panels to be deployed on the small-angle slope in the height layer. The second number of panels laid is designated as the number of photovoltaic panels to be deployed on the large-angle slope in the height layer. If the difference is greater than the total area of ​​the large-angle slope in the height layer, then the difference load is calculated based on the difference, the cross-sectional area of ​​the first photovoltaic panel, and the power of the first photovoltaic panel; Based on the differential load and the total area of ​​the large-angle slopes in the height layer, a second photovoltaic panel is selected and the number of second photovoltaic panels deployed is determined; wherein, the product of the power of the second photovoltaic panel and the number of deployed panels is greater than the differential load, and the product of the cross-sectional area of ​​the second photovoltaic panel and the number of deployed panels is less than the total area of ​​the large-angle slopes in the height layer; The first photovoltaic panel is designated as the photovoltaic panel to be deployed on the small-angle slope in the height layer, and the first number of panels laid is designated as the number of photovoltaic panels to be deployed on the small-angle slope in the height layer. The selected second photovoltaic panel is designated as the photovoltaic panel to be deployed on the large-angle slope in the height layer, and the number of the second photovoltaic panel deployed is designated as the number of photovoltaic panels to be deployed on the large-angle slope in the height layer.

6. A storage medium, characterized in that, The storage medium includes a stored computer program; wherein, when the computer program is running, it controls the device containing the storage medium to execute the photovoltaic deployment plan generation method as described in any one of claims 1-4.

7. A terminal device, characterized in that, The method includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements the photovoltaic deployment planning generation method as described in any one of claims 1-4.

Images