Emergency energy storage power supply distribution optimization method based on artificial intelligence and terminal equipment

Abstract

The invention relates to an emergency energy storage power supply distribution optimization method based on artificial intelligence and terminal equipment. According to the method, the division mode of the power supply area is automatically optimized through the generation model according to the load demand, so that the load demand of each target sub-area is more balanced, the distribution position of the emergency energy storage power supply is determined by taking the target sub-area as a unit, and the emergency energy storage power supply can be combined with the power grid in a multi-agent mode; therefore, the emergency energy storage power supply can be adapted to a power grid control scene, so that after distribution optimization, the emergency energy storage power supply only needs to move in a relatively small range according to load requirements, and the efficiency and convenience of the emergency energy storage power supply are improved.

Description

Technical Field

[0001] The present invention is applicable to the field of energy storage power supply scheduling, and in particular relates to an emergency energy storage power supply distribution optimization method and terminal equipment based on artificial intelligence. Background Art

[0002] At present, mobile emergency energy storage power supply can solve the problem of seasonal load, and has the functions of suppressing power system oscillation, ensuring power system stability, and coordinating the voltage and frequency regulation of the power grid. With the development of energy storage technology, the application scope of mobile emergency energy storage power supply will continue to expand. In addition to emergency rescue for natural disasters such as earthquakes and ice disasters, it can also provide emergency backup power for important facilities such as operating rooms, sports venues, and cloud servers, provide energy for ice-covered lines to eliminate ice and melt, and line maintenance, adjust the peak and valley of power load in suburbs and urban commercial areas, charge electric vehicles, and ensure power supply for major events.

[0003] In a scenario where multiple emergency energy storage power sources work in conjunction with a power grid, a common method in the prior art is to determine the distribution location of the emergency energy storage power sources based on the load demand on the power consumption side of the power grid. However, in this method, the movement frequency of the emergency energy storage power sources is relatively high, resulting in a high application cost of the emergency energy storage power sources. Another common method is to fix the distribution location of the emergency energy storage power sources as much as possible, but this method will cause the emergency energy storage power sources to respond to load demand with a lag.

[0004] Therefore, how to improve the efficiency and convenience of emergency energy storage power supplies by optimizing their distribution has become an urgent problem to be solved. Summary of the invention

[0005] In view of this, an embodiment of the present invention provides an emergency energy storage power distribution optimization method and terminal device based on artificial intelligence to solve the problem.

[0006] In a first aspect, a method for optimizing the distribution of emergency energy storage power sources based on artificial intelligence is provided, the method comprising:

[0007] Divide the acquired preset power supply area image into M initial sub-area images, where M is a positive integer;

[0008] Inputting the M initial sub-region images into a sub-region update model to obtain intermediate sub-region images corresponding to the M initial sub-region images respectively;

[0009] The adjustment loss is calculated according to the load demand images respectively corresponding to the M initial sub-region images, the M intermediate sub-region images and the preset power supply region images at N target time points, where N is a positive integer;

[0010] According to the adjustment loss, the sub-region update model is trained until the adjustment loss converges to obtain a trained sub-region update model;

[0011] Inputting the M initial sub-region images into the trained sub-region update model to obtain M target sub-region images;

[0012] Determining second load demand points respectively included in the M target sub-region images according to the load demand images respectively corresponding to the N target time points and the M target sub-region images;

[0013] For any target sub-region image, determining a power distribution position corresponding to the target sub-region image according to a second load demand point included in the target sub-region image;

[0014] According to the distribution locations of all power sources, the distribution optimization results of the emergency energy storage power source are obtained.

[0015] In a second aspect, an embodiment of the present invention provides a terminal device, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the emergency energy storage power supply distribution optimization method as described in the first aspect when executing the computer program.

[0016] Compared with the prior art, the present invention has the following beneficial effects:

[0017] According to the load demand, the power supply area division method is automatically optimized by generating a model, so that the load demand of each target sub-area is more balanced, and the distribution location of the emergency energy storage power supply is determined based on the target sub-area, so that the emergency energy storage power supply can be combined with the power grid in a multi-agent manner, and then can adapt to the power grid control scenario. After the distribution optimization, the emergency energy storage power supply only needs to move within a smaller range according to the load demand, thereby improving the efficiency and convenience of the emergency energy storage power supply. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the prior art description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative labor.

[0019] Figure 1 This is a schematic diagram of an application environment of an emergency energy storage power distribution optimization method based on artificial intelligence provided in Embodiment 1 of the present invention;

[0020] Figure 2It is a flow chart of an emergency energy storage power supply distribution optimization method based on artificial intelligence provided in Embodiment 1 of the present invention;

[0021] Figure 3 It is a circuit diagram of connecting an emergency energy storage power supply to a power grid in an emergency energy storage power supply distribution optimization method based on artificial intelligence provided in Embodiment 1 of the present invention;

[0022] Figure 4 It is a structural schematic diagram of a terminal device of an emergency energy storage power supply distribution optimization method based on artificial intelligence provided in Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0023] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0024] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0025] It should also be understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0026] As used in the present specification and the appended claims, the term "if" may be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" may be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]", depending on the context.

[0027] In addition, in the description of the present specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0028] References to "one embodiment" or "some embodiments" etc. described in the present specification mean that one or more embodiments of the present invention include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0029] It should be understood that the order of execution of the steps in the following embodiments does not imply a precedence of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0030] In order to illustrate the technical solution of the present invention, specific embodiments are provided below for illustration.

[0031] The first embodiment of the present invention provides an artificial intelligence-based emergency energy storage power distribution optimization method, which can be applied in the following aspects: Figure 1 In the application environment, multiple emergency energy storage power supplies communicate with the client. The client includes but is not limited to handheld computers, desktop computers, laptop computers, ultra-mobile personal computers (UMPC), netbooks, cloud terminal devices, personal digital assistants (PDA) and other computer devices.

[0032] See also Figure 2 , is a flow chart of an emergency energy storage power distribution optimization method based on artificial intelligence provided by the first embodiment of the present invention. The above emergency energy storage power distribution optimization method can be applied to Figure 1 The client in the client can receive the preset power supply area image, load demand information of the power grid, etc. The client has a storage function, and the sub-area update model is stored in the client. The sub-area update model can be used to update the initial sub-area divided. Figure 2 As shown, the emergency energy storage power distribution optimization may include the following steps:

[0033] Step S201: dividing the acquired preset power supply area image into M initial sub-area images.

[0034] Wherein, M is a positive integer, the preset power supply area image corresponds to the preset power supply area, and the preset power supply area may refer to the coverage area of ​​the power grid that can be supported by the emergency energy storage power supply.

[0035] The emergency energy storage power supply can be connected to the power grid through energy storage converter and step-up transformer, see Figure 3 , which is a circuit diagram of connecting an emergency energy storage power supply to a power grid in an emergency energy storage power supply distribution optimization method based on artificial intelligence provided in Example 1 of the present invention.

[0036] The initial sub-area image can be a binary image, and the size of the initial sub-area image is consistent with the size of the preset power supply area image. For example, for a certain initial sub-area image, the pixel value of the pixel points in the preset power supply area image belonging to the initial sub-area image is 1, and the pixel value of the pixel points in the preset power supply area image that do not belong to the initial sub-area image is 0.

[0037] Specifically, the implementer may divide the preset power supply area image into M initial sub-area images according to the historically divided sub-areas. In this embodiment, the preset power supply area image is divided into M initial sub-area images in an evenly divided manner. At this time, M is recommended to be A 2 , to obtain a relatively equal sub-area division method in space, A is a positive integer, for example, A can be 2, then M is 4.

[0038] Optionally, the preset power supply area image corresponds to a preset power supply area, and the method further includes:

[0039] Obtain P first load demand points within a preset power supply area, where P is a positive integer;

[0040] For any first load demand point, obtain the reference demand load corresponding to the first load demand point at K reference time points;

[0041] Input K reference demand loads into the trained load forecasting model to obtain the forecast demand loads corresponding to the first load demand point at N target time points;

[0042] For any target time point, the load demand image corresponding to the target time point is determined according to the predicted demand loads corresponding to the P first load demand points at the target time point.

[0043] Among them, the first load demand point may refer to the corresponding position on the electricity consumption side, and the reference time point may refer to a historical time point. Therefore, the reference demand load corresponding to the first load demand point at K reference time points can be obtained by collecting power grid information.

[0044] The target time point may refer to a predicted time point, and the load forecasting model may be implemented using a time series forecasting model, such as a long short-term memory network model, a recurrent network model, a time domain convolutional network model, and the like.

[0045] Specifically, when determining the load demand image corresponding to the target time point based on the predicted demand loads corresponding to the P first load demand points at the target time point, the predicted demand load needs to be standardized. For example, the predicted demand load can be normalized and then multiplied by 255, and then rounded down to obtain the standardized result. Normalization can be the comparison of the predicted demand load with the maximum value of all predicted demand loads.

[0046] Step S202: input the M initial sub-region images into the sub-region update model to obtain the intermediate sub-region images corresponding to the M initial sub-region images.

[0047] The sub-region update model may be used to update the initial sub-region image corresponding to the divided initial sub-region, and the intermediate sub-region image may refer to an intermediate result after the initial sub-region image is updated using the sub-region update model.

[0048] Specifically, the M initial sub-region images need to be simultaneously input into the sub-region update model to provide the sub-region update model with the connections between the M initial sub-region images. Therefore, the implementer can regard the M initial sub-region images as a multi-channel image with M channels.

[0049] Step S203, calculating the adjustment loss according to the load demand images corresponding to the M initial sub-region images, the M intermediate sub-region images and the preset power supply region images at the N target time points.

[0050] Among them, N is a positive integer. Since the preset power supply area image corresponds to the preset power supply area, a single pixel point in the load demand image corresponds to the physical position of the actual power consumption side, and the pixel value corresponding to the pixel point can represent the load demand value of the actual power consumption side at the corresponding target time point.

[0051] Optionally, the adjustment loss is calculated according to the load demand images respectively corresponding to the M initial sub-region images, the M intermediate sub-region images, and the preset power supply region images at the N target time points, including:

[0052] According to the M initial sub-region images and the M intermediate sub-region images, a first sub-loss is calculated;

[0053] According to the M intermediate sub-region images, the second sub-loss is calculated;

[0054] The third sub-loss is calculated based on the M middle sub-region images and the N load demand images;

[0055] The adjusted loss is obtained by weighted addition of the first sub-loss, the second sub-loss and the third sub-loss.

[0056] Among them, the first sub-loss, the second sub-loss and the third sub-loss are respectively used to determine different attention information when updating the sub-region update model.

[0057] Specifically, the first sub-loss corresponds to the first weight, the second sub-loss corresponds to the second weight, and the third sub-loss corresponds to the third weight. In this embodiment, the sum of the first weight, the second weight and the third weight is 1, the second weight is greater than the third weight, and the third weight is greater than the first weight. For example, the first weight, the second weight and the third weight are 0.2, 0.5, and 0.3, respectively, so that the sub-region update model first ensures the convergence of the second sub-loss, and then optimizes based on the third sub-loss, taking into account the constraints of the first sub-loss.

[0058] Optionally, the first sub-loss is calculated according to the M initial sub-region images and the M intermediate sub-region images, including:

[0059] For any initial sub-region image, subtract the pixel value of the initial sub-region image from the pixel value of the corresponding intermediate sub-region image point by point and take the absolute value to obtain a first reference image, and add the pixel values ​​of all pixels in the first reference image to obtain a first intermediate value corresponding to the initial sub-region image;

[0060] The first intermediate values ​​corresponding to the M initial sub-region images are added together to obtain the first sub-loss.

[0061] Among them, the first sub-loss can be used to supervise that the intermediate sub-region corresponding to the updated intermediate sub-region image and the initial sub-region corresponding to the initial sub-region image change as little as possible, so as to satisfy the prior information when dividing the initial sub-region as much as possible.

[0062] Specifically, the middle sub-region image is also a binary image. It can be known that by subtracting the pixel value of the initial sub-region image from the pixel value of the corresponding middle sub-region image point by point and taking the absolute value, only the pixel value corresponding to the inconsistent part between the initial sub-region and the middle sub-region is 1, otherwise the pixel value is 0.

[0063] The first reference image can be used to characterize the difference information between the initial sub-region image and the corresponding intermediate sub-region image, and the first intermediate value can be used to characterize the degree of difference between the initial sub-region image and the corresponding intermediate sub-region image.

[0064] The first intermediate values ​​respectively corresponding to the M initial sub-region images are added together, which can be used to represent the cumulative difference between all the initial sub-region images and their respectively corresponding intermediate sub-region images.

[0065] Optionally, a second sub-loss is calculated based on the M intermediate sub-region images, including:

[0066] Multiply the pixel values ​​of the M middle sub-region images point by point to obtain a second reference image;

[0067] The pixel values ​​of all pixels in the second reference image are added together to obtain the second sub-loss.

[0068] Among them, the second sub-loss can be used to supervise that there is no overlapping area between the intermediate sub-region images.

[0069] Specifically, since the intermediate sub-region images are all binary images, when there is an overlapping area, the multiplication result of the pixel values ​​corresponding to the pixel points in the overlapping area is 1. Therefore, the second reference image can represent the regional overlap information between the intermediate sub-region images, and the second sub-loss can represent the degree of regional overlap between the intermediate sub-region images.

[0070] Optionally, the third sub-loss is calculated based on the M middle sub-region images and the N load demand images, including:

[0071] For any load demand image, pixel values ​​of the load demand image are multiplied point by point with pixel values ​​of the M intermediate sub-region images to obtain M third reference images;

[0072] Adding pixel values ​​of all pixels in each third reference image to obtain a third intermediate value corresponding to each third reference image;

[0073] The variance of the M third intermediate values ​​is used as the fourth intermediate value of the corresponding load demand image;

[0074] Add up all the fourth intermediate values ​​to get the third sub-loss.

[0075] Among them, the pixel values ​​of the load demand image are multiplied point by point with the pixel values ​​of a single intermediate sub-area image, and the resulting third reference image contains the load demand information of each power consumption side in the corresponding intermediate sub-area. Accordingly, the third intermediate value can be used to characterize the overall load demand information of the power consumption side in the corresponding intermediate sub-area.

[0076] The fourth intermediate value may be used to characterize the difference in overall load demand information corresponding to each intermediate sub-region.

[0077] Specifically, the third sub-loss can be used to supervise that the difference between the overall load demand information corresponding to each intermediate sub-region is as small as possible, so as to achieve a balance among each sub-region both in space and in terms of power load.

[0078] Step S204: train the sub-region update model according to the adjustment loss until the adjustment loss converges to obtain a trained sub-region update model.

[0079] Among them, according to the adjustment loss, the gradient descent method is used to train the sub-region update model until the adjustment loss converges to obtain the trained sub-region update model.

[0080] Step S205, inputting the M initial sub-region images into the trained sub-region update model to obtain M target sub-region images.

[0081] In another embodiment, the implementer may also fix the parameters of the sub-region update model, and train the input M initial sub-region images according to the adjustment loss until the adjustment loss converges to obtain M target sub-region images.

[0082] Step S206 , determining the second load demand points respectively included in the M target sub-region images according to the load demand images respectively corresponding to the N target time points and the M target sub-region images.

[0083] Among them, the second load demand point can be used to characterize the electricity consumption side with large load demand fluctuations.

[0084] Optionally, before determining the power distribution position corresponding to the target sub-region image according to the second load demand point included in the target sub-region image, the method further includes:

[0085] For any first load demand point, the variance of the predicted demand load corresponding to the first load demand point at N target time points is used as a first reference value;

[0086] determining a load fluctuation threshold value according to all first reference values;

[0087] A first load demand point corresponding to a first reference value that is greater than or equal to the load fluctuation threshold is determined as a second load demand point.

[0088] The first reference value may be used to characterize the degree of fluctuation of the predicted demand load of the first load demand point, and the load fluctuation threshold may be used to screen the first load demand point to obtain a second load demand point with a larger load demand fluctuation.

[0089] Specifically, when determining the load fluctuation threshold according to all the first reference values, a mean method, a maximum between-class variance method, a histogram method, etc. may be used.

[0090] Step S207 : for any target sub-region image, according to the second load demand point included in the target sub-region image, determine the power distribution position corresponding to the target sub-region image.

[0091] The power distribution position corresponds to the pixel point in the target sub-region image.

[0092] Optionally, the method further comprises:

[0093] For any target sub-region image, the first reference values ​​corresponding to each second load demand point in the target sub-region image are added together to obtain a second reference value;

[0094] Sorting the M target sub-region images according to the second reference values ​​respectively corresponding to the M target sub-region images to obtain a sorting result;

[0095] According to the sorting result, Q emergency energy storage power sources are allocated to M target sub-region images, where Q is an integer greater than or equal to M.

[0096] Among them, since the first reference value can represent the load demand fluctuation of the second load demand point, the second reference value can be used to represent the load demand fluctuation of the target sub-area.

[0097] Specifically, according to the second reference values ​​respectively corresponding to the M target sub-region images, when sorting the M target sub-region images, the images are sorted in descending order of the second reference values.

[0098] A single target sub-area contains at most B emergency energy storage power sources. In this embodiment, B can be 2, and the implementer can adjust the value of B according to actual conditions.

[0099] When allocating Q emergency energy storage power supplies to M target sub-region images, that is, allocating Q emergency energy storage power supplies to M target sub-regions, first allocate one emergency energy storage power supply to each target sub-region, and then allocate the remaining emergency energy storage power supplies in a front-to-back order according to the sorting result. When the number of emergency energy storage power supplies allocated to a certain target sub-region reaches the B value, the emergency energy storage power supply is allocated to the next target sub-region, and so on.

[0100] The above allocation method can be adapted to the multi-agent system (MAS) commonly used for grid coordination control. The multi-agent system is formed by multiple intelligent agents. Each target sub-area corresponds to an intelligent agent. The intelligent agent can be directly connected to the grid or to the microgrid, and then the microgrid is connected to the grid. One intelligent agent can control the emergency energy storage power supply corresponding to the target sub-area.

[0101] Optionally, determining the power distribution position corresponding to the target sub-region image according to the second load demand point included in the target sub-region image includes:

[0102] When the target sub-region image corresponds to a single emergency energy storage power source, the first-order moment of the target sub-region image is calculated according to the second load demand point contained in the target sub-region image as the power distribution position of the target sub-region image;

[0103] When the target sub-area image corresponds to S emergency energy storage power sources, according to the second load demand point contained in the target sub-area image, a preset clustering algorithm is used to obtain S cluster sets, and the cluster centers of the S cluster sets are used as the power distribution positions of the target sub-area image, where S is an integer greater than 1.

[0104] The first-order moment of the target sub-region image calculated based on the included second load demand point can be used to characterize the centroid of the target sub-region image, and the centroid is used as the power distribution position of the target sub-region image.

[0105] Specifically, the clustering algorithm may adopt a K-means clustering algorithm. The K-means clustering algorithm requires a preset number of cluster sets, and S can be used as the preset number of cluster sets.

[0106] Step S208, obtaining a distribution optimization result of the emergency energy storage power source according to the distribution positions of all power sources.

[0107] Among them, the distribution optimization result includes the power distribution positions corresponding to several emergency energy storage power sources, which can be used to provide reference information for the location scheduling and control of the emergency energy storage power sources.

[0108] In the present invention, according to the load demand, the division mode of the power supply area is automatically optimized by generating a model, so that the load demand of each target sub-area is more balanced, and the distribution position of the emergency energy storage power supply is determined based on the target sub-area, so that the emergency energy storage power supply can be combined with the power grid in a multi-agent manner, and then can adapt to the power grid control scenario, so that after the distribution optimization, the emergency energy storage power supply only needs to move within a smaller range according to the load demand, thereby improving the efficiency and convenience of the emergency energy storage power supply.

[0109] Figure 4 This is a schematic diagram of the structure of a terminal device of a method for associated collaborative management of a comprehensive power grid plan provided in the second embodiment of the present invention. Figure 4 As shown, the terminal device of this embodiment includes: at least one processor ( Figure 4 Only one is shown), a memory, and a computer program stored in the memory and executable on at least one processor, and when the processor executes the computer program, the steps in any of the above-mentioned embodiments of the emergency energy storage power supply distribution optimization method based on artificial intelligence are implemented.

[0110] The terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that Figure 4 It is only an example of a terminal device and does not constitute a limitation on the terminal device. The terminal device may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, it may also include a network interface, a display screen, and an input device.

[0111] The processor may be a CPU, or other general-purpose processors, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0112] The memory includes a readable storage medium, an internal memory, etc., wherein the internal memory may be the memory of the terminal device, and the internal memory provides an environment for the operation of the operating system and the computer-readable instructions in the readable storage medium. The readable storage medium may be the hard disk of the terminal device, and in other embodiments, it may also be an external storage device of the terminal device, for example, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the terminal device. Further, the memory may also include both an internal storage unit of the terminal device and an external storage device. The memory is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of a computer program, etc. The memory may also be used to temporarily store data that has been output or is to be output.

[0113] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention. The specific working process of the units and modules in the above-mentioned device can refer to the corresponding process in the above-mentioned method embodiment, which will not be repeated here. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned method embodiment can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device capable of carrying computer program code, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0114] The present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by a computer program product. When the computer program product runs on a computer device, the terminal device can implement the steps in the above-mentioned method embodiment when executing it.

[0115] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0116] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0117] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0118] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0119] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. An emergency energy storage power distribution optimization method based on artificial intelligence, characterized in that: The method comprises: Divide the acquired preset power supply area image into M initial sub-area images, where M is a positive integer; Inputting the M initial sub-region images into a sub-region update model to obtain intermediate sub-region images corresponding to the M initial sub-region images respectively; The adjustment loss is calculated according to the load demand images respectively corresponding to the M initial sub-region images, the M intermediate sub-region images and the preset power supply region images at N target time points, where N is a positive integer; According to the adjustment loss, the sub-region update model is trained until the adjustment loss converges to obtain a trained sub-region update model; Inputting the M initial sub-region images into the trained sub-region update model to obtain M target sub-region images; Determining second load demand points respectively included in the M target sub-region images according to the load demand images respectively corresponding to the N target time points and the M target sub-region images; For any target sub-region image, determining a power distribution position corresponding to the target sub-region image according to a second load demand point included in the target sub-region image; According to the distribution locations of all power sources, the distribution optimization results of the emergency energy storage power source are obtained.

2. The method for optimizing the distribution of emergency energy storage power sources according to claim 1, characterized in that: The calculating the adjustment loss according to the load demand images respectively corresponding to the M initial sub-region images, the M intermediate sub-region images and the preset power supply region images at N target time points includes: Calculate a first sub-loss according to the M initial sub-region images and the M intermediate sub-region images; Calculate a second sub-loss according to the M intermediate sub-region images; Calculating a third sub-loss according to the M intermediate sub-region images and the N load demand images; The adjusted loss is obtained by weighted addition of the first sub-loss, the second sub-loss and the third sub-loss.

3. The method for optimizing the distribution of emergency energy storage power sources according to claim 2, characterized in that: The calculating a first sub-loss according to the M initial sub-region images and the M intermediate sub-region images includes: For any initial sub-region image, subtract the pixel value of the initial sub-region image from the pixel value of the corresponding intermediate sub-region image point by point and take the absolute value to obtain a first reference image, and add the pixel values ​​of all pixels in the first reference image to obtain a first intermediate value corresponding to the initial sub-region image; The first intermediate values ​​corresponding to the M initial sub-region images are added together to obtain the first sub-loss.

4. The method for optimizing the distribution of emergency energy storage power sources according to claim 2, characterized in that: The calculating a second sub-loss according to the M intermediate sub-region images includes: Multiplying the pixel values ​​of the M middle sub-region images point by point to obtain a second reference image; The pixel values ​​of all pixels in the second reference image are added to obtain the second sub-loss.

5. The method for optimizing the distribution of emergency energy storage power sources according to claim 2, characterized in that: The calculating the third sub-loss according to the M intermediate sub-region images and the N load demand images includes: For any load demand image, pixel values ​​of the load demand image are multiplied point by point with pixel values ​​of the M intermediate sub-region images to obtain M third reference images; Adding pixel values ​​of all pixels in each third reference image to obtain a third intermediate value corresponding to each third reference image; Using the variance of the M third intermediate values ​​as the fourth intermediate value corresponding to the load demand image; All fourth intermediate values ​​are added together to obtain the third sub-loss.

6. The method for optimizing the distribution of emergency energy storage power sources according to claim 1, characterized in that: The preset power supply area image corresponds to a preset power supply area, and the method further includes: Obtain P first load demand points within the preset power supply area, where P is a positive integer; For any first load demand point, obtaining a reference demand load corresponding to the first load demand point at K reference time points; Inputting K reference demand loads into the trained load forecasting model to obtain the predicted demand loads corresponding to the first load demand point at N target time points; For any target time point, the load demand image corresponding to the target time point is determined according to the predicted demand loads respectively corresponding to the P first load demand points at the target time point.

7. The method for optimizing the distribution of emergency energy storage power sources according to claim 6, characterized in that: Before determining the power distribution position corresponding to the target sub-region image according to the second load demand point included in the target sub-region image, the method further includes: For any first load demand point, the variance of the predicted demand load corresponding to the first load demand point at N target time points is used as a first reference value; determining a load fluctuation threshold value according to all first reference values; A first load demand point corresponding to a first reference value that is greater than or equal to the load fluctuation threshold is determined as the second load demand point.

8. The method for optimizing the distribution of emergency energy storage power sources according to claim 7, characterized in that: The method further comprises: For any target sub-region image, the first reference values ​​corresponding to each second load demand point in the target sub-region image are added to obtain a second reference value; Sorting the M target sub-region images according to the second reference values ​​respectively corresponding to the M target sub-region images to obtain a sorting result; According to the sorting result, Q emergency energy storage power supplies are allocated to the M target sub-region images, where Q is an integer greater than or equal to M.

9. The method for optimizing the distribution of emergency energy storage power sources according to any one of claims 1 to 8, characterized in that: The determining, according to the second load demand point included in the target sub-region image, a power distribution position corresponding to the target sub-region image includes: When the target sub-region image corresponds to a single emergency energy storage power source, the first-order moment of the target sub-region image is calculated according to the second load demand point contained in the target sub-region image as the power distribution position of the target sub-region image; When the target sub-area image corresponds to S emergency energy storage power supplies, according to the second load demand point contained in the target sub-area image, a preset clustering algorithm is used to obtain S cluster sets, and the cluster centers of the S cluster sets are used as the power distribution positions of the target sub-area image, and S is an integer greater than 1.

10. A terminal device, characterized in that: The terminal device includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the emergency energy storage power supply distribution optimization method as described in any one of claims 1 to 9 is implemented.

Images