Power regulation method, device, equipment and storage medium

Abstract

The present invention discloses a power regulation method, device, equipment, and storage medium. The present invention relates to the field of power systems. The method includes: for each of the sub-grids, obtaining future weather data of the area where the sub-grid is located, and inputting the future weather data into a power consumption prediction model to obtain predicted power consumption, where the power consumption prediction model is constructed based on historical weather data and historical power consumption data corresponding to the historical weather data; performing power regulation on the energy storage subsystem of the sub-grid according to the predicted power consumption and the power consumption threshold corresponding to the sub-grid. The present invention comprehensively considers the weather conditions affecting power consumption when performing power regulation, thereby improving the accuracy of power regulation for the sub-grid and further meeting the personalized needs of the sub-grid.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of power systems, and in particular, to a power regulation method, device, equipment, and storage medium. Background Art

[0002] A distributed energy storage system consists of multiple energy storage subsystems located in different geographical locations and a cloud server. Each energy storage subsystem includes a local controller and an energy storage module, and the local controller communicates with the cloud server through a wireless network. The cloud server issues control instructions based on the information collected by the data acquisition modules provided by each energy storage subsystem. The local controller receives these instructions and controls the energy storage module to store and output electric energy through an industrial control computer. The distributed energy storage system realizes remote control of the energy storage module, getting rid of the limitations of site and access conditions. Through the unified scheduling of the cloud server and the rapid response of the local controller, the flexibility and regulation ability of the power grid are improved. However, the above-mentioned distributed energy storage systems are all for the entire power grid and cannot perform voltage regulation and peak shaving on a certain sub-grid in a personalized manner. That is, the low data correlation between the control of the energy storage subsystem for power regulation and the sub-grid leads to insufficient accuracy of power regulation, and thus cannot meet the personalized needs of the sub-grid. Summary of the Invention

[0003] Embodiments of the present invention provide a power regulation method, device, equipment, and storage medium, aiming to solve the problem of inaccurate power regulation in existing distributed energy storage systems.

[0004] In a first aspect, an embodiment of the present invention provides a power regulation method, which is applied to a cloud server in a distributed energy storage system. The distributed energy storage system includes the cloud server and multiple energy storage subsystems, and each energy storage subsystem corresponds to a sub-grid. The method includes:

[0005] For each sub-grid, obtain future weather data of the area where the sub-grid is located, and input the future weather data into an electricity consumption prediction model to obtain predicted electricity consumption. The electricity consumption prediction model is constructed based on historical weather data and historical electricity consumption data corresponding to the historical weather data;

[0006] Perform power regulation on the energy storage subsystem of the sub-grid according to the predicted electricity consumption and the electricity consumption threshold corresponding to the sub-grid.

[0007] In a second aspect, an embodiment of the present invention further provides a power regulation device, which is applied to a cloud server in a distributed energy storage system. The distributed energy storage system includes the cloud server and multiple energy storage subsystems, and each energy storage subsystem corresponds to a sub-grid. The device includes:

[0008] A prediction unit, configured to obtain future weather data of the area where each sub-grid is located, and input the future weather data into a power consumption prediction model to obtain predicted power consumption, where the power consumption prediction model is constructed based on historical weather data and historical power consumption data corresponding to the historical weather data;

[0009] An adjustment unit, configured to perform power adjustment on the energy storage subsystem of the sub-grid according to the predicted power consumption and a power consumption threshold corresponding to the sub-grid.

[0010] In a third aspect, an embodiment of the present invention further provides a computer device, which includes a memory and a processor, where a computer program is stored on the memory, and when the processor executes the computer program, the above method is implemented.

[0011] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the storage medium, and when the computer program is executed by a processor, the above method can be implemented.

[0012] An embodiment of the present invention provides a power adjustment method, device, equipment, and storage medium. Among them, the method includes: for each sub-grid, obtaining future weather data of the area where the sub-grid is located, inputting the future weather data into a power consumption prediction model to obtain predicted power consumption, where the power consumption prediction model is constructed based on historical weather data and historical power consumption data corresponding to the historical weather data; performing power adjustment on the energy storage subsystem of the sub-grid according to the predicted power consumption and a power consumption threshold corresponding to the sub-grid. The technical solution of the embodiment of the present invention first constructs a power consumption prediction model according to historical power consumption data and historical weather data, then obtains future weather data of the area where the sub-grid is located and inputs the future weather data into the power consumption prediction model to obtain predicted power consumption, and then performs power adjustment on the energy storage subsystem according to the predicted power consumption and the power consumption threshold. When performing power adjustment, the weather conditions affecting power consumption are comprehensively considered, thereby improving the accuracy of power adjustment for the sub-grid and further meeting the personalized needs of the sub-grid. Description of the Drawings

[0013] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0014] Figure 1Schematic structural diagram of the distributed energy storage system provided by the embodiment of the present invention;

[0015] Figure 2 Schematic flow diagram of a power regulation method provided by the embodiment of the present invention;

[0016] Figure 3 Schematic sub - flow diagram of a power regulation method provided by the embodiment of the present invention;

[0017] Figure 4 Schematic sub - flow diagram of a power regulation method provided by the embodiment of the present invention;

[0018] Figure 5 Schematic flow diagram of the power regulation method provided by another embodiment of the present invention;

[0019] Figure 6 Schematic block diagram of a power regulation device provided by the embodiment of the present invention;

[0020] Figure 7 Schematic block diagram of a computer device provided by the embodiment of the present invention. Detailed implementation manners

[0021] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0022] It should be understood that when used in this specification and the appended claims, the terms "comprises" and "comprising" indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0023] It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in this specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include the plural forms.

[0024] It should be further understood that the term "and / or" used in this specification of the present invention and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0025] As used in this specification and the appended claims, the term "if" can be construed, depending on the context, as "when", "once", "in response to determining", or "in response to detecting". Similarly, the phrase "if determined" or "if [the described condition or event] is detected" can be construed, depending on the context, to mean "once determined", "in response to determining", "once [the described condition or event] is detected", or "in response to detecting [the described condition or event]".

[0026] For ease of understanding, the distributed energy storage system will be described first. As Figure 1 described, the distributed energy storage system consists of n energy storage subsystems distributed in different geographical locations and a cloud server, where n > 2 and is an integer. The cloud server includes a scheduling module. One energy storage subsystem corresponds to one sub-grid. The energy storage subsystems are interconnected. Each energy storage subsystem includes a control module and an energy storage module. The control module communicates with the cloud server through a wireless network. The cloud server issues control instructions based on the data provided by each energy storage subsystem. The control module receives the control instructions and controls the energy storage module to store and output electric energy.

[0027] Please refer to Figure 2 , Figure 2 which is a schematic flowchart of the power regulation method provided by an embodiment of the present invention. The power regulation method will be described in detail below. As Figure 2 shown, the method includes the following steps S110 - S120.

[0028] S110. For each of the sub-grids, obtain the future weather data of the area where the sub-grid is located, and input the future weather data into the power consumption prediction model to obtain the predicted power consumption. The power consumption prediction model is constructed based on historical weather data and historical power consumption data corresponding to the historical weather data.

[0029] In an embodiment of the present invention, historical weather data of the area where the sub-grid is located collected by the Internet of Things meteorological station is obtained, and historical power consumption data corresponding to the historical weather data is obtained. An electricity consumption prediction model is constructed based on the historical weather data and the historical power consumption data. After constructing the electricity consumption prediction model, for each sub-grid, future weather data of the area where the sub-grid is located predicted by the Internet of Things meteorological station is obtained, and the future weather data is input into the electricity consumption prediction model for electricity consumption prediction to obtain the predicted electricity consumption. The obtained predicted electricity consumption is closely related to the weather conditions in the area where the sub-grid is located and more meets the personalized needs of the sub-grid. It should be noted that in the embodiment of the present invention, the historical weather data and the historical power consumption data can be determined according to requirements. For example, the historical weather data can be the weather data of each hour in the past day, or the weather data of each day in the past month; if the historical weather data is the weather data of each hour, the historical power consumption data is the power consumption of each hour under the weather data, and if the historical weather data is the weather data of each day, the historical power consumption data is the power consumption of each day under the weather data.

[0030] Please refer to Figure 3 , Figure 3 which is a schematic sub-process diagram of the power regulation method provided by the embodiment of the present invention. As Figure 3 shown, the specific steps of constructing the electricity consumption prediction model according to the historical weather data and the historical power consumption data corresponding to the historical weather data include steps S111 - S112: S111. Calculate the electricity consumption threshold and the target historical electricity consumption according to the historical power consumption data; S112. Construct an electricity consumption prediction model according to the historical weather data and the target historical electricity consumption.

[0031] Further, as Figure 4 shown, step S111 includes steps S1111 - S1113:

[0032] S1111. Clean and reduce the dimension of the historical power consumption data to obtain the cleaned historical power consumption data.

[0033] In an embodiment of the present invention, outliers, missing values, and duplicate values in the historical power consumption data are removed to ensure the quality of the historical power consumption data, and then deep learning techniques, such as autoencoders, are used to reduce the dimension of the cleaned historical power consumption data to obtain the cleaned historical power consumption data to improve the accuracy and efficiency of cluster analysis.

[0034] S1112. Use a clustering algorithm to perform cluster analysis on the cleaned historical power consumption data and calculate the electricity consumption threshold.

[0035] Further, step S1112 specifically includes: using the K-means algorithm to determine two data points from the cleaned historical power consumption data as the first clustering center and the second clustering center, where the values of the first clustering center and the second clustering center respectively represent the high power consumption mean value and the low power consumption mean value; calculating the power consumption threshold according to the high power consumption mean value and the low power consumption mean value. Specifically, in the embodiment of the present invention, K = 2, that is, the number of clustering centers is 2, that is, two data points are randomly determined from the cleaned historical power consumption data as the first initial clustering center and the second initial clustering center, and then the algorithm is iterated with the first initial clustering center and the second initial clustering center until the clustering centers no longer change significantly or reach the iteration number of the algorithm, and finally the first clustering center and the second clustering center are determined, where the value of the first clustering center represents the high power consumption mean value, and the value of the second clustering center represents the low power consumption mean value; calculating the intermediate value of the high power consumption mean value and the low power consumption mean value, and using the intermediate value as the power consumption threshold. It can be understood that all power consumptions greater than the power consumption threshold are determined as high power consumptions, and all power consumptions not greater than the power consumption threshold are determined as low power consumptions.

[0036] S1113. According to the cleaned historical power consumption data and the power consumption threshold, use a preset formula to calculate the target historical power consumption. For the convenience of understanding and description, the cleaned historical power consumption data is represented by Y i ; the power consumption threshold is represented by L; the target historical power consumption is represented by MA t , where Yi represents the power consumption at the i-th time point, and MA t represents the power consumption at the t-th time point, and both i and t are positive integers. Specifically, use the preset formula to calculate multiple target historical power consumptions MA i from the cleaned historical power consumption data Y t , where the preset formula is a moving average formula, and the moving average formula is shown in formula (1). In the formula, n represents the window size of the moving average, and n is a positive integer. In particular, if the absolute value of the difference between the power consumptions at two consecutive time points in the cleaned historical power consumption data is greater than two-thirds of the power consumption threshold L, then the power consumption at the t-th time point is equal to the power consumption at the i-th time point, that is, if then t = 1. At this time, t ≤ n, and MA t = Y i . It should be noted that if the time point is in hours, that is, the cleaned historical power consumption data Y i represents the power consumption at the i-th hour in a certain past day, then the target historical power consumption MA tThe change trend is the change trend of the electricity consumption on this day; if the time point is in days, that is, the historical electricity consumption data Y to be cleaned i represents the electricity consumption on the i-th day in a certain past month, then the target historical electricity consumption MA t The change trend is the change trend of the electricity consumption in this month; similarly, the change trend of the electricity consumption in a certain past year can be obtained.

[0037]

[0038] In the embodiment of the present invention, the historical weather data includes different weather variables, such as temperature, humidity, and wind speed. Step S112 is specifically: solving the regression coefficients corresponding to the temperature, the humidity, and the wind speed according to the historical weather data and the target historical electricity consumption; constructing the electricity consumption prediction model according to the temperature, the humidity, the wind speed, and the regression coefficients. For the convenience of description, the temperature, the humidity, and the wind speed are respectively represented as X1, X2, and X3. It should be noted that in this embodiment, only the influence of the temperature X1, the humidity X2, and the wind speed X3 on the electricity consumption is considered. In other embodiments of the present invention, the weather data may further include other weather variables that affect the electricity consumption. Specifically, according to the target historical electricity consumption MA t , the temperature X1, the humidity X2, and the wind speed X3, use formula (2) to calculate the regression coefficients corresponding to the temperature X1, the humidity X2, and the wind speed X3. In formula (2), X1, X2, X3... X n are different weather variables, β0, β1, β2, β3... β n are the regression coefficients corresponding to different weather variables, n is a positive integer, and ∈ is the error term. After solving the β n corresponding to X n , construct the electricity consumption prediction model. The electricity consumption prediction model is shown in formula (3), where Y′ is the predicted electricity consumption.

[0039] MAt = β0 + β1X1 + β2X2 +... + β n X n + ∈ (2)

[0040] Y′ = β0 + β1X1 + β2X2 + β3X3 + ∈ (3)

[0041] S120. Perform power regulation on the energy storage subsystem of the sub-grid according to the predicted electricity consumption and the electricity consumption threshold corresponding to the sub-grid.

[0042] In an embodiment of the present invention, after obtaining the predicted power consumption of the sub-grid and the power consumption threshold, compare the magnitudes of the predicted power consumption and the power consumption threshold. If the predicted power consumption is greater than the power consumption threshold, control the energy storage subsystem of the sub-grid to charge so that the energy storage subsystem stores electrical energy, improving the accuracy of power regulation. Specifically, the energy storage subsystem includes the control module and the energy storage module. For each sub-grid, if the predicted power consumption is greater than the power consumption threshold, it indicates that the predicted power consumption is high power consumption, that is, the sub-grid will soon usher in a peak period of power consumption at a certain future moment. Then, send a control instruction to the energy storage subsystem of the sub-grid. The control module in the energy storage subsystem receives the control instruction and controls the energy storage module to charge so that the energy storage module stores electrical energy. When the peak period of power consumption arrives, the energy storage module of the energy storage subsystem can be controlled to quickly discharge to provide additional power for the sub-grid, thereby reducing the burden on traditional power plants and preventing voltage fluctuations. It should be noted that in the embodiment of the present invention, the way to charge the energy storage module can be charging by a traditional power plant, charging by an external power grid, or charging by other power-providing means.

[0043] Please refer to Figure 5 , Figure 5 which is a schematic flowchart of a power regulation method provided by another embodiment of the present invention. As Figure 5 shown, the method includes the following steps S110 - S140, and steps S130 - S140 are also included after step S120.

[0044] S130. If the predicted power consumption is greater than the energy storage capacity of the energy storage subsystem, determine the sub-grid corresponding to the predicted power consumption as the target sub-grid;

[0045] S140. According to the predicted power consumption of each sub-grid, the preset power transmission loss, and the energy storage capacity of the energy storage subsystem, use a global optimization algorithm to determine the dispatching sub-grid from all the sub-grids, and send a dispatching instruction to the dispatching sub-grid so that the dispatching sub-grid transmits electrical energy to the target sub-grid.

[0046] In an embodiment of the present invention, if the predicted power consumption of a certain sub-grid is greater than the energy storage capacity of the energy storage subsystem of the sub-grid, it indicates that the total electric energy that can be provided by the traditional power plant and the energy storage subsystem is no longer sufficient to meet the power consumption of the sub-grid at a certain future moment. Then, the sub-grid corresponding to the predicted power consumption is determined as the target sub-grid. Subsequently, according to the predicted power consumption of each sub-grid, the preset power transmission loss, and the energy storage capacity of the energy storage subsystem, a global optimization algorithm is used to determine the dispatching sub-grid from all the sub-grids, and a dispatching instruction is sent to the dispatching sub-grid to enable the dispatching sub-grid to transmit electric energy to the target sub-grid. Taking a certain sub-grid as an example, the dispatching process is described in detail as follows: As Figure 1 shown, the No. 1 energy storage subsystem of the No. 1 sub-grid will monitor its own energy storage capacity and voltage fluctuation in real time. When the predicted power consumption of the No. 1 sub-grid is greater than the energy storage capacity of the No. 1 energy storage subsystem, the No. 1 energy storage subsystem triggers a demand sending mechanism. The control module of the No. 1 energy storage subsystem encapsulates data such as the voltage, current, the energy storage capacity, and the predicted voltage fluctuation range at the current moment into a grid demand data packet, and encrypts the grid demand data packet and then sends it to the dispatching module of the cloud server. The dispatching module receives and analyzes the grid demand data packet to obtain the power regulation demand. Then, the cloud server uses a global optimization algorithm according to the predicted power consumption of each sub-grid, the preset power transmission loss, and the energy storage capacity of the energy storage subsystem to generate a dispatching plan with the goal of minimizing the overall voltage fluctuation and operation cost of the power grid, that is, to determine the dispatching sub-grid from the No. 2 sub-grid to the No. n sub-grid. The dispatching module sends the dispatching instruction and the power regulation demand to the energy storage subsystem of the dispatching sub-grid. The control module in the energy storage subsystem of the dispatching sub-grid receives the dispatching instruction and the power regulation demand and controls the energy storage module to transmit electric energy to the target sub-grid.

[0047] In summary, in the embodiments of the present invention, the power consumption prediction model is pre-constructed according to historical weather data and historical power consumption data corresponding to the historical weather data. For each sub-grid, the future weather data of the area where the sub-grid is located predicted by the Internet of Things meteorological station is obtained, and the future weather data is input into the power consumption prediction model to predict the power consumption to obtain the predicted power consumption. Then, the energy storage subsystem of the sub-grid is adjusted according to the predicted power consumption and the power consumption threshold corresponding to the sub-grid. If the predicted power consumption of the target sub-grid is greater than the energy storage capacity of the energy storage subsystem of the target sub-grid, the dispatching sub-grid is determined from all sub-grids by using a global optimization algorithm according to the predicted power consumption of each sub-grid, the preset power transmission loss, and the energy storage capacity of the energy storage subsystem, and a dispatching instruction is sent to the energy storage subsystem of the dispatching sub-grid. After receiving the dispatching instruction, the energy storage subsystem of the dispatching sub-grid transmits electric energy to the target sub-grid. When predicting the power consumption, the weather conditions affecting the power consumption of each sub-grid are comprehensively considered. For example, if the temperature in the future weather data of a certain sub-grid is high, especially when the temperature exceeds a certain specific value (such as 30 degrees Celsius), due to the extensive use of refrigeration equipment such as air conditioners, the predicted power consumption will increase significantly. At the same time, if the humidity is also at a high level, the high humidity will reduce the thermal comfort of the human body, resulting in people being more inclined to use refrigeration equipment, further exacerbating the increase in the predicted power consumption. In addition, if the wind speed is low, the natural heat dissipation effect is poor, which will also increase the usage frequency and duration of refrigeration equipment, thereby increasing the predicted power consumption. Adjusting the power according to the predicted power consumption improves the accuracy of power adjustment and further meets the personalized needs of the sub-grid.

[0048] Figure 6 is a schematic block diagram of a power adjustment device 200 provided by an embodiment of the present invention. As Figure 6 shown, corresponding to the above power adjustment method, the present invention also provides a power adjustment device 200. The power adjustment device 200 includes units for executing the above power adjustment method, and the device can be configured in a computer device. Specifically, please refer to Figure 6 , the power adjustment device 200 includes a prediction unit 201 and an adjustment unit 202.

[0049] Among them, the prediction unit 201 is used to obtain the future weather data of the area where each sub-grid is located for each sub-grid, and input the future weather data into the power consumption prediction model to predict the power consumption to obtain the predicted power consumption. The power consumption prediction model is constructed according to historical weather data and historical power consumption data corresponding to the historical weather data; the adjustment unit 202 is used to adjust the power of the energy storage subsystem of the sub-grid according to the predicted power consumption and the power consumption threshold corresponding to the sub-grid.

[0050] In some embodiments, such as this embodiment, the prediction unit 201 includes a calculation unit and a model construction unit.

[0051] Among them, the calculation unit is used to calculate the electricity consumption threshold and the target historical electricity consumption according to the historical electricity consumption data; the model construction unit is used to construct an electricity consumption prediction model according to the historical weather data and the target historical electricity consumption.

[0052] In some embodiments, such as this embodiment, the calculation unit includes a cleaning unit, a clustering unit, and a first calculation subunit.

[0053] Among them, the cleaning unit is used to clean and dimension-reduce the historical electricity consumption data to obtain cleaned historical electricity consumption data; the clustering unit is used to perform clustering analysis on the cleaned historical electricity consumption data using a clustering algorithm and calculate the electricity consumption threshold; the first calculation subunit is used to calculate the target historical electricity consumption according to the cleaned historical electricity consumption data and the electricity consumption threshold using a preset formula.

[0054] In some embodiments, such as this embodiment, the clustering includes a clustering subunit and a second calculation subunit.

[0055] Among them, the clustering subunit is used to determine two data points from the cleaned historical electricity consumption data as the first clustering center and the second clustering center using the K-means algorithm, where the values of the first clustering center and the second clustering center respectively represent the high electricity consumption mean and the low electricity consumption mean; the second calculation subunit is used to calculate the electricity consumption threshold according to the high electricity consumption mean and the low electricity consumption mean.

[0056] In some embodiments, such as this embodiment, the model construction unit includes a solving unit and a model construction subunit.

[0057] Among them, the solving unit is used to solve the regression coefficients corresponding to the temperature, the humidity, and the wind speed according to the historical weather data and the target historical electricity consumption; the model construction subunit is used to construct the electricity consumption prediction model according to the temperature, the humidity, the wind speed, and the regression coefficients.

[0058] In some embodiments, such as this embodiment, the adjustment unit 202 includes a comparison unit and a control unit.

[0059] Among them, the comparison unit is used to compare the magnitudes of the predicted electricity consumption and the electricity consumption threshold; the control unit is used to control the energy storage subsystem of the sub-grid to charge to store electrical energy if the predicted electricity consumption is greater than the electricity consumption threshold.

[0060] In some embodiments, such as another embodiment, the power regulation device 200 further includes a determination unit and a scheduling unit.

[0061] Wherein, the determination unit is configured to determine the sub-grid corresponding to the predicted power consumption as the target sub-grid if the predicted power consumption is greater than the energy storage capacity of the energy storage subsystem; the scheduling unit is configured to use a global optimization algorithm to determine a scheduling sub-grid from all the sub-grids according to the predicted power consumption of each sub-grid, the preset power transmission loss, and the energy storage capacity of the energy storage subsystem, and send a scheduling instruction to the scheduling sub-grid, so that the scheduling sub-grid transmits electric energy to the target sub-grid.

[0062] The above power regulation device can be implemented in the form of a computer program, and this computer program can run on a computer device as shown in Figure 7 Figure.

[0063] Please refer to Figure 7 , Figure 7 which is a schematic block diagram of a computer device provided by an embodiment of the present invention. The computer device 300 is a device with power regulation function.

[0064] Referring to Figure 7 , the computer device 300 includes a processor 302, a memory, and a network interface 305 connected through a system bus 301. Among them, the memory may include a non-volatile storage medium 303 and an internal memory 304.

[0065] The non-volatile storage medium 303 can store an operating system 3031 and a computer program 3032. When the computer program 3032 is executed, the processor 302 can be made to execute a power regulation method.

[0066] The processor 302 is configured to provide computing and control capabilities to support the operation of the entire remote controller 300.

[0067] The internal memory 304 provides an environment for the operation of the computer program 3032 in the non-volatile storage medium 303. When the computer program 3032 is executed by the processor 302, the processor 302 can be made to execute a power regulation method.

[0068] The network interface 305 is used for network communication with other devices. Those skilled in the art can understand that Figure 7 the structure shown in

[0069] Among them, the processor 302 is used to run the computer program 3032 stored in the memory to implement any embodiment of the above power regulation method.

[0070] It should be understood that in the embodiment of the present invention, the processor 302 may be a central processing unit (CPU), and the processor 302 may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), off-the-shelf programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0071] Those of ordinary skill in the art can understand that all or part of the processes in the methods of implementing the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a storage medium, and the storage medium is a computer-readable storage medium. The computer program is executed by at least one processor in the computer system to implement the process steps of the embodiments of the above methods.

[0072] Therefore, the present invention also provides a storage medium. The storage medium may be a computer-readable storage medium. The storage medium stores a computer program. When the computer program is executed by a processor, the processor is caused to execute any embodiment of the above power regulation method.

[0073] The storage medium may be a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, an optical disk, or other various computer-readable storage media that can store program codes.

[0074] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed in this article can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the present invention.

[0075] In several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of each unit is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0076] The steps in the method embodiments of the present invention can be adjusted, combined, and deleted according to actual needs. The units in the device embodiments of the present invention can be combined, divided, and deleted according to actual needs. In addition, the functional units in each embodiment of the present invention can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0077] 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 storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a remote control to execute all or part of the steps of the methods described in the various embodiments of the present invention.

[0078] In the above embodiments, the descriptions of the various embodiments have their own focuses. For the parts not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0079] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, provided that these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention also intends to include these changes and modifications.

[0080] As described above, the above are only the specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A power regulation method is applied to a cloud server in a distributed energy storage system. The distributed energy storage system includes the cloud server and multiple energy storage subsystems, and each energy storage subsystem corresponds to a sub-grid. It is characterized in that, Including: For each of the sub-grids, obtain future weather data of the area where the sub-grid is located, and input the future weather data into an electricity consumption prediction model to obtain predicted electricity consumption, where the electricity consumption prediction model is constructed based on historical weather data and historical electricity consumption data corresponding to the historical weather data; Adjust the power of the energy storage subsystem of the sub-grid according to the predicted electricity consumption and the electricity consumption threshold corresponding to the sub-grid; Among them, constructing the electricity consumption prediction model based on historical weather data and historical electricity consumption data corresponding to the historical weather data includes: Clean and reduce the dimensionality of the historical electricity consumption data to obtain cleaned historical electricity consumption data; Use a clustering algorithm to perform clustering analysis on the cleaned historical electricity consumption data and calculate the electricity consumption threshold; According to the cleaned historical electricity consumption data and the electricity consumption threshold, use a moving average formula to calculate the target historical electricity consumption; Construct an electricity consumption prediction model based on the historical weather data and the target historical electricity consumption; The using a clustering algorithm to perform clustering analysis on the cleaned historical electricity consumption data and calculate the electricity consumption threshold includes: Use the K-means algorithm to determine two data points from the cleaned historical electricity consumption data as the first clustering center and the second clustering center, where the values of the first clustering center and the second clustering center represent the high electricity consumption mean and the low electricity consumption mean respectively; Calculate the electricity consumption threshold according to the high electricity consumption mean and the low electricity consumption mean.

2. The method according to claim 1, wherein The historical weather data includes temperature, humidity, and wind speed; the constructing the electricity consumption prediction model based on the historical weather data and the target historical electricity consumption includes: Solve the regression coefficients corresponding to the temperature, the humidity, and the wind speed according to the historical weather data and the target historical electricity consumption; Construct the electricity consumption prediction model according to the temperature, the humidity, the wind speed, and the regression coefficients.

3. The method according to claim 1, characterized in that, The adjusting the power of the energy storage subsystem of the sub-grid according to the predicted electricity consumption and the electricity consumption threshold corresponding to the sub-grid includes: Compare the magnitudes of the predicted electricity consumption and the electricity consumption threshold; If the predicted electricity consumption is greater than the electricity consumption threshold, control the energy storage subsystem of the sub-grid to charge so that the energy storage subsystem stores electric energy.

4. The method according to claim 1, characterized in that, After the adjusting the power of the energy storage subsystem of the sub-grid according to the predicted electricity consumption and the electricity consumption threshold corresponding to the sub-grid, it further includes: If the predicted electricity consumption is greater than the energy storage capacity of the energy storage subsystem, determine the sub-grid corresponding to the predicted electricity consumption as the target sub-grid; Determine a dispatching sub-grid from all the sub-grids using a global optimization algorithm according to the predicted electricity consumption of each sub-grid, the preset power transmission loss, and the energy storage capacity of the energy storage subsystem, and send a dispatching instruction to the dispatching sub-grid so that the dispatching sub-grid transmits electric energy to the target sub-grid.

5. A power regulation device is applied to a cloud server in a distributed energy storage system. The distributed energy storage system includes the cloud server and multiple energy storage subsystems. Each energy storage subsystem corresponds to a sub-grid. It is characterized in that, Including: A prediction unit, configured to obtain future weather data of the area where each sub-grid is located for each of the sub-grids, and input the future weather data into a power consumption prediction model to obtain predicted power consumption, where the power consumption prediction model is constructed based on historical weather data and historical power consumption data corresponding to the historical weather data; An adjustment unit, configured to perform power adjustment on the energy storage subsystem of the sub-grid according to the predicted power consumption and a power consumption threshold corresponding to the sub-grid; Wherein, constructing the power consumption prediction model based on historical weather data and historical power consumption data corresponding to the historical weather data includes: A cleaning unit, configured to clean and perform dimensionality reduction processing on the historical power consumption data to obtain cleaned historical power consumption data; A clustering unit, configured to perform clustering analysis on the cleaned historical power consumption data by using a clustering algorithm and calculate the power consumption threshold; A first calculation sub-unit, configured to calculate target historical power consumption by using a moving average formula according to the cleaned historical power consumption data and the power consumption threshold; A model construction unit, configured to construct a power consumption prediction model according to the historical weather data and the target historical power consumption; The clustering unit includes: A clustering sub-unit, configured to determine two data points as a first clustering center and a second clustering center from the cleaned historical power consumption data by using the K-means algorithm, where the values of the first clustering center and the second clustering center respectively represent the high power consumption mean value and the low power consumption mean value; A second calculation sub-unit, configured to calculate the power consumption threshold according to the high power consumption mean value and the low power consumption mean value.

6. A computer device, characterized in that, The computer device includes a memory and a processor, where a computer program is stored on the memory, and when the processor executes the computer program, the method according to any one of claims 1-4 is implemented.

7. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1-4 can be implemented.

Images