Power load prediction total score coordination method and device based on coordination planning equation
By adopting the total score coordination method of coordinated planning equations in power load prediction, the prediction results of objects at different levels are optimized, and the problems of unbalanced and inconsistent power load prediction results are solved, and the accuracy of power load prediction and the allocation of power electricity are improved. balance.
Patent Information
- Application Number
- CN202411226975.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-03
- Publication Date
- 2025-02-07
AI Technical Summary
The power load prediction results of objects at different levels are uneven and inconsistent, which affects the distribution and balance of power.
The power load prediction total score coordination method based on the coordinated planning equation is adopted. By obtaining historical statistical data of objects at each level, inputting them into the preset load prediction model for prediction, and then inputting the prediction results into the preset total score coordination model for adjustment, and optimizing Coordination of prediction results.
The accuracy of power load prediction is improved, and the problems of imbalance and inconsistency between the prediction results of objects at different levels are solved, which is conducive to the distribution and balance of power.
Smart Images
Figure CN119398205A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of information technology, and in particular to a method and device for total-division coordination of power load forecasting based on a coordinated planning equation. Background Art
[0002] According to different standards, power load can be divided into multiple levels or layers, which are called total demand and sub-demand. For example, from a structural perspective, the power load (electricity) of each industry (sector) is the sub-demand, and the power load (electricity) of the entire industry (sector) is the total demand. For another example, according to the administrative level, the power load (electricity) of the provincial power grid is the total demand, and the power load (electricity) of the prefecture-level city is the sub-demand.
[0003] At present, in order to support the electricity consumption plan arrangement of objects at different levels, it is necessary to predict the power load of objects at different levels separately. In theory, the total power load demand of objects at one level should be equal to the sum of the power load sub-demands of the corresponding objects at the next level. However, in actual work, the total demand and the sum of the sub-demands are often not equal, that is, there is an imbalance and incoordination between the prediction results of objects at different levels, which affects the distribution and balance of power. Summary of the invention
[0004] In view of this, the present application provides a total-scale coordination method and device for power load forecasting based on coordinated planning equations, which mainly aims to optimize and adjust the power load forecasting results of objects at different levels, improve the accuracy of power load forecasting, and solve the problems of imbalance and incoordination between power load forecasting results of objects at different levels.
[0005] According to a first aspect of the present application, a total-division coordination method for power load forecasting based on a coordinated planning equation is provided, the method comprising:
[0006] Respectively obtaining first historical statistical data of first-level objects and second historical statistical data of each second-level object, wherein the level at which the first-level objects are located is the previous level of the level at which each second-level object is located;
[0007] Inputting the first historical statistical data and the second historical statistical data into corresponding preset load forecasting models respectively to perform power load forecasting, and obtaining load forecasting results of the first-level objects and load forecasting results of each of the second-level objects;
[0008] The load forecast result of the first-level object and the load forecast results of each second-level object are respectively input into a preset total-specific coordination model for power load adjustment to obtain the final load forecast result of the first-level object and the final load forecast result of each second-level object, wherein the preset total-specific coordination model is constructed based on the load coordination planning equation between objects of different levels.
[0009] According to a second aspect of the present application, there is provided a total-division coordination device for power load forecasting based on a coordination planning equation, the device comprising:
[0010] An acquisition unit, configured to respectively acquire first historical statistical data of first-level objects and second historical statistical data of respective second-level objects, wherein the level at which the first-level objects are located is a level above the level at which the respective second-level objects are located;
[0011] A prediction unit, configured to input the first historical statistical data and the second historical statistical data into corresponding preset load prediction models to perform power load prediction, and obtain load prediction results of the first-level objects and load prediction results of each of the second-level objects;
[0012] An adjustment unit is used to input the load forecast results of the first-level object and the load forecast results of each second-level object into a preset total-specific coordination model for power load adjustment, so as to obtain the final load forecast results of the first-level object and the final load forecast results of each second-level object, wherein the preset total-specific coordination model is constructed based on the load coordination planning equations between objects of different levels.
[0013] According to a third aspect of the present application, a storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the above-mentioned total-scale coordination method for power load forecasting based on coordinated planning equations is implemented.
[0014] According to the fourth aspect of the present application, an electronic device is provided, comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein when the processor executes the program, the above-mentioned total-scale coordination method for power load forecasting based on coordinated planning equations is implemented.
[0015] Through the above-mentioned technical scheme, the present application provides a method and device for total-specific coordination of power load forecasting based on coordinated planning equations. By utilizing a preset total-specific coordination model to coordinate and optimize the load forecasting results of objects at different levels, the accuracy of power load forecasting can be improved, thereby solving the problems of imbalance and incoordination between power load forecasting results of objects at different levels, which is beneficial to the distribution and balance of electric power.
[0016] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:
[0018] Figure 1 A schematic diagram of a flow chart of a total-division coordination method for power load forecasting based on a coordinated planning equation provided in an embodiment of the present application is shown;
[0019] Figure 2 A schematic diagram of a flow chart of another method for total-division coordination of power load forecasting based on a coordinated planning equation provided in an embodiment of the present application is shown;
[0020] Figure 3 A schematic diagram of the structure of a total-division coordination device for power load forecasting based on a coordination planning equation provided in an embodiment of the present application is shown;
[0021] Figure 4 A schematic diagram of the structure of another power load forecasting total-division coordination device based on a coordinated planning equation provided in an embodiment of the present application is shown. DETAILED DESCRIPTION
[0022] The present application will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict.
[0023] The existing technology often results in a situation where the total demand is not equal to the sum of the sub-demands, that is, there is an imbalance and incoordination between the prediction results of objects at different levels, which affects the distribution and balance of electric power.
[0024] In order to solve the above problems, the embodiment of the present invention provides a total-scale coordination method for power load forecasting based on a coordinated planning equation, such as Figure 1 As shown, the method includes:
[0025] Step 101: Obtain first historical statistical data of first-level objects and second historical statistical data of each second-level object respectively.
[0026] The level where the first-level object is located is the upper level of the level where each second-level object is located. For example, the first-level object is the entire industry, and the second-level object is each industry. For another example, the first-level object is a province, and the second-level object is each city in the province, or the first-level object is the whole country, and the second-level object is each province. The first historical statistical data and the second historical statistical data include historical load data, meteorological temperature data, policy data, etc.
[0027] It should be noted that the first-level objects and each second-level object in the embodiment of the present invention are not limited to the above-mentioned ones, and this solution can be applied to any objects of different levels that may cause unbalanced and uncoordinated power load forecasting results.
[0028] The embodiment of the present invention is mainly applicable to the scenario of coordinating and optimizing the load forecasting results of objects at different levels. The execution subject of the embodiment of the present invention is a device or equipment capable of coordinating and optimizing the load forecasting results of objects at different levels, such as a server.
[0029] For the embodiment of the present invention, in order to predict the load prediction results of the first-level object and the load prediction results of each second-level object, it is necessary to collect the first historical statistical data of the first-level object and the second historical statistical data of each second-level object in advance. For example, the historical load data of Jiangsu Province in the past three months and the historical load data of each city in Jiangsu Province in the past three months are collected.
[0030] Step 102: Input the first historical statistical data and the second historical statistical data into corresponding preset load forecasting models respectively to perform power load forecasting, and obtain the load forecasting results of the first-level objects and the load forecasting results of each second-level object.
[0031] For the embodiment of the present invention, after obtaining the first historical statistical data and the second historical statistical data, it is necessary to predict the load prediction results of the first-level object and the load prediction results of each second-level object based on the first historical statistical data and the second historical statistical data. When performing power load forecasting, the embodiment of the present invention can use time series analysis methods, such as moving average method, exponential smoothing method, RNN recurrent neural network. The time series analysis method is suitable for short-term load forecasting and can capture the periodic changes of load.
[0032] When using RNN recurrent neural network for power load forecasting, the corresponding preset load forecasting model includes: the preset total load demand forecasting model (total load demand forecasting RNN recurrent network) corresponding to the first-level object and the preset sub-load demand forecasting model (sub-load demand forecasting RNN recurrent network) corresponding to each second-level object. During specific forecasting, the first historical statistical data is input into the preset total load demand forecasting model for power load forecasting to obtain the load forecasting result of the first-level object; the second historical statistical data is input into the preset sub-load demand forecasting model for power load forecasting to obtain the load forecasting result of each second-level object.
[0033] It should be noted that due to the large differences in electricity consumption habits between cities or industries, in order to further improve the load forecasting accuracy, different preset sub-load demand forecasting models (sub-load demand forecasting RNN recurrent network) can be pre-trained for different second-level objects.
[0034] Step 103: Input the load forecast result of the first-level object and the load forecast results of each second-level object into the preset total-specific coordination model for power load adjustment to obtain the final load forecast result of the first-level object and the final load forecast result of each second-level object.
[0035] The preset total-specific coordination model is constructed based on load coordination planning equations between objects at different levels.
[0036] For the embodiment of the present invention, before adjusting the load forecasting result, it is necessary to pre-build a preset total-specific coordination model. Regarding the construction process of the preset total-specific coordination model, the method includes: constructing the load coordination planning equation between the objects at different levels; solving the load coordination planning equation using the Lagrange multiplier method to obtain the expression of the final load forecasting result of the objects at different levels with respect to the weight parameter and the load forecasting result parameter; based on the expression, constructing the preset total-specific coordination model.
[0037] When constructing the load coordination planning equation between the objects at different levels, a load coordination combination model between the objects at different levels is constructed; the load forecast result of the upper-level object among the objects at different levels is taken as a constraint condition that the load forecast result of the upper-level object is equal to the sum of the load forecast results of each lower-level object; based on the load coordination combination model and the constraint condition, the load coordination planning equation between the objects at different levels is constructed.
[0038] Specifically, let the load forecast result of the upper-level object in different-level objects be z0, and the load forecast result of each lower-level object be z i(i=1, ..., n), where n is the number of objects in the next level. For example, let the load forecast result of a province be z0, and the load forecast results of each city in the province be z i (i=1,…,n), n is the number of cities in the province. The load coordination combination model between objects at different levels is established as:
[0039]
[0040] The constraint condition is that the load forecast result of the upper-level object is equal to the sum of the load forecast results of each lower-level object, which can be specifically expressed as:
[0041]
[0042] in, Represents the load forecast results of each lower-level object. Represents the load forecast result of the upper level object. Weight w i (i=0, 1, ..., n) is the credibility of each load forecast result. The smaller the error of the load forecast result, the greater its corresponding credibility. The weight w i If the load demand forecasting model used by the upper-level object and each lower-level object is the same, in order to simplify the calculation, the credibility of each load forecasting result can be assumed to be equal, that is, w i Both are 1.
[0043] Formula (1) and formula (2) are combined to form a load coordination planning equation with equality constraints. For this load coordination planning equation, it can be solved by the Lagrange multiplier method to obtain the expressions of the final load forecasting results of objects at different levels with respect to the weight parameters and load forecasting result parameters, as shown below:
[0044]
[0045]
[0046] Furthermore, let the difference between the load forecast result of the previous level object and the sum of the load forecast results of each next level object be From formula (4), it can be seen that the adjustment amount of the load forecast result is a multiple of the imbalance amount Δz, so this multiple is set as the adjustment coefficient, that is:
[0047]
[0048] After introducing the adjustment coefficient, formula (3) and formula (4) can be unified as follows:
[0049]
[0050] Based on formula (5) and formula (6), the preset total-specific coordination model is determined.
[0051] When the power load is formally adjusted, the load forecast results of the first-level objects, the load forecast results of each second-level object, and the corresponding weights of the first-level objects and the corresponding weights of each second-level object are input into the preset total-specific coordination model to calculate the adjustment amount of each load forecast result, and then obtain the final load forecast results of the first-level objects and the final load forecast results of each second-level object.
[0052] An embodiment of the present invention provides a total-specific coordination method for power load forecasting based on a coordinated planning equation. By utilizing a preset total-specific coordination model to coordinate and optimize load forecasting results for objects at different levels, the accuracy of power load forecasting can be improved, thereby solving the problems of imbalance and incoordination between power load forecasting results for objects at different levels, which is beneficial to the distribution and balance of electric power.
[0053] Further, as a refinement and extension of the specific implementation of the above embodiment, in order to fully illustrate the implementation of this embodiment, this embodiment also provides another total-division coordination method for power load forecasting based on the coordination planning equation, such as Figure 2 As shown, the method includes:
[0054] Step 201: Obtain first historical statistical data of first-level objects and second historical statistical data of each second-level object respectively.
[0055] The level where the first-level objects are located is the upper level of the level where the second-level objects are located.
[0056] For example, collect the historical load data of the entire industry in the past three months, as well as the historical load data of each industry in the past three months.
[0057] Step 202: Input the first historical statistical data and the second historical statistical data into corresponding preset load forecasting models respectively to perform power load forecasting, and obtain the load forecasting results of the first-level objects and the load forecasting results of each second-level object.
[0058] In addition to using the time series analysis method to predict the load prediction results of the first-level objects and each second-level object, the embodiment of the present invention can also use the regression analysis method to predict the power load. Specifically, the meteorological temperature data and date type can be used as independent variables, and the power load can be used as the dependent variable. Then, a regression model between the independent variables and the dependent variables is established to predict the power load. Among them, linear regression and multivariate regression are commonly used regression analysis methods. In addition, the load density method can also be used to predict the power load, that is, by calculating the load density of the current and historical regions, combined with the regional development plan for prediction. This method is suitable for predicting the power load of each functional area.
[0059] Step 203: Based on the load forecasting result of the first-level object and the load forecasting results of each second-level object, the preset total-specific coordination model is used to respectively calculate the load adjustment amount of the first-level object and the load adjustment amount of each second-level object.
[0060] For the embodiment of the present invention, with respect to the process of calculating the load adjustment amount using the preset total-specific coordination model, step 203 specifically includes: based on the load forecast result of the first-level object and the load forecast results of each second-level object, using the preset total-specific coordination model to respectively calculate the adjustment coefficient of the first-level object, the adjustment coefficient of each second-level object, and the difference between the load forecast result of the first-level object and the sum of the load forecast results of each second-level object; based on the preset total-specific coordination model, multiplying the adjustment coefficient of the first-level object and the difference to obtain the load adjustment amount of the first-level object, and multiplying the adjustment coefficient of each second-level object and the difference to obtain the load adjustment amount of each second-level object.
[0061] When calculating the adjustment coefficient, based on the load forecast result of the first-level object and the load forecast results of each second-level object, the preset total-specific coordination model is used to respectively calculate the first square value of the load forecast result of the first-level object and the second square value of the load forecast result of each second-level object; the first square value is divided by the weight corresponding to the first-level object to obtain the first proportional coefficient; each second square value is divided by the weight of the corresponding second-level object to obtain each second proportional coefficient; the first proportional coefficient and each second proportional coefficient are added to obtain the total proportional coefficient; each second proportional coefficient is divided by the total proportional coefficient to obtain the adjustment coefficient of each second-level object; the first proportional coefficient is divided by the total proportional coefficient to obtain the adjustment coefficient of the first-level object.
[0062] Specifically, formula (5) is used to calculate the adjustment coefficient of the first-level object and the adjustment coefficient of each second-level object respectively. Then, based on the calculated adjustment coefficient and the difference between the load prediction result of the first-level object and the sum of the load prediction results of each second-level object, formula (6) is used to calculate the load adjustment amount of the first-level object and the load adjustment amount of each second-level object.
[0063] Step 204: Based on the preset total-specific coordination model, the load adjustment amount and the load forecast result of the first-level object are added to obtain the final load forecast result of the first-level object, and the load adjustment amount and the load forecast result of each second-level object are added to obtain the final load forecast result of each second-level object.
[0064] For the embodiment of the present invention, based on formula (6), the load forecasting result of the first-level object is adjusted using the calculated load adjustment amount of the first-level object to obtain the final load forecasting result of the first-level object. At the same time, the load forecasting result of each second-level object is adjusted using the calculated load adjustment amount of each second-level object to obtain the final load forecasting result of each second-level object.
[0065] For example, the provincial load forecast results are adjusted using the load adjustment amount of the provincial power grid to obtain the final load forecast results of the provincial power grid. At the same time, the load adjustment amount of each city in the province is used to adjust the load forecast results of each city to obtain the final load forecast results of each city in the province.
[0066] Another method for total-specific coordination of power load forecasting based on coordinated planning equations provided in an embodiment of the present invention can improve the accuracy of power load forecasting by coordinating and optimizing load forecasting results of objects at different levels using a preset total-specific coordination model, thereby solving the problems of imbalance and incoordination between power load forecasting results of objects at different levels, and is beneficial to the distribution and balance of electric power.
[0067] Further, as Figure 1 and Figure 2 The specific implementation of the method shown in the embodiment provides a total coordination device for power load forecasting based on the coordination planning equation, such as Figure 3 As shown, the device includes: an acquisition unit 31, a prediction unit 32 and an adjustment unit 33.
[0068] The acquisition unit 31 may be used to respectively acquire first historical statistical data of first-level objects and second historical statistical data of each second-level object, wherein the level at which the first-level objects are located is the upper level of the level at which each second-level object is located.
[0069] The prediction unit 32 can be used to input the first historical statistical data and the second historical statistical data into corresponding preset load prediction models to perform power load prediction, and obtain the load prediction results of the first-level objects and the load prediction results of each second-level object.
[0070] The adjustment unit 33 can be used to input the load forecasting results of the first-level object and the load forecasting results of each second-level object into a preset total-specific coordination model for power load adjustment, so as to obtain the final load forecasting results of the first-level object and the final load forecasting results of each second-level object, wherein the preset total-specific coordination model is constructed based on the load coordination planning equations between objects of different levels.
[0071] In some embodiments, Figure 4 As shown, the device further includes: a construction unit 34 and a solution unit 35.
[0072] The construction unit 34 may be used to construct the load coordination planning equation between the objects at different levels.
[0073] The solving unit 35 can be used to solve the load coordination planning equation using the Lagrange multiplier method to obtain expressions of the final load forecasting results of the objects at different levels with respect to weight parameters and load forecasting result parameters.
[0074] The construction unit 34 may also be used to construct the preset total-score coordination model based on the expression.
[0075] In some embodiments, the construction unit 34 can be specifically used to construct a load coordination combination model between the objects at different levels; set the load forecast result of the upper-level object among the objects at different levels to be equal to the sum of the load forecast results of each lower-level object as a constraint condition; and construct a load coordination planning equation between the objects at different levels based on the load coordination combination model and the constraint conditions.
[0076] In some embodiments, the adjustment unit 33 includes: a calculation module 331 and an addition module 332 .
[0077] The calculation module 331 can be used to calculate the load adjustment amount of the first-level object and the load adjustment amount of each second-level object respectively based on the load forecast result of the first-level object and the load forecast results of each second-level object by using the preset total-specific coordination model.
[0078] The addition module 332 can be used to add the load adjustment amount and load forecast result of the first-level object based on the preset total-specific coordination model to obtain the final load forecast result of the first-level object, and add the load adjustment amount and load forecast result of each second-level object to obtain the final load forecast result of each second-level object.
[0079] In some embodiments, the calculation module 331 includes: a calculation submodule and a multiplication submodule.
[0080] The calculation submodule can be used to calculate the adjustment coefficient of the first-level object, the adjustment coefficient of each second-level object, and the difference between the load forecast result of the first-level object and the sum of the load forecast results of each second-level object based on the load forecast result of the first-level object and the load forecast results of each second-level object by using the preset total-specific coordination model.
[0081] The multiplication submodule can be used to multiply the adjustment coefficient of the first-level object and the difference based on the preset total-specific coordination model to obtain the load adjustment amount of the first-level object, and multiply the adjustment coefficient of each second-level object and the difference to obtain the load adjustment amount of each second-level object.
[0082] In some embodiments, the calculation submodule can be specifically used to calculate the first square value of the load forecast result of the first-level object and the second square value of the load forecast result of each second-level object based on the load forecast result of the first-level object and the load forecast results of each second-level object, using the preset total-specific coordination model; divide the first square value by the weight corresponding to the first-level object to obtain a first proportional coefficient; divide each second square value by the weight of the corresponding second-level object to obtain each second proportional coefficient; add the first proportional coefficient and each second proportional coefficient to obtain a total proportional coefficient; divide each second proportional coefficient by the total proportional coefficient to obtain an adjustment coefficient of each second-level object; divide the first proportional coefficient by the total proportional coefficient to obtain the adjustment coefficient of the first-level object.
[0083] In some embodiments, the corresponding preset load forecasting model includes: a preset total load demand forecasting model corresponding to the first-level object and a preset sub-load demand forecasting model corresponding to each second-level object. The forecasting unit 32 can be specifically used to input the first historical statistical data into the preset total load demand forecasting model to perform power load forecasting and obtain the load forecasting result of the first-level object; input the second historical statistical data into the preset sub-load demand forecasting model to perform power load forecasting and obtain the load forecasting result of each second-level object.
[0084] It should be noted that for other corresponding descriptions of the functional units involved in the power load forecasting total-division coordination device based on the coordination planning equation provided in this embodiment, reference can be made to Figure 1 and Figure 2 The corresponding description in will not be repeated here.
[0085] Based on the above Figure 1 and Figure 2 The method shown in the embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the above-mentioned Figure 1 and Figure 2 The total and sub-coordination method for power load forecasting based on coordinated planning equation is shown.
[0086] Based on this understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, USB flash drive, mobile hard disk, etc.), including a number of instructions for enabling an electronic device (which can be a personal computer, server, or network device, etc.) to execute the methods of various implementation scenarios of the present application.
[0087] Based on the above Figure 1 and Figure 2 The method shown, and Figure 3 and Figure 4 In order to achieve the above-mentioned purpose, the embodiment of the present application also provides an electronic device, which can be a personal computer, a tablet computer, a server, or other network equipment, etc. The device includes a storage medium and a processor; the storage medium is used to store a computer program; the processor is used to execute the computer program to achieve the above-mentioned Figure 1 and Figure 2 The total and sub-coordination method for power load forecasting based on coordinated planning equation is shown.
[0088] Optionally, the above-mentioned physical device may also include a user interface, a network interface, a camera, a radio frequency (RF) circuit, a sensor, an audio circuit, a WI-FI module, etc. The user interface may include a display, an input unit such as a keyboard, etc., and the optional user interface may also include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (such as a WI-FI interface), etc.
[0089] Those skilled in the art will appreciate that the above-mentioned physical device structure provided in this embodiment does not constitute a limitation on the physical device, and may include more or fewer components, or a combination of certain components, or different arrangements of components.
[0090] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of the above-mentioned physical device, and supports the operation of the information processing program and other software and / or programs. The network communication module is used to realize the communication between the components inside the storage medium, and the communication with other hardware and software in the information processing physical device.
[0091] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform, or by hardware.
[0092] The embodiment of the present invention can improve the accuracy of power load prediction by coordinating and optimizing the load prediction results of objects at different levels using a preset total-specific coordination model, thereby solving the problem of imbalance and incoordination between power load prediction results of objects at different levels, which is beneficial to the distribution and balance of electric power.
[0093] Those skilled in the art will appreciate that the accompanying drawings are only schematic diagrams of a preferred implementation scenario, and the modules or processes in the accompanying drawings are not necessarily necessary for implementing the present application. Those skilled in the art will appreciate that the modules in the devices in the implementation scenario can be distributed in the devices of the implementation scenario according to the description of the implementation scenario, or can be changed accordingly and located in one or more devices different from the present implementation scenario. The modules of the above-mentioned implementation scenario can be combined into one module, or can be further split into multiple submodules.
[0094] The above serial numbers of this application are only for description and do not represent the advantages and disadvantages of the implementation scenarios. The above disclosure is only a few specific implementation scenarios of this application, but this application is not limited to them, and any changes that can be thought of by technicians in this field should fall within the scope of protection of this application.
Claims
1. A total and sub-coordination method for power load forecasting based on coordinated planning equations, characterized in that: include: Respectively obtaining first historical statistical data of first-level objects and second historical statistical data of each second-level object, wherein the level at which the first-level objects are located is the previous level of the level at which each second-level object is located; Inputting the first historical statistical data and the second historical statistical data into corresponding preset load forecasting models respectively to perform power load forecasting, and obtaining load forecasting results of the first-level objects and load forecasting results of each of the second-level objects; The load forecast result of the first-level object and the load forecast results of each second-level object are respectively input into a preset total-specific coordination model for power load adjustment to obtain the final load forecast result of the first-level object and the final load forecast result of each second-level object, wherein the preset total-specific coordination model is constructed based on the load coordination planning equation between objects of different levels.
2. The method according to claim 1, characterized in that Before respectively inputting the load forecasting result of the first-level object and the load forecasting results of each second-level object into a preset total-specific coordination model for power load adjustment and obtaining a final load forecasting result of the first-level object and a final load forecasting result of each second-level object, the method further includes: Constructing load coordination planning equations between objects at different levels; The load coordination planning equation is solved by using the Lagrange multiplier method to obtain expressions of the final load forecasting results of the objects at different levels with respect to weight parameters and load forecasting result parameters; Based on the expression, the preset total-score coordination model is constructed.
3. The method according to claim 2, characterized in that Constructing load coordination planning equations between objects at different levels, including: Constructing a load coordination combination model between objects at different levels; Taking the load forecast result of the upper-level object among the objects of different levels as a constraint condition equal to the sum of the load forecast results of each lower-level object; Based on the load coordination combination model and the constraint conditions, a load coordination planning equation between the objects at different levels is constructed.
4. The method according to any one of claims 1 to 3, characterized in that: Inputting the load forecasting result of the first-level object and the load forecasting results of each second-level object into a preset total-specific coordination model to adjust the power load, and obtaining the final load forecasting result of the first-level object and the final load forecasting result of each second-level object, including: Based on the load forecast result of the first-level object and the load forecast results of each of the second-level objects, respectively calculating the load adjustment amount of the first-level object and the load adjustment amount of each of the second-level objects by using the preset total-specific coordination model; Based on the preset total-specific coordination model, the load adjustment amount and load forecast result of the first-level object are added to obtain the final load forecast result of the first-level object, and the load adjustment amount and load forecast result of each second-level object are added to obtain the final load forecast result of each second-level object.
5. The method according to claim 4, characterized in that Based on the load forecasting result of the first-level object and the load forecasting results of each of the second-level objects, the load adjustment amount of the first-level object and the load adjustment amount of each of the second-level objects are calculated respectively by using the preset total-to-specific coordination model, including: Based on the load forecast result of the first-level object and the load forecast results of each of the second-level objects, the preset total-to-specific coordination model is used to respectively calculate the adjustment coefficient of the first-level object, the adjustment coefficient of each of the second-level objects, and the difference between the load forecast result of the first-level object and the sum of the load forecast results of each of the second-level objects; Based on the preset total-specific coordination model, the adjustment coefficient of the first-level object is multiplied by the difference to obtain the load adjustment amount of the first-level object, and the adjustment coefficient of each second-level object is multiplied by the difference to obtain the load adjustment amount of each second-level object.
6. The method according to claim 5, characterized in that Based on the load forecast result of the first-level object and the load forecast results of each of the second-level objects, the adjustment coefficient of the first-level object and the adjustment coefficient of each of the second-level objects are calculated respectively by using the preset total-specific coordination model, including: Based on the load forecast result of the first-level object and the load forecast results of each of the second-level objects, respectively calculating a first square value of the load forecast result of the first-level object and a second square value of the load forecast result of each of the second-level objects using the preset total-specific coordination model; Dividing the first square value by the weight corresponding to the first level object to obtain a first proportional coefficient; Divide each second square value by the weight of the corresponding second-level object to obtain each second proportional coefficient; Adding the first proportionality coefficient and each of the second proportionality coefficients to obtain a total proportionality coefficient; Dividing each of the second proportional coefficients by the total proportional coefficient to obtain an adjustment coefficient of each of the second-level objects; The first scale factor is divided by the total scale factor to obtain an adjustment factor of the first-level object.
7. The method according to claim 1, characterized in that The corresponding preset load forecasting model includes: a preset total load demand forecasting model corresponding to the first-level object and a preset sub-load demand forecasting model corresponding to each of the second-level objects, and the first historical statistical data and the second historical statistical data are respectively input into the corresponding preset load forecasting model to perform power load forecasting, and the load forecasting results of the first-level object and the load forecasting results of each of the second-level objects are obtained, including: Inputting the first historical statistical data into the preset total load demand forecasting model to perform power load forecasting, and obtaining a load forecasting result of the first-level object; The second historical statistical data is input into the preset sub-load demand forecasting model to perform power load forecasting, so as to obtain load forecasting results for each second-level object.
8. A total and sub-coordination device for power load forecasting based on coordinated planning equations, characterized in that: include: An acquisition unit, configured to respectively acquire first historical statistical data of first-level objects and second historical statistical data of respective second-level objects, wherein the level at which the first-level objects are located is a level above the level at which the respective second-level objects are located; A prediction unit, configured to input the first historical statistical data and the second historical statistical data into corresponding preset load prediction models to perform power load prediction, and obtain load prediction results of the first-level objects and load prediction results of each of the second-level objects; An adjustment unit is used to input the load forecast results of the first-level object and the load forecast results of each second-level object into a preset total-specific coordination model for power load adjustment, so as to obtain the final load forecast results of the first-level object and the final load forecast results of each second-level object, wherein the preset total-specific coordination model is constructed based on the load coordination planning equations between objects of different levels.
9. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.
10. An electronic device comprising a storage medium, a processor, and a computer program stored in the storage medium and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.