Power grid load prediction method, device, equipment, medium and program product

Abstract

The invention relates to a power grid load prediction method, device and equipment, a medium and a program product. The power grid load prediction method comprises the following steps: carrying out grid division on an area administered by a power grid to be predicted to obtain a plurality of target grids; for each target grid, obtaining a maximum load corresponding to the target grid in the first unit time, first environment data corresponding to the to-be-predicted time, and second environment data corresponding to each unit time in a preset time period; and determining a second unit time with a minimum difference value with the environmental data of the to-be-predicted time and a third unit time with a minimum difference value with the environmental data of the first unit time, and predicting the maximum load corresponding to the to-be-predicted time of the to-be-predicted power grid according to the maximum load corresponding to each target grid in the second unit time and the third unit time. Power grid load prediction can be carried out by combining the difference of the environmental meteorological conditions of each grid in the area where the power grid is located, and the accuracy of load prediction is improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of electric power, and particularly to a power grid load forecasting method, device, equipment, medium and program product. Background Art

[0002] Power grid load forecasting is a key link in the management and control of power systems, and has important economic, technical and social significance. Accurate load forecasting can help power companies understand future electricity demand in advance, so as to ensure that the power generation capacity matches the load demand, avoid power shortages or surpluses, contribute to optimizing dispatching, thereby reducing the power outage risk caused by load fluctuations, and ensuring that users can use electricity stably and safely.

[0003] In the process of power grid load forecasting, the main factor affecting the change of power grid load is meteorological conditions, and the meteorological conditions in different regions within a power grid vary greatly. Therefore, how to accurately forecast the power grid load within a certain power grid range under the condition of large differences in regional meteorological conditions is a technical problem that needs to be solved urgently. Summary of the Invention

[0004] To solve the above technical problems, the present disclosure provides a power grid load forecasting method, device, equipment, medium and program product.

[0005] The first aspect of the embodiments of the present disclosure provides a power grid load forecasting method, including:

[0006] Determine the area under the jurisdiction of the power grid to be forecast, and divide the area into grids to obtain a plurality of target grids;

[0007] For each target grid, obtain the first maximum load corresponding to the target grid in the first unit time, the first environmental data corresponding to the target grid at the time to be forecast, and the second environmental data corresponding to each unit time within a preset time period for each target grid, wherein the first unit time is within the preset time period;

[0008] Determine the second unit time corresponding to the minimum difference between the second environmental data and the first environmental data within the preset time period, and the third unit time corresponding to the minimum difference between the second environmental data corresponding to each unit time before the first unit time within the preset time period and the target environmental data corresponding to the first unit time;

[0009] Obtain the second maximum load corresponding to each target grid at the second unit time, and the third maximum load corresponding to each target grid at the third unit time;

[0010] Based on the first maximum load, the second maximum load and the third maximum load, determine the maximum load forecast value corresponding to the power grid to be forecast at the time to be forecast.

[0011] A second aspect of the embodiments of the present disclosure provides a power grid load prediction device, including:

[0012] A grid division module, configured to determine the area under the jurisdiction of the power grid to be predicted and divide the area into grids to obtain a plurality of target grids;

[0013] A data acquisition module, configured to, for each target grid, acquire a first maximum load corresponding to the target grid in a first unit time, first environmental data corresponding to the target grid at the time to be predicted, and second environmental data corresponding to the target grid at each unit time within a preset time period, wherein the first unit time is within the preset time period;

[0014] A time determination module, configured to determine a second unit time corresponding to the minimum difference between the second environmental data and the first environmental data within the preset time period, and a third unit time corresponding to the minimum difference between the second environmental data corresponding to each unit time before the first unit time within the preset time period and the target environmental data corresponding to the first unit time;

[0015] A maximum load acquisition module, configured to acquire a second maximum load corresponding to each target grid at the second unit time and a third maximum load corresponding to each target grid at the third unit time;

[0016] A load prediction module, configured to determine a maximum load prediction value corresponding to the power grid to be predicted at the time to be predicted based on the first maximum load, the second maximum load, and the third maximum load.

[0017] A third aspect of the embodiments of the present disclosure provides an electronic device, including:

[0018] A processor;

[0019] A memory, configured to store executable instructions;

[0020] Wherein, the processor is configured to read the executable instructions from the memory and execute the executable instructions to implement the power grid load prediction method provided in the first aspect above.

[0021] A fourth aspect of the embodiments of the present disclosure provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, enables the processor to implement the power grid load prediction method provided in the first aspect above.

[0022] A fifth aspect of the embodiments of the present disclosure provides a computer program product, which includes a computer program or instruction, and when the computer program or instruction is executed by a processor, implements the power grid load prediction method as described in the first aspect above.

[0023] The technical solutions provided by the embodiments of the present disclosure have the following advantages compared with the prior art:

[0024] The power grid load prediction method, device, equipment, medium and program product provided by the embodiments of the present disclosure can determine the area under the jurisdiction of the power grid to be predicted, divide the area into grid cells to obtain a plurality of target grid cells. For each target grid cell, obtain the first maximum load corresponding to the target grid cell in the first unit time, the first environmental data corresponding to the target grid cell at the time to be predicted, and the second environmental data corresponding to the target grid cell at each unit time within a preset time period, wherein the first unit time is within the preset time period. After obtaining the first environmental data and the second environmental data, determine the second unit time corresponding to the minimum difference between the second environmental data and the first environmental data within the preset time period, and the third unit time corresponding to the minimum difference between the second environmental data corresponding to each unit time before the first unit time within the preset time period and the target environmental data corresponding to the first unit time. Obtain the second maximum load corresponding to each target grid cell at the second unit time, and the third maximum load corresponding to each target grid cell at the third unit time. Furthermore, based on the first maximum load, the second maximum load and the third maximum load, determine the maximum load prediction value corresponding to the power grid to be predicted at the time to be predicted. Thus, the area under the jurisdiction of the power grid to be predicted can be divided into a plurality of target grid cells, and according to the maximum load of each target grid cell within a unit time and the environmental data of each unit grid cell at different unit times, determine the unit time with the minimum difference from the environmental data at the time to be predicted, and use it as a reference to predict the load of the power grid to be predicted at the time to be predicted, taking into account the differences in the environmental meteorological conditions of each grid cell in the area where the power grid is located, and improving the accuracy of load prediction. Brief Description of the Drawings

[0025] The accompanying drawings here are incorporated into the specification and form a part of this specification, showing the embodiments consistent with the present disclosure and used together with the specification to explain the principles of the present disclosure.

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

[0027] Figure 1 is a flowchart of a power grid load prediction method provided by an embodiment of the present disclosure;

[0028] Figure 2 is a flowchart of a method for determining the maximum load prediction value corresponding to a power grid to be predicted at the time to be predicted provided by an embodiment of the present disclosure;

[0029] Figure 3 It is a schematic structural diagram of a power grid load forecasting device provided by an embodiment of the present disclosure;

[0030] Figure 4 It is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure. Detailed implementation manners

[0031] In order to be able to more clearly understand the above-mentioned objects, features and advantages of the present disclosure, the solutions of the present disclosure will be further described below. It should be noted that, without conflict, the embodiments of the present disclosure and the features in the embodiments may be combined with each other.

[0032] In the following description, many specific details are set forth in order to fully understand the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only a part of the embodiments of the present disclosure, rather than all the embodiments.

[0033] It should be understood that the various steps recorded in the method implementation manners of the present disclosure may be executed in different orders and / or executed in parallel. In addition, the method implementation manners may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this regard.

[0034] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of another identical element in the process, method, article or device including the said element.

[0035] It should be noted that the modifiers "a" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive. Those skilled in the art should understand that, unless clearly specified otherwise in the context, it should be understood as "one or more".

[0036] Generally, during the power grid load forecasting process, the main factor affecting the change of power grid load is meteorological conditions. However, the meteorological conditions vary greatly in different regions within a power grid. Therefore, how to accurately forecast the power grid load within a certain power grid scope under the condition of large differences in regional meteorological conditions is a technical problem that urgently needs to be solved. In view of this problem, the embodiments of the present disclosure provide a power grid load forecasting method, which will be introduced below in combination with specific embodiments.

[0037] Figure 1 FIG. is a flowchart of a power grid load forecasting method provided by an embodiment of the present disclosure. This method can be executed by a power grid load forecasting device, which can be implemented in software and / or hardware, and can be configured in an electronic device, such as a server or a terminal. Specifically, the terminal includes a mobile phone, a computer, a tablet computer, etc.

[0038] As Figure 1 shown, the power grid load forecasting method provided in this embodiment includes the following steps.

[0039] S110. Determine the area under the jurisdiction of the power grid to be predicted, and divide the area into grids to obtain a plurality of target grids.

[0040] Specifically, after receiving the power grid load forecasting instruction from the user, the electronic device parses the power grid load forecasting instruction to determine the power grid to be predicted for load forecasting and its jurisdiction area, and performs equally spaced grid division on the area according to the position information of the jurisdiction area, such as longitude and latitude information, and the preset number of grids or grid size, and divides the area into N×M target grids of the same size. Among them, the target grid can be rectangular or square, which can be set according to the actual situation.

[0041] S120. For each target grid, obtain the first maximum load corresponding to the target grid in the first unit time, the first environmental data corresponding to the target grid at the time to be predicted, and the second environmental data corresponding to the target grid at each unit time within a preset time period, where the first unit time is within the preset time period.

[0042] In the embodiments of the present disclosure, the unit time can be in days.

[0043] The first unit time can be a certain unit time before the time to be predicted and within a certain time from the time to be predicted. For example, it can be any day within a few days before the time to be predicted.

[0044] The preset time period can be a certain time period before the time to be predicted.

[0045] The environmental data can be meteorological data related to power grid load forecasting. Specifically, it can include the average temperature, average humidity, average wind speed, etc.

[0046] The first environmental data can include the first average temperature, the first average humidity, the first average wind speed, etc.; the second environmental data includes the second average temperature, the second average humidity, the second average wind speed, etc.

[0047] Specifically, after the electronic device obtains multiple target grids, for each target grid, it obtains the first maximum load corresponding to each target grid at the first unit time, the first environmental data corresponding to the target grid at the time to be predicted, and the second environmental data corresponding to each unit time within the preset time period for each target grid in the preset database. Among them, the first environmental data of the target grid at the time to be predicted can be determined based on the meteorological prediction data of the meteorological station.

[0048] Exemplarily, taking a day as a unit for illustration, for example, if it is necessary to predict the power grid load of tomorrow, at this time the time to be predicted is tomorrow, the first unit time can be yesterday, and the preset time period can be the time period where today, the day before yesterday, the day before the day before yesterday, …, the (Q - 1)th day before yesterday before tomorrow is located. At this time, the first maximum load is the maximum load corresponding to each target grid yesterday, denoted as (i = 1, 2, 3, …, N; j = 1, 2, 3, …, M); the first environmental data is the average temperature, average humidity, average wind speed, etc. respectively corresponding to each target grid predicted for tomorrow obtained, and are respectively denoted as Let the vector composed of the first environmental data be (i = 1, 2, 3, …, N; j = 1, 2, 3, …, M); the second environmental data is the average temperature, average humidity, average wind speed, etc. respectively corresponding to each target grid for today, the day before yesterday, the day before the day before yesterday, …, the (Q - 1)th day before yesterday obtained, and are respectively denoted as Let the vector composed of the second environmental data be

[0049] S130. Determine the second unit time corresponding to the minimum difference between the second environmental data and the first environmental data within the preset time period, and the third unit time corresponding to the minimum difference between the second environmental data corresponding to multiple unit times before the first unit time within the preset time period and the target environmental data corresponding to the first unit time.

[0050] In the embodiments of the present disclosure, the second unit time can be understood as the unit time within the multiple unit times of the preset time period where the environmental data has the smallest difference or the similarity index is closest to the first environmental data of the time to be predicted.

[0051] The third unit time can be understood as the unit time with the smallest difference or the closest similarity index between the environmental data and the target environmental data corresponding to the first unit time among multiple unit times before the first unit time within a preset time period.

[0052] Specifically, after the electronic device obtains the first environmental data and the second environmental data, according to the distance or difference between the first environmental data and the second environmental data, it determines the second unit time corresponding to the minimum difference between the second environmental data and the first environmental data within the preset time period, and the third unit time corresponding to the minimum difference between the second environmental data corresponding to each of the multiple unit times before the first unit time within the preset time period and the target environmental data corresponding to the first unit time.

[0053] S140. Obtain the second maximum load corresponding to each target grid at the second unit time, and the third maximum load corresponding to each target grid at the third unit time.

[0054] Specifically, after the electronic device determines the second unit time and the third unit time, it obtains the second maximum load corresponding to each target grid at the second unit time and the third maximum load corresponding to each target grid at the third unit time from the preset database.

[0055] S150. Determine the maximum load prediction value corresponding to the power grid to be predicted at the time to be predicted based on the first maximum load, the second maximum load, and the third maximum load.

[0056] Specifically, after the electronic device obtains the second maximum load and the third maximum load, for each target grid, it determines the growth coefficient of the power grid load according to the first maximum load and the third maximum load, and determines the product of the growth coefficient and the second maximum load as the target prediction value of the maximum load corresponding to this target grid at the time to be predicted. Furthermore, it determines the sum of the target prediction values of the maximum loads of multiple target grids as the maximum load prediction value corresponding to the power grid to be predicted at the time to be predicted.

[0057] In an embodiment of the present disclosure, it is possible to determine the area under the jurisdiction of the power grid to be predicted, divide the area into grid cells to obtain a plurality of target grid cells. For each target grid cell, obtain the first maximum load corresponding to the target grid cell in the first unit time, the first environmental data corresponding to the target grid cell at the time to be predicted, and the second environmental data corresponding to the target grid cell at each unit time within a preset time period, where the first unit time is within the preset time period. After obtaining the first environmental data and the second environmental data, determine the second unit time corresponding to the minimum difference between the second environmental data and the first environmental data within the preset time period, and the third unit time corresponding to the minimum difference between the second environmental data corresponding to each unit time before the first unit time within the preset time period and the target environmental data corresponding to the first unit time. Obtain the second maximum load corresponding to each target grid cell at the second unit time, and the third maximum load corresponding to each target grid cell at the third unit time. Furthermore, based on the first maximum load, the second maximum load, and the third maximum load, determine the maximum load prediction value corresponding to the power grid to be predicted at the time to be predicted. Thus, it is possible to divide the area under the jurisdiction of the power grid to be predicted into a plurality of target grid cells, and based on the maximum load of each target grid cell per unit time and the environmental data of each unit grid at different unit times, determine the unit time with the minimum difference in environmental data from the time to be predicted, and use it as a reference to predict the load of the power grid to be predicted at the time to be predicted, taking into account the differences in environmental meteorological conditions of each grid in the area where the power grid is located, and improving the accuracy of load prediction.

[0058] Based on the above embodiments of the present disclosure, before determining the second unit time corresponding to the minimum difference between the second environmental data and the first environmental data within the preset time period, and the third unit time corresponding to the minimum difference between the second environmental data corresponding to each unit time before the first unit time within the preset time period and the target environmental data corresponding to the first unit time, the power grid load prediction method may further include: calculating the weight coefficient corresponding to each target grid cell based on the first maximum load.

[0059] Further, calculating the weight coefficient corresponding to each target grid cell based on the first maximum load may specifically include: calculating the sum of the first maximum loads of the plurality of target grid cells; for each target grid cell, calculating the first ratio of the first maximum load corresponding to the target grid cell to the sum of the first maximum loads, and determining the first ratio as the weight coefficient corresponding to the target grid cell.

[0060] The specific formula for calculating the weight coefficient corresponding to each target grid cell is as follows:

[0061]

[0062] where c ij represents the weight coefficient of each grid cell; represents the maximum load of the target grid at the i-th row and j-th column in the first unit time.

[0063] In the embodiments of the present disclosure, determining the second unit time corresponding to the minimum difference between the second environmental data and the first environmental data within a preset time period may specifically include: for each target grid, calculating the first Euclidean distance between the first vector corresponding to the first environmental data and the second vector corresponding to the second environmental data at each unit time, multiplying the first Euclidean distance by the weight coefficient corresponding to the target grid to obtain a first product; calculating the sum of the first products corresponding to multiple target grids, and determining the sum of the first products as the difference between the second environmental data and the first environmental data; determining the unit time corresponding to the minimum difference between the second environmental data and the first environmental data within the preset time period as the second unit time.

[0064] In the embodiments of the present disclosure, the specific implementation manner of determining the third unit time corresponding to the minimum difference between the second environmental data corresponding to multiple unit times before the first unit time and the target environmental data corresponding to the first unit time within the preset time period is similar to the above specific implementation manner of determining the second unit time in the present disclosure, and will not be elaborated here.

[0065] The following further illustrates with the first unit time being yesterday and the time to be predicted being tomorrow as an example.

[0066] The difference calculation formula between the second environmental data and the first environmental data is specifically as follows:

[0067]

[0068] where f k represents the difference between the first environmental data of tomorrow and the second environmental data corresponding to the k-th day within the preset time period, where k = 1, 2, 3,..., Q; represents the vector representation of the first environmental data corresponding to the target grid at the i-th row and j-th column tomorrow; represents the vector representation of the second environmental data corresponding to the target grid at the i-th row and j-th column on the k-th day.

[0069] The difference calculation formula between the second environmental data corresponding to multiple unit times before the first unit time and the target environmental data corresponding to the first unit time within the preset time period is specifically as follows:

[0070]

[0071] where g p represents the difference between the target environmental data of yesterday and the second environmental data corresponding to the p-th day before the first unit time within the preset time period, where p = 3, 4, 5,..., Q; The vector representation of the target environmental data corresponding to the target grid at the i-th row and j-th column yesterday; The vector representation of the second environmental data corresponding to the target grid at the i-th row and j-th column on the p-th day.

[0072] Exemplarily, taking a day as the unit for illustration, the time to be predicted is tomorrow, the first unit of time is yesterday. When the difference between the second environmental data and the first environmental data is the smallest, the corresponding k is k'. When the differences between the second environmental data corresponding to multiple units of time before the first unit of time and the target environmental data corresponding to the first unit of time are the smallest, the corresponding p is p'. At this time, the maximum load corresponding to the target grid at the i-th row and j-th column on the k'-th day before tomorrow, that is, the second maximum load, and the maximum load corresponding to the target grid at the i-th row and j-th column on the p'-th day before tomorrow, that is, the third maximum load, are obtained.

[0073] In the embodiments of the present disclosure, the weight coefficient of each target grid can be calculated through the maximum load corresponding to each target grid at the first unit of time, and the proportion of each grid is combined to determine the second unit of time and the third unit of time with the smallest difference from the environmental data at the time to be predicted and the first unit of time, improving the accuracy of time determination and further improving the accuracy of load prediction.

[0074] Figure 2 It is a flowchart of a method for determining the maximum load prediction value corresponding to a power grid to be predicted at the time to be predicted provided by the embodiments of the present disclosure. As Figure 2 shown, after determining the second maximum load and the third maximum load, determining the maximum load prediction value corresponding to the power grid to be predicted at the time to be predicted specifically includes the following steps:

[0075] S210. For each target grid, determine the target prediction value corresponding to the target grid at the time to be predicted based on the first maximum load, the second maximum load, and the third maximum load.

[0076] Among them, determining the target prediction value corresponding to the target grid at the time to be predicted based on the first maximum load, the second maximum load, and the third maximum load may specifically include: calculating the second ratio between the first maximum load and the third maximum load, and determining the product of the second ratio and the second maximum load as the target prediction value corresponding to the target grid.

[0077] The specific calculation formula of the target prediction value is as follows:

[0078]

[0079] Among them, represents the maximum load, that is, the target prediction value, corresponding to the target grid at the i-th row and j-th column at the time to be predicted; represents the maximum load of the target grid at the i-th row and j-th column in the second unit time; represents the maximum load of the target grid at the i-th row and j-th column in the third unit time.

[0080] S220. Calculate the sum of the target prediction values corresponding to multiple target grids, and determine the sum of the target prediction values as the maximum load prediction value.

[0081] The specific calculation formula for the maximum load prediction value is as follows:

[0082]

[0083] where, L 0 represents the maximum load prediction value.

[0084] In the embodiments of the present disclosure, the growth situation of the grid load can be determined according to the maximum load of the third unit time closest to the first unit time and its environmental data, and then the maximum load prediction value of the grid to be predicted can be determined according to the growth situation of the grid load and the maximum load of the second unit time closest to the environmental data of the time to be predicted. Considering the growth situation of the grid load, the accuracy of the grid load prediction is improved.

[0085] The following is illustrated by a specific implementation case:

[0086] 1. Divide the area under the jurisdiction of a certain power grid into 200×200 grids at equal intervals.

[0087] 2. Obtain the maximum load within the grid at the i-th row and j-th column yesterday, denoted as (i = 1, 2, 3,..., 200; j = 1, 2, 3,..., 200).

[0088] 3. Calculate the weight coefficient of each grid, and the calculation formula is as follows:

[0089]

[0090] 4. Obtain the average temperature, average humidity, average wind speed, etc. corresponding to each grid tomorrow, and denote them as Let the vector composed of the first environmental data be (i = 1, 2, 3,..., 200; j = 1, 2, 3,..., 200).

[0091] 5. Obtain the average temperature, average humidity, average wind speed, etc. corresponding to each grid today, the day before yesterday, the day before the day before yesterday,..., the (Q - 1)-th day before yesterday, and denote them as Let the vector composed of the second environmental data be

[0092] 6. For k = 1, 2, 3, …, Q, calculate the difference f between the environmental data tomorrow and the environmental data corresponding to the k-th day within the preset time period. k .

[0093]

[0094] When f k is the smallest, the corresponding k is denoted as k′.

[0095] 7. For p = 3, 4, 5, …, Q, calculate the difference g between the environmental data yesterday and the environmental data corresponding to the p-th day before yesterday. p .

[0096]

[0097] When g p is the smallest, the corresponding p is denoted as p′.

[0098] 8. Obtain the maximum load of the grid at the i-th row and j-th column on the k′-th day before tomorrow, denoted as (i = 1, 2, 3, …, 200; j = 1, 2, 3, …, 200). At the same time, obtain the maximum load of the grid at the i-th row and j-th column on the p′-th day before tomorrow, denoted as (i = 1, 2, 3, …, 200; j = 1, 2, 3, …, 200).

[0099] 9. Calculate the predicted value of the maximum load of each grid tomorrow, denoted as (i = 1, 2, 3, …, 200; j = 1, 2, 3, …, 200).

[0100]

[0101] 10. Calculate the predicted value of the maximum load of the power grid tomorrow, denoted as L 0 .

[0102]

[0103] By adopting the method of multi-region analysis through the above steps, the differences in the environmental meteorological conditions of each sub-region of the power grid are considered, and the accuracy of load prediction is improved.

[0104] Figure 3 It is a schematic structural diagram of a power grid load prediction device provided by an embodiment of the present disclosure.

[0105] In the embodiment of the present disclosure, the power grid load prediction device can be arranged in an electronic device and is understood as some functional modules in the above-mentioned electronic device. Specifically, the electronic device can be a server or a terminal. Among them, the terminal specifically includes a mobile phone, a computer, a tablet computer, etc., which are not limited herein.

[0106] As Figure 3 shown, the power grid load prediction device 300 may include a grid division module 310, a data acquisition module 320, a time determination module 330, a maximum load acquisition module 340, and a load prediction module 350.

[0107] The grid division module 310 may be configured to determine the area under the power grid to be predicted and divide the area into grids to obtain a plurality of target grids.

[0108] The data acquisition module 320 may be configured to, for each target grid, acquire the first maximum load corresponding to the target grid in the first unit time, the first environmental data corresponding to the target grid at the time to be predicted, and the second environmental data corresponding to each unit time within a preset time period for the target grid, where the first unit time is within the preset time period.

[0109] The time determination module 330 may be configured to determine the second unit time corresponding to the minimum difference between the second environmental data and the first environmental data within the preset time period, and the third unit time corresponding to the minimum difference between the second environmental data corresponding to each unit time before the first unit time within the preset time period and the target environmental data corresponding to the first unit time.

[0110] The maximum load acquisition module 340 may be configured to acquire the second maximum load corresponding to each target grid at the second unit time, and the third maximum load corresponding to each target grid at the third unit time.

[0111] The load prediction module 350 may be configured to determine the maximum load prediction value corresponding to the power grid to be predicted at the time to be predicted based on the first maximum load, the second maximum load, and the third maximum load.

[0112] In the embodiments of the present disclosure, it is possible to determine the area under the jurisdiction of the power grid to be predicted, divide the area into grid cells to obtain a plurality of target grid cells. For each target grid cell, obtain the first maximum load corresponding to the target grid cell in the first unit time, the first environmental data corresponding to the target grid cell at the time to be predicted, and the second environmental data corresponding to each unit time within a preset time period for the target grid cell, where the first unit time is within the preset time period. After obtaining the first environmental data and the second environmental data, determine the second unit time corresponding to the minimum difference between the second environmental data and the first environmental data within the preset time period, and the third unit time corresponding to the minimum difference between the second environmental data corresponding to each unit time before the first unit time within the preset time period and the target environmental data corresponding to the first unit time. Obtain the second maximum load corresponding to each target grid cell at the second unit time, and the third maximum load corresponding to each target grid cell at the third unit time. Then, based on the first maximum load, the second maximum load, and the third maximum load, determine the maximum load prediction value corresponding to the power grid to be predicted at the time to be predicted. Thus, it is possible to divide the area under the jurisdiction of the power grid to be predicted into a plurality of target grid cells, and based on the maximum load of each target grid cell within a unit time and the environmental data of each unit grid cell at different unit times, determine the unit time with the minimum difference in environmental data from the time to be predicted, and use it as a reference to predict the load of the power grid to be predicted at the time to be predicted, taking into account the differences in the environmental meteorological conditions of each grid cell in the area where the power grid is located, and improving the accuracy of load prediction.

[0113] In some embodiments of the present disclosure, the power grid load prediction device 300 may further include a weight coefficient determination module.

[0114] The weight coefficient determination module may be used to calculate the weight coefficient corresponding to each target grid cell based on the first maximum load before determining the second unit time corresponding to the minimum difference between the second environmental data and the first environmental data within the preset time period, and the third unit time corresponding to the minimum difference between the second environmental data corresponding to each unit time before the first unit time within the preset time period and the target environmental data corresponding to the first unit time.

[0115] The weight coefficient determination module may specifically be used to calculate the sum of the first maximum loads of the plurality of target grid cells;

[0116] For each target grid cell, calculate the first ratio of the first maximum load corresponding to the target grid cell to the sum of the first maximum loads, and determine the first ratio as the weight coefficient corresponding to the target grid cell.

[0117] In some embodiments of the present disclosure, the first environmental data includes the first average temperature, the first average humidity, and the first average wind speed, and the second environmental data includes the second average temperature, the second average humidity, and the second average wind speed.

[0118] In some embodiments of the present disclosure, the time determination module 330 may specifically be configured to, for each target grid, calculate the first Euclidean distance between the first vector corresponding to the first environmental data and the second vector corresponding to the second environmental data per unit time, multiply the first Euclidean distance by the weight coefficient corresponding to the target grid to obtain a first product;

[0119] Calculate the sum of the first products corresponding to multiple target grids, and determine the sum of the first products as the difference between the second environmental data and the first environmental data;

[0120] Determine the unit time corresponding to the minimum difference between the second environmental data and the first environmental data within a preset time period as the second unit time.

[0121] In some embodiments of the present disclosure, the load prediction module 350 may specifically be configured to, for each target grid, determine the target prediction value corresponding to the target grid at the time to be predicted based on the first maximum load, the second maximum load, and the third maximum load;

[0122] Calculate the sum of the target prediction values corresponding to multiple target grids, and determine the sum of the target prediction values as the maximum load prediction value.

[0123] In some embodiments of the present disclosure, the load prediction module 350 may also specifically be configured to calculate the second ratio between the first maximum load and the third maximum load, and determine the product of the second ratio and the second maximum load as the target prediction value corresponding to the target grid.

[0124] It should be noted that Figure 3 the power grid load prediction device 300 shown may execute each step in the above method embodiments, and implement each process and effect in the above method embodiments, which will not be elaborated here.

[0125] Figure 4 is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure.

[0126] In the embodiments of the present disclosure, Figure 4 the electronic device shown may be a server or a terminal. Among them, the terminal specifically includes a mobile phone, a computer, a tablet computer, etc., which are not limited herein.

[0127] As Figure 4 shown, the electronic device may include a processor 410 and a memory 420 storing computer program instructions.

[0128] Specifically, the above-mentioned processor 410 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured as one or more integrated circuits for implementing the embodiments of the present disclosure.

[0129] The memory 420 may include a mass memory for information or instructions. By way of example and not limitation, the memory 420 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 420 may include removable or non-removable (or fixed) media. Where appropriate, the memory 420 may be internal or external to the integrated gateway device. In a particular embodiment, the memory 420 is a non-volatile solid-state memory. In a particular embodiment, the memory 420 includes a read-only memory (ROM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically alterable ROM (EAROM), or a flash memory, or a combination of two or more of these.

[0130] The processor 410 reads and executes the computer program instructions stored in the memory 420 to perform the steps of the grid load prediction method provided by the embodiments of the present disclosure.

[0131] In one example, the electronic device may further include a transceiver 430 and a bus 440. Among them, as Figure 4 shown, the processor 410, the memory 420, and the transceiver 430 are connected through the bus 440 and complete communication with each other.

[0132] The bus 440 includes hardware, software, or both. By way of example and not limitation, the bus can include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side BUS (FSB), a Hyper Transport (HT) interconnect, an Industrial Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a MicroChannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable bus or a combination of two or more of these. Where appropriate, the bus 440 can include one or more buses.

[0133] Embodiments of the present disclosure also provide a computer-readable storage medium that can store a computer program, which, when executed by a processor, enables the processor to implement the power grid load forecasting method provided by the embodiments of the present disclosure.

[0134] The above storage medium can, for example, include a memory 420 storing computer program instructions, and the above instructions can be executed by a processor 410 of an electronic device to complete the power grid load forecasting method provided by the embodiments of the present disclosure. Optionally, the storage medium can be a non-transitory computer-readable storage medium. For example, the non-transitory computer-readable storage medium can be a ROM, a Random Access Memory (RAM), a Compact Disc ROM (CD-ROM), a magnetic tape, a floppy disk, and an optical data storage device, etc.

[0135] Embodiments of the present disclosure also provide a computer program product, which includes a computer program or instructions. When the computer program or instructions are executed by a processor, the power grid load forecasting method provided by the embodiments of the present disclosure is implemented, and each process and effect in the above embodiments of the present disclosure can be achieved. Details are not described herein again.

[0136] The above are only specific embodiments of the present disclosure, enabling those skilled in the art to understand or implement the present disclosure. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to these embodiments described herein, but will be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for predicting power grid load, characterized in that: include: Determine the area covered by the power grid to be predicted, and divide the area into grids to obtain multiple target grids; For each target grid, obtain a first maximum load corresponding to the target grid at a first unit time, first environmental data corresponding to the target grid at a time to be predicted, and second environmental data corresponding to each unit time of the target grid within a preset time period, wherein the first unit time is within the preset time period; Determine a second unit time corresponding to when the difference between the second environmental data and the first environmental data is the smallest within the preset time period, and a third unit time corresponding to when the difference between the second environmental data corresponding to a plurality of unit times before the first unit time within the preset time period and the target environmental data corresponding to the first unit time is the smallest; Acquire a second maximum load corresponding to each target grid in the second unit time, and a third maximum load corresponding to each target grid in the third unit time; A maximum load prediction value of the to-be-predicted power grid corresponding to the to-be-predicted time is determined based on the first maximum load, the second maximum load, and the third maximum load.

2. The method according to claim 1, characterized in that In determining the second unit time corresponding to when the difference between the second environment data and the first environment data is the smallest within the preset time period, and before the third unit time corresponding to when the difference between the second environment data corresponding to a plurality of unit times before the first unit time within the preset time period and the target environment data corresponding to the first unit time is the smallest, the method further includes: Calculate the weight coefficient corresponding to each target grid based on the first maximum load; The calculating the weight coefficient corresponding to each target grid based on the first maximum load includes: Calculate the sum of the first maximum loads of multiple target grids; For each target grid, a first ratio of a first maximum load corresponding to the target grid to a sum of the first maximum loads is calculated, and the first ratio is determined as a weight coefficient corresponding to the target grid.

3. The method according to claim 2, characterized in that The first environmental data includes a first average temperature, a first average humidity, and a first average wind speed, and the second environmental data includes a second average temperature, a second average humidity, and a second average wind speed.

4. The method according to claim 3, characterized in that The determining of the second unit time corresponding to the time when the difference between the second environment data and the first environment data is the smallest within the preset time period includes: For each target grid, calculating a first Euclidean distance between a first vector corresponding to the first environmental data and a second vector corresponding to the second environmental data per unit time, and multiplying the first Euclidean distance by a weight coefficient corresponding to the target grid to obtain a first product; Calculating a sum of first products corresponding to a plurality of target grids, and determining the sum of the first products as a difference between the second environment data and the first environment data; The unit time corresponding to the time when the difference between the second environment data and the first environment data within the preset time period is the smallest is determined as the second unit time.

5. The method according to claim 1, characterized in that The determining, based on the first maximum load, the second maximum load, and the third maximum load, a maximum load forecast value of the to-be-forecasted power grid corresponding to the to-be-forecasted time includes: For each target grid, determining a target prediction value corresponding to the target grid at the time to be predicted based on the first maximum load, the second maximum load, and the third maximum load; The sum of target prediction values ​​corresponding to the plurality of target grids is calculated, and the sum of the target prediction values ​​is determined as the maximum load prediction value.

6. The method according to claim 5, characterized in that The determining the target prediction value corresponding to the target grid at the time to be predicted based on the first maximum load, the second maximum load, and the third maximum load includes: A second ratio between the first maximum load and the third maximum load is calculated, and a product of the second ratio and the second maximum load is determined as a target prediction value corresponding to the target grid.

7. A power grid load prediction device, characterized in that: include: A grid division module is used to determine the area covered by the power grid to be predicted and to divide the area into grids to obtain multiple target grids; A data acquisition module, for acquiring, for each target grid, a first maximum load corresponding to the target grid at a first unit time, first environmental data corresponding to the target grid at a time to be predicted, and second environmental data corresponding to each unit time of the target grid within a preset time period, wherein the first unit time is within the preset time period; A time determination module, used to determine a second unit time corresponding to when the difference between the second environment data and the first environment data is the smallest within the preset time period, and a third unit time corresponding to when the difference between the second environment data corresponding to a plurality of unit times before the first unit time within the preset time period and the target environment data corresponding to the first unit time is the smallest; A maximum load acquisition module, used to acquire a second maximum load corresponding to each target grid in the second unit time, and a third maximum load corresponding to each target grid in the third unit time; A load prediction module is used to determine a maximum load prediction value of the to-be-predicted power grid corresponding to the to-be-predicted time based on the first maximum load, the second maximum load and the third maximum load.

8. An electronic device, characterized in that: include: processor; A memory for storing executable instructions; Wherein, the processor is used to read the executable instructions from the memory and execute the executable instructions to implement the power grid load forecasting method described in any one of claims 1-6 above.

9. 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 processor implements the power grid load forecasting method described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program or instructions, characterized in that: When the computer program or instruction is executed by a processor, the power grid load forecasting method according to any one of claims 1 to 6 is implemented.

Images