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

Abstract

The invention relates to a power grid load prediction method and device, equipment, a storage medium and a program product, and particularly relates to the technical field of power systems. Comprising the following steps: acquiring the daily highest temperature and the daily maximum power grid load in a historical period; calculating the maximum air temperature sum and the maximum power grid load sum in the historical period; performing weighted averaging on the sum of the highest air temperatures of adjacent time periods in the historical periods to obtain a historical highest air temperature weighted average; carrying out weighted averaging on the sum of the maximum power grid loads of adjacent time periods in the historical period to obtain a weighted mean value of the historical maximum power grid loads; based on the historical maximum air temperature weighted mean and the maximum air temperature sum of the historical period, the maximum air temperature sum of the future period is obtained through fitting; based on the maximum air temperature sum in the future period and the maximum power grid load sum in the historical period, the maximum power grid load sum in the future period is obtained through fitting; and predicting the maximum power grid load of the target date according to the sum of the maximum power grid loads of the future period.

Description

Technical Field

[0001] The present application relates to the technical field of power systems, and in particular, to a method, device, equipment, storage medium and program product for predicting grid load. Background Art

[0002] The frequent occurrence of continuous sunny, hot and high-temperature situations has brought great challenges to the power grid's peak load shaving and power supply guarantee work in summer, which are mainly reflected in the following aspects: First, the continuous sunny, hot and high-temperature weather leads to a straight rise in the perceived temperature and a significant increase in air-conditioning load; second, the electricity consumption at night increases significantly, and the peak electricity consumption period is extended; third, the continuous drought causes the water level of the reservoir to drop, and the agricultural irrigation load increases; fourth, power equipment such as transformers is prone to overload and overheating, increasing the risk of failures.

[0003] Grid load prediction under continuous sunny, hot and high-temperature conditions is an extreme situation where the load level breaks through historical extreme values. Traditional grid load prediction methods are not applicable to sunny, hot and high-temperature situations. Therefore, a method that can effectively predict the changing trend of grid load under continuous sunny, hot and high-temperature conditions is needed to effectively support the development of the power grid's peak load shaving and power supply guarantee work in summer. Summary of the Invention

[0004] In order to solve the above technical problems or at least partially solve the above technical problems, the present application provides a method, device, equipment, storage medium and program product for predicting grid load, which can predict the extreme value of the daily maximum grid load when the daily maximum temperature reaches an extreme situation under continuous strong heat and high temperature, so as to ensure that the power generation capacity is sufficient to meet the peak electricity demand, which is beneficial to the development of the power grid's peak load shaving and power supply guarantee work in summer.

[0005] To achieve the above object, the technical solutions provided by the embodiments of the present application are as follows:

[0006] In a first aspect, the present application provides a method for predicting grid load, including:

[0007] Obtaining the daily maximum temperature and the daily maximum grid load in a historical period; calculating the total sum of the maximum temperatures in the historical period and the total sum of the maximum grid loads in the historical period; performing weighted averaging on the total sum of the maximum temperatures in adjacent time periods in the historical period to obtain the weighted average value of the historical maximum temperature; and performing weighted averaging on the total sum of the maximum grid loads in adjacent time periods in the historical period to obtain the weighted average value of the historical maximum grid load; fitting the total sum of the maximum temperatures in a future period based on the weighted average value of the historical maximum temperature and the total sum of the maximum temperatures in the historical period; fitting the total sum of the maximum grid loads in the future period based on the total sum of the maximum grid loads in the future period and the total sum of the maximum grid loads in the historical period; predicting the maximum grid load on a target date according to the total sum of the maximum grid loads in the future period.

[0008] As an alternative implementation manner of an embodiment of the present application, based on the weighted average of historical maximum temperatures and the daily maximum temperatures, fitting to obtain the total maximum temperature in a future period, including: constructing a first design matrix based on the weighted average of historical maximum temperatures; constructing a first vector based on the daily maximum temperatures in a historical period; solving the historical maximum temperature-related parameters by using the least squares method based on the first design matrix and the first vector; and fitting to obtain the total maximum temperature in a future period based on the historical maximum temperature-related parameters and the total maximum temperature in a historical period.

[0009] As an alternative implementation manner of an embodiment of the present application, fitting to obtain the total maximum temperature in a future period based on the historical maximum temperature-related parameters and the total maximum temperature in a historical period, including: fitting to obtain the total maximum temperature in a future period according to the following formula: In the formula, n is the number of days in a historical period, t (1) (n + 1) represents the total maximum temperature from the first day to the (n + 1)-th day; t (1) (1) represents the maximum temperature on the first day; u and a are historical maximum temperature-related parameters.

[0010] As an alternative implementation manner of an embodiment of the present application, fitting to obtain the total maximum grid load in a future period based on the total maximum temperature in a future period and the total maximum grid load in a historical period, including: constructing a second design matrix based on the total maximum temperature in a historical period and the weighted average of the historical maximum grid load; constructing a second vector based on the daily maximum grid load in a historical period; solving the historical maximum grid load-related parameters by using the least squares method based on the second design matrix and the second vector; and fitting to obtain the total maximum grid load in a future period based on the historical maximum grid load-related parameters, the total maximum grid load in a historical period, and the total maximum temperature in a future period.

[0011] As an alternative implementation manner of an embodiment of the present application, fitting to obtain the total maximum grid load in a future period based on the historical maximum grid load-related parameters, the total maximum grid load in a historical period, and the total maximum temperature in a future period, including: fitting to obtain the total maximum grid load in a future period according to the following formula: In the formula, n is the number of days in a historical period, l (1) (n + 1) represents the total maximum grid load from the first day to the (n + 1)-th day; l (1) (1) represents the maximum grid load on the first day; f and e are historical maximum grid load-related parameters; t (1) (n + 1) represents the total maximum temperature corresponding to the (n + 1)-th day.

[0012] As an optional implementation manner of the embodiment of the present application, predicting the maximum grid load on the target date according to the sum of the maximum grid loads in the future period includes: If the target date is the (n + 1)-th day, predicting the maximum grid load on the (n + 1)-th day according to the following formula: l (0) (n + 1) = l (1) (n + 1) - l (1) (n), where l (1) (n + 1) represents the sum of the maximum grid loads from the 1st day to the (n + 1)-th day, and l (1) (n) represents the sum of the maximum grid loads from the 1st day to the n-th day.

[0013] In a second aspect, the present application provides a grid load prediction device, which includes:

[0014] An acquisition module, configured to acquire the daily highest temperature and the daily maximum grid load in the historical period;

[0015] A calculation module, configured to calculate the sum of the highest temperatures in the historical period and the sum of the maximum grid loads in the historical period;

[0016] A weighted average module, configured to perform weighted averaging on the sum of the highest temperatures in adjacent time periods in the historical period to obtain a weighted average value of the historical highest temperature; and perform weighted averaging on the sum of the maximum grid loads in adjacent time periods in the historical period to obtain a weighted average value of the historical maximum grid load;

[0017] A highest temperature sum fitting module, configured to fit the sum of the highest temperatures in the future period based on the weighted average value of the historical highest temperature and the sum of the highest temperatures in the historical period;

[0018] A maximum grid load sum fitting module, configured to fit the sum of the maximum grid loads in the future period based on the sum of the highest temperatures in the future period and the sum of the maximum grid loads in the historical period;

[0019] A daily maximum grid load prediction module, configured to predict the maximum grid load on the target date according to the sum of the maximum grid loads in the future period.

[0020] As an optional implementation manner of the embodiment of the present application, the highest temperature sum fitting module is specifically configured to: construct a first design matrix based on the weighted average value of the historical highest temperature; construct a first vector based on the daily highest temperature in the historical period; solve the historical highest temperature related parameters by using the least squares method based on the first design matrix and the first vector; and fit the sum of the highest temperatures in the future period based on the historical highest temperature related parameters and the sum of the highest temperatures in the historical period.

[0021] As an optional implementation manner of the embodiment of the present application, when the maximum daily temperature sum fitting module fits the maximum daily temperature sum in the future period based on the historical maximum daily temperature related parameters and the maximum daily temperature sum in the historical period, it is specifically used for: fitting the maximum daily temperature sum in the future period according to the following formula: In the formula, n is the number of days in the historical period, and t (1) (n + 1) represents the sum of the maximum daily temperatures from the 1st day to the (n + 1)-th day; t (1) (1) represents the maximum daily temperature on the 1st day; u and a are the historical maximum daily temperature related parameters.

[0022] As an optional implementation manner of the embodiment of the present application, the maximum grid load sum fitting module is specifically used for: constructing a second design matrix based on the sum of the maximum daily temperatures in the historical period and the weighted average value of the historical maximum grid load; constructing a second vector based on the daily maximum grid load in the historical period; solving the historical maximum grid load related parameters by using the least square method based on the second design matrix and the second vector; and fitting the maximum grid load sum in the future period based on the historical maximum grid load related parameters, the sum of the maximum grid loads in the historical period, and the sum of the maximum daily temperatures in the future period.

[0023] As an optional implementation manner of the embodiment of the present application, when the maximum grid load sum fitting module fits the maximum grid load sum in the future period based on the historical maximum grid load related parameters, the sum of the maximum grid loads in the historical period, and the sum of the maximum daily temperatures in the future period, it is specifically used for: fitting the maximum grid load sum in the future period according to the following formula: In the formula, n is the number of days in the historical period, and l (1) (n + 1) represents the sum of the maximum grid loads from the 1st day to the (n + 1)-th day; l (1) (1) represents the maximum grid load on the 1st day; f and e are the historical maximum grid load related parameters; t (1) (n + 1) represents the sum of the maximum daily temperatures corresponding to the (n + 1)-th day.

[0024] As an optional implementation manner of the embodiment of the present application, the daily maximum grid load prediction module is specifically used for: if the target date is the (n + 1)-th day, predicting the maximum grid load on the (n + 1)-th day according to the following formula: l (0) (n + 1) = l (1) (n + 1) - l (1) (n), where in the formula, l (1) (n + 1) represents the sum of the maximum grid loads from the 1st day to the (n + 1)-th day, and l (1) (n) represents the sum of the maximum grid loads from the 1st day to the n-th day.

[0025] In a third aspect, the present application provides an electronic device, including: a processor, a memory, and a computer program stored on the memory and executable on the processor, where when the computer program is executed by the processor, it implements the grid load forecasting method as described in the first aspect or any of its optional embodiments.

[0026] In a fourth aspect, the present application provides a computer-readable storage medium, including: a computer program stored on the computer-readable storage medium, where when the computer program is executed by a processor, it implements the grid load forecasting method as described in the first aspect or any of its optional embodiments.

[0027] In a fifth aspect, the present application provides a computer program product, including: the computer program product includes a computer program, where when the computer program runs on a computer, it causes the computer to implement the grid load forecasting method as described in the first aspect or any of its optional embodiments.

[0028] The technical solutions provided by the embodiments of the present application have the following advantages compared with the prior art:

[0029] The embodiments of the present disclosure provide a grid load forecasting method, device, equipment, storage medium, and program product. The method first collects the daily maximum temperature and the daily maximum grid load in the historical period, then calculates the total sum of the maximum temperatures and the total sum of the maximum grid loads in the historical period, then performs weighted averaging on the total sum of the maximum temperatures in adjacent time periods and performs weighted averaging on the total sum of the maximum grid loads in adjacent time periods to obtain a weighted value related to the historical maximum temperature and a weighted value related to the historical maximum grid load; further, first fits the total sum of the maximum temperatures in the future period according to the weighted value related to the historical maximum temperature and the total sum of the maximum temperatures in the historical period, and then based on the total sum of the maximum temperatures in this future period, fits the total sum of the maximum grid loads in the historical period to obtain the total sum of the maximum grid loads in the future period. In this way, through the collected historical data, the law of the maximum temperature in the historical period is mined to predict the extreme situation of the daily maximum temperature under continuous strong heat and high temperature, and then the extreme value of the maximum grid load in this extreme situation is predicted to ensure that the power generation capacity is sufficient to meet the peak electricity demand, which is beneficial to the development of the grid's summer peak load regulation and power supply guarantee work. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The accompanying drawings here are incorporated into the specification and form a part of this specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application.

[0031] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the accompanying drawings required in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0032] Figure 1 It is a schematic flow chart of a power grid load forecasting method provided by an embodiment of the present application;

[0033] Figure 2 It is a schematic structural diagram of a power grid load forecasting device provided by an embodiment of the present application;

[0034] Figure 3 It is a schematic structural diagram of an electronic device according to an embodiment of the present application. Detailed implementation manners

[0035] In order to be able to more clearly understand the above-mentioned objects, features, and advantages of the present application, the following will further describe the solutions of the present application. It should be noted that, without conflict, the embodiments of the present application and the features in the embodiments can be combined with each other.

[0036] Many specific details are set forth in the following description in order to fully understand the present application, but the present application can 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 application, rather than all the embodiments.

[0037] To solve some or all of the technical problems existing in the related art, an embodiment of the present application provides a power grid load forecasting method, device, equipment, storage medium, and program product. The method collects the daily highest temperature and the daily maximum power grid load in the historical period, then calculates the total sum of the highest temperatures and the total sum of the maximum power grid loads in the historical period, then performs weighted averaging on the total sum of the highest temperatures in adjacent time periods and performs weighted averaging on the total sum of the maximum power grid loads in adjacent time periods to obtain a weighted value related to the historical highest temperature and a weighted value related to the historical maximum power grid load; and then first fits the total sum of the highest temperatures in the future period based on the weighted value related to the historical highest temperature and the total sum of the highest temperatures in the historical period, and then fits the maximum power grid load in the future period based on the total sum of the highest temperatures in this future period and the total sum of the maximum power grid loads in the historical period. In this way, through the collected historical data, the law of the highest temperature in the historical period is mined to predict the extreme situation of the daily highest temperature under continuous strong heat and high temperature, and then the extreme value of the maximum power grid load in this extreme situation is predicted to ensure that the power generation capacity is sufficient to meet the peak electricity demand, which is beneficial to the development of the power grid's peak summer power supply guarantee work.

[0038] A power grid load forecasting method provided in an embodiment of the present application can be implemented by a power grid load forecasting device or an electronic device. The electronic device includes but is not limited to a personal computer, a laptop computer, a tablet computer, a smart phone, etc. The operating system of the electronic device can include Android, iOS developed by Apple Inc., Windows developed by Microsoft Corporation in the United States, etc. The embodiments of the present application do not limit this. The electronic device can run alone to implement the present application, or can be connected to the network and implement the present application through interactive operations with other computer devices in the network. Among them, the network where the electronic device is located includes but is not limited to the Internet, a wide area network, a metropolitan area network, a local area network, a Virtual Private Network (VPN) network, etc.

[0039] It should be noted that the protection scope of a power grid load forecasting method described in an embodiment of the present application is not limited to the execution order of the steps listed in this embodiment. Any solution achieved by adding or reducing steps of the prior art and replacing steps according to the principle of the present application is included in the protection scope of the present application.

[0040] As Figure 1 shown, Figure 2 is a schematic flow chart of a power grid load forecasting method according to an embodiment of the present application. This method can be executed by a power grid load forecasting device, where the device can be implemented by software and / or hardware and is generally integrated in an electronic device. This method mainly includes the following steps S101 to S106:

[0041] S101. Obtain the daily maximum temperature and the daily maximum power grid load in the historical period.

[0042] Among them, the daily maximum temperature in the historical period can be expressed as t (0) (n), t (0) (n - 1), …, t (0) (1). Here, n represents the number of days in the historical period, and t (0) (n) is the maximum temperature of the day closest to the current time. The nth day can be today, and correspondingly, the (n - 1)th day is yesterday, and the (n - 1)th day is the (n - 1)th day before today.

[0043] The daily maximum power grid load in the historical period can be expressed as l (0) (n), l (0) (n - 1), …, l (0) (1). l (0) (n) is the maximum power grid load of the day closest to the current time.

[0044] S102. Calculate the total sum of the maximum temperatures in the historical period and the total sum of the maximum power grid loads in the historical period.

[0045] Calculate the sum of the highest temperatures in the historical period according to the following formula (1).

[0046]

[0047] In formula (1), k = 1, 2, …, n, t (0) (i) is the highest temperature actually recorded on the i-th day in this historical period. The sum of the highest temperatures in the historical period is the cumulative value of the daily highest temperatures from the 1st day to the k-th day. The sum of the highest temperatures in the historical period includes: t (1) (1), t (1) (2), …, t (1) (n). For example, t (1) (7) is the sum of the highest temperatures from the 1st day to the 7th day. Calculating the sum of the highest temperatures t (1) (k) can make the originally discrete daily highest temperature data show a cumulative change trend, which helps to explore the internal laws of the data, such as observing the change of temperature with time accumulation, etc.

[0048] Calculate the sum of the maximum grid loads in the historical period according to the following formula (2).

[0049]

[0050] In formula (2), k = 1, 2, …, n, l (0) (i) is the maximum grid load actually recorded on the i-th day in this historical period. The sum of the maximum grid loads in the historical period is the cumulative value of the daily maximum grid loads from the 1st day to the k-th day. The sum of the maximum grid loads in the historical period includes: l (1) (1), l (1) (2), …, l (1) (n). For example, l (1) (7) is the cumulative sum of the original maximum grid loads from the 1st day to the 7th day. Through such a cumulative operation, the randomness of the original daily maximum grid load can be weakened to a certain extent, making the daily maximum grid load show a smoother and more regular trend, which is convenient for subsequent modeling analysis and exploring deeper relationships between data, creating conditions for more accurate prediction of future grid load conditions.

[0051] S103. Perform weighted averaging on the sum of the highest temperatures in adjacent time periods in the historical period to obtain the weighted average of the historical highest temperature; and, perform weighted averaging on the sum of the maximum grid loads in adjacent time periods in the historical period to obtain the weighted average of the historical maximum grid load.

[0052] Calculate the weighted average of the historical highest temperature according to formula (3):

[0053] z(1) (k) = 0.5t (1) (k - 1)+0.5t (1) (k)(3)

[0054] In formula (3), k = 2, 3, …, n. k - 1 and k are two adjacent time periods in the historical period. t (1) (k - 1) is the sum of the highest temperatures corresponding to the k - 1 time period, which is the cumulative value of the daily highest temperatures from the first day to the (k - 1)-th day; t (1) (k) is the sum of the highest temperatures corresponding to the k time period, which is the cumulative value of the daily highest temperatures from the first day to the k-th day. For specific calculation, reference can be made to formula (1).

[0055] By performing a weighted average on the sum of the highest temperatures of two adjacent time periods (the k - 1 time period and the k time period), the comprehensive change of the sum of the highest temperatures of adjacent time periods is reflected, which can better capture the continuity characteristics of the temperature data changes between different stages and prepare for constructing a suitable model in the subsequent steps.

[0056] Calculate the weighted mean of the historical maximum grid load according to formula (4):

[0057] x (1) (k) = 0.5l (1) (k - 1)+0.5l (1) (k)(4)

[0058] In formula (4), k = 2, 3, …, n. l (1) (k - 1) is the cumulative value of the daily maximum grid loads from the first day to the (k - 1)-th day; l (1) (k) is the cumulative value of the daily maximum grid loads from the first day to the k-th day. For specific calculation, reference can be made to formula (2).

[0059] It is obtained by performing a weighted average on the sum of the maximum grid loads of two adjacent time periods (the k - 1 time period and the k time period), which can reflect the comprehensive change of the sum of the maximum grid loads of adjacent time periods. The purpose of this is to further refine the data characteristics, comprehensively consider the cumulative load of adjacent stages, so that the model constructed subsequently can better capture the internal connection of the data changing with time and provide a more suitable data basis for subsequent steps such as constructing a matrix.

[0060] S104. Based on the weighted mean of the historical highest temperatures and the sum of the highest temperatures in the historical period, fit to obtain the sum of the highest temperatures in the future period.

[0061] In some embodiments, step S104 includes the following steps S1041 to S1044:

[0062] S1041. Based on the weighted mean z of the historical highest temperatures (1)(k), where k = 2, 3, …, n, construct the first design matrix B.

[0063]

[0064] The first column elements of the first design matrix B are -z (1) (k), k = 2, 3, …, n; the second column elements are all 1. Such a structure is to lay the foundation for subsequent calculations such as linear regression, facilitating the exploration of the relationship between independent variables and dependent variables (maximum temperature data) through relevant operations.

[0065] S1042. Based on the daily maximum temperature t (0) (i) in the historical period, where i = 2, 3, …, n, construct the first vector Y.

[0066]

[0067] The first vector Y is a column vector composed of the daily maximum temperatures t (0) (i) from the 2nd day to the nth day (i = 2, 3, …, n). It represents the set of observed values of the explained variable (maximum temperature) and participates in subsequent operations with the matrix to determine the linear relationship between maximum temperature data.

[0068] S1043. Based on the first design matrix B and the first vector Y, use the least squares method to solve for the historical maximum temperature related parameters a and u.

[0069] The calculation formula is as follows:

[0070]

[0071] In formula (5), first calculate the transpose matrix B of the first design matrix B T , and then perform the multiplication of B T B, and find its inverse matrix (B T B) -1 , and then multiply it with the first vector Y in sequence. Finally, obtain a column vector containing the historical maximum temperature related parameters a and u. Use the matrix form of the least squares method to solve for the historical maximum temperature related parameters, find the historical maximum temperature related parameters a and u that minimize the sum of squared errors of the linear regression model, and fit the linear relationship of the maximum temperature data, so that the constructed model can better predict future temperature conditions based on historical data.

[0072] S1044. Based on the historical maximum temperature related parameters a and u, and the sum of the maximum temperatures in the historical period, fit to obtain the sum of the maximum temperatures in the future period.

[0073] According to the following formula (6):

[0074]

[0075] In formula (6), t (1) (n + 1) represents the sum of the highest temperatures from the 1st day to the (n + 1)-th day. t (1) (1) = t (0) (1) represents the highest temperature on the first day. Estimating the future sum of the highest temperatures can help us understand in advance the extreme situation of the continuous increase in future temperatures.

[0076] S105. Based on the sum of the highest temperatures in the future period and the sum of the maximum grid loads in the historical period, fit to obtain the sum of the maximum grid loads in the future period.

[0077] In some embodiments, step S105 includes the following steps S1051 to S1054:

[0078] S1051. Based on the sum of the highest temperatures t (1) (k), k = 2, 3,..., n, in the historical period, and the weighted mean x (1) (k), k = 2, 3,..., n, of the historical maximum grid loads, construct the second design matrix A.

[0079]

[0080] The first column elements of the second design matrix A are -x (1) (k), k = 2, 3,..., n; the second column elements are the sum of the highest temperatures t (1) (k), k = 2, 3,..., n, in the historical period.

[0081] S1052. Based on the daily maximum grid loads l (0) (i), i = 2, 3,..., n, in the historical period, construct the second vector C.

[0082]

[0083] The second vector C is a column vector composed of the daily maximum grid loads l (0) (i), i = 2, 3,..., n, from the 2nd day to the nth day.

[0084] S1053. Based on the second design matrix A and the second vector C, use the least squares method to solve the historical maximum grid load related parameters e and f.

[0085] The calculation formula is as follows:

[0086]

[0087] In formula (7), first calculate the transpose matrix A of the second design matrix A T , and then perform A T A multiplication and find its inverse matrix (AT A) -1 , and then multiply it with A T and the second vector C in sequence, and finally obtain a column vector containing the parameters e and f related to the historical maximum grid load. This is done to find the parameters that conform to the pattern of the existing grid load data, so that the subsequent prediction model constructed based on these parameters can better fit the performance of the historical data and accurately predict the future grid load.

[0088] S1054. Based on the parameters e and f related to the historical maximum grid load, the total sum of the historical maximum grid load, and the total sum of the highest temperatures t in the future period (1) (n + 1), fit to obtain the total sum of the maximum grid load in the future period.

[0089] The total sum of the maximum grid load in the future period is obtained by fitting according to the following formula (8):

[0090]

[0091] In formula (8), l (1) (n + 1) represents the total sum of the maximum grid load from the 1st day to the (n + 1)th day; l (1) (1) = l (0) (1), representing the maximum grid load on the 1st day. t (1) (n + 1) represents the total sum of the highest temperatures corresponding to the (n + 1)th day, and the specific calculation is shown in formula (6).

[0092] S106. Predict the maximum grid load on the target date based on the total sum of the maximum grid load in the future period.

[0093] The maximum grid load on the (n + 1)th day is calculated according to the following formula:

[0094] l (0) (n + 1) = l (1) (n + 1) - l (1) (n) (9)

[0095] In formula (9), l (1) (n + 1) represents the total sum of the maximum grid load from the 1st day to the (n + 1)th day, as in formula (8); l (1) (n) represents the total sum of the maximum grid load from the 1st day to the nth day. In this way, the daily maximum grid load on the (n + 1)th day in non - cumulative form is predicted, completing the prediction of the future grid load situation, and providing a reference basis for aspects such as the operation planning and dispatching of the power system.

[0096] Exemplarily, assume that the daily maximum temperature and the daily maximum grid load for 8 days are collected, as shown in Table 1, so as to apply the grid load prediction method provided in the embodiments of the present application to predict what the maximum grid load on the 9th day is, including the following steps S01 to S11:

[0097] Table 1

[0098] Actual daily maximum load value Actual daily maximum air temperature Today <![CDATA[l (0) (8)]]> <![CDATA[t (0) (8)]]> Yesterday <![CDATA[l (0) (7)]]> <![CDATA[t (0) (7)]]> The day before yesterday <![CDATA[l (0) (6)]]> <![CDATA[t (0) (6)]]> …… …… …… The seventh day before <![CDATA[l (0) (1)]]> <![CDATA[t (0) (1)]]>

[0099] S01. Calculate the sum of the maximum temperatures in the historical period k = 1, 2, …, 8.

[0100] S02. Calculate the weighted average value z of the historical maximum temperatures (1) (k) = 0.5t (1) (k - 1) + 0.5t (1) (k), k = 2, 3, …, 8.

[0101] S03. Construct the first design matrix and the first vector

[0102] S04. Calculate the relevant parameters of the historical maximum temperatures

[0103] S05. Calculate the sum of the maximum temperatures in the future period

[0104] S06. Calculate the sum of the maximum grid loads in the historical period k = 1, 2, …, 8.

[0105] S07. Calculate the weighted average value x of the historical maximum grid loads (1) (k) = 0.5l (1) (k - 1) + 0.5l (1) (k), k = 2, 3, …, 8.

[0106] S08. Construct the second design matrix and the second vector

[0107] S09. Calculate the relevant parameters of the historical maximum grid loads

[0108] S10. Calculate the sum of the maximum grid loads in the future period

[0109] S11. Calculate the maximum grid load l on the 9th day (0) (9) = l (1) (9) - l (1) (8).

[0110] In the above embodiments, the present application collects historical data, performs a series of data transformations, matrix construction, and parameter solving operations, and finally uses relevant formulas to predict the corresponding index values in the future, aiming to make a reasonable prediction of future situations by mining the laws of historical data.

[0111] In summary, the embodiments of the present application provide a power grid load forecasting method. This method collects the daily maximum temperature and the daily maximum power grid load in the historical period, then calculates the total sum of the maximum temperatures and the total sum of the maximum power grid loads in the historical period, then performs a weighted average on the total sum of the maximum temperatures in adjacent time periods and a weighted average on the total sum of the maximum power grid loads in adjacent time periods to obtain the weighted value related to the historical maximum temperature and the weighted value related to the historical maximum power grid load. Furthermore, first, based on the weighted value related to the historical maximum temperature and the total sum of the maximum temperatures in the historical period, the total sum of the maximum temperatures in the future period is fitted, and then, based on the total sum of the maximum temperatures in this future period, the total sum of the maximum power grid loads in the future period is fitted with the total sum of the maximum power grid loads in the historical period. In this way, through the collected historical data, the law of the maximum temperature in the historical period is mined to predict the extreme situation of the daily maximum temperature under continuous strong heat and high temperature, and then the extreme value of the maximum power grid load in this extreme situation is predicted to ensure that the power generation capacity is sufficient to meet the peak power demand, which is beneficial to the implementation of the power grid's peak load regulation and power supply guarantee work in summer.

[0112] As Figure 2 shown, Figure 2 Figure 10 is a schematic structural diagram of a power grid load forecasting device provided by an embodiment of the present application. The device includes:

[0113] An acquisition module 201, configured to acquire the daily maximum temperature and the daily maximum power grid load in the historical period;

[0114] A calculation module 202, configured to calculate the total sum of the maximum temperatures in the historical period and the total sum of the maximum power grid loads in the historical period;

[0115] A weighted average module 203, configured to perform a weighted average on the total sum of the maximum temperatures in adjacent time periods in the historical period to obtain a weighted average value of the historical maximum temperature; and perform a weighted average on the total sum of the maximum power grid loads in adjacent time periods in the historical period to obtain a weighted average value of the historical maximum power grid load;

[0116] A maximum temperature total sum fitting module 204, configured to fit the total sum of the maximum temperatures in the future period based on the weighted average value of the historical maximum temperature and the total sum of the maximum temperatures in the historical period;

[0117] A maximum power grid load total sum fitting module 205, configured to fit the total sum of the maximum power grid loads in the future period based on the total sum of the maximum temperatures in the future period and the total sum of the maximum power grid loads in the historical period;

[0118] The daily maximum grid load prediction module 206 is used to predict the maximum grid load on the target date according to the total maximum grid load in the future period.

[0119] As an optional implementation manner of the embodiment of the present application, the highest temperature sum fitting module 204 is specifically used for: constructing a first design matrix based on the weighted mean of historical highest temperatures; constructing a first vector based on the daily highest temperatures in the historical period; solving the historical highest temperature related parameters by using the least square method based on the first design matrix and the first vector; and fitting to obtain the highest temperature sum in the future period based on the historical highest temperature related parameters and the highest temperature sum in the historical period.

[0120] As an optional implementation manner of the embodiment of the present application, when the highest temperature sum fitting module 204 fits to obtain the highest temperature sum in the future period based on the historical highest temperature related parameters and the highest temperature sum in the historical period, it is specifically used for: fitting to obtain the highest temperature sum in the future period according to the following formula: t (1) (n + 1) = (t (i) (1) - uae - an + ua, where n is the number of days in the historical period, and t1n + 1 represents the sum of the highest temperatures from the first day to the (n + 1)-th day; t (1) (1) represents the highest temperature on the first day; u and a are the historical highest temperature related parameters.

[0121] As an optional implementation manner of the embodiment of the present application, the maximum grid load sum fitting module 205 is specifically used for: constructing a second design matrix based on the highest temperature sum in the historical period and the weighted mean of the historical maximum grid load; constructing a second vector based on the daily maximum grid loads in the historical period; solving the historical maximum grid load related parameters by using the least square method based on the second design matrix and the second vector; and fitting to obtain the maximum grid load sum in the future period based on the historical maximum grid load related parameters, the maximum grid load sum in the historical period, and the highest temperature sum in the future period.

[0122] As an optional implementation manner of the embodiment of the present application, when the maximum grid load sum fitting module 205 fits to obtain the maximum grid load sum in the future period based on the historical maximum grid load related parameters, the maximum grid load sum in the historical period, and the highest temperature sum in the future period, it is specifically used for: fitting to obtain the maximum grid load sum in the future period according to the following formula: where n is the number of days in the historical period, l (1) (n + 1) represents the sum of the maximum grid loads from the first day to the (n + 1)-th day; l (1) (1) represents the maximum grid load on the first day; f and e are the historical maximum grid load related parameters; t (1)(n + 1) represents the total sum of the highest temperatures corresponding to the (n + 1)-th day.

[0123] As an optional implementation manner of an embodiment of the present application, the daily maximum power grid load prediction module 206 is specifically configured to: if the target date is the (n + 1)-th day, then predict the maximum power grid load of the (n + 1)-th day according to the following formula: l (0) (n + 1) = l (1) (n + 1) - l (1) (n), where l (1) (n + 1) represents the total sum of the maximum power grid loads from the 1st day to the (n + 1)-th day, and l (1) (n) represents the total sum of the maximum power grid loads from the 1st day to the n-th day.

[0124] For the specific limitations on the power grid load prediction device, reference can be made to the limitations on the power grid load prediction method in the above text, which will not be elaborated here. Each module in the above power grid load prediction device can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor of the computer device in the form of hardware or be independent of it, or be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above respective modules.

[0125] In one embodiment, the present application provides an electronic device, which can be a terminal, and its internal structure diagram can be as Figure 3 shown. The electronic device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the electronic device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a carrier network, near field communication (NFC), or other technologies. When the computer program is executed by the processor, it realizes a stuttering detection method. The display screen of the electronic device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the electronic device can be a touch layer covered on the display screen, or a button, a trackball, or a touchpad provided on the housing of the electronic device, or an external keyboard, a touchpad, or a mouse, etc.

[0126] Those skilled in the art can understand that Figure 3 the structure shown in only represents the block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the electronic device to which the solution of the present application is applied. The specific electronic device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0127] In one embodiment, the power grid load prediction device provided by the present application can be implemented in the form of a computer program, and the computer program can run on an electronic device as shown in Figure 3 . Each program module that constitutes the power grid load prediction device can be stored in the memory of the electronic device. For example, Figure 2 the acquisition module 201, the calculation module 202, the weighted average module 203, the highest temperature sum fitting module 204, the maximum power grid load sum fitting module 205, and the daily maximum power grid load prediction module 206 shown in. The computer program constituted by each program module enables the processor to execute the steps in the power grid load prediction method of each embodiment of the present application described in this specification.

[0128] For example, Figure 3 the electronic device shown in can execute, through the acquisition module 201 in the power grid load prediction device as shown in Figure 2 , to acquire the daily highest temperature and the daily maximum power grid load in the historical period; the electronic device can execute, through the calculation module 202, to calculate the sum of the highest temperatures in the historical period and the sum of the maximum power grid loads in the historical period; the electronic device can execute, through the weighted average module 203, to perform a weighted average on the sum of the highest temperatures in adjacent time periods in the historical period to obtain the weighted average value of the historical highest temperature; and, perform a weighted average on the sum of the maximum power grid loads in adjacent time periods in the historical period to obtain the weighted average value of the historical maximum power grid load; the electronic device can execute, through the highest temperature sum fitting module 204, to fit the sum of the highest temperatures in the future period based on the weighted average value of the historical highest temperature and the sum of the highest temperatures in the historical period; the electronic device can execute, through the maximum power grid load sum fitting module 205, to fit the sum of the maximum power grid loads in the future period based on the sum of the highest temperatures in the future period and the sum of the maximum power grid loads in the historical period; the electronic device can execute, through the daily maximum power grid load prediction module 206, to predict the maximum power grid load on the target date according to the sum of the maximum power grid loads in the future period.

[0129] In one embodiment, the present application provides an electronic device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0130] Obtain the daily maximum temperature and the daily maximum grid load for the historical period; calculate the total sum of the maximum temperatures and the total sum of the maximum grid loads for the historical period; perform a weighted average on the total sum of the maximum temperatures for adjacent time periods in the historical period to obtain the weighted average of the historical maximum temperature; and, perform a weighted average on the total sum of the maximum grid loads for adjacent time periods in the historical period to obtain the weighted average of the historical maximum grid load; based on the weighted average of the historical maximum temperature and the total sum of the maximum temperatures for the historical period, fit to obtain the total sum of the maximum temperatures for the future period; based on the total sum of the maximum temperatures for the future period and the total sum of the maximum grid loads for the historical period, fit to obtain the total sum of the maximum grid loads for the future period; predict the maximum grid load for the target date according to the total sum of the maximum grid loads for the future period.

[0131] In one embodiment, when the processor executes the computer program, the following steps are further implemented: based on the weighted average of the historical maximum temperature and the daily maximum temperature, fit to obtain the total sum of the maximum temperatures for the future period, including: based on the weighted average of the historical maximum temperature, construct a first design matrix; based on the daily maximum temperatures for the historical period, construct a first vector; based on the first design matrix and the first vector, use the least squares method to solve for the historical maximum temperature related parameters; based on the historical maximum temperature related parameters and the total sum of the maximum temperatures for the historical period, fit to obtain the total sum of the maximum temperatures for the future period.

[0132] In one embodiment, when the processor executes the computer program, the following steps are further implemented: based on the historical maximum temperature related parameters and the total sum of the maximum temperatures for the historical period, fit to obtain the total sum of the maximum temperatures for the future period, including: fit to obtain the total sum of the maximum temperatures for the future period according to the following formula: In the formula, n is the number of days in the historical period, t (1) (n + 1) represents the total sum of the maximum temperatures from the first day to the (n + 1)-th day; t (1) (1) represents the maximum temperature on the first day; u and a are the historical maximum temperature related parameters.

[0133] In one embodiment, when the processor executes the computer program, the following steps are further implemented: based on the total sum of the maximum temperatures for the future period and the total sum of the maximum grid loads for the historical period, fit to obtain the total sum of the maximum grid loads for the future period, including: based on the total sum of the maximum temperatures for the historical period and the weighted average of the historical maximum grid load, construct a second design matrix; based on the daily maximum grid loads for the historical period, construct a second vector; based on the second design matrix and the second vector, use the least squares method to solve for the historical maximum grid load related parameters; based on the historical maximum grid load related parameters, the total sum of the maximum grid loads for the historical period, and the total sum of the maximum temperatures for the future period, fit to obtain the total sum of the maximum grid loads for the future period.

[0134] In one embodiment, when the processor executes the computer program, the following steps are further implemented: Based on the historical maximum grid load related parameters, the total sum of the maximum grid loads in the historical period, and the total sum of the highest temperatures in the future period, fitting to obtain the total sum of the maximum grid loads in the future period, including: Fitting to obtain the total sum of the maximum grid loads in the future period according to the following formula: Where n is the number of days in the historical period, l (1) (n + 1) represents the total sum of the maximum grid loads from the 1st day to the (n + 1)-th day; l (1) (1) represents the maximum grid load on the 1st day; f and e are the historical maximum grid load related parameters; t (1) (n + 1) represents the total sum of the highest temperatures corresponding to the (n + 1)-th day.

[0135] In one embodiment, when the processor executes the computer program, the following steps are further implemented: According to the total sum of the maximum grid loads in the future period, predicting the maximum grid load on the target date, including: If the target date is the (n + 1)-th day, then predicting the maximum grid load on the (n + 1)-th day according to the following formula: l (0) (n + 1) = l (1) (n + 1) - l (1) (n), where l (1) (n + 1) represents the total sum of the maximum grid loads from the 1st day to the (n + 1)-th day, l (1) (n) represents the total sum of the maximum grid loads from the 1st day to the n-th day.

[0136] When the processor in the electronic device provided in this application executes the computer program, it first collects the daily highest temperatures and the daily maximum grid loads in the historical period, then calculates the total sum of the highest temperatures and the total sum of the maximum grid loads in the historical period, then performs weighted averaging on the total sum of the highest temperatures in adjacent time periods and performs weighted averaging on the total sum of the maximum grid loads in adjacent time periods to obtain the historical highest temperature related weighted value and the historical maximum grid load related weighted value; then first fits the total sum of the highest temperatures in the future period according to the historical highest temperature related weighted value and the total sum of the highest temperatures in the historical period, and then based on this total sum of the highest temperatures in the future period, fits with the total sum of the maximum grid loads in the historical period to obtain the total sum of the maximum grid loads in the future period. In this way, through the collected historical data, the law of the highest temperature in the historical period is mined to predict the extreme situation of the daily highest temperature under continuous strong heat and high temperature, and then the extreme value of the maximum grid load in this extreme situation is predicted to ensure that the power generation capacity is sufficient to meet the demand of the peak electricity consumption, which is beneficial to the development of the grid's summer peak load regulation and power supply guarantee work.

[0137] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a computer, the following steps are implemented:

[0138] Obtain the daily maximum temperature and the daily maximum grid load for historical periods; calculate the total sum of the maximum temperatures and the total sum of the maximum grid loads for historical periods; perform a weighted average on the total sum of the maximum temperatures for adjacent time periods in the historical period to obtain the weighted average of the historical maximum temperature; and, perform a weighted average on the total sum of the maximum grid loads for adjacent time periods in the historical period to obtain the weighted average of the historical maximum grid load; based on the weighted average of the historical maximum temperature and the total sum of the maximum temperatures for the historical period, fit to obtain the total sum of the maximum temperatures for the future period; based on the total sum of the maximum temperatures for the future period and the total sum of the maximum grid loads for the historical period, fit to obtain the total sum of the maximum grid loads for the future period; predict the maximum grid load for the target date according to the total sum of the maximum grid loads for the future period.

[0139] In one embodiment, when the computer program executes the computer program, the following steps are further implemented: based on the weighted average of the historical maximum temperature and the daily maximum temperature, fit to obtain the total sum of the maximum temperatures for the future period, including: based on the weighted average of the historical maximum temperature, construct a first design matrix; based on the daily maximum temperature for the historical period, construct a first vector; based on the first design matrix and the first vector, use the least squares method to solve for the historical maximum temperature related parameters; based on the historical maximum temperature related parameters and the total sum of the maximum temperatures for the historical period, fit to obtain the total sum of the maximum temperatures for the future period.

[0140] In one embodiment, when the computer program executes the computer program, the following steps are further implemented: based on the historical maximum temperature related parameters and the total sum of the maximum temperatures for the historical period, fit to obtain the total sum of the maximum temperatures for the future period, including: fit to obtain the total sum of the maximum temperatures for the future period according to the following formula: In the formula, n is the number of days in the historical period, t (1) (n + 1) represents the total sum of the maximum temperatures from the 1st day to the (n + 1)th day; t (1) (1) represents the maximum temperature on the 1st day; u and a are the historical maximum temperature related parameters.

[0141] In one embodiment, when the computer program executes the computer program, the following steps are further implemented: based on the total sum of the maximum temperatures for the future period and the total sum of the maximum grid loads for the historical period, fit to obtain the total sum of the maximum grid loads for the future period, including: based on the total sum of the maximum temperatures for the historical period and the weighted average of the historical maximum grid load, construct a second design matrix; based on the daily maximum grid load for the historical period, construct a second vector; based on the second design matrix and the second vector, use the least squares method to solve for the historical maximum grid load related parameters; based on the historical maximum grid load related parameters, the total sum of the maximum grid loads for the historical period, and the total sum of the maximum temperatures for the future period, fit to obtain the total sum of the maximum grid loads for the future period.

[0142] In one embodiment, when the computer program executes the computer program, the following steps are also implemented: Based on the historical maximum power grid load related parameters, the total sum of the maximum power grid loads in the historical period, and the total sum of the highest temperatures in the future period, fitting to obtain the total sum of the maximum power grid loads in the future period, including: Fitting to obtain the total sum of the maximum power grid loads in the future period according to the following formula: In the formula, n is the number of days in the historical period, l (1) (n + 1) represents the total sum of the maximum power grid loads from the 1st day to the (n + 1)-th day; l (1) (1) represents the maximum power grid load on the 1st day; f and e are the historical maximum power grid load related parameters; t (1) (n + 1) represents the total sum of the highest temperatures corresponding to the (n + 1)-th day.

[0143] In one embodiment, when the computer program executes the computer program, the following steps are also implemented: According to the total sum of the maximum power grid loads in the future period, predicting the maximum power grid load on the target date, including: If the target date is the (n + 1)-th day, then predicting the maximum power grid load on the (n + 1)-th day according to the following formula: l (0) (n + 1) = l (1) (n + 1) - l (1) (n), where l (1) (n + 1) represents the total sum of the maximum power grid loads from the 1st day to the (n + 1)-th day, l (1) (n) represents the total sum of the maximum power grid loads from the 1st day to the n-th day.

[0144] When the computer program in the computer-readable storage medium provided by this application executes the computer program, it first collects the daily highest temperatures and the daily maximum power grid loads in the historical period, then calculates the total sum of the highest temperatures and the total sum of the maximum power grid loads in the historical period, then performs weighted averaging on the total sum of the highest temperatures in adjacent time periods and performs weighted averaging on the total sum of the maximum power grid loads in adjacent time periods to obtain the historical highest temperature related weighted value and the historical maximum power grid load related weighted value; and then first fits the total sum of the highest temperatures in the future period according to the historical highest temperature related weighted value and the total sum of the highest temperatures in the historical period, and then based on the total sum of the highest temperatures in this future period, fits with the total sum of the maximum power grid loads in the historical period to obtain the total sum of the maximum power grid loads in the future period. In this way, through the collected historical data, the law of the historical highest temperature is mined to predict the extreme situation of the daily highest temperature under continuous strong heat and high temperature, and then the extreme value of the maximum power grid load in this extreme situation is predicted to ensure that the power generation capacity is sufficient to meet the demand of the peak power consumption, which is beneficial to the development of the power grid's summer peak load regulation and power supply guarantee work.

[0145] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media that contain computer-usable program code.

[0146] In several embodiments provided by the present application, it should be understood that the disclosed apparatus and method can also be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions, and operations of the apparatus, method, and computer program product according to multiple embodiments of the present application. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a part of code, and the module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0147] In the present application, the processor can be a central processing unit (CPU), or can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor, or the processor can also be any conventional processor, etc.

[0148] In the present application, the memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. The memory is an example of computer-readable media.

[0149] In this application, computer-readable media include both permanent and non-permanent, removable and non-removable storage media. The storage media can implement information storage by any method or technology, and the information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information accessible by a computing device. As defined herein, computer-readable media do not include transitory media such as modulated data signals and carrier waves.

[0150] It should be noted that, in this document, 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 variation thereof are intended to cover non-exclusive inclusion, such that a process, method, article or device that includes a series of elements includes not only those elements but also other elements not expressly listed, or 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 additional identical elements in the process, method, article or device that includes the element.

[0151] The above are only specific embodiments of this application, enabling those skilled in the art to understand or implement this application. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application will not be limited to these embodiments herein, but rather will conform to the broadest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for predicting power grid load, characterized in that: include: Get the daily maximum temperature and daily maximum grid load in the historical period; Calculate the sum of the highest temperatures during the historical period and the sum of the maximum power grid load during the historical period; Taking a weighted average of the sum of the maximum temperatures in adjacent time periods in the historical period to obtain a weighted mean of the historical maximum temperatures; and taking a weighted average of the sum of the maximum power grid loads in adjacent time periods in the historical period to obtain a weighted mean of the historical maximum power grid loads; Based on the weighted mean of the historical maximum temperatures and the sum of the maximum temperatures in the historical period, the sum of the maximum temperatures in the future period is fitted; Based on the sum of the maximum temperatures in the future period and the sum of the maximum grid loads in the historical period, the sum of the maximum grid loads in the future period is fitted; The maximum grid load on the target date is predicted based on the sum of the maximum grid loads in the future period.

2. The method according to claim 1, characterized in that: The sum of the maximum temperatures in the future period is obtained by fitting based on the weighted mean of the historical maximum temperatures and the daily maximum temperatures, including: Constructing a first design matrix based on the weighted mean of the historical maximum temperatures; constructing a first vector based on the daily maximum temperature during the historical period; Based on the first design matrix and the first vector, solving the historical maximum temperature related parameters by using the least square method; Based on the relevant parameters of the historical maximum temperature and the sum of the maximum temperatures in the historical period, the sum of the maximum temperatures in the future period is fitted.

3. The method according to claim 2, characterized in that The fitting of the sum of the maximum temperatures in the future period based on the historical maximum temperature related parameters and the sum of the maximum temperatures in the historical period includes: The sum of the maximum temperatures in the future period is obtained by fitting according to the following formula: Where n is the number of days in the historical period, t (1) (n+1) represents the sum of the highest temperatures from the 1st day to the n+1th day; t (1) (1) represents the maximum temperature on the first day; u and a are parameters related to the historical maximum temperature.

4. The method according to claim 1, characterized in that: The maximum grid load sum in the future period is obtained by fitting based on the maximum temperature sum in the future period and the maximum grid load sum in the historical period, including: constructing a second design matrix based on the sum of the highest temperatures in the historical period and the weighted mean of the historical maximum grid load; constructing a second vector based on the daily maximum grid load during the historical period; Based on the second design matrix and the second vector, solving the historical maximum grid load related parameters by using the least square method; Based on the relevant parameters of the historical maximum grid load, the sum of the maximum grid loads in the historical period, and the sum of the maximum temperatures in the future period, the sum of the maximum grid loads in the future period is fitted.

5. The method according to claim 4, characterized in that The fitting method based on the historical maximum grid load related parameters, the maximum grid load sum in the historical period, and the maximum temperature sum in the future period to obtain the maximum grid load sum in the future period includes: The maximum total grid load in the future period is obtained by fitting according to the following formula: Where n is the number of days in the historical period, l (1) (n+1) represents the total maximum grid load from day 1 to day n+1; l (1) (1) represents the maximum grid load on the first day; f and e are the parameters related to the historical maximum grid load; t (1) (n+1) represents the sum of the maximum temperatures corresponding to the n+1th day.

6. The method according to claim 5, characterized in that The method of predicting the maximum grid load on the target date based on the sum of the maximum grid loads in the future period includes: If the target date is day n+1, the maximum grid load on day n+1 is predicted according to the following formula: L (0) (n+1)=l (1) (n+1)-l (1) (n) In the formula, l (1) (n+1) represents the total maximum grid load from day 1 to day n+1, l (1) (n) represents the sum of the maximum grid loads from day 1 to day n.

7. A power grid load prediction device, characterized in that: include: An acquisition module is used to obtain the daily maximum temperature and daily maximum power grid load in the historical period; A calculation module, used to calculate the sum of the highest temperatures in the historical period and the sum of the maximum power grid loads in the historical period; A weighted average module is used to perform a weighted average on the sum of the maximum temperatures of adjacent time periods in the historical period to obtain a weighted mean of the historical maximum temperatures; and to perform a weighted average on the sum of the maximum power grid loads of adjacent time periods in the historical period to obtain a weighted mean of the historical maximum power grid loads; A maximum temperature sum fitting module, used for fitting the maximum temperature sum of a future period based on the weighted mean of the historical maximum temperature and the maximum temperature sum of the historical period; A maximum grid load sum fitting module is used to fit the maximum grid load sum in the future period based on the maximum temperature sum in the future period and the maximum grid load sum in the historical period; The daily maximum grid load prediction module is used to predict the maximum grid load on a target date based on the total maximum grid load in the future period.

8. An electronic device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the power grid load forecasting method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: include: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the power grid load forecasting method according to any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that include: The computer program product comprises a computer program, and when the computer program is executed on a computer, the computer is enabled to implement the power grid load forecasting method according to any one of claims 1 to 6.

Images