Electric quantity influence factor positioning method and device, equipment and storage medium

Abstract

The invention belongs to the electromechanical field, and discloses an electric quantity influence factor positioning method and device, equipment and a storage medium, and the method comprises the steps: obtaining electric quantity data and influence factor data corresponding to a plurality of electric quantity influence factors, and carrying out the processing of the data, and generating a time sequence set; calculating an autocorrelation coefficient corresponding to each time sequence in the time sequence set through an autocorrelation analysis model, and selecting the time sequence of which the autocorrelation coefficient reaches a first preset threshold value; and calculating a Spearman correlation coefficient corresponding to each time sequence in the selected time sequences through a Spearman correlation analysis model, and determining the electric quantity influence factor corresponding to a target time sequence of which the Spearman correlation coefficient reaches a second preset threshold as a key factor. And the processing capability of the nonlinear relationship and the dynamic identification of the electric quantity influence factors are improved, so that the accuracy of key factor positioning is improved.

Description

Technical Field

[0001] The present invention belongs to the field of electromechanics, and relates to a positioning method, and in particular to a positioning method, device, equipment and storage medium for factors affecting electrical quantity. Background Art

[0002] In the field of power forecasting in the power industry, accurately grasping the key factors that affect power fluctuations is crucial to optimizing power resource allocation and ensuring stable power grid operation. Power forecasts at different time scales, such as short-term, medium-term and long-term, are affected by a variety of complex factors, including long-term factors such as macroeconomic conditions and industry development trends, as well as short-term fluctuations such as seasonal changes and weather conditions. In order to more accurately locate these key influencing factors, especially considering the differences in power characteristics of various industries, it is particularly important to use methods based on statistical correlation analysis.

[0003] As a result, the "Spearman-based method for locating key factors affecting short-term and medium-term electricity consumption" came into being. This method uses the Spearman rank correlation coefficient, a non-parametric statistical indicator that measures the monotonic relationship between two variables, to analyze the correlation between historical electricity consumption data and potential influencing factors. The Spearman coefficient is not limited by the data distribution form and can effectively capture nonlinear relationships, which is particularly applicable to dealing with variable influencing factors in electricity consumption forecasting.

[0004] In related technologies, the factors affecting electricity consumption are analyzed based on multiple linear regression and correlation screening. This method first collects historical data covering multiple dimensions such as economic indicators, policy changes, and climate change; then, by calculating the Pearson or Spearman correlation coefficient between each factor and electricity consumption after preliminary screening, the candidate factors with significant correlation with electricity consumption are identified; then, the actual impact of these factors is further verified using a multiple linear regression model, and the model is adjusted accordingly to optimize the prediction accuracy. However, although this method has taken into account the factors affecting electricity fluctuations to a certain extent, its ability to handle nonlinear relationships and dynamically identify key influencing factors still has room for improvement. Summary of the invention

[0005] In view of this, the present invention discloses a method, device, equipment and storage medium for locating power influencing factors, which can solve the deficiencies existing in the related art.

[0006] To achieve the above purpose, the present invention discloses the following technical solutions: According to a first aspect of the present invention, a method for locating power influencing factors is proposed, the method comprising: Acquire power data and influencing factor data corresponding to multiple power influencing factors, and process the acquired data to generate a time series set; wherein each time series in the time series set includes a combination of power data and influencing factor data at different times; Calculate the autocorrelation coefficient corresponding to each time series in the time series set by using an autocorrelation analysis model, and select the time series whose autocorrelation coefficient reaches a first preset threshold; The Spearman correlation analysis model is used to calculate the Spearman correlation coefficient corresponding to each time series in the selected time series, and the power influencing factor corresponding to the target time series whose Spearman correlation coefficient reaches the second preset threshold is determined as the key factor.

[0007] According to a second aspect of the present invention, a positioning device for power influencing factors is provided, the device comprising: Acquisition unit: acquires power data and influencing factor data corresponding to multiple power influencing factors, and processes the acquired data to generate a time series set; wherein each time series in the time series set includes a combination of power data and influencing factor data at different times; A selection unit: calculating the autocorrelation coefficient corresponding to each time series in the time series set through an autocorrelation analysis model, and selecting the time series whose autocorrelation coefficient reaches a first preset threshold; Determining unit: Calculate the Spearman correlation coefficient corresponding to each time series in the selected time series through the Spearman correlation analysis model, and determine the power influencing factor corresponding to the target time series whose Spearman correlation coefficient reaches the second preset threshold as the key factor.

[0008] According to a third aspect of the present invention, an electronic device is provided, comprising: processor; a memory for storing processor-executable instructions; The processor implements the steps of the method described in the first aspect by running the executable instructions.

[0009] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, on which computer instructions are stored, and when the instructions are executed by a processor, the steps of the method described in the first aspect are implemented.

[0010] It can be seen from the above technical solutions that the method for locating power influencing factors disclosed in the present invention, on the one hand, by combining Spearman correlation analysis and autocorrelation analysis, performs autocorrelation analysis and screening on power influencing factors before performing Spearman correlation analysis, thereby improving the processing capability of nonlinear relationships and the dynamic identification of power influencing factors, thereby improving the accuracy of locating key factors; on the other hand, dynamically identifies power influencing factors at different time scales, thereby providing a more accurate and comprehensive basis for factor positioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 It is a flow chart of a method for locating power influencing factors provided by an exemplary embodiment.

[0012] Figure 2 It is a schematic diagram of a key factor positioning process provided by an exemplary embodiment.

[0013] Figure 3 It is a schematic structural diagram of a device provided by an exemplary embodiment.

[0014] Figure 4 It is a block diagram of a positioning device for power influencing factors provided by an exemplary embodiment. DETAILED DESCRIPTION

[0015] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with one or more embodiments of the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of one or more embodiments of the present invention as detailed in the appended claims.

[0016] It should be noted that: in other embodiments, the steps of the corresponding method are not necessarily performed in the order shown and described in the present invention. In some other embodiments, the steps included in the method may be more or less than those described in the present invention. In addition, a single step described in the present invention may be decomposed into multiple steps for description in other embodiments; and multiple steps described in the present invention may be combined into a single step for description in other embodiments.

[0017] To further illustrate the present invention, the following examples are provided: In the field of power forecasting in the power industry, accurately grasping the key factors that affect power fluctuations is crucial to optimizing power resource allocation and ensuring stable power grid operation. Power forecasts at different time scales, such as short-term, medium-term and long-term, are affected by a variety of complex factors, including long-term factors such as macroeconomic conditions and industry development trends, as well as short-term fluctuations such as seasonal changes and weather conditions. In order to more accurately locate these key influencing factors, especially considering the differences in power characteristics of various industries, it is particularly important to use methods based on statistical correlation analysis.

[0018] As a result, the "Spearman-based method for locating key factors affecting short-term and medium-term electricity consumption" came into being. This method uses the Spearman rank correlation coefficient, a non-parametric statistical indicator that measures the monotonic relationship between two variables, to analyze the correlation between historical electricity consumption data and potential influencing factors. The Spearman coefficient is not limited by the data distribution form and can effectively capture nonlinear relationships, which is particularly applicable to dealing with variable influencing factors in electricity consumption forecasting.

[0019] In related technologies, the factors affecting electricity consumption are analyzed based on multiple linear regression and correlation screening. This method first collects historical data covering multiple dimensions such as economic indicators, policy changes, and climate change; then, by calculating the Pearson or Spearman correlation coefficient between each factor and electricity consumption after preliminary screening, the candidate factors with significant correlation with electricity consumption are identified; then, the actual impact of these factors is further verified using a multiple linear regression model, and the model is adjusted accordingly to optimize the prediction accuracy. However, although this method has taken into account the factors affecting electricity fluctuations to a certain extent, its ability to handle nonlinear relationships and dynamically identify key influencing factors still has room for improvement.

[0020] In order to solve the deficiencies existing in the related art, the present invention proposes a method for locating factors affecting power consumption.

[0021] Figure 1 FIG. 1 is a flow chart of a method for locating power influencing factors provided by an exemplary embodiment. Figure 1 As shown, the method may include the following steps: Step S101, acquiring power data and influencing factor data corresponding to a plurality of power influencing factors, and processing the acquired data to generate a time series set; wherein each time series in the time series set includes a combination of power data and influencing factor data at different times.

[0022] The factors affecting electricity consumption include at least one of the following: temperature factor, humidity factor, season factor, light factor, rainfall factor, and economic indicator factor.

[0023] Step S102, calculating the autocorrelation coefficient corresponding to each time series in the time series set by using an autocorrelation analysis model, and selecting the time series whose autocorrelation coefficient reaches a first preset threshold.

[0024] In one embodiment, the step of calculating the autocorrelation coefficient corresponding to each time series in the time series set by using an autocorrelation analysis model includes: Calculate the mean, variance, and covariance of the time series, and calculate the autocorrelation coefficient based on the mean, variance, and covariance; wherein the autocorrelation function in the autocorrelation analysis model is used to describe the correlation between the time series and its lagged value, and the autocorrelation coefficient of the lag k Initially defined as: ; in, is a time series, Represents the time series at time and The covariance of and Respectively represent the time series at time and The variance of The formula for calculating the mean is: ; in,

[0025] The formula for calculating variance is: ; The formula for calculating covariance is: ; The calculation formula of the autocorrelation coefficient is converted to: .

[0026] Step S103, calculating the Spearman correlation coefficient corresponding to each time series in the selected time series through the Spearman correlation analysis model, and determining the power influencing factor corresponding to the target time series whose Spearman correlation coefficient reaches the second preset threshold as the key factor.

[0027] In one embodiment, the Spearman correlation coefficient corresponding to each time series in the selected time series is calculated by using the Spearman correlation analysis model, including: Calculate the sum of squares of the rank differences of each combination of the electric quantity data and the influencing factor data in the time series input into the Spearman correlation analysis model, and calculate the Spearman correlation coefficient based on the sum of squares of the rank differences; wherein, The calculation formula of rank difference is: ; in, is the rank difference, the combination of power data and influencing factor data is express, and Respectively and Rank among all combinations of the corresponding time series; The calculation formula of Spearman correlation coefficient is: ; in, is the sum of squared rank differences, and n is the number of combinations in the time series.

[0028] In this embodiment, by combining Spearman correlation analysis and autocorrelation analysis, autocorrelation analysis is performed on the factors affecting power before performing Spearman correlation analysis, which improves the processing capability of nonlinear relationships and the dynamic identification of factors affecting power, thereby improving the accuracy of locating key factors.

[0029] In one embodiment, In the case of power data, is the influencing factor data; In the case of power data, Influencing factor data.

[0030] In this embodiment, since there may be a bidirectional causal relationship between the power influencing factors and the power demand, for example, when the power influencing factors are economic activities, on the one hand, economic growth usually drives the increase in power demand; on the other hand, the improvement of power supply may also promote economic growth. Therefore, the Spearman correlation analysis method can be used to perform a bidirectional analysis on the two.

[0031] In one embodiment, if Figure 2 As shown, the processing of the acquired data to generate a time series set includes: dividing the acquired data processing into a short-term time series set corresponding to short-term data and a long-term time series set corresponding to long-term data; determining the power influencing factors corresponding to the target time series whose Spearman correlation coefficient reaches the second preset threshold as key factors, includes: determining the power influencing factors corresponding to the time series in the target time series corresponding to the short-term time series set as short-term key factors, and determining the power influencing factors corresponding to the time series in the target time series corresponding to the long-term time series set as long-term key factors.

[0032] In this embodiment, the factors affecting power consumption are dynamically identified at different time scales, thereby providing a more accurate and comprehensive basis for factor positioning.

[0033] In one embodiment, the method also includes: obtaining mediating factor data, and inputting the mediating factor data and the time series in the short-term time series set except the target time series into a mediating effect analysis model; wherein the mediating effect analysis model calculates the mediating effect between the electricity data and the influencing factor data based on the stepwise regression method; and dividing the electricity influencing factors corresponding to the time series input into the mediating effect analysis model into complete mediating effect factors, partial mediating effect factors and no mediating effect factors according to a preset judgment criterion of the assumed value of the time series output by the mediating effect analysis model.

[0034] Stepwise regression is a method for statistical model selection, especially for selecting variables in a multiple linear regression model. Its basic idea is to gradually select explanatory variables that have a significant impact on the dependent variable through a forward (adding variables to the model) and backward (removing variables from the model) process, thereby establishing an optimal regression model.

[0035] The method includes the following steps: Step 202, Forward Selection: Starting from a model without independent variables, select a variable that is most closely related to the dependent variable from all available independent variables to enter the model; refit the model using the selected variable and calculate the statistical significance of the model. Repeat the above operation, adding only one variable each time, until no other independent variable can significantly improve the model. Step 204, Backward Elimination: Starting from a model containing all independent variables, check each independent variable in the model and remove the variable with the smallest effect on the dependent variable. Refit the model using the remaining variables and calculate the statistical significance of the model. Repeat the above operation, removing only one variable each time, until all remaining variables have a statistically significant contribution to the model. Step 206, Stepwise Regression: Combine forward selection and backward elimination, and consider adding or removing variables at each step. In each step, decide whether to add or remove variables based on predetermined criteria (such as AIC, BIC, adjusted R square, etc.). This process continues until no variables can be added or removed, resulting in an optimal model.

[0036] The advantage of stepwise regression is that it simplifies the model and removes unimportant variables, which helps the interpretation and prediction of the model. However, it also has disadvantages, such as including wrong variables due to accidental factors in the data, or excluding actually important variables.

[0037] The mediation effect, also known as the indirect effect, refers to the process by which the independent variable affects the dependent variable through the mediating variable.

[0038] Through mediating effect analysis, we explore whether other meteorological factors indirectly affect electricity demand through major related factors. The specific process is as follows: Assuming that the correlation between the dependent variable Y and the independent variable X is significant means that the regression coefficient c is significant (that is, the hypothesis H0: c = 0 is rejected). Under this premise, the mediating variable M is considered. To determine whether M plays the role of a mediating variable, or to determine whether its mediating effect is significant, the stepwise regression method is generally used, as follows: Test whether the independent variable (X) has a significant effect on the dependent variable (Y), that is, test the direct effect. This is usually achieved by performing a regression analysis with Y as the dependent variable and X as the independent variable.

[0039] Test whether the independent variable (X) has a significant effect on the mediating variable (M). This is usually achieved by performing a regression analysis with M as the dependent variable and X as the independent variable.

[0040] Test whether the mediating variable (M) has a significant effect on the dependent variable (Y). This is usually achieved by performing a regression analysis with Y as the dependent variable and M as the independent variable.

[0041] At the same time, the independent variable (X) and the mediating variable (M) are used as independent variables to perform regression analysis on the dependent variable (Y). If the effect of X on Y is no longer significant, or the significance level decreases, while the effect of M on Y is still significant, then it can be considered that there is a mediating effect.

[0042] The above mediating variables correspond to the intermediate factor data, and the independent variables and dependent variables correspond to the electricity data and influencing factor data respectively.

[0043] The mediation effect is also divided into three categories: full mediation effect, partial mediation effect and no mediation effect: (1) Full mediation effect: When the influence of the independent variable (X) on the dependent variable (Y) is completely realized through the mediating variable (M), the direct influence of the independent variable (X) on the dependent variable (Y) becomes insignificant after controlling for the mediating variable (M). In this case, all the influence of the independent variable on the dependent variable is transmitted through the mediating variable. In other words, the independent variable has no direct influence on the dependent variable, but is completely dependent on the influence of the mediating variable.

[0044] Judgment criteria: The independent variable has a significant impact on the mediating variable (p<0.05). After controlling for the mediating variable, the direct impact of the independent variable on the dependent variable is not significant (p>= 0.05).

[0045] (2) Partial mediation effect: When the influence of the independent variable on the dependent variable is partially realized through the mediating variable, the direct influence of the independent variable on the dependent variable is still significant after controlling for the mediating variable, but the influence is weakened. In this case, the influence of the independent variable on the dependent variable is partially transmitted through the mediating variable and partially direct. Even if the mediating variable is taken into account, the direct influence of the independent variable on the dependent variable still exists, but it will be weakened.

[0046] Judgment criteria: The independent variable has a significant impact on the mediating variable (p<0.05). After controlling for the mediating variable, the direct impact of the independent variable on the dependent variable is still significant (p<0.05), but the regression coefficient decreases.

[0047] (3) No mediation effect: When the independent variable has no significant effect on the mediating variable, or the direct effect of the independent variable on the dependent variable does not change significantly after controlling the mediating variable. In this case, the effect of the independent variable on the dependent variable is not transmitted through the mediating variable, or the mediating variable has no significant mediation effect.

[0048] Judgment criteria: The independent variable has no significant effect on the mediating variable (p>= 0.05). Or, even if the independent variable has a significant effect on the mediating variable, after controlling for the mediating variable, the direct effect of the independent variable on the dependent variable is still significant and has not weakened (p<0.05 and the regression coefficient does not change much).

[0049] The above p is an assumed value.

[0050] Figure 3 is a schematic structural diagram of a device provided by an exemplary embodiment. Figure 3 At the hardware level, the device includes a processor 301, an internal bus 302, a network interface 303, a memory 304, and a non-volatile memory 305, and may also include hardware required for other functions. One or more embodiments of the present invention may be implemented based on software, such as the processor 301 reading the corresponding computer program from the non-volatile memory 305 into the memory 304 and then running it. Of course, in addition to the software implementation, one or more embodiments of the present invention do not exclude other implementations, such as logic devices or a combination of software and hardware, etc., that is, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0051] Please refer to Figure 4 A block diagram of a positioning device for power influencing factors is shown, and the device may include: The acquisition unit 401 is used to acquire the power data and the influencing factor data corresponding to the multiple power influencing factors, and process the acquired data to generate a time series set; wherein each time series in the time series set includes a combination of power data and influencing factor data at different times; A selection unit 402 is used to calculate the autocorrelation coefficient corresponding to each time series in the time series set through an autocorrelation analysis model, and select the time series whose autocorrelation coefficient reaches a first preset threshold; The determination unit 403 is used to calculate the Spearman correlation coefficient corresponding to each time series in the selected time series through the Spearman correlation analysis model, and determine the power influencing factor corresponding to the target time series whose Spearman correlation coefficient reaches the second preset threshold as the key factor.

[0052] Optional, The acquisition unit 401 is specifically used to: process and divide the acquired data into a short-term time series set corresponding to short-term data and a long-term time series set corresponding to long-term data; The determination unit 403 is specifically used to: determine the power influencing factors corresponding to the time series in the target time series corresponding to the short-term time series set as short-term key factors, and determine the power influencing factors corresponding to the time series in the target time series corresponding to the long-term time series set as long-term key factors.

[0053] Optionally, the method further includes: An input unit 404 is used to obtain mediating factor data, and input the mediating factor data and the time series in the short-term time series set except the target time series into a mediating effect analysis model; wherein the mediating effect analysis model calculates the mediating effect between the electricity data and the influencing factor data based on a stepwise regression method; The division unit 405 is used to divide the power influencing factors corresponding to the time series input to the mediation effect analysis model into complete mediation effect factors, partial mediation effect factors and no mediation effect factors according to the preset judgment criteria of the assumed value of the time series output by the mediation effect analysis model.

[0054] Optionally, the selection unit 402 is specifically configured to: Calculate the mean, variance, and covariance of the time series, and calculate the autocorrelation coefficient based on the mean, variance, and covariance; wherein the autocorrelation function in the autocorrelation analysis model is used to describe the correlation between the time series and its lagged value, and the autocorrelation coefficient of the lag k Initially defined as: ; in, is a time series, Represents the time series at time and The covariance of and Respectively represent the time series at time and The variance of The formula for calculating the mean is: ; in,

[0055] The formula for calculating variance is: ; The formula for calculating covariance is: ; The calculation formula of the autocorrelation coefficient is converted to: .

[0056] Optionally, the determining unit 403 is specifically configured to: Calculate the sum of squares of the rank differences of each combination of the electric quantity data and the influencing factor data in the time series input into the Spearman correlation analysis model, and calculate the Spearman correlation coefficient based on the sum of squares of the rank differences; wherein, The calculation formula of rank difference is: ; in, is the rank difference, the combination of power data and influencing factor data is express, and Respectively and Rank among all combinations of the corresponding time series; The calculation formula of Spearman correlation coefficient is: ; in, is the sum of squared rank differences, and n is the number of combinations in the time series.

[0057] Optional, exist In the case of power data, is the influencing factor data; exist In the case of power data, Influencing factor data.

[0058] Optionally, the factors affecting electricity consumption include at least one of the following: temperature factor, humidity factor, season factor, light factor, rainfall factor, and economic indicator factor.

[0059] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer, which may be in the form of a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email transceiver, a game console, a tablet computer, a wearable device or a combination of any of these devices.

[0060] In a typical configuration, a computer includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0061] Memory may include non-permanent storage in a computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0062] Computer-readable media include permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. 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 technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, disk storage, quantum memory, graphene-based storage media or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0063] With respect to the computer-readable medium (or computer-readable storage medium) as described above or in any other form, computer instructions may be stored thereon, and when the instructions are executed by a processor, one or more of the above-mentioned embodiments are implemented, thereby realizing the technical solution of the present invention.

[0064] The present invention also proposes a computer program, which, when executed by a processor, implements one or more of the above embodiments, thereby realizing the technical solution of the present invention. The computer program may be specifically recorded in the above or any other form of computer-readable medium, and the present invention is not limited thereto.

[0065] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0066] The above describes specific embodiments of the present invention. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0067] The terms used in one or more embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of the present invention. The singular forms of "a", "said" and "the" used in one or more embodiments of the present invention and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0068] It should be understood that although the terms first, second, third, etc. may be used to describe various information in one or more embodiments of the present invention, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of the present invention, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0069] The above description is merely a preferred embodiment of one or more embodiments of the present invention and is not intended to limit one or more embodiments of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of one or more embodiments of the present invention shall be included in the scope of protection of one or more embodiments of the present invention.

Claims

1. A method for locating factors affecting power consumption, characterized in that: The method comprises: Acquire power data and influencing factor data corresponding to multiple power influencing factors, and process the acquired data to generate a time series set; wherein each time series in the time series set includes a combination of power data and influencing factor data at different times; Calculate the autocorrelation coefficient corresponding to each time series in the time series set by using an autocorrelation analysis model, and select the time series whose autocorrelation coefficient reaches a first preset threshold; The Spearman correlation analysis model is used to calculate the Spearman correlation coefficient corresponding to each time series in the selected time series, and the power influencing factor corresponding to the target time series whose Spearman correlation coefficient reaches the second preset threshold is determined as the key factor.

2. The method according to claim 1, characterized in that The step of processing the acquired data to generate a time series set includes: dividing the acquired data into a short-term time series set corresponding to the short-term data and a long-term time series set corresponding to the long-term data; The method of determining the power influencing factors corresponding to the target time series whose Spearman correlation coefficient reaches the second preset threshold as key factors includes: determining the power influencing factors corresponding to the time series in the target time series corresponding to the short-term time series set as short-term key factors, and determining the power influencing factors corresponding to the time series in the target time series corresponding to the long-term time series set as long-term key factors.

3. The method according to claim 2, characterized in that The method further comprises: Obtaining mediating factor data, and inputting the mediating factor data and the time series in the short-term time series set except the target time series into a mediating effect analysis model; wherein the mediating effect analysis model calculates the mediating effect between the electricity data and the influencing factor data based on a stepwise regression method; According to the preset judgment criteria of the assumed value of the time series output by the mediation effect analysis model, the electricity influencing factors corresponding to the time series input to the mediation effect analysis model are divided into complete mediation effect factors, partial mediation effect factors and no mediation effect factors.

4. The method according to claim 1, characterized in that: The step of calculating the autocorrelation coefficient corresponding to each time series in the time series set by using the autocorrelation analysis model includes: Calculate the mean, variance, and covariance of the time series, and calculate the autocorrelation coefficient based on the mean, variance, and covariance; wherein the autocorrelation function in the autocorrelation analysis model is used to describe the correlation between the time series and its lagged value, and the autocorrelation coefficient of the lag k Initially defined as: ； in, is a time series, Represents the time series at time and The covariance of and Respectively represent the time series at time and The variance of The formula for calculating the mean is: ； in, The formula for calculating variance is: ； The formula for calculating covariance is: ； The calculation formula of the autocorrelation coefficient is converted to: 。 5. The method according to claim 1, characterized in that The Spearman correlation coefficient corresponding to each time series in the selected time series is calculated by the Spearman correlation analysis model, including: Calculate the sum of squares of the rank differences of each combination of the electric quantity data and the influencing factor data in the time series input into the Spearman correlation analysis model, and calculate the Spearman correlation coefficient based on the sum of squares of the rank differences; wherein, The calculation formula of rank difference is: ； in, is the rank difference, the combination of power data and influencing factor data is express, and Respectively and Rank among all combinations of the corresponding time series; The calculation formula of Spearman correlation coefficient is: ； in, is the sum of squared rank differences, and n is the number of combinations in the time series.

6. The method according to claim 5, characterized in that exist In the case of power data, is the influencing factor data; exist In the case of power data, Influencing factor data.

7. The method according to claim 1, characterized in that The power influencing factors include at least one of the following: temperature factor, humidity factor, season factor, light factor, rainfall factor, and economic indicator factor.

8. A device for locating factors affecting power, characterized in that: The device comprises: Acquisition unit: acquires power data and influencing factor data corresponding to multiple power influencing factors, and processes the acquired data to generate a time series set; wherein each time series in the time series set includes a combination of power data and influencing factor data at different times; A selection unit: calculating the autocorrelation coefficient corresponding to each time series in the time series set through an autocorrelation analysis model, and selecting the time series whose autocorrelation coefficient reaches a first preset threshold; Determining unit: Calculate the Spearman correlation coefficient corresponding to each time series in the selected time series through the Spearman correlation analysis model, and determine the power influencing factor corresponding to the target time series whose Spearman correlation coefficient reaches the second preset threshold as the key factor.

9. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor implements the steps of the method according to any one of claims 1 to 7 by running the executable instructions.

10. A computer-readable storage medium having computer instructions stored thereon, characterized in that: When the instruction is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images