Missing value filling method of power grid time sequence curve and related device

Abstract

The invention provides a missing value filling method for a power grid time sequence curve and a related device. The missing value filling method for the power grid time sequence curve comprises the following steps: acquiring a missing time sequence curve and a correlation curve set; carrying out interpolation calculation on the missing time sequence curve by adopting a preset interpolation algorithm, and obtaining an interpolation time sequence curve; inputting the at least one associated time sequence curve into a first prediction model, and obtaining a first prediction time sequence curve output by the first prediction model; inputting the first prediction time sequence curve and the interpolation time sequence curve into a second prediction model, and obtaining a second prediction time sequence curve output by the second prediction model; and performing missing value filling on the missing time sequence curve according to the second prediction time sequence curve. Therefore, the second prediction time sequence curve more fitting the actual curve trend can be obtained, and missing value filling is performed according to the second prediction time sequence curve, so that the complete time sequence curve can be effectively restored, and the accuracy can be improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method for filling missing values ​​of a power grid timing curve and a related device. Background Art

[0002] In order to monitor the operation of the power grid and realize the functions of fault warning, fault detection, fault location, daily operation and maintenance, the power grid is equipped with a variety of acquisition devices to collect various time series data during the operation of the power grid, such as voltage, current, active power and other data, and form the power grid time series curve. However, under the influence of factors such as acquisition equipment failure, software system failure and communication failure, the power grid time series curve will lack the value of certain time points, and there is a problem of data missing.

[0003] At present, the existing technology usually uses relatively conventional methods such as mean filling, median filling, and mode filling to fill the missing values ​​in the timing curve. For curves with certain regularity and periodicity, the restoration effect of the existing technology is acceptable. However, for power grid timing curves with poor regularity and strong randomness, the filling effect of the existing technology is poor and it is impossible to accurately restore the complete power grid timing curve. Summary of the invention

[0004] The purpose of this application is to solve at least one of the above-mentioned technical defects, especially the technical defect that the prior art cannot accurately restore the grid timing curve.

[0005] In a first aspect, the present application provides a method for filling missing values ​​of a power grid timing curve, comprising:

[0006] Obtaining a missing timing curve and an associated curve set; wherein the missing timing curve is used to reflect the change of a first physical quantity of the power grid over time; the associated curve set includes at least one associated timing curve, and the associated timing curve is used to reflect the change of a second physical quantity of the power grid over time, and the second physical quantity is associated with the first physical quantity;

[0007] Using a preset interpolation algorithm to perform interpolation calculation on the missing timing curve, and obtain an interpolated timing curve;

[0008] Inputting the at least one associated timing curve into a first prediction model, and obtaining a first prediction timing curve output by the first prediction model; wherein the first prediction timing curve is used to reflect the change of the first physical quantity over time;

[0009] Inputting the first prediction time series curve and the interpolation time series curve into a second prediction model, and obtaining a second prediction time series curve output by the second prediction model; wherein the second prediction time series curve is used to reflect the change of the first physical quantity over time;

[0010] The missing value of the missing timing curve is filled according to the second predicted timing curve.

[0011] In some embodiments, the first prediction model is a random forest regression model.

[0012] In some embodiments, the second prediction model is a polynomial regression model.

[0013] In some embodiments, the interpolation algorithm is a KNN interpolation method.

[0014] In some embodiments, the step of filling missing values ​​of the missing timing curve according to the second predicted timing curve includes:

[0015] Determining a data missing moment in the missing timing curve;

[0016] Determine a data prediction value at the data missing moment in the second prediction time series curve;

[0017] Based on the data missing time and the data prediction value, the missing value of the missing time series curve is filled.

[0018] In a second aspect, the present application also provides a missing value filling device for a power grid timing curve, comprising:

[0019] A curve acquisition module, used to acquire a missing timing curve and an associated curve set; wherein the missing timing curve is used to reflect the change of a first physical quantity of the power grid over time; the associated curve set includes at least one associated timing curve, and the associated timing curve is used to reflect the change of a second physical quantity of the power grid over time, and the second physical quantity is associated with the first physical quantity;

[0020] An interpolation calculation module, used to perform interpolation calculation on the missing timing curve using a preset interpolation algorithm, and obtain an interpolated timing curve;

[0021] A first prediction module, used for inputting the at least one associated time series curve into a first prediction model, and obtaining a first prediction time series curve output by the first prediction model; wherein the first prediction time series curve is used for reflecting the change of the first physical quantity over time;

[0022] A second prediction module, used for inputting the first prediction time series curve and the interpolation time series curve into a second prediction model, and obtaining a second prediction time series curve output by the second prediction model; wherein the second prediction time series curve is used for reflecting the change of the first physical quantity over time;

[0023] A filling module is used to fill the missing values ​​of the missing timing curve according to the second predicted timing curve.

[0024] In some embodiments, the first prediction model is a random forest regression model.

[0025] In a third aspect, the present application further provides a computer device. The computer device includes: one or more processors, and a memory;

[0026] The memory stores computer-readable instructions, and when the computer-readable instructions are executed by the one or more processors, the steps of the method for filling missing values ​​of a power grid timing curve described in any of the above embodiments are performed.

[0027] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method for filling missing values ​​of a power grid timing curve described in any of the above embodiments.

[0028] In a fifth aspect, the present application further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the method for filling missing values ​​of a power grid timing curve described in any of the above embodiments are implemented.

[0029] In a method for filling missing values ​​of a power grid timing curve and a related device provided in some embodiments of the present application, a curve missing value filling scheme using multi-dimensional deep learning is proposed. The present application performs a primary prediction by using a set of associated curves, and performs a secondary prediction based on a first predicted timing curve obtained by the primary prediction and an interpolated timing curve obtained by interpolation calculation, thereby obtaining a second predicted timing curve that is more in line with the actual curve trend. The missing values ​​of the missing timing curve are filled based on the second predicted timing curve, so that the complete timing curve can be effectively restored, thereby improving the accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0031] Figure 1 A schematic diagram of a flow chart of a method for filling missing values ​​of a power grid timing curve in one embodiment;

[0032] Figure 2 1 is a schematic diagram of the structure of a device for filling missing values ​​of a power grid timing curve in one embodiment;

[0033] Figure 3 FIG. 1 is a diagram of the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0035] In some embodiments, the present application provides a method for filling missing values ​​of a power grid timing curve. The method can be applied to any computer device with data acquisition and data processing functions, wherein the computer device described herein can be, but is not limited to, a laptop, a desktop computer, a notebook computer, a tablet computer, and an Internet of Things device.

[0036] like Figure 1 As shown, the method for filling missing values ​​of a power grid timing curve provided by the present application may include the following steps:

[0037] S102: Obtain missing timing curves and a set of associated curves.

[0038] The missing timing curve refers to a timing curve in which the physical quantities corresponding to some time points are missing. The missing timing curve can reflect the change of the first physical quantity of the power grid over time.

[0039] The associated curve set may include at least one associated timing curve, and the associated timing curve is used to reflect the change of a second physical quantity of the power grid over time, and the second physical quantity is associated with the first physical quantity. During the operation of the power grid, multiple physical quantities of the power grid are usually interrelated and affect each other. In the present application, the associated timing curve can be used to reflect the change of other physical quantities associated with the first physical quantity over time.

[0040] It can be understood that the number of associated timing curves can be determined according to actual conditions, for example, 1, 2, 5, etc., and this application does not impose specific restrictions on this. In addition, the first physical quantity and the second physical quantity can also be determined according to actual conditions, and this application does not impose specific restrictions on this, as long as the missing timing curve and the associated timing curve meet the above requirements.

[0041] For ease of description, some embodiments of the present application are described by taking the first physical quantity as the grid load and the second physical quantity as the current and voltage as examples. That is, the missing timing curve of the present application may be the load timing curve, and the associated curve set may include the voltage timing curve and the current timing curve of the grid.

[0042] In this step, the computer device can obtain the missing timing curve and the associated timing curve that is mutually associated with and affects the missing timing curve. In some examples, both the missing timing curve and the associated timing curve can be obtained by collecting the operation data of the power grid through the collection device, and the computer device can obtain the timing curve by communicating with the collection device or communicating with the database.

[0043] S104: Using a preset interpolation algorithm to perform interpolation calculation on the missing timing curve, and obtaining an interpolated timing curve.

[0044] In this step, the computer device may use a preset interpolation algorithm to perform interpolation calculation on the missing timing curve, so as to infer the value of the first physical quantity at the time when data is missing through the known value in the missing timing curve, thereby obtaining the interpolated timing curve.

[0045] It can be understood that any interpolation algorithm can be used in this step to complete the interpolation calculation, and the interpolation timing curve can be obtained accordingly. In some examples, the computer device can use the KNN (K-Nearest Neighbor) interpolation method to perform interpolation calculations to make the interpolation timing curve closer to the actual situation. The KNN interpolation method is a method of data interpolation using the k-nearest neighbor algorithm. It predicts the value of the missing data based on the attribute values ​​of these points by finding the k data points of the nearest neighbors of the point to be interpolated. When using the KNN interpolation method for interpolation calculations, the computer device can perform KNN interpolation calculations for each time point involved in the missing timing curve, thereby forming a KNN interpolation timing curve.

[0046] S106: Inputting at least one associated timing curve into the first prediction model, and obtaining a first prediction timing curve output by the first prediction model.

[0047] The first prediction time series curve is used to reflect the change of the first physical quantity over time. That is, the first prediction time series curve is the change of the first physical quantity of the power grid over time predicted by the first prediction model according to the associated curve set.

[0048] In this step, the computer device can input each associated timing curve in the associated curve set into the first prediction model, so that the first prediction model can predict the data of the first physical quantity based on the second physical quantity that is mutually associated and influences the first physical quantity, thereby obtaining the first prediction timing curve.

[0049] It can be understood that before applying the first prediction model for actual prediction, the first prediction model can be first trained using training data so that the first prediction model learns the correlation between the first physical quantity and the second physical quantity until the first prediction model meets the preset training end conditions.

[0050] In the present application, the first prediction model can be implemented using any model structure. Exemplarily, the first prediction model can be a random forest regression model. In this example, the computer device can use a random forest interpolation method, with voltage and current as independent variables and load as a dependent variable, to perform prediction based on random forest regression, and obtain a first prediction time series curve output by the random forest regression model.

[0051] S108: Input the first prediction timing curve and the interpolation timing curve into the second prediction model, and obtain a second prediction timing curve output by the second prediction model.

[0052] The second prediction time series curve is used to reflect the change of the first physical quantity over time. That is, the second monthly time series curve is the change of the first physical quantity of the power grid over time predicted by the second prediction model based on the first prediction time series curve and the interpolation time series curve.

[0053] In this step, considering that the first physical quantity is predicted only based on the second physical quantity, the obtained predicted value (i.e., the first predicted time series curve) has deficiencies in terms of curve smoothness and curve trend fit. In order to improve the accuracy of missing value filling, the computer equipment can perform another prediction to obtain a second predicted time series curve whose curve trend is more in line with the actual situation.

[0054] Specifically, the computer device can make a re-prediction based on the first prediction timing curve and the interpolation timing curve. Among them, the first prediction timing curve can be used to preliminarily determine the value interval range of the first physical quantity at the moment of data missing. Since the missing timing curve lacks the values ​​of the first physical quantity at some moments, the missing timing curve as a whole has the problem of jumps and non-smoothness. The more missing values, the more serious the situation is, which is not conducive to the re-prediction. In order to eliminate jumps and achieve curve smoothness and improve the accuracy of re-prediction, the computer device can input the first prediction timing curve and the interpolation timing curve into the second prediction model, so that the second prediction model can combine the first prediction timing curve and the interpolation timing curve to predict the change of the first physical quantity over time, thereby obtaining the second prediction timing curve.

[0055] It can be understood that before applying the second prediction model for actual prediction, the second prediction model can first be trained using training data so that the second prediction model learns the correlation between the first prediction timing curve, the interpolation timing curve and the actual curve until the second prediction model meets the preset training end conditions.

[0056] In the present application, the second prediction model can be implemented using any model structure. Exemplarily, the second prediction model can be a polynomial regression model. In this example, the computer device can perform curve prediction based on polynomial regression, using the first prediction time series curve and the interpolation time series curve as independent variables and the actual curve as the dependent variable, thereby obtaining the second prediction time series curve. In this way, the second prediction time series curve can be more consistent with the actual change trend of the first physical quantity.

[0057] S110: Filling missing values ​​of the missing timing curve according to the second predicted timing curve.

[0058] In this step, when the second predicted timing curve is obtained, the computer device can fill in the missing values ​​in the missing timing curve according to the second predicted timing curve, thereby completing the missing value filling.

[0059] In some examples, S110 may include:

[0060] Step A1: determining the data missing time in the missing time series curve;

[0061] Step A3: determining the data prediction value in the second prediction time series curve at the time when the data is missing;

[0062] Step A5: Fill missing values ​​of missing time series curves based on the missing data moments and data prediction values.

[0063] The data missing moment refers to the moment when the value of the first physical quantity is lost, and the computer device can use any method to determine the data missing moment, and this application does not impose specific restrictions on this. For example, the computer device can traverse each moment of the missing time series curve, and query whether the first physical quantity has a corresponding value at each moment, so as to determine the data missing moment at each moment.

[0064] When the data missing moment is determined, the computer device may take a value from the second predicted timing curve. Specifically, the computer device may determine a specific value of the second predicted timing curve at the data missing moment, and use the value as a missing value to fill the missing timing curve.

[0065] For example, when the data missing times are T1 and T2 respectively, the computer device can determine the value of the first physical quantity at time T1 in the second predicted timing curve and obtain L1. Similarly, the computer device can determine the value of the first physical quantity at time T2 in the second predicted timing curve and obtain L2. Finally, the computer device can fill L1 into the position corresponding to time T1 in the missing timing curve, and fill L2 into the position corresponding to time T2 in the missing timing curve, so as to fill the missing timing curve into a complete timing curve. In the complete timing curve, the value of the first physical quantity at time T1 is L1, and the value of the first physical quantity at time T2 is L2.

[0066] In the above embodiments, the present application proposes a curve missing value filling scheme using multi-dimensional deep learning. The present application performs a primary prediction by using a set of associated curves, and performs a secondary prediction based on the first predicted timing curve obtained by the primary prediction and the interpolated timing curve obtained by interpolation calculation, so as to obtain a second predicted timing curve that is more in line with the actual curve trend. The missing values ​​of the missing timing curve are filled based on the second predicted timing curve, so that the complete timing curve can be effectively restored, thereby improving the accuracy.

[0067] The following is a description of a missing value filling device for a power grid timing curve provided in an embodiment of the present application. The missing value filling device for a power grid timing curve described below and the missing value filling method for a power grid timing curve described above can be referenced to each other.

[0068] In some embodiments, the present application provides a missing value filling device 200 for a power grid timing curve, comprising:

[0069] The curve acquisition module 202 is used to acquire a missing timing curve and an associated curve set; wherein the missing timing curve is used to reflect the change of a first physical quantity of the power grid over time; the associated curve set includes at least one associated timing curve, and the associated timing curve is used to reflect the change of a second physical quantity of the power grid over time, and the second physical quantity is associated with the first physical quantity;

[0070] An interpolation calculation module 204 is used to perform interpolation calculation on the missing timing curve using a preset interpolation algorithm to obtain an interpolated timing curve;

[0071] A first prediction module 206, configured to input the at least one associated time series curve into a first prediction model, and obtain a first prediction time series curve output by the first prediction model; wherein the first prediction time series curve is used to reflect the change of the first physical quantity over time;

[0072] A second prediction module 208, configured to input the first prediction time series curve and the interpolation time series curve into a second prediction model, and obtain a second prediction time series curve output by the second prediction model; wherein the second prediction time series curve is used to reflect the change of the first physical quantity over time;

[0073] The filling module 210 is used to fill the missing values ​​of the missing timing curve according to the second predicted timing curve.

[0074] In some embodiments, the first prediction model is a random forest regression model.

[0075] In some embodiments, the second prediction model is a polynomial regression model.

[0076] In some embodiments, the interpolation algorithm is a KNN interpolation method.

[0077] In some embodiments, the filling module 210 of the present application includes:

[0078] A missing time determination unit, used to determine the data missing time in the missing timing curve;

[0079] A data value determination unit, used to determine the data prediction value in the second prediction time series curve at the data missing moment;

[0080] A filling unit is used to fill the missing value of the missing time series curve based on the data missing moment and the data prediction value.

[0081] In one embodiment, the present application also provides a computer device having computer-readable instructions stored therein. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the method for filling missing values ​​of a power grid timing curve in any embodiment.

[0082] Indicatively, Figure 3 The internal structure diagram of a computer device provided in an embodiment of the present application is shown in FIG. 1 . In one example, the computer device may be a server. Figure 3 The computer device 900 includes a processing component 902, which further includes one or more processors, and a memory resource represented by a memory 901, for storing instructions executable by the processing component 902, such as an application. The application stored in the memory 901 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 902 is configured to execute instructions to perform the steps of the missing value filling method of the power grid timing curve described in any of the above embodiments.

[0083] The computer device 900 may further include a power supply component 903 configured to perform power management of the computer device 900, a wired or wireless network interface 904 configured to connect the computer device 900 to a network, and an input / output (I / O) interface 905. The computer device 900 may operate based on an operating system stored in the memory 901, such as Windows Server TM, Mac OS X TM, Unix TM, Linux TM, Free BSD TM, or the like.

[0084] Those skilled in the art will understand that the internal structure of the computer device shown in the present application is merely a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0085] In some embodiments, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0086] Obtaining a missing timing curve and an associated curve set; wherein the missing timing curve is used to reflect the change of a first physical quantity of the power grid over time; the associated curve set includes at least one associated timing curve, and the associated timing curve is used to reflect the change of a second physical quantity of the power grid over time, and the second physical quantity is associated with the first physical quantity;

[0087] Using a preset interpolation algorithm to perform interpolation calculation on the missing timing curve, and obtain an interpolated timing curve;

[0088] Inputting the at least one associated timing curve into a first prediction model, and obtaining a first prediction timing curve output by the first prediction model; wherein the first prediction timing curve is used to reflect the change of the first physical quantity over time;

[0089] Inputting the first prediction time series curve and the interpolation time series curve into a second prediction model, and obtaining a second prediction time series curve output by the second prediction model; wherein the second prediction time series curve is used to reflect the change of the first physical quantity over time;

[0090] The missing value of the missing timing curve is filled according to the second predicted timing curve.

[0091] In some embodiments, the first prediction model is a random forest regression model.

[0092] In some embodiments, the second prediction model is a polynomial regression model.

[0093] In some embodiments, the interpolation algorithm is a KNN interpolation method.

[0094] In some embodiments, when the computer program is executed by the processor, the following steps are also implemented:

[0095] Determining a data missing moment in the missing timing curve;

[0096] Determine a data prediction value at the data missing moment in the second prediction time series curve;

[0097] Based on the data missing time and the data prediction value, the missing value of the missing time series curve is filled.

[0098] In some embodiments, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0099] Obtaining a missing timing curve and an associated curve set; wherein the missing timing curve is used to reflect the change of a first physical quantity of the power grid over time; the associated curve set includes at least one associated timing curve, and the associated timing curve is used to reflect the change of a second physical quantity of the power grid over time, and the second physical quantity is associated with the first physical quantity;

[0100] Using a preset interpolation algorithm to perform interpolation calculation on the missing timing curve, and obtain an interpolated timing curve;

[0101] Inputting the at least one associated timing curve into a first prediction model, and obtaining a first prediction timing curve output by the first prediction model; wherein the first prediction timing curve is used to reflect the change of the first physical quantity over time;

[0102] Inputting the first prediction time series curve and the interpolation time series curve into a second prediction model, and obtaining a second prediction time series curve output by the second prediction model; wherein the second prediction time series curve is used to reflect the change of the first physical quantity over time;

[0103] The missing value of the missing timing curve is filled according to the second predicted timing curve.

[0104] In some embodiments, the first prediction model is a random forest regression model.

[0105] In some embodiments, the second prediction model is a polynomial regression model.

[0106] In some embodiments, the interpolation algorithm is a KNN interpolation method.

[0107] In some embodiments, when the computer program is executed by the processor, the following steps are also implemented:

[0108] Determining a data missing moment in the missing timing curve;

[0109] Determine a data prediction value at the data missing moment in the second prediction time series curve;

[0110] Based on the data missing time and the data prediction value, the missing value of the missing time series curve is filled.

[0111] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. Moreover, the term "include", "comprise" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or equipment including a series of elements not only includes those elements, but also includes other elements not clearly listed, or also includes elements inherent to such process, method, article or equipment. In the absence of more restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the process, method, article or equipment including the elements. Herein, "one", "one", "said", "the" and "it" may also include plural forms, unless the context clearly indicates another way. A plurality refers to at least two cases, such as 2, 3, 5 or 8, etc. "And / or" includes any and all combinations of the relevant listed items.

[0112] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The various embodiments can be combined as needed, and the same or similar parts can refer to each other.

[0113] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for filling missing values ​​of a power grid timing curve, characterized in that: include: Obtaining a missing timing curve and an associated curve set; wherein the missing timing curve is used to reflect the change of a first physical quantity of the power grid over time; the associated curve set includes at least one associated timing curve, and the associated timing curve is used to reflect the change of a second physical quantity of the power grid over time, and the second physical quantity is associated with the first physical quantity; Using a preset interpolation algorithm to perform interpolation calculation on the missing timing curve, and obtain an interpolated timing curve; Inputting the at least one associated timing curve into a first prediction model, and obtaining a first prediction timing curve output by the first prediction model; wherein the first prediction timing curve is used to reflect the change of the first physical quantity over time; Inputting the first prediction time series curve and the interpolation time series curve into a second prediction model, and obtaining a second prediction time series curve output by the second prediction model; wherein the second prediction time series curve is used to reflect the change of the first physical quantity over time; The missing value of the missing timing curve is filled according to the second predicted timing curve.

2. The method according to claim 1, characterized in that: The first prediction model is a random forest regression model.

3. The method according to claim 1, characterized in that The second prediction model is a polynomial regression model.

4. The method according to claim 1, characterized in that The interpolation algorithm is the KNN interpolation method.

5. The method according to any one of claims 1 to 4, characterized in that: The step of filling missing values ​​of the missing timing curve according to the second predicted timing curve includes: Determining a data missing moment in the missing timing curve; Determine a data prediction value at the data missing moment in the second prediction time series curve; Based on the data missing time and the data prediction value, the missing value of the missing time series curve is filled.

6. A device for filling missing values ​​of a power grid timing curve, characterized in that: include: A curve acquisition module, used to acquire a missing timing curve and an associated curve set; wherein the missing timing curve is used to reflect the change of a first physical quantity of the power grid over time; the associated curve set includes at least one associated timing curve, and the associated timing curve is used to reflect the change of a second physical quantity of the power grid over time, and the second physical quantity is associated with the first physical quantity; An interpolation calculation module, used to perform interpolation calculation on the missing timing curve using a preset interpolation algorithm, and obtain an interpolated timing curve; A first prediction module, used for inputting the at least one associated time series curve into a first prediction model, and obtaining a first prediction time series curve output by the first prediction model; wherein the first prediction time series curve is used for reflecting the change of the first physical quantity over time; A second prediction module, used for inputting the first prediction time series curve and the interpolation time series curve into a second prediction model, and obtaining a second prediction time series curve output by the second prediction model; wherein the second prediction time series curve is used for reflecting the change of the first physical quantity over time; A filling module is used to fill the missing values ​​of the missing timing curve according to the second predicted timing curve.

7. The device according to claim 1, characterized in that The first prediction model is a random forest regression model.

8. A computer device, characterized in that: include: one or more processors, and memory; The memory stores computer-readable instructions, and when the computer-readable instructions are executed by the one or more processors, the steps of the method for filling missing values ​​of a power grid timing curve as claimed in any one of claims 1 to 5 are performed.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for filling missing values ​​of a power grid timing curve according to any one of claims 1 to 5 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method for filling missing values ​​of a power grid timing curve as described in any one of claims 1 to 5 are implemented.

Images