A load data management method and system for enterprise middle platform

Abstract

The embodiment of the application provides a load data management and control method and system for enterprise middle stations, and belongs to the technical field of artificial intelligence. The method comprises the following steps: obtaining historical load data of each power distribution station in a current area; determining a minimum change period of each power distribution station; dividing the historical load data of each power distribution station into a plurality of load data elements according to the minimum change period; calculating a central change rate of each load data element; determining a correlation between a current power distribution station and load data elements of each of the remaining power distribution stations according to the central change rate; constructing a sample data set for predicting each power distribution station according to the correlation; training a corresponding prediction model by using the sample data set; predicting load data of each power distribution station by using the trained prediction model; and performing power supply management and control operations according to the load data. The method and system can improve the management and control efficiency of the enterprise middle station for the load data in the area.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, in particular to a load data management and control method and system for enterprise middle platform. BACKGROUND

[0002] The enterprise middle platform is a comprehensive system for unified scheduling and control of various information in the management and control area, including scheduling of load, material and personnel information in the area, etc. Among them, the scheduling and control of power supply is an important part of the work of the enterprise middle platform.

[0003] In the prior art, the scheduling of power supply by the enterprise middle platform is mostly real-time scheduling, lacking a warning mechanism. In other related fields of production, a method of using a network model to predict load data has appeared to increase the warning measures. However, this method is only applicable to a single transformer area or a single group of data, and when facing larger data volume, a larger network model is needed. This will cause greater consumption of manpower and material resources. SUMMARY

[0004] The purpose of the embodiment of the present application is to provide a load data management and control method and system for enterprise middle platform, which can improve the management and control efficiency of the enterprise middle platform for the load data in the area.

[0005] In order to achieve the above purpose, the embodiment of the present application provides a load data management and control method for enterprise middle platform, comprising:

[0006] obtaining historical load data of each power distribution transformer area in the current area;

[0007] determining the minimum change period of each power distribution transformer area;

[0008] dividing the historical load data of each power distribution transformer area into a plurality of load data units according to the minimum change period;

[0009] calculating the center change rate of each load data unit;

[0010] determining the correlation between the load data units of the current power distribution transformer area and each of the remaining power distribution transformer areas according to the center change rate;

[0011] constructing a sample data set for predicting each power distribution transformer area according to the correlation;

[0012] training a corresponding prediction model using the sample data set;

[0013] predicting the load data of each power distribution transformer area using the trained prediction model;

[0014] performing power supply control operation according to the load data.

[0015] Optionally, determining the minimum change period for each of the said distribution radio zones includes:

[0016] Initial change cycle;

[0017] The historical load data is divided into multiple load data elements according to the change cycle;

[0018] Calculate the central rate of change for each of the load data elements;

[0019] Determine whether the termination condition is currently met;

[0020] If the termination condition is met, the change period with the lowest historical rate of change is selected as the final determined change period.

[0021] If the termination condition is not met, the change period is updated, and the process returns to the step of calculating the central change rate of each load data element.

[0022] Optionally, the initial change period includes:

[0023] Construct the upper and lower limits of the change cycle;

[0024] Set the initial change period to the lower limit value.

[0025] Optionally, determining whether the termination condition is currently met includes:

[0026] Determine whether the change period is greater than or equal to the upper limit value;

[0027] If the change period is determined to be greater than or equal to the upper limit value, it is determined that the termination condition is currently met;

[0028] If the change period is determined to be less than the upper limit value, it is determined that the termination condition is not currently met.

[0029] Optionally, calculating the central rate of change for each of the load data elements includes:

[0030] The central rate of change is calculated according to formula (1):

[0031] (1)

[0032] in, The rate of change of the center, The number of sampling points included in the load data element. For the first One sampling point, It is the average value of the sampling points within the same load data element.

[0033] Optionally, the change period is updated, comprising:

[0034] The change period is updated according to formula (2):

[0035] , (2)

[0036] wherein, is the updated change period, is the change period before being updated, is an update gradient.

[0037] Optionally, a correlation between the current power distribution area and each of the remaining power distribution areas is determined according to the center change rate, comprising:

[0038] The center change rate is hierarchically coded to obtain a corresponding hierarchical code;

[0039] The time distance between the load data element of the current power distribution area and the load data element of the to-be-matched power distribution area is initialized;

[0040] The load data element of the current power distribution area and the load data element of the to-be-matched power distribution area are associated according to the time distance;

[0041] The hierarchical code difference of each two of the associated load data elements is calculated;

[0042] It is judged whether the hierarchical code difference is less than or equal to a preset minimum threshold value;

[0043] In a case where it is judged that the hierarchical code difference is less than or equal to the minimum threshold value, the currently associated load data element is taken as the correlation between the two power distribution areas;

[0044] In a case where it is judged that the hierarchical code difference is greater than the minimum threshold value, the time distance is updated, and the step of associating the load data element of the current power distribution area and the load data element of the to-be-matched power distribution area according to the time distance is executed again.

[0045] Optionally, the hierarchical code difference of each two of the associated load data elements is calculated, comprising:

[0046] The hierarchical code difference is updated according to formula (3):

[0047] , (3)

[0048] wherein, is the hierarchical code difference between the i th power distribution area and the j th power distribution area, ​​the number of load data elements, the change rate of the first load data element of the first power distribution area, the change rate of the first load data element of the first power distribution area, the change rate of the first load data element of the first power distribution area, the change rate of the first load data element of the first power distribution area, the change rate of the first load data element of the first power distribution area.

[0049] Optionally, updating the time distance comprises:

[0050] updating the time distance according to formula (4):

[0051] , (4)

[0052] wherein, is the updated time distance, is the time distance before updating, is the update step of the time distance.

[0053] In another aspect, the embodiments of the present application also provide a load data management system for enterprise middle station, the system comprising a processor configured to perform the method as described above.

[0054] Through the above technical solutions, the embodiments of the present application provide a load data management method and system for enterprise middle station, which analyzes the correlation of load data of each power distribution area in the region, combines the correlation to form a training sample set related to the power consumption load between two areas, and finally trains a general prediction model through the training sample set. The method and system reduce the cost of manpower and material resources, complete the prediction of large amount of load data of multiple power distribution areas by small amount of load data of a single power distribution area, and improve the management efficiency of load data in the region.

[0055] Other features and advantages of the embodiments of the present application will be described in detail in the following specific implementation part. BRIEF DESCRIPTION OF DRAWINGS

[0056] The accompanying drawings are included to provide a further understanding of the embodiments of the present application, and constitute a part of the specification, and are used together with the following specific implementation to explain the embodiments of the present application, but do not constitute a limitation on the embodiments of the present application. In the drawings:

[0057] Figure 1 is a flowchart of a load data management method for enterprise middle station according to an embodiment of the present application;

[0058] Figure 2 is a flowchart of a method for obtaining a minimum change period according to an embodiment of the present application;​

[0059] Figure 3 is a flow chart of a method for determining a correlation according to an embodiment of the present application;

[0060] Figure 4 is a schematic diagram of an interval length according to an example of the present application. DETAILED DESCRIPTION

[0061] The specific embodiments of the present application will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely intended to illustrate and explain the present application, and are not intended to limit the present application.

[0062] It should be noted that the acquisition, transmission, storage, use, processing, etc. of data in the technical solutions of the present application comply with relevant provisions of national laws and regulations. In the embodiments of the present application, some existing industry solutions such as software, components, models, etc. may be mentioned, which should be considered as exemplary, and the purpose is only to illustrate the feasibility of the implementation of the technical solutions of the present application, but it does not mean that the applicant has or will necessarily use the solutions.

[0063] As shown in Figure 1 is a flow chart of a load data management method for an enterprise middle station according to an embodiment of the present application. In this Figure 1 , the method can include the following steps:

[0064] In step S10, historical load data of each power distribution station in the current area is acquired;

[0065] In step S11, the minimum change period of each power distribution station is determined;

[0066] In step S12, the historical load data of each power distribution station is divided into a plurality of load data elements according to the minimum change period;

[0067] In step S13, the center change rate of each load data element is calculated;

[0068] In step S14, the correlation between the current power distribution station and each of the remaining power distribution stations is determined according to the center change rate;

[0069] In step S15, a sample data set for predicting each power distribution station is constructed according to the correlation;

[0070] In step S16, the sample data set is used to train a corresponding prediction model;

[0071] In step S17, the trained prediction model is used to predict the load data of each power distribution station;

[0072] In step S18, power supply control operations are performed based on load data.

[0073] In such Figure 1 In the method shown, step S10 can be used to obtain historical load data for each distribution substation within the current area. This historical load data can be collected data from the transformer groups of the distribution substations, statistically analyzed according to a time series.

[0074] Step S11 can be used to determine the minimum change period for each distribution substation. This minimum change period can represent a specific time length during which historical load data undergoes concentrated changes. The method for obtaining this minimum change period can take many forms known to those skilled in the art. In one example of the invention, the method for obtaining the minimum change period may include, for example... Figure 2 The steps shown are described. Figure 2 In this context, the method for obtaining the minimum change period may include the following steps:

[0075] In step S20, the initial change period is determined. Considering that a minimum change period that is too large would result in a smaller sample size in the subsequent dataset and impose additional requirements on the size of the prediction model, while a minimum change period that is too small would result in insufficient features provided by the subsequent samples, in this example, an upper limit and a lower limit can be preset when initializing the change period, with the initial change period set to the lower limit.

[0076] In step S21, the historical load data is divided into multiple load data elements according to the change cycle;

[0077] In step S22, the center change rate of each load data element is calculated. The specific calculation method for this center change rate can be of various forms known to those skilled in the art. In one example of the present invention, the center change rate can be calculated using the following formula (1):

[0078] (1)

[0079] in, For the central rate of change, The number of sampling points included in the load data element. For the first One sampling point, It represents the average value of the sampling points within the same load data element.

[0080] In step S23, it is judged whether the termination condition is met at present. The termination condition can be various forms known by those skilled in the art, and in this example, the termination condition can be judging whether the change period is greater than or equal to the upper limit value. If it is judged that the change period is greater than or equal to the upper limit value, it is determined that the termination condition is met at present; otherwise, if it is judged that the change period is less than the upper limit value, it is determined that the termination condition is not met at present.

[0081] In step S24, if it is judged that the termination condition is met at present, the change period with the lowest historical change rate is selected as the finally determined change period.

[0082] In step S25, if it is judged that the termination condition is not met at present, the change period is updated, and the step of calculating the center change rate of each load data element is executed, i.e., returning to step S21. The specific method of updating the change period can be various forms known by those skilled in the art. In one example of the present application, the change period can be updated by using formula (2):

[0083] , (2)

[0084] wherein, is the updated change period, is the change period before updating, is the update gradient.

[0085] Step S14 can be used to determine the correlation between the load data elements of the current distribution area and each of the remaining distribution areas according to the center change rate. The specific method of determining the correlation can be various forms known by those skilled in the art. In one example of the present application, the correlation can be determined by using the method shown in formula (3) as follows: Figure 3 Specifically, in the formula (3), Figure 3 the method of determining the correlation can include the following steps:

[0086] In step S30, the center change rate is hierarchically coded to obtain the corresponding level code;

[0087] In step S31, the time distance between the load data elements of the current distribution area and the load data elements of the distribution area to be matched is initialized;

[0088] In step S32, the load data elements of the current distribution area and the load data elements of the distribution area to be matched are associated according to the time distance;

[0089] In step S33, the level code difference of each two associated load data elements is calculated;

[0090] In step S34, it is judged whether the grade coding difference is less than or equal to a preset minimum threshold value;

[0091] In step S35, in the case that the grade coding difference is less than or equal to the minimum threshold value, the current associated load data element is taken as the correlation of the two power distribution areas;

[0092] In step S36, in the case that the grade coding difference is greater than the minimum threshold value, the time distance is updated, and the step of associating the current load data element of the power distribution area and the load data element of the power distribution area to be matched according to the time distance is executed, i.e., returning to step S32.

[0093] In the method as shown in the figure, Figure 3 Step S30 can be used for grading coding of the center change rate to obtain the corresponding grade coding. Since the numerical value of the center change rate has a relatively discrete numerical distribution when calculated, this is obviously not conducive to judging the correlation. Therefore, in this example, by using the grading coding method, the relatively discrete numerical distribution is converted into a grade coding with fewer discrete points, so that when the correlation is determined subsequently, the problem of numerical overflow does not occur.

[0094] Step S31 can be used for initializing the time distance of the current load data element of the power distribution area and the load data element of the power distribution area to be matched. The time distance can be the interval time length of the current load data element of the power distribution area and the load data element of the power distribution area to be matched in the time sequence. The schematic diagram of the interval time length can be as shown in the figure. Figure 4

[0095] Step S33 can be used for calculating the grade coding difference of each two associated load data elements. The specific calculation method of the grade coding difference can be various forms known by those skilled in the art. In one example of the present application, the following formula (3) can be used to update the grade coding difference:

[0096] , (3)

[0097] wherein, is the grade coding difference of the i th power distribution area and the j th power distribution area, is the number of load data elements, is the change rate of the i th load data element of the i th power distribution area, is the change rate of the i th load data element of the j th power distribution area.

[0098] ​​​​​​​Step S34 can be used to determine whether the level coding difference is less than or equal to a preset minimum threshold value. If the level coding difference is less than the minimum threshold value, it means that the correlation of the two load data elements is strong enough, so the current associated load data element can be directly used as the correlation of the two power distribution areas, i.e., step S35. Otherwise, it means that the current correlation strength is insufficient, so the time distance needs to be updated for further iteration calculation, i.e., step S36. The method for updating the time distance in step S36 can be various forms known to those skilled in the art. In an example of the present application, the following formula (4) can be used to update the time distance:

[0099] , (4)

[0100] wherein, is the updated time distance, is the time distance before updating, is the update step of the time distance.

[0101] On the other hand, the embodiments of the present application also provide a load data management system for enterprise substations, which comprises a processor configured to perform the method as described in any of the above. Specifically, the method can comprise the following steps:

[0102] In step S10, the historical load data of each power distribution area in the current area is obtained;

[0103] In step S11, the minimum change period of each power distribution area is determined;

[0104] In step S12, the historical load data of each power distribution area is divided into multiple load data elements according to the minimum change period;

[0105] In step S13, the center change rate of each load data element is calculated;

[0106] In step S14, the correlation of the load data elements of the current power distribution area and each of the remaining power distribution areas is determined according to the center change rate;

[0107] In step S15, a sample data set for predicting each power distribution area is constructed according to the correlation;

[0108] In step S16, the corresponding prediction model is trained using the sample data set;

[0109] In step S17, the trained prediction model is used to predict the load data of each power distribution area;

[0110] In step S18, power supply management operations are performed according to the load data.

[0111] In the method as shown in the figure, Figure 1 Step S10 can be used to obtain historical load data of each power distribution substation in the current region. The historical load data can be collected data of transformer groups of the power distribution substations according to time series.

[0112] Step S11 can be used to determine a minimum change period of each power distribution substation. The minimum change period can be used to represent a specific time length of centralized changes in the historical load data. The method for obtaining the minimum change period can be various forms known to those skilled in the art. In an example of the present application, the method for obtaining the minimum change period can include steps as shown in the figure. Figure 2 In the figure, Figure 2 The method for obtaining the minimum change period can include the following steps:

[0113] In step S20, the initial change period. Considering that the value of the minimum change period is too large, the number of samples in the subsequent sample data set is small, and the size of the prediction model is additionally required; while the value of the minimum change period is too small, the features provided by the subsequent samples are too few. Therefore, in this example, the upper limit value and the lower limit value can be preset when the change period is initially set, and the initial change period is set to the lower limit value.

[0114] In step S21, the historical load data is divided into a plurality of load data elements according to the change period.

[0115] In step S22, the center change rate of each load data element is calculated. The specific calculation method of the center change rate can be various forms known to those skilled in the art. In an example of the present application, the center change rate can be calculated using the following formula (1):

[0116] , (1)

[0117] Wherein, is the center change rate, is the number of sampling points included in the load data element, is the i-th sampling point, is the average value of the sampling points in the same load data element.

[0118] In step S23, it is determined whether the termination condition is met. The termination condition can be various forms known to those skilled in the art, and in this example, the termination condition can be whether the change period is greater than or equal to the upper limit value. In the case where the change period is greater than or equal to the upper limit value, it is determined that the termination condition is met; otherwise, in the case where the change period is less than the upper limit value, it is determined that the termination condition is not met.​

[0119] In step S24, in the case where it is judged that the termination condition is currently satisfied, the change period with the lowest history change rate is selected as the finally determined change period;

[0120] In step S25, in the case where it is judged that the termination condition is not currently satisfied, the change period is updated, and the step of calculating the center change rate of each load data element is executed, i.e., step S21 is returned to. The specific method of updating the change period can be various forms known to those skilled in the art. In an example of the present application, the change period can be updated by using formula (2):

[0121] , (2)

[0122] wherein, is the updated change period, is the change period before updating, is the updating gradient.

[0123] Step S14 can be used to determine the correlation relationship of the load data element of the current power distribution area and each of the remaining power distribution areas according to the center change rate. The specific method of determining the correlation relationship can be various forms known to those skilled in the art. In an example of the present application, the correlation relationship can be determined by using the method shown in formula (3) as follows: Figure 3 Specifically, in the formula (3), the method of determining the correlation relationship can include the following steps: Figure 3

[0124] In step S30, the center change rate is hierarchically coded to obtain the corresponding hierarchical code;

[0125] In step S31, the time distance of the load data element of the current power distribution area and the load data element of the power distribution area to be matched is initialized;

[0126] In step S32, the load data element of the current power distribution area and the load data element of the power distribution area to be matched are associated according to the time distance;

[0127] In step S33, the hierarchical code difference of each two associated load data elements is calculated;

[0128] In step S34, it is judged whether the hierarchical code difference is less than or equal to a preset minimum threshold value;

[0129] In step S35, in the case where it is judged that the hierarchical code difference is less than or equal to the minimum threshold value, the currently associated load data element is taken as the correlation relationship of the two power distribution areas;

[0130] ​In step S36, in the case that the level coding difference is greater than the minimum threshold, the time distance is updated, and the step of associating the load data element of the current power distribution substation with the load data element of the to-be-matched power distribution substation according to the time distance is executed, that is, step S32 is executed.

[0131] In the method as shown in the figure, Figure 3 In the method as shown in the figure,

[0132] Step S31 can be used to initialize the time distance of the load data element of the current power distribution substation and the load data element of the to-be-matched power distribution substation. The time distance can be the interval time length of the load data element of the current power distribution substation and the load data element of the to-be-matched power distribution substation in the time sequence. The schematic diagram of the interval time length can be as shown in the figure. Figure 4

[0133] Step S33 can be used to calculate the level coding difference of each two associated load data elements. The specific calculation method of the level coding difference can be various forms known by those skilled in the art. In one example of the present application, the following formula (3) can be used to update the level coding difference:

[0134] , (3)

[0135] wherein, is the level coding difference of the i th power distribution substation and the j th power distribution substation, is the number of load data elements, is the change rate of the i th load data element of the i th power distribution substation, is the change rate of the i th load data element of the i th power distribution substation.

[0136] ​​​​​​​Step S34 can be used to determine whether the level coding difference is less than or equal to a preset minimum threshold value. If the level coding difference is less than the minimum threshold value, it means that the correlation of the two load data elements is strong enough, and thus the current associated load data element can be directly used as the correlation of the two power distribution areas, i.e., step S35. Otherwise, it means that the current correlation strength is insufficient, and thus the time distance needs to be updated for further iteration calculation, i.e., step S36. The method for updating the time distance in step S36 can be various forms known by those skilled in the art. In an example of the present application, the following formula (4) can be used to update the time distance:

[0137] , (4)

[0138] wherein, is the updated time distance, is the time distance before updating, is the updating step of the time distance.

[0139] Through the above technical solution, the load data management and control method and system for enterprise middle platform provided by the embodiments of the present application analyze the correlation of the load data of each power distribution area in the region, combine the correlation to form a training sample set of the correlation between the power load of two areas, and finally train a general prediction model through the training sample set. The method and system reduce the labor and material costs, complete the prediction of the large amount of load data of multiple power distribution areas by the small amount of load data of a single power distribution area, and thus improve the management and control efficiency of the load data in the region.

[0140] 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 adopt a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer usable storage media containing computer usable program code (including but not limited to disk storage, CD-ROM, optical storage, etc.).

[0141] The present application is described with reference to flowcharts and / or block diagrams according to the methods, devices (systems), and computer program products of the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices produce a device that implements the flowcharts and / or block diagrams. Figure 1one or more processes and / or blocks Figure 1 an apparatus with the functionality to achieve the specified processes or functions in the block or blocks.

[0142] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the Figure 1 one or more processes and / or blocks Figure 1 an apparatus with the functionality to achieve the specified processes or functions in the block or blocks.

[0143] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the Figure 1 one or more processes and / or blocks Figure 1 an apparatus with the functionality to achieve the specified processes or functions in the block or blocks.

[0144] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0145] The memory can include non-persistent memory and / or volatile memory, such as random access memory (RAM) about which the processor can execute instructions. The memory can also include non-volatile memory, such as read only memory (ROM), electrically programmable read only memory (EPROM), electrically erasable programmable read only memory (EEPROM), programmable read only memory (PROM), or flash memory, for example. Memory is an example of computer readable media.

[0146] Computer readable media includes permanent and non-permanent, removable and non-removable media implemented in any method or technology for storage of information such as 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 programmable read only memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital versatile discs (DVDs) or other optical storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to computing devices. According to the definition herein, computer readable media does not include transitory media, such as modulated data signals and carrier waves.

[0147] It should also be noted that the terms "comprising", "comprises" or other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus.

[0148] The above embodiments are only used to illustrate the present application, but not to limit it. Instead of the above, various modifications and changes can be made to the application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the application shall fall into the scope of the claims of the application.

Claims

1. A load data management method for an enterprise middle platform, characterized in that, The method comprises: obtaining historical load data of each power distribution station in a current area; determining a minimum change period of each power distribution station; dividing the historical load data of each power distribution station into a plurality of load data units according to the minimum change period; calculating a central change rate of each load data unit; determining a correlation between the current power distribution station and each of the remaining power distribution stations according to the central change rate; constructing a sample data set for predicting each power distribution station according to the correlation; training a corresponding prediction model using the sample data set; predicting load data of each power distribution station using the trained prediction model; performing power supply control operations according to the load data; determining a minimum change period of each power distribution station, comprising: an initial change period; dividing the historical load data into a plurality of load data units according to the change period; calculating a central change rate of each load data unit; determining whether the current satisfies a termination condition; in the case where it is determined that the current satisfies the termination condition, selecting the change period with the lowest historical change rate as the finally determined change period; in the case where it is determined that the current does not satisfy the termination condition, updating the change period and returning to the step of calculating the central change rate of each load data unit; calculating a central change rate of each load data unit, comprising: calculating the central change rate according to formula (1): ，（1） wherein, is the center rate of change, is the number of sampling points comprised by the load data element, is the first sampling point, is the average value of the sampling points within the same load data element; determining a correlation between the current power distribution station and each of the remaining power distribution stations according to the central change rate, comprising: grading coding the central change rate to obtain corresponding grade coding; initializing a time distance between the load data unit of the current power distribution station and the load data unit of the power distribution station to be matched; associating the load data unit of the current power distribution station and the load data unit of the power distribution station to be matched according to the time distance; calculating a grade coding difference between each two associated load data units; determining whether the grade coding difference is less than or equal to a preset minimum threshold value; in the case where it is determined that the grade coding difference is less than or equal to the minimum threshold value, taking the currently associated load data unit as the correlation between the two power distribution stations; in the case where it is determined that the grade coding difference is greater than the minimum threshold value, updating the time distance and returning to the step of associating the load data unit of the current power distribution station and the load data unit of the power distribution station to be matched according to the time distance.

2. The method of claim 1, wherein, an initial change period, comprising: constructing an upper limit value and a lower limit value of the change period; setting the initial change period as the lower limit value.

3. The method of claim 2, wherein, determining whether the current satisfies a termination condition, comprising: determining whether the change period is greater than or equal to the upper limit value; in the case where it is determined that the change period is greater than or equal to the upper limit value, determining that the current satisfies the termination condition; in the case where it is determined that the change period is less than the upper limit value, determining that the current does not satisfy the termination condition.

4. The method of claim 1, wherein, updating the change period, comprising: updating the change period according to formula (2): ，（2） wherein, is the updated change period, is the change period before update, is the update gradient.

5. The method of claim 4, wherein, calculating a grade coding difference between each two associated load data units, comprising: updating the rank encoding difference according to equation (3): ，（3） in, For the first Each distribution station area and the first The level coding difference of each distribution radio station area The number of load data elements, For the first The first distribution radio zone The rate of change of each load data element For the first The first distribution radio zone Rate of change of each load data element.

6. The method of claim 5, wherein, updating the temporal distance, including: updating the temporal distance according to equation (4): ，（4） wherein, is the time distance after the update, is the time distance before the update, is the update step of the time distance.

7. A load data management system for an enterprise middle platform, characterized in that, The system comprises a processor configured to perform the method of any one of claims 1 to 6.

Images