Load prediction method

Abstract

The embodiment of the invention discloses a load prediction method. The method comprises the steps that first power utilization data corresponding to a plurality of to-be-divided power utilization objects associated with a target station area are acquired, and the first power utilization data are power utilization data of the corresponding to-be-divided power utilization objects in a first time period; dividing the plurality of to-be-divided power utilization objects according to the first power utilization data corresponding to the plurality of to-be-divided power utilization objects to obtain at least one long-term power utilization object and at least one short-term power utilization object; according to the first power consumption data corresponding to the at least one short-term power consumption object, determining the fluctuation power consumption of the first time period; and according to the fluctuation power consumption and the first power consumption data corresponding to the at least one long-term power consumption object, first load prediction data of the target transformer area in a to-be-predicted time period is determined, and the to-be-predicted time period is associated with the first time period. According to the technical scheme of the embodiment of the invention, the accuracy of load prediction is improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of electric power technology, and in particular to a load forecasting method. Background Art

[0002] In the power system, a substation usually refers to the power supply range or area of ​​a transformer, which is used to describe the power supply area of ​​the transformer. According to the different load types, substations can be divided into four categories: urban residential substations, commercial substations, industrial substations and agricultural substations. These different types of substations differ in power supply demand, load characteristics and management requirements.

[0003] With the development of economy and society, the grid load in the substation has increased sharply, and the load in some areas is dense, resulting in the planned capacity of the transformer in the substation being unable to meet the surge in power load, which brings great challenges to the stable operation of the substation power grid.

[0004] The existing power grid in the substation area intervenes in the power grid in advance by predicting the load of the substation area, thereby ensuring the stable operation of the power grid in the substation area. However, the prediction accuracy of the existing load forecasting method is not high, which needs to be solved urgently. Summary of the invention

[0005] The embodiment of the present invention provides a load forecasting method, which improves the accuracy of load forecasting.

[0006] According to one aspect of the present invention, a load forecasting method is provided, which may include:

[0007] Acquire first power consumption data corresponding to a plurality of power consumption objects to be divided associated with the target substation, wherein the first power consumption data is power consumption data of the corresponding power consumption objects to be divided in a first time period;

[0008] Dividing the plurality of power consumption objects to be divided according to the first power consumption data respectively corresponding to the plurality of power consumption objects to be divided, to obtain at least one long-term power consumption object and at least one short-term power consumption object;

[0009] Determine the fluctuating power consumption in the first time period according to the first power consumption data respectively corresponding to at least one short-term power consumption object;

[0010] According to the fluctuating power consumption and the first power consumption data respectively corresponding to at least one long-term power consumption object, the first load forecast data of the target substation in the time period to be predicted is determined, wherein the time period to be predicted is associated with the first time period.

[0011] The technical solution of the embodiment of the present invention is to obtain first power consumption data corresponding to multiple power consumption objects to be divided that are associated with the target substation, wherein the first power consumption data is the power consumption data of the corresponding power consumption objects to be divided in a first time period, so as to facilitate load prediction through the first power consumption data; by dividing the multiple power consumption objects to be divided according to the first power consumption data corresponding to the multiple power consumption objects to be divided, at least one long-term power consumption object and at least one short-term power consumption object are obtained, so as to realize long-term and short-term division of the power consumption objects to be divided; by determining the fluctuating power consumption in the first time period according to the first power consumption data corresponding to at least one short-term power consumption object, so as to realize the determination of unstable fluctuating power consumption; by determining the first load prediction data of the target substation in the time period to be predicted according to the fluctuating power consumption and the first power consumption data corresponding to at least one long-term power consumption object, wherein the time period to be predicted is associated with the first time period, so as to realize the prediction of the load of the target substation in the time period to be predicted. The above technical scheme determines the first load forecast data of the target substation within the forecast period by determining the fluctuating power consumption based on the first power consumption data corresponding to at least one short-term power consumer and the first power consumption data corresponding to at least one long-term power consumer. This effectively uses the fluctuating power consumption that characterizes the unstable power consumption characteristics of the short-term power consumer as a reference factor for load forecasting, thereby improving the accuracy of load forecasting.

[0012] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0014] Figure 1 is a flow chart of a load forecasting method provided according to an embodiment of the present invention;

[0015] Figure 2 is a flow chart of another load forecasting method provided according to an embodiment of the present invention;

[0016] Figure 3 is a flow chart of another load forecasting method provided according to an embodiment of the present invention;

[0017] Figure 4 is a structural diagram of an optional example of another load forecasting method provided according to an embodiment of the present invention;

[0018] Figure 5 is a flow chart of an optional example of another load forecasting method provided according to an embodiment of the present invention;

[0019] Figure 6 is a structural block diagram of a load forecasting device provided according to an embodiment of the present invention;

[0020] Figure 7 It is a structural schematic diagram of an electronic device for implementing the load forecasting method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0022] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. The situations of "target", "original", etc. are similar and will not be repeated here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0023] Figure 1 1 is a flow chart of a load forecasting method provided in an embodiment of the present invention. This embodiment is applicable to the case of load forecasting in a substation. The method can be executed by a load forecasting device provided in an embodiment of the present invention, which can be implemented by software and / or hardware, and can be integrated in an electronic device, which can be various user terminals or servers.

[0024] See also Figure 1 The method of the embodiment of the present invention specifically includes the following steps:

[0025] S110, obtaining first power usage data corresponding to a plurality of power usage objects to be classified associated with the target substation, wherein the first power usage data is power usage data of the corresponding power usage objects to be classified in a first time period.

[0026] The target substation is the substation for which load forecasting is to be performed. The power consumption object to be divided is the object for power consumption within the power supply area of ​​the target substation. The first time period is the power consumption time period corresponding to the first power consumption data; the first time period may be, for example, a single day, a single week, or a single month, etc.; the number of the first time periods may be one or more. It may include at least one of the total power consumption of the power consumption object to be divided corresponding to the first time period and the power consumption corresponding to each third time period in the first time period, etc.

[0027] Exemplarily, the time period collection data of the fourth time period in the form of a time series or a form of expression that can be converted into a time series can be obtained. The fourth time period can be a single historical year, for example, it can be the time period corresponding to the previous year. The time period collection data can be, for example, the annual electricity consumption collection data obtained through the smart meter to which the target substation belongs. Among them, the fourth time period includes at least one first time period, and the time period collection data includes at least one set of first electricity consumption data. In the embodiment of the present invention, there is no specific limitation on the method of obtaining the first electricity consumption data corresponding to the multiple electricity consumption objects to be divided associated with the target substation.

[0028] S120. Divide the multiple power consumption objects to be divided according to the first power consumption data respectively corresponding to the multiple power consumption objects to be divided, and obtain at least one long-term power consumption object and at least one short-term power consumption object.

[0029] Among them, the long-term electricity user is an electricity user to be classified with relatively stable electricity consumption and obvious periodic changes. For example, the long-term electricity user can be an object with periodic stable electricity consumption characteristics in the fourth time period. The short-term electricity user is an object with unstable electricity consumption. For example, the short-term electricity user can be an object that does not have periodic stable electricity consumption characteristics in the fourth time period.

[0030] In an embodiment of the present invention, for each of the multiple power consumption objects to be divided, an object power consumption curve of the power consumption object to be divided can be generated according to one or more groups of first power consumption data of the power consumption object to be divided, and the object power consumption curve can characterize the change of power consumption of the power consumption object to be divided; according to the object power consumption curves respectively corresponding to the multiple power consumption objects to be divided, the multiple power consumption objects to be divided are divided to obtain at least one long-term power consumption object and at least one short-term power consumption object. In an embodiment of the present invention, there is no specific limitation on the manner in which the multiple power consumption objects to be divided are divided according to the first power consumption data respectively corresponding to the multiple power consumption objects to be divided to obtain at least one long-term power consumption object and at least one short-term power consumption object.

[0031] S130. Determine the fluctuating power consumption in the first time period according to the first power consumption data corresponding to at least one short-term power consumption object.

[0032] Among them, fluctuating electricity consumption refers to the electricity consumption that may fluctuate during the forecast period.

[0033] In an embodiment of the present invention, the power consumption represented by the first power consumption data corresponding to the plurality of power consumption objects to be divided can be summed. For example, when the first time period is a single day, the power consumption within the same day corresponding to the first time period is summed to obtain the total power consumption of the first time period; the power consumption represented by the first power consumption data corresponding to at least one short-term power consumption object is summed to obtain the short-term power consumption of the first time period; the proportion of the short-term power consumption in the total power consumption of the time period is used as the weighted ratio; the proportion of the number of at least one short-term power consumption object in the plurality of power consumption objects to be divided is used as the weighted ratio; the weighted ratio and the weighted ratio are summed or multiplied to obtain the target ratio; the product between the target ratio and the total power consumption of the time period is used as the fluctuating power consumption of the first time period. The power consumption represented by the first power consumption data corresponding to at least one short-term power consumption object can also be summed to obtain the short-term power consumption of the first time period; the short-term power consumption is used as the fluctuating power consumption. In an embodiment of the present invention, there is no specific limitation on the method of determining the fluctuating power consumption of the first time period according to the first power consumption data corresponding to at least one short-term power consumption object.

[0034] S140. Determine first load forecast data of a target substation within a time period to be predicted based on the fluctuating power consumption and first power consumption data corresponding to at least one long-term power consumption object, wherein the time period to be predicted is associated with the first time period.

[0035] Among them, the period to be predicted is the period for which the load forecast is required; the period to be predicted is associated with the first period, for example, if the first period is a single day corresponding to October 10, 2024, the period to be predicted can be a single day corresponding to October 10, 2025, and for another example, if the first period is a single day corresponding to November 10, 2024, the period to be predicted can be a single day corresponding to December 10, 2024, and so on. The association between the period to be predicted and the first period is not specifically limited. The first load forecast result can be a forecast result corresponding to the target substation power consumption or power consumption range in the period to be predicted associated with the first period.

[0036] In an embodiment of the present invention, the power consumption represented by the first power consumption data corresponding to at least one long-term power consumption object can be summed to obtain the long-term power consumption; the long-term power consumption and the fluctuating power consumption can be summed to obtain the summed power consumption; the summed power consumption can be used as the first load forecast data, and the power consumption interval composed of the summed power consumption and the long-term power consumption can be used as the first load forecast data. In an embodiment of the present invention, there is no specific limitation on the method of determining the first load forecast data of the target substation within the forecast period based on the fluctuating power consumption and the first power consumption data corresponding to at least one long-term power consumption object.

[0037] In an embodiment of the present invention, when there are multiple first time periods, alternative load forecast data corresponding to each first time period can be determined based on the fluctuating power consumption and the first power consumption data corresponding to at least one long-term power consumption object; and from the alternative load forecast data corresponding to at least one first time period, the alternative load forecast data of the first time period associated with the time period to be predicted is determined as the first load forecast data of the target substation in the time period to be predicted.

[0038] The technical solution of the embodiment of the present invention is to obtain first power consumption data corresponding to multiple power consumption objects to be divided that are associated with the target substation, wherein the first power consumption data is the power consumption data of the corresponding power consumption objects to be divided in a first time period, so as to facilitate load prediction through the first power consumption data; by dividing the multiple power consumption objects to be divided according to the first power consumption data corresponding to the multiple power consumption objects to be divided, at least one long-term power consumption object and at least one short-term power consumption object are obtained, so as to realize long-term and short-term division of the power consumption objects to be divided; by determining the fluctuating power consumption in the first time period according to the first power consumption data corresponding to at least one short-term power consumption object, so as to realize the determination of unstable fluctuating power consumption; by determining the first load prediction data of the target substation in the time period to be predicted according to the fluctuating power consumption and the first power consumption data corresponding to at least one long-term power consumption object, wherein the time period to be predicted is associated with the first time period, so as to realize the prediction of the load of the target substation in the time period to be predicted. The above technical scheme determines the first load forecast data of the target substation within the forecast period by determining the fluctuating power consumption based on the first power consumption data corresponding to at least one short-term power consumer and the first power consumption data corresponding to at least one long-term power consumer. This effectively uses the fluctuating power consumption that characterizes the unstable power consumption characteristics of the short-term power consumer as a reference factor for load forecasting, thereby improving the accuracy of load forecasting.

[0039] In order to better understand the technical solution of the above-mentioned embodiment of the present invention, an optional example is provided herein. Exemplarily, first power consumption data corresponding to at least one first time period respectively corresponding to multiple power consumption objects to be divided and associated with the target substation are obtained; according to the first power consumption data corresponding to the multiple power consumption objects to be divided and respectively corresponding to at least one first time period respectively, the multiple power consumption objects to be divided are divided to obtain at least one long-term power consumption object and at least one short-term power consumption object; according to the first power consumption data corresponding to the first time period associated with the time period to be predicted in at least one first time period respectively corresponding to at least one short-term power consumption object, the fluctuating power consumption of the first time period associated with the time period to be predicted in at least one first time period is determined; according to the fluctuating power consumption and the first power consumption data corresponding to the first time period associated with the time period to be predicted in at least one first time period respectively corresponding to at least one long-term power consumption object, the first load prediction data of the target substation in the time period to be predicted is determined. It should be noted that the above scheme will use all the first electricity consumption data only when dividing multiple electricity consumption objects to be divided and obtaining at least one long-term electricity consumption object and at least one short-term electricity consumption object. When determining the fluctuating electricity consumption and determining the first load forecast data, only the first electricity consumption data corresponding to the first time period associated with the time period to be predicted in at least one first time period can be used. Correspondingly, when determining the fluctuating electricity consumption and determining the first load forecast data, all the first electricity consumption data can be used to determine the fluctuating electricity consumption corresponding to at least one first time period and then determine the alternative load forecast data corresponding to at least one first time period. From the alternative load forecast data corresponding to at least one first time period, the alternative load forecast data of the first time period associated with the time period to be predicted is determined as the first load forecast data of the target substation in the time period to be predicted.

[0040] An optional technical solution determines the first load forecast data of the target substation within the time period to be predicted based on the first electricity consumption data corresponding to the fluctuating electricity consumption and at least one long-term electricity consumption object, including: determining the long-term electricity consumption in the first time period based on the first electricity consumption data corresponding to at least one long-term electricity consumption object; determining the first load forecast data of the target substation within the time period to be predicted based on the fluctuating electricity consumption and the long-term electricity consumption.

[0041] The long-term electricity consumption is the total electricity consumption of at least one long-term electricity user in the first time period.

[0042] In an embodiment of the present invention, the power consumption represented by the first power consumption data corresponding to at least one long-term power consumption object may be summed to obtain the long-term power consumption. In an embodiment of the present invention, there is no specific limitation on the method of determining the long-term power consumption in the first period based on the first power consumption data corresponding to at least one long-term power consumption object.

[0043] In an embodiment of the present invention, the long-term power consumption and the fluctuating power consumption may be summed to obtain the summed power consumption, and the summed power consumption may be used as the first load forecast data, or the interval formed by the summed power consumption and the long-term power consumption may be used as the first load forecast data; the preset ratio may be multiplied by the fluctuating power consumption to obtain the ratio power consumption, and the long-term power consumption and the ratio power consumption may be summed to obtain the summed power consumption, and the summed power consumption may be used as the first load forecast data, or the interval formed by the summed power consumption and the long-term power consumption may be used as the first load forecast data. In an embodiment of the present invention, there is no specific limitation on the method of determining the first load forecast data of the target substation in the period to be predicted based on the fluctuating power consumption and the long-term power consumption.

[0044] In an embodiment of the present invention, by determining the first load forecast data based on the determined fluctuating power consumption and long-term power consumption, it is achieved that the fluctuating power consumption that characterizes the unstable power consumption characteristics of short-term power users and the long-term power consumption that characterizes the stable power consumption characteristics of long-term power users are used as reference factors for load forecasting, thereby improving the accuracy of load forecasting.

[0045] Figure 2 It is a flowchart of another load forecasting method provided in an embodiment of the present invention. This embodiment is optimized based on the above-mentioned technical solutions. In this embodiment, optionally, according to the first power consumption data respectively corresponding to the multiple power consumption objects to be divided, multiple power consumption objects to be divided are divided to obtain at least one long-term power consumption object and at least one short-term power consumption object, including: for each of the multiple power consumption objects to be divided, according to the first power consumption data of the power consumption object to be divided, the power consumption growth of the power consumption object to be divided is determined; according to the power consumption growth corresponding to the multiple power consumption objects to be divided, the multiple power consumption objects to be divided are divided to obtain at least one long-term power consumption object and at least one short-term power consumption object. Among them, the explanations of the terms that are the same or corresponding to the above-mentioned embodiments are not repeated here.

[0046] See also Figure 2 The method of this embodiment may specifically include the following steps:

[0047] S210, obtaining first power usage data corresponding to a plurality of power usage objects to be classified associated with the target substation, wherein the first power usage data is power usage data of the corresponding power usage objects to be classified in a first time period.

[0048] S220. For each of the multiple power consumption objects to be classified, determine the power consumption growth of the power consumption object to be classified according to the first power consumption data of the power consumption object to be classified.

[0049] The electricity consumption growth situation may characterize the growth change of the total electricity consumption of the electricity consumption object to be classified in the first time period.

[0050] In the embodiment of the present invention, for example, the object power consumption curve of the power consumption object to be divided can be determined based on the first power consumption data of the power consumption object to be divided, and the power consumption growth of the power consumption object to be divided can be determined based on the change of the object power consumption curve. In the embodiment of the present invention, the method of determining the power consumption growth of the power consumption object to be divided based on the first power consumption data of the power consumption object to be divided is not specifically limited.

[0051] S230. Divide the multiple power users to be divided according to the power consumption growth conditions respectively corresponding to the multiple power users to be divided, and obtain at least one long-term power user and at least one short-term power user.

[0052] In an embodiment of the present invention, for example, among multiple power users to be divided, the power users to be divided whose power consumption growth is characterized by a power consumption growth of a preset duration within a first time period can be taken as a long-term power user object to obtain at least one long-term power user object, and the other power users to be divided among the multiple power users to be divided except the long-term power users can be taken as short-term power users to obtain at least one short-term power user object. In an embodiment of the present invention, there is no specific limitation on the manner of dividing the multiple power users to be divided according to the power consumption growth conditions respectively corresponding to the multiple power users to be divided to obtain at least one long-term power user object and at least one short-term power user object.

[0053] S240: Determine the fluctuating power consumption in the first time period according to the first power consumption data corresponding to at least one short-term power consumption object.

[0054] S250. Determine first load forecast data of a target substation within a time period to be predicted based on the fluctuating power consumption and first power consumption data corresponding to at least one long-term power consumption object, wherein the time period to be predicted is associated with the first time period.

[0055] The technical solution of the embodiment of the present invention divides multiple electricity users to be divided according to the electricity consumption growth situations corresponding to the multiple electricity users to be divided, and obtains at least one long-term electricity user and at least one short-term electricity user. This can make the division of long-term electricity users and short-term electricity users more suitable for subsequent load forecasting, thereby improving the accuracy of load forecasting.

[0056] An optional technical solution, the number of first time periods is at least one; multiple power users to be divided are divided according to the power consumption growth corresponding to the multiple power users to be divided, so as to obtain at least one long-term power user and at least one short-term power user, including: according to the power consumption growth corresponding to the multiple power users to be divided in at least one first time period, multiple power users to be divided are divided to obtain at least one long-term power user and at least one short-term power user.

[0057] In an embodiment of the present invention, taking into account that when the duration of the first time period is short, there may be little difference in the electricity consumption growth situations of long-term electricity users and short-term electricity users, or even the electricity consumption growth rate represented by the electricity consumption growth situation of the short-term electricity users is greater than the electricity consumption growth rate represented by the electricity consumption growth situation of the long-term electricity users, etc., which may lead to the problem of inaccurate division of long-term electricity users and short-term electricity users. According to the electricity consumption growth situations corresponding to the multiple electricity users to be divided in at least one first time period, at least one long-term electricity user and at least one short-term electricity user are obtained, thereby improving the accuracy of the division of long-term electricity users and short-term electricity users, and further making the division of long-term electricity users and short-term electricity users more suitable for subsequent load forecasting, thereby further improving the accuracy of load forecasting.

[0058] On the basis of the above scheme, another optional technical scheme is to divide multiple electricity users to be divided according to their corresponding electricity consumption growth in at least one first time period to obtain at least one long-term electricity user and at least one short-term electricity user, including: taking the multiple electricity users to be divided whose electricity consumption growth in each first time period is characterized by an electricity consumption growth of a preset duration as the long-term electricity user to obtain at least one long-term electricity user; taking the other electricity users to be divided among the multiple electricity users to be divided except the long-term electricity users as the short-term electricity users to obtain at least one short-term electricity user.

[0059] It is understandable that long-term electricity users usually have relatively stable electricity consumption and obvious periodic changes. For example, long-term electricity users may have relatively stable electricity consumption and obvious periodic changes due to the long-term use of household appliances such as refrigerators, and electricity-consuming activities such as turning on lights or watching TV at night. That is, as the user continues to use electricity, the amount of electricity used will also continue to increase. Therefore, among the multiple electricity users to be divided, the electricity users to be divided whose electricity consumption growth in each first time period is characterized by an increase in electricity consumption for a preset period of time can be regarded as long-term electricity users; short-term electricity users may have large fluctuations in electricity consumption due to various reasons such as holding activities, and have unstable characteristics. Therefore, among the multiple electricity users to be divided, except for the long-term electricity users, the other electricity users to be divided except for the long-term electricity users can be regarded as short-term electricity users.

[0060] The preset duration is the preset duration for treating the electricity consumption growth demand of the electricity user to be classified as a long-term electricity user.

[0061] In an embodiment of the present invention, for each of the multiple electricity consumption objects to be divided, based on the electricity consumption growth corresponding to the electricity consumption object to be divided in at least one first time period, it is determined that if the object electricity consumption curve of the electricity consumption object to be divided indicates that there is an electricity consumption growth of a preset duration in each first time period, the electricity consumption object to be divided will be treated as a long-term electricity consumption object; otherwise, the electricity consumption object to be divided will be treated as a short-term electricity consumption object.

[0062] In an embodiment of the present invention, among multiple electricity users to be divided, the electricity users to be divided whose electricity consumption growth situation in each first time period is characterized by an electricity consumption growth of a preset duration are selected as long-term electricity users to obtain at least one long-term electricity user object, and the other electricity users to be divided among the multiple electricity users to be divided except the long-term electricity users are selected as short-term electricity users to obtain at least one short-term electricity user object, thereby improving the accuracy of the division between long-term electricity users and short-term electricity users, and further making the division between long-term electricity users and short-term electricity users more suitable for subsequent load forecasting, thereby further improving the accuracy of load forecasting.

[0063] Before introducing the embodiments of the present invention, an exemplary explanation is given of the implementation process of the current load forecasting scheme and the reasons why the problem of low prediction accuracy of the load forecasting method exists, so as to better understand why the scheme proposed in the embodiments of the present invention improves the accuracy of load forecasting.

[0064] For example, with the development of the economy and society, the grid load in substations, especially residential substations, has risen sharply. The load in some areas is dense, resulting in the inability of the planned capacity of substation transformers to meet the surge in power load. In addition, the load shows strong seasonal and cyclical fluctuations, and the peak-valley load difference has intensified, posing great challenges to the stable operation of the substation power grid.

[0065] The existing power grid in the substation area intervenes in the power grid in advance by predicting the load of the substation area, thereby ensuring the stable operation of the power grid in the substation area. However, the existing load prediction method often predicts the total power load of a single day based on the historical power consumption data of the substation area. This load prediction method lacks the prediction of power consumption in different periods of a single day, and has the defect of inaccurate prediction. Especially for residential substations, there are some residents whose power consumption fluctuates greatly due to various reasons, such as temporary residence or commercial activities, which can easily affect the prediction accuracy of the substation area load. Therefore, the prediction accuracy of the existing load prediction method is not high.

[0066] In view of this, the embodiment of the present invention determines the first load forecast data of the target substation in the forecast period by determining the fluctuating power consumption according to the first power consumption data corresponding to at least one short-term power consumption object and the first power consumption data corresponding to at least one long-term power consumption object, thereby effectively using the fluctuating power consumption that characterizes the unstable power consumption characteristics of the short-term power consumption object as a reference factor for load forecasting, thereby realizing the forecast of the total load in the forecast period, and can also predict the second load forecast data that characterizes the changes in power load in different periods in the forecast period, which can effectively reduce the impact of load changes caused by seasonal changes, thereby improving the accuracy of load forecasting. This will be explained in detail below.

[0067] Figure 3 It is a flow chart of another load forecasting method provided in an embodiment of the present invention. This embodiment is optimized based on the above-mentioned technical solutions. In this embodiment, optionally, the load forecasting method also includes: obtaining the predicted temperature data of the time period to be predicted, at least one temperature gradient, and the alternative prediction results corresponding to at least one temperature gradient, and determining the target gradient corresponding to the predicted temperature data from at least one temperature gradient; using the alternative prediction result corresponding to the target gradient in the alternative prediction results corresponding to at least one temperature gradient as the second load forecast data of the target substation in the time period to be predicted.

[0068] The explanations of the terms that are the same as or corresponding to the above embodiments are not repeated here.

[0069] See also Figure 3 The method of this embodiment may specifically include the following steps:

[0070] S310, obtaining first power usage data corresponding to a plurality of power usage objects to be classified associated with the target substation, wherein the first power usage data is power usage data of the corresponding power usage objects to be classified in a first time period.

[0071] S320. Divide the multiple power consumption objects to be divided according to the first power consumption data respectively corresponding to the multiple power consumption objects to be divided, and obtain at least one long-term power consumption object and at least one short-term power consumption object.

[0072] S330: Determine the fluctuating power consumption in the first time period according to the first power consumption data corresponding to at least one short-term power consumption object.

[0073] S340, determining first load forecast data of the target substation within the time period to be predicted based on the fluctuating power consumption and the first power consumption data corresponding to at least one long-term power consumption object, wherein the time period to be predicted is associated with the first time period.

[0074] S350, obtaining predicted temperature data of a time period to be predicted, at least one temperature gradient, and candidate prediction results corresponding to at least one temperature gradient, and determining a target gradient corresponding to the predicted temperature data from the at least one temperature gradient.

[0075] Among them, the predicted temperature data is the predicted temperature data of the time period to be predicted; the predicted temperature data may include at least one of the average temperature of the time period to be predicted, the lowest temperature, the highest temperature, the temperature of each third time period in the time period to be predicted, the temperature observation values ​​corresponding to the observation time in the time period to be predicted, etc.; the predicted temperature data may be obtained according to the weather forecast, or may be predicted by other methods, which is not specifically limited here. The temperature gradient is the gradient of the temperature interval, and a temperature gradient can correspond to a temperature gradient interval. The alternative prediction result is an alternative prediction result as the second load prediction data; the alternative prediction result can be expressed in the form of a curve, for example, the alternative prediction result may include a power consumption reference curve. The target gradient is the temperature gradient corresponding to the predicted temperature data.

[0076] In the embodiment of the present invention, the average temperature of the predicted temperature data may be determined, and the temperature gradient corresponding to the gradient interval in which the average temperature is located is used as the target gradient. In the embodiment of the present invention, the method of determining the target gradient corresponding to the predicted temperature data from at least one temperature gradient is not specifically limited.

[0077] S360: Use the alternative prediction result corresponding to the target gradient among the alternative prediction results corresponding to at least one temperature gradient as the second load prediction data of the target substation in the time period to be predicted.

[0078] The technical solution of the embodiment of the present invention uses the alternative prediction results corresponding to the target gradient in the alternative prediction results corresponding to at least one temperature gradient as the second load prediction data of the target substation within the time period to be predicted, so as to predict the second load prediction data representing the changes in the power load in different time periods within the time period to be predicted, which can effectively reduce the impact of load changes caused by temperature changes, thereby improving the accuracy of load prediction.

[0079] An optional technical solution, the number of first time periods is at least one; the load prediction method also includes: obtaining temperature data corresponding to at least one first time period, and determining at least one temperature gradient based on the temperature data corresponding to at least one first time period; for each temperature gradient in at least one temperature gradient, determining a second time period of the temperature gradient from at least one first time period based on the temperature data corresponding to at least one first time period, and determining an alternative prediction result of the temperature gradient based on the first power consumption data corresponding to at least one long-term power user in the second time period.

[0080] The temperature data is data related to the temperature of the first period; the temperature data may include at least one of the average temperature of the first period, the lowest temperature, the highest temperature, the temperature of each third period in the first period, the temperature observation values ​​corresponding to the observation time in the first period, etc. The second period is the first period in which the temperature data matches the temperature gradient in at least one first period.

[0081] In the embodiment of the present invention, for example, at least one temperature gradient is determined based on the gradient value, the maximum temperature and the minimum temperature in the temperature data corresponding to at least one first time period; for another example, the average temperature corresponding to at least one first time period can be determined based on the temperature data corresponding to at least one first time period, and at least one temperature gradient can be determined based on the minimum temperature and the gradient value in the average temperature corresponding to at least one first time period. In the embodiment of the present invention, the method of determining at least one temperature gradient based on the temperature data corresponding to at least one first time period is not specifically limited.

[0082] In the embodiment of the present invention, the average temperature corresponding to at least one first time period can be determined according to the temperature data corresponding to at least one first time period; for each temperature gradient in at least one temperature gradient, the first time period in which the average temperature is located in the gradient interval corresponding to the temperature gradient in at least one first time period is taken as the second time period of the temperature gradient. In the embodiment of the present invention, the method of determining the second time period of the temperature gradient from at least one first time period according to the temperature data corresponding to at least one first time period is not specifically limited.

[0083] In an embodiment of the present invention, for example, the first power consumption data corresponding to at least one long-term power consumption object in the second time period may be aggregated and integrated to obtain an alternative prediction result of the temperature gradient. In an embodiment of the present invention, there is no specific limitation on the method of determining the alternative prediction result of the temperature gradient based on the first power consumption data corresponding to at least one long-term power consumption object in the second time period.

[0084] In an embodiment of the present invention, by determining at least one temperature gradient based on temperature data corresponding to at least one first time period, and determining a second time period corresponding to at least one temperature gradient, and determining an alternative prediction result of the temperature gradient based on first power consumption data corresponding to at least one long-term power user in the second time period, accurate determination of at least one temperature gradient and an alternative prediction result corresponding to at least one temperature gradient can be achieved.

[0085] Based on the above scheme, another optional technical scheme is to determine at least one temperature gradient according to the temperature data corresponding to at least one first time period, including: determining the average temperature corresponding to at least one first time period according to the temperature data corresponding to at least one first time period; determining at least one temperature gradient according to the lowest temperature and gradient value among the average temperatures corresponding to at least one first time period.

[0086] The average temperature is the average value of the temperature in the first period, and the gradient value is the difference between adjacent temperature gradients that are preset.

[0087] In the embodiment of the present invention, for example, at least one observation time may be preset in the first time period, and for each first time period, at least one temperature observation value corresponding to each observation time may be determined from the temperature data of the first time period, and the average value of the temperature observation value corresponding to each observation time may be used as the average temperature of the first time period. In the embodiment of the present invention, the method of determining the average temperature corresponding to each of the at least one first time period according to the temperature data corresponding to each of the at least one first time period is not specifically limited.

[0088] Exemplarily, when the first time period is a single day, 2 a.m., 8 a.m., 2 p.m. and 8 p.m. can be set as observation times in the first time period, and for each first time period, at least one temperature observation value corresponding to each observation time is determined from the temperature data of the first time period, and the temperature observation value corresponding to at least one observation time is added and divided by 4, and the result is taken as the average temperature of the first time period.

[0089] In an embodiment of the present invention, the sum of the lowest temperature and the gradient value can be used as the gradient temperature, and the gradient interval formed by the lowest temperature and the gradient temperature can be used as a temperature gradient; when the gradient temperature is less than the highest temperature among the average temperatures corresponding to at least one first time period, the gradient temperature is updated to the lowest temperature, and the step of using the sum of the lowest temperature and the gradient value as the gradient temperature is repeated to obtain at least one temperature gradient. In an embodiment of the present invention, the method of determining at least one temperature gradient according to the lowest temperature and the gradient value among the average temperatures corresponding to at least one first time period is not specifically limited.

[0090] Exemplarily, 4° C. can be used as the gradient value, and based on the lowest temperature among the average temperatures corresponding to at least one first time period, each gradient interval consisting of a temperature gradient higher by 4° C. can be used as a temperature gradient to obtain at least one temperature gradient.

[0091] In an embodiment of the present invention, by determining at least one temperature gradient based on the lowest temperature and gradient value of the average temperatures corresponding to at least one first time period, the setting of at least one temperature gradient can be made more reasonable, thereby improving the accuracy of load prediction.

[0092] Based on the above scheme, there is another optional technical scheme, in which the second time period includes at least one third time period, and the first power consumption data includes second power consumption data corresponding to at least one third time period; according to the first power consumption data corresponding to at least one long-term power consumption object in the second time period, an alternative prediction result of the temperature gradient is determined, including: for each third time period in at least one third time period, the second power consumption data corresponding to at least one long-term power consumption object in the third time period is averaged to obtain the average calculation result of the third time period; according to the average calculation result corresponding to at least one third time period, an alternative prediction result of the temperature gradient is determined.

[0093] Among them, the third time period is the time period obtained by dividing the second time period; for example, when the second time period is a single day, each third time period can be each hour time period in the single day; it should be noted that since the second time period is determined from at least one first time period, the first time period can also include at least one third time period; at least one third time period corresponding to each first time period or second time period can be the same, for example, when the second time period is a single day, each second time period can be divided into 24 hour time periods as the third time period. The second power consumption data is the power consumption data of the corresponding power consumption object to be divided in the third time period; the second power consumption data can include the total power consumption of the corresponding power consumption object to be divided in the third time period, etc. The mean calculation result is the result obtained by averaging the second power consumption data corresponding to at least one long-term power consumption object in the third time period.

[0094] In an embodiment of the present invention, for each third period in at least one third period, average calculation may be performed on the second power consumption data corresponding to at least one long-term power consumption object in the third period, that is, average calculation may be performed on the power consumption represented by each second power consumption data in the third period to obtain the average calculation result of the third period, and the average calculation result may represent the reference power consumption in the third period. In an embodiment of the present invention, the method of performing average calculation on the second power consumption data corresponding to at least one long-term power consumption object in the third period to obtain the average calculation result of the third period is not specifically limited.

[0095] In an embodiment of the present invention, a power consumption reference curve under a temperature gradient can be determined based on the mean calculation results corresponding to at least one third time period, and the power consumption reference curve can be used as an alternative prediction result of the temperature gradient. It should be noted that, for each third time period, the reference power consumption represented by the mean calculation results of the third time period can be used as the specific power consumption corresponding to the third time period in the power consumption reference curve; it is also possible not to assign a value to the power consumption reference curve, but only to allow the power consumption reference curve to represent the changes in power consumption in each third time period within the second time period. In an embodiment of the present invention, there is no specific limitation on the method of determining the alternative prediction result of the temperature gradient based on the mean calculation results corresponding to at least one third time period.

[0096] In an embodiment of the present invention, by determining an alternative prediction result of the temperature gradient based on the mean value calculation results corresponding to at least one third time period, the setting of the alternative prediction result can be made more reasonable, thereby further improving the accuracy of load prediction.

[0097] Another optional technical solution, the load forecasting method, further includes: assigning a value to the second load forecasting result according to the first load forecasting result to obtain a target load forecasting result.

[0098] Among them, the target load prediction result can be the load prediction result of the target substation in the time period to be predicted associated with the first time period; the target load prediction result can, for example, include at least one of the predicted total power in the time period to be predicted, the predicted time period power of each third time period in the time period to be predicted, and the change in power consumption in the time period to be predicted, etc.

[0099] In an embodiment of the present invention, it is considered that the first load forecast result may be a forecast result corresponding to the target substation power consumption or power consumption range in the time period to be predicted associated with the first time period, and the second load forecast result may be the change in power consumption of the target substation in the time period to be predicted, for example, it may be a curve of the change in power consumption of the target substation in the time period to be predicted, but the second load forecast result may only be able to characterize the change in power consumption, but cannot know the specific power consumption of each third time period in the time period to be predicted. Therefore, in an embodiment of the present invention, the second load forecast result can be assigned a value based on the first load forecast result, so that the obtained target load forecast result can characterize the specific power consumption of each third time period in the time period to be predicted, thereby realizing the distribution prediction of the load in different third time periods in the time period to be predicted.

[0100] In an embodiment of the present invention, the power consumption or power consumption interval represented by the first load forecast result can be divided according to the power consumption change in the second load forecast result, and the power consumption of each third time period in the time period to be predicted is assigned a value according to each division result, so as to obtain a target load forecast result. In an embodiment of the present invention, the method of assigning a value to the second load forecast result according to the first load forecast result to obtain a target load forecast result is not specifically limited.

[0101] In an embodiment of the present invention, by assigning a value to the second load forecast result based on the first load forecast result to obtain a target load forecast result, it is possible to predict the target load forecast result that characterizes the changes in power load in different time periods within the forecast period and the power consumption, thereby improving the comprehensiveness of the load forecast.

[0102] In order to better understand the technical solution of the above embodiment of the present invention, an optional example is provided here. Figure 4 , a load forecasting system can be used for load forecasting; the load forecasting system can include a data sorting module, a data classification module, a prediction analysis module, a temperature classification module and a load forecasting module; the data sorting module can be used to determine the object power consumption curve; in order to achieve effective utilization of the data collected by the smart meter, the data classification module can be connected to the data sorting module, and the data classification module can be used to divide multiple power consumption objects to be divided; in order to achieve effective prediction of the load in the forecast period, the prediction analysis module can be connected to the data classification module, and the prediction analysis module can be used to predict the total prediction curve; in order to reduce the impact of seasonal changes and realize the analysis of the changes in power consumption in different third time periods within the first time period, the prediction analysis module can be connected to the temperature classification module, and the temperature classification module can be used to determine the power consumption reference curves corresponding to each temperature gradient; the temperature classification module can be connected to the load forecasting module, and the load forecasting module is used to forecast the load for the forecast period according to the forecast period and the target gradient to which the forecast period belongs.

[0103] See also Figure 5Specifically, the load forecasting system can obtain the annual electricity consumption data of a historical single year in the form of a time series through the smart meter to which the target substation belongs, wherein the historical single year includes at least one first time period, and each first time period represents each single day in the historical single year, and according to each electricity consumption object to be divided, according to the first electricity consumption data corresponding to the electricity consumption object to be divided in at least one first time period, determine the object electricity consumption curve of the electricity consumption object to be divided; according to the object electricity consumption curves corresponding to the multiple electricity consumption objects to be divided, divide the multiple electricity consumption objects to be divided to obtain at least one long-term electricity consumption object and at least one short-term electricity consumption object; according to the first electricity consumption data corresponding to the multiple electricity consumption objects to be divided in at least one first time period, determine the total electricity consumption of the first time period corresponding to each first time period, and determine the annual total electricity consumption curve according to the total consumption of the first time period corresponding to each first time period; according to the annual total electricity consumption curve, determine the short-term electricity consumption of at least one short-term electricity consumption object in each first time period, and according to the short-term electricity consumption corresponding to each first time period, perform weight optimization on the annual total electricity consumption curve to obtain the total prediction curve; according to the first electricity consumption data corresponding to at least one long-term electricity consumption object in each first time period, determine The second power consumption data of each long-term power user in different third time periods in each first time period, according to the second power consumption data of each long-term power user in different third time periods in each first time period, determine the power consumption curve corresponding to each long-term power user in each first time period, obtain the temperature data corresponding to at least one first time period, determine at least one temperature gradient according to the temperature data corresponding to at least one first time period, and classify and divide at least one first time period according to the temperature data corresponding to at least one first time period according to at least one temperature gradient, and obtain at least one second time period corresponding to at least one temperature gradient; for each temperature gradient, perform mean integration on each power consumption curve belonging to at least one second time period under the temperature gradient, and obtain the power consumption reference curve corresponding to the temperature gradient in different third time periods as the alternative prediction result; determine the first load prediction data of the target substation in the time period to be predicted from the total prediction curve, determine the target gradient belonging to the time period to be predicted from at least one temperature gradient, use the alternative prediction result corresponding to the target gradient as the second load prediction data of the target substation in the time period to be predicted, and determine the target load prediction result according to the first load prediction result and the second load prediction result.

[0104] The above technical scheme divides the multiple electricity users to be divided associated with the target substation into long-term electricity users and short-term electricity users, realizes the judgment of the long-term electricity users with stable electricity consumption in the substation, and optimizes the annual total electricity consumption curve by using the total short-term electricity consumption of the short-term electricity users in different first time periods, and determines the total prediction curve with a fluctuation range, which effectively considers the unstable electricity consumption characteristics of the short-term electricity users, and introduces the interference of temperature factors to perform gradient division on the long-term electricity users, and then generates alternative prediction results under different temperature gradients. In this way, when performing load forecasting for the period to be predicted, the target load forecasting result composed of the electricity consumption forecast for the period to be predicted in different third time periods can be achieved under the condition of understanding the temperature, which realizes more accurate prediction and provides accurate and reliable data support for the stable operation of the substation power grid.

[0105] Figure 6 This is a structural block diagram of a load prediction device provided in an embodiment of the present invention, and the device is used to execute the load prediction method provided in any of the above embodiments. The device and the load prediction method of the above embodiments belong to the same inventive concept, and the details not described in detail in the embodiment of the load prediction device can refer to the embodiment of the above load prediction method. Figure 6 The device may specifically include: a first power consumption data acquisition module 410, a power consumption object classification module 420, a fluctuating power consumption determination module 430 and a first load prediction data determination module 440.

[0106] The first power consumption data acquisition module 410 is used to acquire first power consumption data corresponding to a plurality of power consumption objects to be divided associated with the target substation, wherein the first power consumption data is power consumption data of the corresponding power consumption objects to be divided in the first time period;

[0107] The power consumption object classification module 420 is used to classify the multiple power consumption objects to be classified according to the first power consumption data respectively corresponding to the multiple power consumption objects to be classified, so as to obtain at least one long-term power consumption object and at least one short-term power consumption object;

[0108] The fluctuating power consumption determination module 430 is used to determine the fluctuating power consumption in the first time period according to the first power consumption data respectively corresponding to at least one short-term power consumption object;

[0109] The first load forecast data determination module 440 is used to determine the first load forecast data of the target substation within the forecast period according to the fluctuating power consumption and the first power consumption data corresponding to at least one long-term power consumption object, wherein the forecast period is associated with the first period.

[0110] Optionally, the module 420 for dividing the electricity consumption objects to be divided includes:

[0111] A power consumption growth determination submodule, for determining the power consumption growth of each power consumption object to be divided among the multiple power consumption objects to be divided according to the first power consumption data of the power consumption object to be divided;

[0112] The submodule for dividing the power users to be divided is used to divide the multiple power users to be divided according to the power consumption growth conditions respectively corresponding to the multiple power users to be divided, and obtain at least one long-term power user and at least one short-term power user.

[0113] Optionally, based on the above device, the number of the first time period is at least one;

[0114] The submodule for dividing the electricity users to be divided includes:

[0115] The unit for dividing power users to be divided is used to divide multiple power users to be divided according to their corresponding power consumption growth in at least one first time period to obtain at least one long-term power user and at least one short-term power user.

[0116] Optionally, based on the above device, the unit for dividing the power consumption objects to be divided includes:

[0117] The long-term electricity consumption object obtaining subunit is used to select, among the multiple electricity consumption objects to be divided, the electricity consumption objects to be divided whose electricity consumption growth in each first time period is characterized by an increase in electricity consumption for a preset time as long-term electricity consumption objects, so as to obtain at least one long-term electricity consumption object;

[0118] The short-term power user object obtaining subunit is used to take the other power users to be divided among the multiple power users to be divided except the long-term power users as short-term power users to obtain at least one short-term power user.

[0119] Optionally, the first load forecast data determination module 440 includes:

[0120] A long-term power consumption determination submodule, configured to determine the long-term power consumption in a first period of time according to first power consumption data respectively corresponding to at least one long-term power consumption object;

[0121] The first load forecast data determination submodule is used to determine the first load forecast data of the target substation within the forecast period according to the fluctuating power consumption and the long-term power consumption.

[0122] Optionally, the device further comprises:

[0123] a target gradient determination module, configured to obtain predicted temperature data of a time period to be predicted, at least one temperature gradient, and candidate prediction results corresponding to at least one temperature gradient, and determine a target gradient corresponding to the predicted temperature data from the at least one temperature gradient;

[0124] The second load forecast data is used as a module to use the alternative forecast results corresponding to the target gradient in the alternative forecast results corresponding to at least one temperature gradient as the second load forecast data of the target substation in the time period to be predicted.

[0125] Optionally, based on the above device, the number of the first time period is at least one;

[0126] The device also includes:

[0127] A temperature gradient determination module, used to obtain temperature data corresponding to at least one first time period, and determine at least one temperature gradient according to the temperature data corresponding to at least one first time period;

[0128] The module for determining alternative prediction results is used to determine, for each temperature gradient in at least one temperature gradient, a second time period of the temperature gradient from at least one first time period based on the temperature data corresponding to at least one first time period, and to determine an alternative prediction result of the temperature gradient based on the first power consumption data corresponding to at least one long-term power user in the second time period.

[0129] Optionally, based on the above device, a temperature gradient determination module includes:

[0130] An average temperature determination submodule, used to determine an average temperature corresponding to at least one first time period according to temperature data corresponding to at least one first time period;

[0131] The temperature gradient determination submodule is used to determine at least one temperature gradient according to the lowest temperature and the gradient value of the average temperatures respectively corresponding to at least one first time period.

[0132] Optionally, based on the above device, the second time period includes at least one third time period, and the first power usage data includes second power usage data corresponding to at least one third time period;

[0133] The module for determining the candidate prediction results includes:

[0134] The submodule for obtaining the mean calculation result is used to perform mean calculation on the second power consumption data respectively corresponding to at least one long-term power consumption object in each third time period in at least one third time period to obtain the mean calculation result of the third time period;

[0135] The alternative prediction result determination submodule is used to determine the alternative prediction result of the temperature gradient according to the mean value calculation results respectively corresponding to at least one third time period.

[0136] Optionally, based on the above device, the device further includes:

[0137] The target load forecast result obtaining module is used to assign a value to the second load forecast result according to the first load forecast result to obtain the target load forecast result.

[0138] The load prediction device provided by the embodiment of the present invention obtains first power consumption data corresponding to multiple power consumption objects to be divided associated with the target substation through a first power consumption data acquisition module, wherein the first power consumption data is the power consumption data of the corresponding power consumption objects to be divided in a first time period, so as to facilitate load prediction through the first power consumption data; the power consumption object division module divides the multiple power consumption objects to be divided according to the first power consumption data corresponding to the multiple power consumption objects to be divided, and obtains at least one long-term power consumption object and at least one short-term power consumption object, thereby realizing long-term and short-term division of the power consumption objects to be divided; the fluctuating power consumption determination module determines the fluctuating power consumption in the first time period according to the first power consumption data corresponding to at least one short-term power consumption object, thereby realizing the determination of unstable fluctuating power consumption; the first load prediction data determination module determines the first load prediction data of the target substation in the time period to be predicted according to the fluctuating power consumption and the first power consumption data corresponding to at least one long-term power consumption object, wherein the time period to be predicted is associated with the first time period, thereby realizing the prediction of the load of the target substation in the time period to be predicted. The above-mentioned device determines the first load forecast data of the target substation within the forecast period by determining the fluctuating power consumption based on the first power consumption data corresponding to at least one short-term power consumer and the first power consumption data corresponding to at least one long-term power consumer. This effectively uses the fluctuating power consumption that characterizes the unstable power consumption characteristics of the short-term power consumer as a reference factor for load forecasting, thereby improving the accuracy of load forecasting.

[0139] The load prediction device provided in the embodiment of the present invention can execute the load prediction method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0140] It is worth noting that in the embodiment of the above-mentioned load forecasting device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0141] Figure 7A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0142] like Figure 7 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0143] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0144] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a load forecasting method.

[0145] In some embodiments, the load forecasting method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the load forecasting method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the load forecasting method in any other appropriate manner (e.g., by means of firmware).

[0146] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0147] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0148] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0149] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0150] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0151] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0152] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0153] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A load forecasting method, characterized in that: include: Acquire first power consumption data corresponding to a plurality of power consumption objects to be classified associated with the target substation, wherein the first power consumption data is power consumption data of the corresponding power consumption objects to be classified in a first time period; According to the first power consumption data respectively corresponding to the multiple power consumption objects to be divided, the multiple power consumption objects to be divided are divided to obtain at least one long-term power consumption object and at least one short-term power consumption object; Determining the fluctuating power consumption in the first time period according to the first power consumption data respectively corresponding to the at least one short-term power consumption object; The first load forecast data of the target substation in the time period to be predicted is determined according to the fluctuating power consumption and the first power consumption data respectively corresponding to the at least one long-term power consumption object, wherein the time period to be predicted is associated with the first time period.

2. The method according to claim 1, characterized in that The method of dividing the plurality of power consumption objects to be divided according to the first power consumption data respectively corresponding to the plurality of power consumption objects to be divided to obtain at least one long-term power consumption object and at least one short-term power consumption object includes: For each of the plurality of power consumption objects to be divided, determining the power consumption growth of the power consumption object to be divided according to the first power consumption data of the power consumption object to be divided; According to the power consumption growth conditions respectively corresponding to the multiple power consumption objects to be divided, the multiple power consumption objects to be divided are divided to obtain at least one long-term power consumption object and at least one short-term power consumption object.

3. The method according to claim 2, characterized in that The number of the first time periods is at least one; The method of dividing the plurality of power users to be divided according to the power consumption growth conditions respectively corresponding to the plurality of power users to be divided to obtain at least one long-term power user and at least one short-term power user includes: According to the power consumption growth conditions respectively corresponding to the multiple power consumption objects to be divided in at least one first time period, the multiple power consumption objects to be divided are divided to obtain at least one long-term power consumption object and at least one short-term power consumption object.

4. The method according to claim 3, characterized in that The method of dividing the plurality of power users to be divided according to the power consumption growth conditions respectively corresponding to the plurality of power users to be divided in at least one first time period to obtain at least one long-term power user and at least one short-term power user includes: Among the plurality of electricity users to be classified, the electricity users to be classified whose electricity consumption growth in each first time period is characterized by an increase in electricity consumption for a preset time period are classified as long-term electricity users, so as to obtain at least one long-term electricity user; The other power users to be classified except the long-term power users among the multiple power users to be classified are taken as short-term power users to obtain at least one short-term power user.

5. The method according to claim 1, characterized in that The determining, according to the fluctuating power consumption and the first power consumption data respectively corresponding to the at least one long-term power consumption object, the first load forecast data of the target substation in the forecast period includes: Determining the long-term power consumption in the first time period according to the first power consumption data respectively corresponding to the at least one long-term power consumption object; According to the fluctuating power consumption and the long-term power consumption, first load forecast data of the target substation in the time period to be predicted is determined.

6. The method according to claim 1, characterized in that Also includes: Acquire predicted temperature data of the time period to be predicted, at least one temperature gradient, and candidate prediction results respectively corresponding to the at least one temperature gradient, and determine a target gradient corresponding to the predicted temperature data from the at least one temperature gradient; The alternative prediction results corresponding to the target gradient among the alternative prediction results corresponding to the at least one temperature gradient are used as the second load prediction data of the target substation in the time period to be predicted.

7. The method according to claim 6, characterized in that The number of the first time periods is at least one; The method further comprises: Acquire temperature data corresponding to the at least one first time period, and determine at least one temperature gradient according to the temperature data corresponding to the at least one first time period; For each temperature gradient in at least one temperature gradient, the second time period of the temperature gradient is determined from the at least one first time period based on the temperature data corresponding to the at least one first time period, and an alternative prediction result of the temperature gradient is determined based on the first power consumption data corresponding to the at least one long-term power user in the second time period.

8. The method according to claim 7, characterized in that The determining at least one temperature gradient according to the temperature data respectively corresponding to the at least one first time period comprises: Determine an average temperature corresponding to each of the at least one first time period according to the temperature data corresponding to each of the at least one first time period; At least one temperature gradient is determined according to the lowest temperature in the average temperatures respectively corresponding to the at least one first time period and the gradient value.

9. The method according to claim 7, characterized in that: The second time period includes the at least one third time period, and the first power usage data includes the second power usage data respectively corresponding to the at least one third time period; The determining the alternative prediction result of the temperature gradient according to the first power consumption data respectively corresponding to the at least one long-term power consumption object in the second time period includes: For each third time period in the at least one third time period, average calculation is performed on the second power consumption data respectively corresponding to the at least one long-term power consumption object in the third time period to obtain the average calculation result of the third time period; The alternative prediction result of the temperature gradient is determined according to the mean value calculation results respectively corresponding to the at least one third time period.

10. The method according to claim 6, characterized in that Also includes: According to the first load forecasting result, the second load forecasting result is assigned a value to obtain a target load forecasting result.

Images