Load prediction method of transformer substation, electronic equipment and computer product

Abstract

The invention discloses a load prediction method of a transformer substation, electronic equipment and a computer product. The method relates to the technical field of substations, and comprises the following steps: in response to a received newly-added instruction of a substation, obtaining a site selection position and load demand data of the substation; determining load associated data of the transformer substation based on the site selection position; and inputting the load associated data into a load prediction model, and predicting the load demand data by using the load prediction model to obtain predicted load data of the transformer substation in a future time period. The technical problem that the reliability of the transformer substation is poor due to the fact that the accuracy of load prediction on the transformer substation is low is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of substations, and in particular to a load prediction method, electronic equipment and computer product for a substation. Background Art

[0002] With the rapid development of social economy and the acceleration of urbanization, the demand for electricity has shown a rapid growth trend. Modern power grids not only need to meet the increasing demand for electricity, but also need stable, reliable and continuous power supply. In this context, the planning and operation of power systems have become more and more complicated. How to accurately predict future load demand has become a key issue in power grid planning and operation. Substations, as important node facilities in the power system, undertake the important task of power transmission and distribution. With the expansion of the scale of the power grid and the complexity of the structure, traditional substation facilities and layout can no longer fully meet the needs of modern power grid development. Building new substations, expanding existing substations, and optimizing substation site selection and construction planning have become important means for power grid companies to improve power supply capacity and ensure power safety. In the planning and construction of substation facilities, load forecasting is a key link. Accurate load forecasting can help power companies reasonably layout substation facilities and ensure the reliability and economy of power supply. However, the methods for predicting substation loads in related technologies are relatively one-sided, resulting in low accuracy in load forecasting for substations, so that the reliability of substations is poor.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiments of the present invention provide a load forecasting method, electronic equipment and computer product for a substation, so as to at least solve the technical problem of poor reliability of the substation caused by low accuracy of load forecasting for the substation.

[0005] According to one aspect of an embodiment of the present invention, a load prediction method for a substation is provided, comprising: in response to receiving a new addition instruction of the substation, obtaining a site selection location and load demand data of the substation, wherein the site selection location is used to represent the geographical location of the substation to be constructed; determining load-related data of the substation based on the site selection location, wherein the load-related data is used to represent related data of at least one factor of a target location area affecting the load state of the substation, the target location area being a location area of ​​a target level corresponding to the site selection location; inputting the load-related data into a load prediction model, using the load prediction model to predict the load demand data, and obtaining predicted load data of the substation in a future time period.

[0006] Furthermore, the method also includes: obtaining sample load demand data of the sample substation and multiple sample load associated data corresponding to the sample load demand data, wherein different sample load associated data are used to represent associated data of the impact of sample location areas of different levels on the load state of the sample substation, and the area ranges of sample location areas of different levels are different; inputting the multiple sample load associated data into the initial load prediction model respectively, using the initial load prediction model to predict the sample load demand data, and obtaining the sample predicted load data corresponding to the multiple sample load associated data; determining the target level based on the sample predicted load data and the sample load demand data corresponding to the multiple sample load associated data.

[0007] Furthermore, a target level is determined based on sample predicted load data and sample load demand data corresponding to multiple sample load association data, including: determining prediction deviations corresponding to multiple sample load association data based on sample predicted load data and sample load demand data corresponding to multiple sample load association data; determining target sample load association data from multiple sample load association data based on the prediction deviations, wherein the prediction deviations of the target sample load association data are smaller than other sample load association data in the multiple sample load association data except the target sample load association data; and determining a preset level of the sample location area corresponding to the target sample load association data as the target level.

[0008] Furthermore, prediction deviations corresponding to multiple sample load associated data are determined based on sample prediction load data and sample load demand data corresponding to multiple sample load associated data, including: determining overall prediction deviation rates of different levels based on multiple sample load associated data and sample load demand data, wherein the overall prediction deviation rate is used to represent the prediction deviation rate of sample load associated data of different levels for multiple sample load associated data; and determining the prediction deviation based on batch information contained in multiple sample load associated data and the overall prediction deviation rate.

[0009] Furthermore, the prediction deviation is determined based on the batch information and the overall prediction deviation rate contained in multiple sample load associated data, including: determining the batch number and the weights of different batches in the batch information, and determining the prediction deviation rates of different levels of the multiple sample load associated data in different batches; determining the prediction deviation based on the batch number, the weights of different batches, the prediction deviation rate and the overall prediction deviation rate.

[0010] Furthermore, the method also includes: acquiring multiple sample load variable data; performing correlation analysis on multiple sample load variable data and sample load demand data based on a preset correlation coefficient to obtain correlation factors of multiple sample load variable data; screening multiple sample load variable data based on the correlation factor and the preset correlation coefficient to obtain multiple sample load correlation data.

[0011] Furthermore, the load associated data of the substation is determined based on the site selection location, including: determining the initial load associated data of the substation based on the site selection location; constructing a site selection influence factor based on the site selection location and construction information of the substation; and adjusting the initial load associated data based on the site selection influence factor to obtain load associated data.

[0012] According to another aspect of an embodiment of the present invention, there is further provided an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein the method in each embodiment of the present invention is executed when the program is running.

[0013] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the methods in various embodiments of the present invention.

[0014] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0015] According to another aspect of the embodiments of the present invention, a computer program is further provided. When the computer program is executed by a processor, the methods in the embodiments of the present invention are implemented.

[0016] In an embodiment of the present invention, in response to receiving a new instruction of a substation, the site selection location and load demand data of the substation are obtained; the load-related data of the substation is determined based on the site selection location; the load-related data is input into a load prediction model, and the load prediction model is used to predict the load demand data to obtain the predicted load data of the substation in the future time period. In the present application, the load-related data of the substation is determined by the site selection location, so as to accurately represent the associated data of at least one factor in the target location area that affects the load state of the substation, so that the load of the substation can be predicted based on at least one load-related data associated with the load of the substation, thereby achieving the purpose of effectively improving the accuracy of the load prediction of the substation, thereby achieving the technical effect of effectively improving the reliability of the substation, and then solving the technical problem of poor reliability of the substation caused by the low accuracy of the load prediction of the substation. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0018] Figure 1is a flow chart of an optional load forecasting method for a substation according to an embodiment of the present invention;

[0019] Figure 2 is a schematic diagram of optional city-level, district-level and street-level correlation factors according to an embodiment of the present invention;

[0020] Figure 3 It is a schematic structural diagram of an optional load prediction device for a substation 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 interchanged 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. 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 that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0023] According to an embodiment of the present invention, an embodiment of a load forecasting method for a substation is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0024] Figure 1 is a flow chart of an optional load forecasting method for a substation according to an embodiment of the present invention, such as Figure 1 As shown, the method comprises the following steps:

[0025] Step S102, in response to receiving a new addition instruction of a substation, obtaining the site selection location and load demand data of the substation, wherein the site selection location is used to indicate the geographical location of the substation to be constructed.

[0026] The above substation is an important part of the power system. The above substation is used to convert electricity from one voltage level to another voltage level to meet the needs of long-distance power transmission and different users. In this application, with the demand for electricity consumption, it is necessary to build a new substation or expand the original substation.

[0027] The above-mentioned new instructions refer to instructions for adding or expanding a substation, wherein the above-mentioned new instructions for the substation can be obtained through manual input, and the above-mentioned new instructions for the substation can also be obtained through demand-based calculation by a program.

[0028] The above-mentioned site selection location refers to the location selected when building a new substation or expanding an existing substation. The above-mentioned site selection location usually refers to the surrounding area of ​​the original substation or the area where the substation is needed, that is, the geographical location of the substation to be built.

[0029] The above-mentioned load demand data refers to the load demand data at the substation site selection location, that is, the load demand data of the target location area corresponding to the substation site selection location, wherein the above-mentioned load demand data includes but is not limited to: electricity demand, seasonal changes, weather conditions, energy policies, technological progress, energy storage technology, international energy market, voltage demand data, maximum current demand data, industry demand data, price demand data and energy-saving demand data, etc. By determining the above-mentioned load demand data, the type of load demand that needs to be considered in the current substation construction can be determined. The specific value corresponding to the specific load demand type, that is, the predicted load data, is predicted by the load prediction model.

[0030] In an optional embodiment, a new instruction for a substation is obtained in a manually determined manner to determine that a new substation is needed, the site selection location of the substation is determined in a manually determined manner, and based on the situation of the substation site selection location, for example: commercial electricity or residential electricity, etc., the load demand data of the substation site selection location is determined, and the above site selection location indicates the geographical location of the substation to be built.

[0031] In another optional embodiment, a new substation instruction is sent to the substation by remotely sending a computer, determining that the original substation needs to be expanded, and the site selection location of the substation is determined manually. Based on the situation of the substation site selection location, for example: commercial electricity or residential electricity, etc., the load demand data of the substation site selection location is determined, and the above site selection location indicates the geographical location of the substation to be built.

[0032] In this application, by obtaining the site selection location of the substation and the load demand data corresponding to the site selection location, the accuracy of the predicted load data of the substation in the future time period is improved, the efficiency of substation establishment is improved, and the user experience is improved.

[0033] Step S104, determining the load associated data of the substation based on the site selection location, wherein the load associated data is used to represent the associated data of at least one factor of the target location area affecting the load state of the substation, and the target location area is a location area of ​​the target level corresponding to the site selection location.

[0034] The above-mentioned load-related data refers to data associated with the location of the above-mentioned substation, that is, data that affects the substation demand data, including but not limited to: electricity demand, seasonal changes, weather conditions, energy policies, technological progress, energy storage technology, international energy market, voltage demand data, maximum current demand data, industry demand data, price demand data, and energy-saving demand data. The above-mentioned load-related data will affect the load of the above-mentioned substation at the location of the site selection, and may cause the load data of the substation to fail to meet the load demand, thereby affecting the user experience. The above-mentioned load-related data is one or more of the above-mentioned load demand data, and the above-mentioned load demand data is subjected to correlation analysis to determine the above-mentioned load-related data.

[0035] In an optional embodiment, the substation load association data is determined based on the site selection of the above-mentioned substation, wherein the above-mentioned load association data represents the association data of at least one factor in the target location area affecting the load state of the substation, and the load association data of different site selection locations are not necessarily the same. For example, when the substation is expanded nearby, the load association data is often not much different from the load association data of the original substation. However, if a new substation is built in a place where there is no substation nearby, it is necessary to conduct a correlation analysis on the local temperature, seasonal changes, electricity demand, energy policy, technical conditions, energy storage technology and international energy market load demand data to determine the factors that affect the load state of the substation as load association data.

[0036] In this application, by determining the load-related data that affects the load status of the substation, the predicted load data of the substation in the future time period is accurately predicted, which effectively improves the accuracy of the predicted load data and improves the user experience.

[0037] Step S106, inputting the load-related data into the load prediction model, using the load prediction model to predict the load demand data, and obtaining the predicted load data of the substation in the future time period.

[0038] The above-mentioned load prediction model is a pre-established model for predicting load demand data through load-related data. The load-related data is taken as input, and after passing through the load prediction model, the predicted load data of the substation in the future time period is output. Among them, the above-mentioned prediction load model includes but is not limited to: support vector regression algorithm model (SVR), multi-layer perception algorithm model (MLP) or ridge regression algorithm model (Ridge Regression, Ridge for short).

[0039] The above-mentioned future time period refers to a period of time after the current time period, wherein the above-mentioned future time period may be a period of time after the construction of the above-mentioned substation is completed.

[0040] In an optional embodiment, the load-related data is input into the SVR algorithm model through a pre-established SVR algorithm model, and the load demand data is predicted using the SVR algorithm model to obtain the predicted load data of the substation in the future time period. The above-mentioned SVR algorithm model can also be replaced by an MLP algorithm model or a Ridge algorithm model.

[0041] Among them, the overall structure of the above SVR algorithm model is as follows:

[0042]

[0043] Among them, w represents the weight vector; b represents the bias term; ξ i and represents a slack variable, which is used to indicate the extent to which the prediction error exceeds ∈; ∈ represents the tolerance in the loss function; a i represents the weight of data point i; C represents the regularization parameter; n represents the number of samples in the data set.

[0044] Among them, the constraints of the SVR algorithm model are as follows:

[0045]

[0046] Among them, φ(x i ) represents the kernel function, which is used to transform the data feature x i Mapped to high-dimensional feature space; y i represents the true load corresponding to the i-th sample; w represents the weight vector; b represents the bias term; ξ i and represents a slack variable, which is used to indicate the extent to which the prediction error exceeds ∈; ∈ represents the tolerance in the loss function; a i represents the weight of data point i; C represents the regularization parameter; n represents the number of samples in the data set.

[0047] Among them, the expression of the above kernel function is as follows:

[0048] K(x i ,x j )=exp(-γ||x i -x j ||) 2 ,

[0049] Among them, γ represents the coefficient of the kernel function, which is used to control the width of the Gaussian distribution.

[0050] Among them, the expression of the above loss function is as follows:

[0051]

[0052] Among them, f(x i ) represents the prediction result of the SVR algorithm model.

[0053] Through the above steps, in response to receiving the new instruction of the substation, the site selection location and load demand data of the substation are obtained; the load-related data of the substation is determined based on the site selection location; the load-related data is input into the load prediction model, and the load prediction model is used to predict the load demand data to obtain the predicted load data of the substation in the future time period. In the present application, the load-related data of the substation is determined by the site selection location to accurately represent the associated data of at least one factor in the target location area that affects the load state of the substation, so that the load of the substation can be predicted based on at least one load-related data associated with the substation load, thereby achieving the purpose of effectively improving the accuracy of the substation load prediction, thereby achieving the technical effect of effectively improving the reliability of the substation, and then solving the technical problem of poor reliability of the substation caused by the low accuracy of the load prediction of the substation.

[0054] Optionally, the method also includes: obtaining sample load demand data of the sample substation and multiple sample load association data corresponding to the sample load demand data, wherein different sample load association data are used to represent the association data of the impact of sample location areas of different levels on the load state of the sample substation, and the area ranges of sample location areas of different levels are different; inputting the multiple sample load association data into the initial load prediction model respectively, using the initial load prediction model to predict the sample load demand data, and obtaining the sample predicted load data corresponding to the multiple sample load association data; determining the target level based on the sample predicted load data and the sample load demand data corresponding to the multiple sample load association data.

[0055] The above-mentioned sample substation refers to the substation corresponding to the initial load forecasting model. Based on the above-mentioned sample substation and related sample load demand data and sample load association data, prediction is performed through the initial load forecasting model to obtain multiple sample forecasted load data to determine the target level.

[0056] The above-mentioned sample load-related data refers to the load-related data corresponding to the sample substation, including but not limited to: electricity demand, seasonal changes, weather conditions, energy policies, technological progress, energy storage technology and international energy markets of the sample substation.

[0057] The above-mentioned sample load demand data, including but not limited to the load demand data corresponding to the sample substation, includes but is not limited to: voltage demand data, maximum current demand data, industry demand data, price demand data and energy-saving demand data of the sample substation.

[0058] The above-mentioned initial load forecasting model refers to a load forecasting model whose parameters have not been adjusted. The accuracy of the initial load forecasting model is lower than that of the load forecasting model. It is necessary to screen out a load forecasting model with sufficient accuracy from the initial load forecasting model.

[0059] The above target level refers to the level of the sample location area corresponding to the above sample substation, wherein the above target level includes but is not limited to: city level, district level or street level, etc. The performance requirements of the above sample substations are determined by grading the above sample substations. Generally, the power demand of a city-level substation is greater than that of a district-level substation, and the power demand of a district-level substation is greater than that of a street-level substation.

[0060] In an optional embodiment, by obtaining the sample load demand of the sample substation and multiple sample load associated data corresponding to the sample load demand data, different sample load associated data are used to represent the associated data of the influence of sample location areas of different levels on the load state of the sample substation, and the area range of sample location areas of different levels is different, wherein the level is divided into city level, district level and street level, the sample location area range of the city level is larger than the sample location area range of the district level, and the sample location area range of the district level is larger than the sample location area range of the street level. Multiple sample load associated data are input into the initial load prediction model, and the sample load data are predicted using the initial load prediction model to obtain multiple sample predicted load data corresponding to the multiple sample load associated data. The target level is determined based on the sample predicted load data corresponding to the multiple sample load associated data and the sample load demand data. The load prediction model is determined from the initial load prediction model based on the multiple sample prediction data corresponding to each level.

[0061] In the present application, sample predicted load data corresponding to multiple sample load associated data are obtained through sample substations, sample load demand data, and multiple sample load associated data, and the target level is determined through sample load data and sample load demand data corresponding to the multiple sample load associated data to determine a load prediction model with higher accuracy, which effectively improves the accuracy of load data prediction and enhances the user experience.

[0062] Optionally, determining a target level based on sample predicted load data and sample load demand data corresponding to multiple sample load association data includes: determining prediction deviations corresponding to multiple sample load association data based on sample predicted load data and sample load demand data corresponding to multiple sample load association data; determining target sample load association data from multiple sample load association data based on the prediction deviations, wherein the prediction deviations of the target sample load association data are smaller than other sample load association data in the multiple sample load association data except the target sample load association data; and determining a preset level of the sample location area corresponding to the target sample load association data as the target level.

[0063] The above-mentioned prediction deviation refers to the deviation between the sample prediction load data and the sample load demand data corresponding to the multiple sample load association data.

[0064] In an optional embodiment, the prediction deviations corresponding to the multiple sample load association data are determined based on the sample prediction load data and the sample load demand data corresponding to the multiple sample load association data. The target sample load association data is determined from the multiple sample load association data based on the prediction deviation, wherein the prediction deviation of the target sample load association data is the minimum value among the multiple prediction deviations. The preset level of the sample location area corresponding to the target sample load association data is determined to be the target level. Exemplarily, after determining the target sample association data, it is determined that the preset level of the sample location area corresponding to the sample load association data is the district level, and then the level of the location area where the substation is constructed is determined to be the district level.

[0065] In this application, by determining multiple prediction deviations and determining the minimum value among the multiple prediction deviations, and then determining the target level, the accuracy of determining the regional level of the substation to be constructed is effectively improved, the accuracy of the predicted load data is effectively improved, and the user experience is improved.

[0066] Optionally, prediction deviations corresponding to multiple sample load associated data are determined based on sample prediction load data and sample load demand data corresponding to multiple sample load associated data, including: determining overall prediction deviation rates of different levels based on multiple sample load associated data and sample load demand data, wherein the overall prediction deviation rate is used to represent the prediction deviation rate of sample load associated data of different levels with respect to multiple sample load associated data; and determining the prediction deviation based on batch information contained in multiple sample load associated data and the overall prediction deviation rate.

[0067] The batch information refers to the information contained in the multiple sample load associated data and used to characterize the batches of the multiple sample load associated data. The batch information can be used to determine the acquisition order of the multiple sample load associated data and the related batches.

[0068] In an optional embodiment, the overall prediction deviation rate of different levels is determined based on multiple sample load association data and sample load demand data, wherein the overall prediction deviation rate is used to represent the prediction deviation rate of sample load association data of different levels to multiple sample load association data. The prediction deviation rates of different levels of multiple sample load association data in different batches are determined based on batch information in multiple pseudo load association data and weights of different batches. The prediction deviation is determined based on the number of batches, weights of different batches, prediction deviation rate and overall prediction deviation rate.

[0069] In this application, the prediction deviation is determined by the batch information and overall prediction deviation rate contained in multiple sample load-related data, which effectively improves the accuracy and reliability of the prediction deviation, effectively improves the accuracy of the predicted load data, and improves the user experience.

[0070] Optionally, the prediction deviation is determined based on batch information and the overall prediction deviation rate contained in multiple sample load associated data, including: determining the number of batches and weights of different batches in the batch information, and determining the prediction deviation rates of different levels of the multiple sample load associated data in different batches; determining the prediction deviation based on the number of batches, weights of different batches, the prediction deviation rate and the overall prediction deviation rate.

[0071] In an optional embodiment, the batch number and the weights of different batches in the batch information are determined, and the prediction deviation rates of different levels of multiple sample load association data in different batches are determined. The calculation formula for the overall prediction deviation rate of the corresponding level based on the weighted average is as follows:

[0072]

[0073] Among them, p i represents the overall prediction deviation rate corresponding to the i-th level, m represents the number of batches in the batch information, and w jrepresents the weight of the jth batch, y ij It represents the prediction deviation rate of the i-th level in the j-th batch.

[0074] Finally, the prediction deviation is determined based on the batch number, the weights of different batches, the prediction deviation rate, and the overall prediction deviation rate.

[0075] In this application, the prediction deviation is determined based on the batch number, the weights of different batches, the prediction deviation rate and the overall prediction deviation rate, which effectively improves the accuracy of the prediction deviation, effectively improves the accuracy of the predicted load data, and improves the user experience.

[0076] Optionally, the method also includes: acquiring multiple sample load variable data; performing correlation analysis on the multiple sample load variable data and sample load demand data based on a preset correlation coefficient to obtain correlation factors of the multiple sample load variable data; screening the multiple sample load variable data based on the correlation factor and the preset correlation coefficient to obtain multiple sample load correlation data.

[0077] The above-mentioned multiple sample load variable data refer to the variable data in the above-mentioned multiple sample load demand data, wherein the above-mentioned sample load variable data will change regularly over time, while the remaining data in the multiple sample load demand data is not easy to change, or the change cycle is relatively long.

[0078] In an optional embodiment, a plurality of sample load variable data that are easy to change are selected from a plurality of sample load demand data based on experience, and a Pearson correlation coefficient is calculated between each sample load variable data and the sample load demand in the city-level sample load variable data, the district-level sample load variable data, and the street-level sample load variable data to obtain a correlation factor, and the plurality of sample load variable data are screened based on the correlation factor and the preset correlation coefficient to obtain a plurality of sample load correlation data. Exemplarily, the city-level correlation factor is the correlation data with an absolute value of the correlation coefficient greater than 0.75, the district-level correlation factor is the correlation data with an absolute value of the correlation coefficient greater than 0.75, and the street-level correlation factor is the correlation data with an absolute value of the correlation coefficient greater than 0.65.

[0079] For example, Figure 2 is a schematic diagram of optional city-level, district-level and street-level correlation factors according to an embodiment of the present invention, such as Figure 2As shown, when the target level is street level, the associated factors include but are not limited to: total retail sales of social sales products, total output value of agriculture, forestry, animal husbandry and fishery, comprehensive energy consumption and project investment, etc.; when the target level is district level, the associated factors include but are not limited to: green coverage rate of built-up areas, added value of general equipment manufacturing industry, industrial output value, per capita disposable income of urban residents, gasoline energy consumption, electricity energy consumption, added value of water production and supply industry, per capita park green space, added value of traditional industries with industrial advantages, light industry output value, centralized treatment rate of urban domestic sewage, per capita consumption expenditure of urban residents, gross domestic product of the primary industry, comprehensive energy consumption of light industry, diesel energy consumption, regional GDP, cloth product output, natural gas energy consumption, fuel oil energy consumption, industrial electricity consumption, construction industry output value, industrial advanced manufacturing value-added, accommodation and catering industry output value and gross domestic product of the secondary industry, etc. ; When the target level is municipal level, the associated factors include but are not limited to: gross product of the secondary industry, gross regional product, gross industrial product, gross water and supply industry product, gross computer industry product, gross communications industry product, gross electronic equipment manufacturing industry product, gross construction product, total assets of manufacturing industry, gross power production and supply industry product, gross heat production and supply industry product, gross gas production and supply industry product, gross manufacturing industry product, industrial waste gas emissions, gross heavy industry product, residential-per capita consumer expenditure, population density, raw coal consumption, gross primary industry product, annual average concentration of inhalable particulate matter, gross furniture manufacturing industry product, total water consumption, gross gas production and supply industry product, retail price index, diesel consumption, year-end length of public water supply pipelines, total liquefied petroleum gas supply and industrial sulfur dioxide emissions, etc.

[0080] In this application, the Pearson coefficient and correlation factor are used to obtain associated data with larger absolute values ​​of correlation coefficients, exclude data with smaller correlation coefficients, reduce the amount of calculation of the load forecasting model, increase the speed of predicting load data, and improve the user experience.

[0081] Optionally, determining the load association data of the substation based on the site selection location includes: determining the initial load association data of the substation based on the site selection location; constructing a site selection influence factor based on the site selection location and construction information of the substation; and adjusting the initial load association data based on the site selection influence factor to obtain load association data.

[0082] The above-mentioned site selection influencing factors refer to data for adjusting the initial load associated data after the initial load associated data of the substation is determined.

[0083] The accuracy of the above initial load correlation data is lower than that of the load correlation data. In the present application, it is necessary to adjust the initial load correlation data by using the site selection influencing factor to obtain more accurate load correlation data.

[0084] In an optional embodiment, the initial load association data is determined based on the initial load association data of the substation, and the site selection influence factor is constructed based on the site selection location and the construction information of the substation, wherein the formula for determining the site selection influence factor is as follows:

[0085]

[0086] Among them, S i represents the influencing factor of site selection; w1, w2, w3 represent weights; d i is the distance factor, and the smaller the distance, the greater the impact; N i Represents the network structure factor, which indicates the quality of network connection.

[0087] Adjusting the initial load correlation data based on the site selection influencing factors includes: obtaining the correction factor through the site selection factor and the load demand, combining the stage load distribution ratio and the site selection correction factor, and recalculating the corrected forecast load data. Among them, the calculation formula of the stage load distribution ratio is as follows:

[0088]

[0089] Among them, P i represents the load proportion that the new substation can share in stage i; C i represents the load capacity that the new substation can share in the i-th phase; L k Represents the original load forecast of the kth area.

[0090] The correction factor is calculated as follows:

[0091]

[0092] Among them, R i represents the correction factor of the ith region; S i represents the location influencing factor of the ith region; n represents the total number of regions.

[0093] The calculation formula for the revised forecast load data is as follows:

[0094] f(x i ) * =f(x i )×(1-P i ·R i ),

[0095] Among them, f(x i ) * represents the revised forecast load data; f(x i ) represents the predicted load data of the sample substation.

[0096] In this application, by obtaining the correction factor and the stage load distribution ratio, the modified forecast load data is recalculated, which effectively improves the accuracy of the forecast load data and enhances the user experience.

[0097] According to another aspect of an embodiment of the present invention, a load prediction device for a substation is also provided, which can execute the load prediction method for a substation of the above embodiment. The specific implementation method and preferred application scenario are the same as those of the above embodiment and will not be repeated here.

[0098] Figure 3 is a schematic diagram of the structure of an optional load prediction device for a substation according to an embodiment of the present invention, such as Figure 3 As shown, the device includes: an acquisition module 30, which is used to obtain the site selection location and load demand data of the substation in response to receiving a new addition instruction of the substation, wherein the site selection location is used to represent the geographical location of the substation to be built; a determination module 32, which is used to determine the load-related data of the substation based on the site selection location, wherein the load-related data is used to represent the related data of at least one factor of the target location area affecting the load state of the substation, and the target location area is a location area of ​​the target level corresponding to the site selection location; a prediction module 34, which is used to input the load-related data into a load prediction model, use the load prediction model to predict the load demand data, and obtain the predicted load data of the substation in the future time period.

[0099] Optionally, the device also includes: an association module, used to obtain sample load demand data of the sample substation and multiple sample load association data corresponding to the sample load demand data, wherein different sample load association data are used to represent the association data of the impact of sample location areas of different levels on the load state of the sample substation, and the area ranges of sample location areas of different levels are different; an input module, used to input multiple sample load association data into the initial load prediction model respectively, and use the initial load prediction model to predict the sample load demand data to obtain sample predicted load data corresponding to the multiple sample load association data; a level module, used to determine the target level based on the sample predicted load data and the sample load demand data corresponding to the multiple sample load association data.

[0100] Optionally, the above-mentioned level module includes: a first determination unit, used to determine the prediction deviation corresponding to multiple sample load association data based on the sample prediction load data and sample load demand data corresponding to the multiple sample load association data; a second determination unit, used to determine the target sample load association data from the multiple sample load association data based on the prediction deviation, wherein the prediction deviation of the target sample load association data is smaller than other sample load association data in the multiple sample load association data except the target sample load association data; a third determination unit, used to determine that the preset level of the sample location area corresponding to the target sample load association data is the target level.

[0101] Optionally, the above-mentioned first determination unit includes: a first prediction deviation sub-unit, used to determine the overall prediction deviation rate of different levels based on multiple sample load association data and sample load demand data, wherein the overall prediction deviation rate is used to represent the prediction deviation rate of sample load association data of different levels with respect to multiple sample load association data; a second prediction deviation sub-unit, used to determine the prediction deviation based on the batch information contained in the multiple sample load association data and the overall prediction deviation rate.

[0102] Optionally, the above-mentioned second prediction deviation sub-unit is also used to determine the batch number and weights of different batches in the batch information, and determine the prediction deviation rates of different levels of multiple sample load-related data in different batches; determine the prediction deviation based on the batch number, weights of different batches, prediction deviation rate and overall prediction deviation rate.

[0103] Optionally, the device also includes: a data module for acquiring multiple sample load variable data; an analysis module for performing correlation analysis on multiple sample load variable data and sample load demand data based on a preset correlation coefficient to obtain correlation factors of multiple sample load variable data; and a screening module for screening multiple sample load variable data based on the correlation factor and a preset correlation coefficient to obtain multiple sample load correlation data.

[0104] Optionally, the determination module includes: an association unit, used to determine the initial load association data of the substation based on the site selection location; an influence unit, used to construct a site selection influence factor based on the site selection location and construction information of the substation; and an adjustment unit, used to adjust the initial load association data based on the site selection influence factor to obtain load association data.

[0105] An embodiment of the present application further provides an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods in various embodiments of the present invention when running.

[0106] An embodiment of the present application further provides a computer-readable storage medium, which includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the methods in various embodiments of the present invention.

[0107] An embodiment of the present application further provides a computer program product, including a computer program, which implements the methods in various embodiments of the present invention when executed by a processor.

[0108] The embodiments of the present application further provide a computer program, which implements the methods in the above-mentioned embodiments of the present invention when executed by a processor.

[0109] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0110] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0111] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0112] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0113] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0114] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0115] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A load forecasting method for a substation, characterized in that: include: In response to receiving a new addition instruction of a substation, acquiring a site selection location and load demand data of the substation, wherein the site selection location is used to represent a geographical location of the substation to be constructed; Determine the load associated data of the substation based on the site selection location, wherein the load associated data is used to represent the associated data of at least one factor of a target location area affecting the load state of the substation, and the target location area is a location area of ​​a target level corresponding to the site selection location; The load-related data is input into a load prediction model, and the load demand data is predicted using the load prediction model to obtain predicted load data of the substation in a future time period.

2. The load forecasting method for a substation according to claim 1, characterized in that: The method further comprises: Acquire sample load demand data of a sample substation and a plurality of sample load association data corresponding to the sample load demand data, wherein different sample load association data are used to represent association data of the influence of sample location areas of different levels on the load state of the sample substation, and the area ranges of sample location areas of different levels are different; Inputting the plurality of sample load associated data into an initial load prediction model respectively, using the initial load prediction model to predict the sample load demand data, and obtaining sample predicted load data corresponding to the plurality of sample load associated data; The target level is determined based on the sample predicted load data corresponding to the plurality of sample load association data and the sample load demand data.

3. The load forecasting method for a substation according to claim 2, characterized in that: Determining the target level based on the sample predicted load data corresponding to the plurality of sample load association data and the sample load demand data includes: determining prediction deviations corresponding to the plurality of sample load-related data based on the sample prediction load data corresponding to the plurality of sample load-related data and the sample load demand data; Determine target sample load associated data from the plurality of sample load associated data based on the prediction deviation, wherein the prediction deviation of the target sample load associated data is smaller than other sample load associated data among the plurality of sample load associated data except the target sample load associated data; The preset level of the sample location area corresponding to the target sample load association data is determined as the target level.

4. The load forecasting method for a substation according to claim 3, characterized in that: Determining prediction deviations corresponding to the plurality of sample load association data based on the sample prediction load data corresponding to the plurality of sample load association data and the sample load demand data includes: Determine overall prediction deviation rates of different levels based on the multiple sample load association data and the sample load demand data, wherein the overall prediction deviation rates are used to represent prediction deviation rates of the sample load association data of different levels with respect to the multiple sample load association data; The prediction deviation is determined based on batch information included in the plurality of sample load-related data and the overall prediction deviation rate.

5. The load forecasting method for a substation according to claim 4, characterized in that: Determining the prediction deviation based on the batch information included in the plurality of sample load associated data and the overall prediction deviation rate includes: Determine the number of batches and weights of different batches in the batch information, and determine the prediction deviation rates of different levels of the plurality of sample load association data in different batches; The prediction deviation is determined based on the batch number, the weights of the different batches, the prediction deviation rate, and the overall prediction deviation rate.

6. The load forecasting method for a substation according to claim 2, characterized in that: The method further comprises: Obtain multiple sample loading variable data; Performing correlation analysis on the plurality of sample load variable data and the sample load demand data based on a preset correlation coefficient to obtain correlation factors of the plurality of sample load variable data; The plurality of sample load variable data are screened based on the correlation factor and the preset correlation coefficient to obtain the plurality of sample load correlation data.

7. The load forecasting method for a substation according to claim 1, characterized in that: Determining the load associated data of the substation based on the site selection location includes: Determining initial load associated data of the substation based on the site selection location; Constructing a site selection influencing factor based on the site selection location and the construction information of the substation; The initial load association data is adjusted based on the site selection influencing factor to obtain the load association data.

8. An electronic device, characterized in that: include: A memory storing an executable program; A processor, configured to run the program, wherein the program executes the method according to any one of claims 1 to 7 when running.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored executable program, wherein when the executable program is run, the device where the storage medium is located is controlled to execute the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that The invention comprises a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 7.

Images