Load prediction method and device, equipment and storage medium

Abstract

The invention discloses a load prediction method, apparatus and device, and a storage medium. The method comprises the steps of obtaining a load data of n electric devices in a historical time period; b pieces of environment data of the n pieces of electric equipment in the historical time period are obtained through m kinds of environment sensors; constructing a basic measurement matrix according to the a load data; constructing a first augmented measurement matrix according to the b environmental data; determining a coupling analysis matrix according to the basic measurement matrix and the first augmented measurement matrix; according to the coupling analysis matrix, determining T linear characteristic value statistic difference values; n first load data sets are determined according to the T linear feature value statistic difference values; and inputting the n first load data sets into a load prediction model to obtain a target first load data set of each electric device in the n electric devices in a future time period, and obtaining n target first load data sets. The method is beneficial for improving the accuracy of load prediction.

Description

Technical Field

[0001] The present application relates to the technical field of power forecasting, and in particular to a load forecasting method, device, equipment and storage medium. Background Art

[0002] With the continuous development of modern power systems, load forecasting has become a key link in power system planning, operation and management. Accurate load forecasting directly affects the reliability and economy of the power system, helps optimize the allocation of power resources, and avoids power outages or waste caused by imbalance between supply and demand. In the context of the rapid development of renewable energy, load forecasting can effectively cope with the volatility of energy and improve the stability and operating efficiency of the power system.

[0003] In the existing load forecasting methods, the load data of the power users' electrical equipment in the historical time period is collected, and the load data of the power equipment in the future time period is predicted by using statistical analysis, regression analysis, neural network prediction and other methods. However, in the operation of the power system, the load data will be affected by many factors. The accuracy of load forecasting is poor if the load data of the power users in the future time period is predicted only by the load data of the power users in the historical time period. Summary of the invention

[0004] In order to solve the above-mentioned problems existing in the prior art, the embodiments of the present application provide a load forecasting method, device, equipment and storage medium. A basic measurement matrix is ​​constructed based on the load data of n electrical equipment in the same physical space in a historical time period, and a first augmented measurement matrix is ​​constructed based on the environmental data of the physical space, so as to determine the coupling analysis matrix, and the linear eigenvalue statistic difference determined by the coupling analysis matrix is ​​used to determine n first load data sets, and the n first load data sets are input into the load forecasting model to obtain the target first load data set of each electrical equipment in the n electrical equipment in the future time period. The load is predicted by combining the influence of environmental data on the load data of the electrical equipment and the historical load data of the electrical equipment, thereby improving the accuracy of load prediction.

[0005] In a first aspect, an embodiment of the present application provides a load forecasting method, including: Obtain T load data of each of n electrical devices in a historical time period to obtain a load data; obtain T environmental data of the n electrical devices in the historical time period through each of m environmental sensors to obtain b environmental data; the n electrical devices are in the same physical space; n, m, T are all integers greater than 1, a=n T,b=m T; According to the a load data, construct a basic measurement matrix; Constructing a first augmented measurement matrix according to the b environmental data; Determining a coupling analysis matrix according to the basic measurement matrix and the first augmented measurement matrix; Determining T linear eigenvalue statistical difference values ​​according to the coupling analysis matrix; Determine n first load data sets according to the T linear eigenvalue statistical difference values; the n first load data sets correspond one-to-one to the n electrical devices; The n first load data sets are input into a load prediction model to obtain a target first load data set for each of the n electrical devices in a future time period, thereby obtaining n target first load data sets.

[0006] In a second aspect, an embodiment of the present application provides a load forecasting device, including: The acquisition unit is used to acquire T load data of each of the n electrical devices in the historical time period to obtain a load data; acquire T environmental data of the n electrical devices in the historical time period through each of the m environmental sensors to obtain b environmental data; the n electrical devices are in the same physical space; n, m, T are all integers greater than 1, a=n T, b = m T; A processing unit, used for constructing a basic measurement matrix according to the a load data; Constructing a first augmented measurement matrix according to the b environmental data; Determining a coupling analysis matrix according to the basic measurement matrix and the first augmented measurement matrix; Determining T linear eigenvalue statistical difference values ​​according to the coupling analysis matrix; Determine n first load data sets according to the T linear eigenvalue statistical difference values; the n first load data sets correspond one-to-one to the n electrical devices; The n first load data sets are input into a load prediction model to obtain a target first load data set for each of the n electrical devices in a future time period, thereby obtaining n target first load data sets.

[0007] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor and a memory, the processor being connected to the memory, the memory being used to store a computer program, and the processor being used to execute the computer program stored in the memory, so that the electronic device performs the method described in the first aspect.

[0008] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method described in the first aspect.

[0009] In a fifth aspect, an embodiment of the present application provides a computer program product, wherein the computer program product includes a computer program, and when the computer program is executed by a processor, the method described in the first aspect is implemented.

[0010] Implementing the embodiments of the present application has the following beneficial effects: In an embodiment of the present application, first, T load data of each of the n electrical devices in the same physical space within a historical time period are obtained to obtain a load data. T environmental data of the n electrical devices within a historical time period are obtained through each of the m environmental sensors to obtain b environmental data. Then, based on the a load data, a basic measurement matrix is ​​constructed, and based on the b environmental data, a first augmented measurement matrix is ​​constructed. Based on the basic measurement matrix and the first augmented measurement matrix, a coupling analysis matrix can be determined. Further, based on the coupling analysis matrix, T linear eigenvalue statistical differences are determined, and based on the T linear eigenvalue statistical differences, n first load data sets are determined. Finally, the n first load data sets are input into the load prediction model to obtain the target first load data set of each of the n electrical devices in the future time period, and n target first load data sets are obtained. Therefore, a coupling analysis matrix can be determined through a basic measurement matrix constructed by load data of electrical equipment in the same physical space within a historical time period and a first augmented measurement matrix constructed by environmental data in the physical space. The linear eigenvalue statistic difference determined by the coupling analysis matrix can represent the influence index of environmental data on the load data of electrical equipment, thereby determining a first load data set that considers the influence of environmental data. By inputting the first load data set into a load forecasting model and predicting the target first load data set of electrical equipment in a future time period, the accuracy of load forecasting can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0012] Figure 1 A schematic diagram of an application scenario of a load forecasting method provided in an embodiment of the present application; Figure 2A flow chart of a load forecasting method provided in an embodiment of the present application; Figure 3 A schematic diagram of the structure of a preset load forecasting model provided in an embodiment of the present application; Figure 4 A schematic diagram of the structure of a gated recurrent unit provided in an embodiment of the present application; Figure 5 A schematic diagram of a load forecasting device provided in an embodiment of the present application; Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0013] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0014] The terms "first", "second", "third" and "fourth" etc. in the specification and claims of the present application and the drawings are used to distinguish different objects, rather than to describe a specific order. 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 limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0015] Reference to "embodiments" herein means that a particular feature, result, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0016] First, see Figure 1 , Figure 1 A schematic diagram of an application scenario of a load forecasting method provided in an embodiment of the present application. Figure 1 The application scenario shown includes: distribution network, power equipment and load forecasting device.

[0017] Among them, the distribution network is a power grid that connects the transmission line and the power user's power equipment in the power system, and is used to distribute the electric energy in the transmission line or power plant to the power user's power equipment. Power equipment is equipment that consumes electric energy in the power system, for example, industrial manufacturing equipment, commercial power equipment, residential power equipment, charging piles for electric vehicles, and the like. The power equipment in the embodiment of the present application is all in the same physical space, for example, multiple charging piles in the same physical space. Since the power equipment is in the same physical space, the power equipment is running in the same environmental data. Among them, each power equipment is provided with a smart meter, and the smart meter can collect power data of the power equipment, including: current, voltage, load data, and the like. The power data of the power equipment collected by the smart meter can be fed back to the distribution network, so that the distribution network adjusts the power supply to the power equipment according to the power data of the power equipment. A variety of environmental sensors are also provided in the physical space where the power equipment is located, for example, a temperature sensor, a humidity sensor, a wind speed detector, and the like, which are used to detect the temperature, humidity, wind speed, and the like in the physical space, respectively. The smart meter of each electrical device and various environmental sensors in the physical space are all connected to the load forecasting device for communication.

[0018] Among them, the load forecasting device can be a server for data transmission and reception, data processing and data storage functions. The server can provide high-performance computing services for other devices in the network. For example, the server can include: application server, virtual private server (Virtual Private Server, VPS), complex instruction set computer (Complex Instruction Set Computer, CISC), etc. This application does not make specific restrictions on this. The load forecasting device can also be a processor with data transmission and reception and data processing. The processor can be connected to the memory, and run the corresponding computer program by reading and executing the computer program instructions in the memory. For example, the processor can include: digital signal processor (Digital Signal Processor, DSP), central processing unit (Central Processing Unit, CPU), micro-controller unit (Micro-Controller Unit, MCU), etc. This application does not make specific restrictions on this.

[0019] In an embodiment of the present application, the load prediction device may send a data acquisition instruction to a smart meter of an electric device to obtain load data of the electric device returned by the smart meter. The load prediction device may also send a data acquisition instruction to an environmental sensor in a physical space to obtain environmental data returned by the environmental sensor. Optionally, the load prediction device may also be connected to a distribution device in a distribution network to obtain power data corresponding to the distribution device.

[0020] It should be noted that in the existing load prediction methods for electrical equipment, the load data of electrical equipment in the future time period is usually predicted based on the load data of the electrical equipment in the historical time period by using statistical analysis, regression analysis, neural network prediction and other methods. However, since the load data of electrical equipment in the same physical space will affect each other, and the environmental data will affect the load data of the electrical equipment, the accuracy of load prediction is poor if the load data of the electrical equipment in the future time period is predicted only by the load data of the electrical equipment in the historical time period.

[0021] To this end, applied to the above scenario, in the load forecasting method provided in the present application, the load forecasting device obtains T load data of each of the n electrical devices in the historical time period to obtain a load data; the load forecasting device obtains T environmental data of the n electrical devices in the historical time period through each of the m environmental sensors to obtain b environmental data; The load forecasting device constructs a basic measurement matrix based on a load data; The load forecasting device constructs a first augmented measurement matrix according to b pieces of environmental data; The load forecasting device determines a coupling analysis matrix according to the basic measurement matrix and the first augmented measurement matrix; The load forecasting device determines T linear eigenvalue statistical difference values ​​according to the coupling analysis matrix; The load prediction device determines n first load data sets according to T linear eigenvalue statistical difference values; The load prediction device inputs n first load data sets into the load prediction model to obtain a target first load data set of each of the n electrical devices in a future time period, thereby obtaining n target first load data sets.

[0022] It can be seen that, applied to the above scenario, the load prediction device can construct a basic measurement matrix based on the load data of n electrical equipment in the same physical space, construct a first augmented measurement matrix based on the environmental data in the physical space, and determine the coupling analysis matrix based on the basic measurement matrix and the first augmented measurement matrix. The linear eigenvalue statistic difference determined by the coupling analysis matrix can represent the influence of environmental data on the load data of the electrical equipment, thereby determining the n first load data sets input into the load prediction model based on the linear eigenvalue statistic difference to predict the load data of the n electrical equipment in the future time period. The predicted load data combines the influence of environmental data on the load data, thereby improving the accuracy of load prediction. In addition, by simultaneously predicting n electrical equipment in the same physical space, the influence of load data between electrical equipment is combined, further improving the accuracy of load prediction.

[0023] See also Figure 2 , Figure 2 A flow chart of a load forecasting method provided in an embodiment of the present application is shown in FIG. The method is applied to a load forecasting device in the above scenario. Figure 2 As shown, the method includes but is not limited to the following steps: 201: Obtain T load data of each of the n power-consuming devices in a historical time period to obtain a load data.

[0024] In the embodiment of the present application, n electrical devices are in the same physical space. The historical time period represents a preset time period between the current moment. The load data is the electrical power consumed by the electrical device corresponding to the load data. n and T are both integers greater than 1, and a=n T.

[0025] Specifically, in the historical time period, the smart meter of each of the n electrical devices will collect the load data of the electrical device at T sampling moments in the historical time period according to the preset collection cycle of the load data, that is, the smart meter of each electrical device collects T load data to obtain a load data. The load prediction device can obtain the above a load data from the smart meter of each of the n electrical devices.

[0026] 202: Obtain T environmental data of n electrical devices in a historical time period through each of the m environmental sensors to obtain b environmental data.

[0027] In the embodiment of the present application, the environmental sensor may include: a temperature sensor, a humidity sensor, a wind speed detector, etc. The environmental data may include: temperature, humidity, wind speed, etc. m is an integer greater than 1, b=m T.

[0028] Specifically, taking the acquisition of T temperatures through a temperature sensor as an example, during a historical time period, the temperature sensor can collect the temperature of the physical space where n electrical devices are located at T collection moments according to a preset temperature collection cycle. The load prediction device can obtain the T temperatures collected by the temperature sensor from the temperature sensor. Similarly, the load prediction device can obtain T environmental data of the physical space where n electrical devices are located during a historical time period from each of the m environmental sensors to obtain b environmental data.

[0029] 203: Construct a basic measurement matrix based on a load data.

[0030] In the embodiment of the present application, the basic measurement matrix is ​​a matrix with a dimension of n×T. The T data in each row of the basic measurement matrix are the T load data of the electric device corresponding to the row in the historical time period. The n data in each column of the basic measurement matrix are the n load data of n electric devices at the sampling time corresponding to the column, and each electric device corresponds to one load data of the column. The load prediction device can construct the above basic measurement matrix based on the a load data of n electric devices in the historical time period.

[0031] 204: Construct a first augmented measurement matrix according to the b environmental data.

[0032] In an embodiment of the present application, the first augmented measurement matrix is ​​a matrix with a dimension of m×T. The T data in each row of the first augmented measurement matrix are T environmental data collected by the environmental sensor corresponding to the row during the historical time period. Each column of the first augmented measurement matrix is ​​m environmental data collected by m types of environmental sensors at the collection time corresponding to the column, and each environmental sensor collects one environmental data in the column. The load forecasting device can construct the above-mentioned first augmented measurement matrix based on the b environmental data obtained above.

[0033] 205: Determine a coupling analysis matrix according to the basic measurement matrix and the first augmented measurement matrix.

[0034] In the embodiment of the present application, the coupling analysis matrix is ​​a matrix with a dimension of (n+k m)×T. The coupling analysis matrix is ​​formed by concatenating the basic measurement matrix and the first augmented measurement matrix after dimension expansion, and the data in the coupling analysis matrix includes: a load data, b environmental data, and multiple white noises. The load forecasting device can expand the dimension of the first augmented measurement matrix, and concatenate the expanded first augmented measurement matrix with the basic measurement matrix to obtain the coupling analysis matrix.

[0035] Exemplarily, determining the coupling analysis matrix according to the basic measurement matrix and the first augmented measurement matrix may include: Obtaining an initial white noise intensity control matrix when performing dimension expansion on the first augmented measurement matrix; Determining a first signal-to-noise ratio corresponding to a first augmented measurement matrix; According to the initial white noise intensity control matrix, the first augmented measurement matrix is ​​dimensionally expanded to obtain a second augmented measurement matrix; determining a second signal-to-noise ratio of a second augmented measurement matrix; If the second signal-to-noise ratio is consistent with the first signal-to-noise ratio, the basic measurement matrix and the second augmented measurement matrix are concatenated to obtain a coupling analysis matrix; If the second signal-to-noise ratio is inconsistent with the first signal-to-noise ratio, adjusting the initial white noise intensity control matrix according to the second signal-to-noise ratio and the first signal-to-noise ratio to obtain a target white noise intensity control matrix; According to the target white noise intensity control matrix, the first augmented measurement matrix is ​​dimensionally expanded to obtain a third augmented measurement matrix; The basic measurement matrix is ​​concatenated with the third augmented measurement matrix to obtain a coupling analysis matrix.

[0036] In the embodiment of the present application, the initial white noise intensity control matrix is ​​a matrix with a dimension of (k mm)×T white noise matrix. The initial white noise intensity control matrix can be pre-set according to the actual test results. The second augmented measurement matrix is ​​a dimension of (k The second augmented measurement matrix includes all the data in the first augmented measurement matrix and all the data in the initial white noise intensity control matrix.

[0037] Specifically, the load prediction device first obtains the initial white noise intensity control matrix when the dimension expansion of the first augmented measurement matrix is ​​performed. Then, the load prediction device determines the transposed matrix of the first augmented measurement matrix, and takes the product of the transposed matrix of the first augmented measurement matrix and the first augmented measurement matrix as the first square matrix. The load prediction device determines the transposed matrix of the initial white noise intensity control matrix, and takes the product of the transposed matrix of the initial white noise intensity control matrix and the initial white noise intensity control matrix as the second square matrix. Next, the trace of the first square matrix and the trace of the second square matrix are determined. The ratio of the trace of the first square matrix to the trace of the second square matrix is ​​taken as the first ratio. The ratio of the first ratio to the square of the signal-to-noise ratio adjustment parameter is taken as the first signal-to-noise ratio corresponding to the first augmented measurement matrix. Among them, the signal-to-noise ratio adjustment parameter can be pre-set according to the actual test results.

[0038] Then, the load forecasting device performs dimension expansion on the first augmented measurement matrix according to the initial white noise intensity control matrix, so as to expand the dimension of the first augmented measurement matrix to (k m)×T, and obtain a second augmented measurement matrix. The second augmented measurement matrix includes m rows of environmental data and (km) rows of white noise. The introduction of white noise is to prevent repeated data in the first augmented measurement matrix from interfering with subsequent processing. Then, the load forecasting device determines a second signal-to-noise ratio of the second augmented measurement matrix. Exemplarily, determining the second signal-to-noise ratio of the second augmented measurement matrix includes: The second signal-to-noise ratio is calculated by the following formula (1): Formula (1) In formula (1), SNR represents the second signal-to-noise ratio, Tr() represents the trace of the calculation matrix, and Y represents the second augmented measurement matrix. represents the transposed matrix of the second augmented measurement matrix, represents the signal-to-noise ratio adjustment parameter, represents the initial white noise intensity control matrix, Represents the transposed matrix of the initial white noise intensity control matrix.

[0039] As can be seen from formula (1), the load forecasting device first determines the transposed matrix of the second augmented measurement matrix, and takes the product of the transposed matrix of the second augmented measurement matrix and the second augmented measurement matrix as the third matrix. Then, the trace of the third matrix is ​​determined. The trace of the third matrix and the trace of the second matrix are taken as the second ratio. The ratio of the second ratio to the square of the signal-to-noise ratio adjustment parameter is taken as the second signal-to-noise ratio of the second augmented measurement matrix. It should be noted that during the dimensional expansion of the first augmented measurement matrix, the signal-to-noise ratio of the matrix needs to remain consistent in order to determine a more accurate coupling analysis matrix and improve the accuracy of load forecasting.

[0040] If the second signal-to-noise ratio is consistent with the first signal-to-noise ratio, the load forecasting device concatenates the basic measurement matrix with the second augmented measurement matrix to obtain a coupling analysis matrix, wherein, since the basic measurement matrix is ​​a matrix with a dimension of n×T, the second augmented measurement matrix is ​​a matrix with a dimension of (k The basic measurement matrix and the second augmented measurement matrix need to be concatenated column by column to obtain a coupling analysis matrix.

[0041] If the second signal-to-noise ratio is inconsistent with the first signal-to-noise ratio, the load forecasting device determines the difference between the first signal-to-noise ratio and the second signal-to-noise ratio. According to the difference between the first signal-to-noise ratio and the second signal-to-noise ratio and the above formula (1), the trace of the target white noise intensity control matrix is ​​determined. According to the trace of the target white noise intensity control matrix, the data in the initial white noise intensity control matrix is ​​adjusted to obtain the target white noise intensity control matrix.

[0042] Furthermore, the load forecasting device inserts the data in the target white noise intensity control matrix into the matrix expanded from the first augmented measurement matrix according to the target white noise intensity control matrix to obtain a third augmented measurement matrix. Finally, the basic measurement matrix and the third augmented measurement matrix are spliced ​​by column to obtain a coupling analysis matrix.

[0043] It can be seen that in an embodiment of the present application, the initial white noise intensity control matrix when the first augmented measurement matrix is ​​dimensionally expanded is obtained, and the first signal-to-noise ratio of the first augmented measurement matrix is ​​determined. Then, according to the initial white noise intensity control matrix, the first augmented measurement matrix is ​​dimensionally expanded to obtain the second augmented measurement matrix, and the second signal-to-noise ratio of the second augmented measurement matrix is ​​determined. By determining whether the second signal-to-noise ratio is consistent with the first signal-to-noise ratio during the dimension expansion process, the first augmented measurement matrix can be dimensionally expanded to avoid repeated data in the first augmented measurement matrix from interfering with subsequent processing processes, and the expanded matrix is ​​spliced ​​with the basic measurement matrix to obtain a coupling analysis matrix, thereby combining load data with environmental data to improve the accuracy of load prediction.

[0044] 206: Determine T linear eigenvalue statistical difference values ​​according to the coupling analysis matrix.

[0045] In an embodiment of the present application, the linear eigenvalue statistic difference is the difference between the linear eigenvalue statistic (LES) of the coupling analysis matrix and the linear eigenvalue statistic of the reference matrix. The reference matrix is ​​a matrix with the same dimension as the coupling analysis matrix obtained by dimensional expansion of the basic measurement matrix. The load forecasting device can determine the T linear eigenvalue statistic differences by determining the T linear eigenvalue statistics of the coupling analysis matrix and the T linear eigenvalue statistics of the reference matrix.

[0046] Exemplarily, determining T linear eigenvalue statistical difference values ​​according to the coupling analysis matrix may include: According to the dimension of the coupling analysis matrix, the dimension of the basic measurement matrix is ​​expanded to obtain a reference matrix; Get the size of the scroll window; According to the size of the rolling window, T first window data are obtained from the coupling analysis matrix; Determine a first eigenvalue set corresponding to each first window data in the T first window data to obtain T first eigenvalue sets; Determine T first linear eigenvalue statistics according to the T first eigenvalue sets; According to the T first window data, T second window data are obtained from the reference matrix; Determine a second eigenvalue set corresponding to each second window data in the T second window data to obtain T second eigenvalue sets; Determine T second linear eigenvalue statistics according to the T second eigenvalue sets; T linear eigenvalue statistical differences are determined according to the T first linear eigenvalue statistics and the T second linear eigenvalue statistics.

[0047] In the embodiment of the present application, the T first linear eigenvalue statistics correspond one-to-one to the T first window data, the T first window data correspond one-to-one to the T second window data, and the T second linear eigenvalue statistics correspond one-to-one to the T second window data.

[0048] Specifically, the load forecasting device first expands the dimension of the basic measurement matrix to (n+k m)×T matrix to obtain the reference matrix. The first n rows of the reference matrix are the data of the basic measurement matrix, and the last (k The data in row m) is the added preset white noise.

[0049] Then, the size of the rolling window is obtained, wherein the rolling window is used to obtain window data from the coupling analysis matrix or the reference matrix, and the size of the rolling window can be preset. The load forecasting device will obtain T first window data from the coupling analysis matrix according to the size of the rolling window. It can be understood that the first window data is a matrix, the dimension of which is determined by the size of the rolling window, and any two of the T first window data may include repeated data.

[0050] Furthermore, the load forecasting device determines the first eigenvalue set corresponding to each first window data in the T first window data, and obtains T first eigenvalue sets. The first eigenvalue set includes multiple first eigenvalues ​​of the first window data corresponding to the first eigenvalue set, and the number of first eigenvalues ​​is determined by the size of the rolling window. The load forecasting device determines that the sum of the multiple first eigenvalues ​​in each first eigenvalue set is the first linear eigenvalue statistic of the first window data corresponding to the first eigenvalue set. In this way, T first linear eigenvalue statistics can be determined.

[0051] Furthermore, the load forecasting device obtains the second window data corresponding to each of the T first window data from the reference matrix based on the T first window data, and obtains T second window data. Then, the second eigenvalue set corresponding to each of the T second window data is determined to obtain T second eigenvalue sets. The second eigenvalue set includes multiple second eigenvalues ​​of the second window data corresponding to the second eigenvalue set. The load forecasting device determines that the sum of the multiple second eigenvalues ​​in each second eigenvalue set is the second linear eigenvalue statistic of the second window data corresponding to the second eigenvalue set. In this way, T second linear eigenvalue statistics can be determined.

[0052] Finally, the load forecasting device subtracts T first linear eigenvalue statistics from T second linear eigenvalue statistics according to the corresponding relationship between T first window data and T second window data, and obtains T linear eigenvalue statistic differences. It should be noted that the linear eigenvalue statistic difference can represent the coupling between environmental data and load data, and also represents the influence index of environmental data on load data. The larger the linear eigenvalue statistic difference, the better the coupling between environmental data and load data, and the smaller the influence index of environmental data on load data.

[0053] It can be seen that the reference matrix is ​​obtained by dimensional expansion of the basic measurement matrix. Then. According to the size of the rolling window, T first window data are obtained from the coupling analysis matrix, and the first eigenvalue set of each first window data in the T first window data is determined, so as to determine the first linear eigenvalue statistic of the first window data according to the first eigenvalue set of each first window data. Then, according to the T first window data, T second window data are obtained from the reference matrix, and the second eigenvalue set corresponding to each second window data is determined to obtain T second eigenvalue sets. According to the T second eigenvalue sets, T second linear eigenvalue statistics are determined. Finally, according to the T first linear eigenvalue statistics and the T second linear eigenvalue statistics, the difference of T linear eigenvalue statistics can be determined. Therefore, through the difference of linear eigenvalue statistics between the coupling analysis matrix and the reference matrix, the influence of environmental data on load data can be determined to improve the accuracy of load prediction.

[0054] 207: Determine n first load data sets according to the T linear eigenvalue statistical difference values.

[0055] In the embodiment of the present application, n first load data sets correspond to n electrical devices one by one. The first load data set corresponding to each electrical device includes T load data adjusted according to the environmental data for the T load data of the electrical device. The load prediction device can determine the influence index of the environmental data on the load data based on the difference of the T linear eigenvalue statistics, and thus adjust the load data corresponding to the n electrical devices according to the influence index corresponding to each load data, thereby obtaining n first load data sets.

[0056] Exemplarily, determining n first load data sets according to T linear eigenvalue statistical difference values ​​may include: Determine n second load data sets according to a load data; Determine the linear eigenvalue statistical difference values ​​that are smaller than the preset difference value among the T linear eigenvalue statistical difference values, and obtain c linear eigenvalue statistical difference values; Obtain c first window data from T first window data according to c linear eigenvalue statistical differences; Determine, according to the c linear eigenvalue statistical difference values, an influence index of the environmental data in each of the c first window data on the load data; According to the influence index of the environmental data in each of the c first window data on the load data, determine the sum of the influence index corresponding to each load data in the d load data of the c first window data, and obtain d total influence indexes; According to the d total impact indexes and the d load data, d adjusted load data are determined; According to the d adjusted load data, the n second load data sets are updated to obtain n first load data sets.

[0057] In the embodiment of the present application, each second load data set corresponds to an electrical device. c is an integer greater than 1 and less than or equal to T. The d load data are all the load data in the c first window data.

[0058] Specifically, the load prediction device first extracts the a load data from the coupling analysis matrix, takes the T load data corresponding to each of the n electrical devices as a load data set corresponding to the electrical device, and obtains n second load data sets.

[0059] Then, the load prediction device determines the linear eigenvalue statistical difference values ​​that are smaller than the preset difference value among the T linear eigenvalue statistical difference values, and obtains c linear eigenvalue statistical difference values. Among them, the linear eigenvalue statistical difference value is smaller than the preset difference value, indicating that the coupling between the environmental data and the load data in the first window data corresponding to the linear eigenvalue statistical difference value is smaller than the preset coupling, and the influence index of the environmental data in the first window data corresponding to the linear eigenvalue statistical difference value on the load data is greater than the preset influence index. The load prediction device will obtain c first window data corresponding to the c linear eigenvalue statistical difference values ​​from the T first window data based on the c linear eigenvalue statistical difference values.

[0060] Furthermore, the load prediction device determines the influence index of the environmental data in each of the c first window data on the load data based on the c linear eigenvalue statistical difference values. The mapping relationship between the linear eigenvalue statistical difference value and the influence index can be preset according to the actual test results. It can be understood that there may be one or more environmental data and one or more load data in each first window data, and the influence index of each environmental data corresponding to the same first window data on each load data is the same. The c first window data include a total of d load data, and the d load data can be any d load data among the T load data.

[0061] Furthermore, the load forecasting device will count the sum of the impact indexes corresponding to each load data in the d load data to obtain d total impact indexes. According to the d total impact indexes and the d load data, d adjusted load data are determined, wherein the adjusted load data is equal to the product of the total impact index and the load data.

[0062] Finally, the load prediction device updates the d load data corresponding to the d adjusted load data in the n second load data sets based on the d adjusted load data. For example, the adjusted load data corresponding to each load data in the d load data is subtracted to update the n second load data sets to obtain n first load data sets.

[0063] It can be seen that the load prediction device can obtain c first window data from T first window data by determining c linear eigenvalue statistical differences that are less than a preset difference among T linear eigenvalue statistical differences. Then, the influence index of the environmental data in the c first window data on the load data is determined according to the c linear eigenvalue statistical differences, and d adjusted load data can be determined according to the total influence index corresponding to each load data in the d load data, so as to update the n second load data sets according to the d adjusted load data to obtain n first load data sets. Thus, it is determined that the n first load data sets are all load data sets that consider the influence of environmental data on load data, and load prediction is performed according to the n first load data sets, which can improve the accuracy of load prediction.

[0064] 208: Inputting the n first load data sets into the load prediction model to obtain a target first load data set for each of the n electrical devices in a future time period, thereby obtaining n target first load data sets.

[0065] In an embodiment of the present application, the load forecasting model is obtained by training a preset load forecasting model, and the preset load forecasting model can be a neural network model based on a gated recurrent unit (GRU) and a multi-task learning (MTL) framework. The input of the load forecasting model is n first load data sets corresponding to n power-consuming devices, and the output of the load forecasting model is n target first load data sets for n power-consuming devices in a future time period.

[0066] Exemplarily, before inputting the n target first load data sets into the load forecasting model, the method further includes: Obtain multiple load correlation matrices from the coupling analysis matrix; Determine an eigenvalue set corresponding to each load correlation matrix in a plurality of load correlation matrices to obtain a plurality of third eigenvalue sets; Any electric device corresponding to each load association matrix is ​​used as the associated electric device corresponding to the load association matrix, and the load data corresponding to the associated electric device of each load association matrix is ​​used as the associated load data of the load association matrix; Filling the associated load data of each load association matrix in the multiple load association matrices with preset white noise to obtain multiple associated reference matrices; Determine an eigenvalue set corresponding to each of the multiple correlation reference matrices to obtain multiple fourth eigenvalue sets; Determining the correlation between any two electrical devices among the n electrical devices according to the plurality of third eigenvalue sets and the plurality of fourth eigenvalue sets; According to the correlation degree between any two electric devices among the n electric devices, the n first load data sets are adjusted to obtain the adjusted n first load data sets.

[0067] In the embodiment of the present application, the load association matrix includes load data corresponding to any two of the n electrical devices. It should be noted that the load data between the n electrical devices in the same physical space will be associated, so it is necessary to adjust the n first load data sets input into the load prediction model according to the degree of association between any two load data.

[0068] Specifically, the load prediction device obtains the load data corresponding to any two electrical devices from the coupling analysis matrix to construct a load association matrix and obtain multiple load association matrices. Then, the eigenvalue set of each load association matrix in the multiple load association matrices is determined to obtain multiple third eigenvalue sets. The third eigenvalue set includes multiple third eigenvalues ​​of the load association matrix corresponding to the third eigenvalue set. Next, the load prediction device uses any electrical device corresponding to each load association matrix as the associated electrical device corresponding to the load association matrix, and uses the load data corresponding to the associated electrical device of each load association matrix as the associated load data of the load association matrix.

[0069] Furthermore, the load forecasting device fills the associated load data of each load association matrix in the multiple load association matrices with preset white noise to obtain multiple associated reference matrices. Determine the eigenvalue set corresponding to each associated reference matrix in the multiple associated reference matrices to obtain multiple fourth eigenvalue sets. The fourth eigenvalue set includes multiple fourth eigenvalues ​​of the associated reference matrix corresponding to the fourth eigenvalue set.

[0070] Furthermore, the load prediction device determines multiple association differences based on multiple third eigenvalue sets and multiple fourth eigenvalue sets, wherein the association difference is equal to the difference between the sum of multiple third eigenvalues ​​in the third eigenvalue set and the sum of multiple fourth eigenvalues ​​in the fourth eigenvalue set, one third eigenvalue set and one fourth eigenvalue set determine one association difference, and multiple association differences correspond to multiple load association matrices one by one. According to each of the multiple association differences, the association degree of two electrical devices corresponding to the load association matrix corresponding to the association difference can be determined. Among them, the mapping relationship between the association difference and the association degree can be preset. In this way, the association degree of any two electrical devices among n electrical devices can be determined.

[0071] Finally, according to the correlation between any two of the n electrical devices, the sum of the correlations corresponding to each of the n electrical devices can be determined to obtain the total correlation corresponding to the electrical device. According to the total correlation of each of the n electrical devices, the load correlation of the electrical device in the future time period can be determined. Among them, the mapping relationship between the total correlation and the load correlation can be preset. According to the load correlation corresponding to each of the n electrical devices, the n first load data sets are adjusted to obtain the adjusted n first load data sets. For example, the load data in the first load data set is added to the load correlation of the electrical device corresponding to the first load data set to obtain the adjusted first load data set corresponding to the electrical device, thereby obtaining the adjusted n first load data sets.

[0072] Therefore, the adjusted n first load data sets are load data sets that combine the correlation between all electrical equipment in the same physical space. By predicting the load data sets of n electrical equipment in future time periods through the adjusted n first load data sets, the accuracy of load prediction can be improved.

[0073] Based on this, the adjusted n first load data sets can be input into the load forecasting model. Exemplarily, the load forecasting model is obtained by training a preset load forecasting model, and the method further includes: Obtaining a preset load forecasting model; Get multiple training sets, test sets, and validation sets; Using n third load data sets of each training set in a plurality of training sets as input of a preset load forecasting model, using n target third load data sets of the training set as output of the preset load forecasting model, training the preset load forecasting model, and obtaining a candidate load forecasting model; Inputting the n fourth load data sets into the candidate load forecasting model to obtain n expected load data sets; Determining n mean square errors based on the n expected load data sets and the n target fourth load data sets; Determine the sum of n mean square errors as the model loss; According to the model loss, the model parameters of the candidate load forecasting model are adjusted to obtain the load forecasting model.

[0074] In an embodiment of the present application, the training set includes n third load data sets of n electrical devices in a first time period and n target third load data sets in a second time period, and each electrical device corresponds to a third load data set and a target third load data set. The test set includes n fourth load data sets of n electrical devices in a third time period. The validation set includes n target fourth load data sets of n electrical devices in a fourth time period, and each electrical device corresponds to a fourth load data set and a target fourth load data set. The time length of the first time period and the time length of the third time period are equal to the time length of the historical time period, and the time length of the second time period and the time length of the fourth time period are equal to the time length of the future time period.

[0075] It should be noted that the interval between the historical time period and the future time period is equal to the interval between the first time period and the second time period, and is equal to the interval between the third time period and the fourth time period. In this way, the trained load forecasting model can determine the n target first load data sets in the future time period based on the n first load data sets in the historical time period.

[0076] Specifically, the load forecasting device first obtains a preset load forecasting model, and obtains multiple training sets, test sets, and validation sets. Figure 3 As shown, the preset load forecasting model may include: an input layer, a shared layer, multiple hidden layers, and multiple output layers. The preset load forecasting model includes multiple tasks, such as Figure 3 As shown in Task 1, Task 2 and Task 3, it can be understood that Figure 3 The preset load prediction model shown is only exemplary, and the number of tasks is determined by the number of electrical equipment. Each task corresponds to an electrical equipment, and each task is used to predict the load data set of the electrical equipment corresponding to the task.

[0077] When training the preset load forecasting model through multiple training sets, the n third load data sets of each training set in the multiple training sets are used as the input of the preset load forecasting model and input into the input layer of the preset load forecasting model. The n target third load data sets of the training set are used as the output of the multiple output layers of the preset load forecasting model to train the preset load forecasting model. Among them, each output layer in the preset load forecasting model is used to output the target third load data set of each of the n electrical devices. Among them, the shared layer mainly includes a GRU layer, which is used to extract common features from the input n third load data sets, and transmit the n third load data sets and the common features to the hidden layers of n tasks respectively, so as to predict the target third load data sets of the n electrical devices. The hidden layer of each task is used to transfer the load data set of the task, and finally output the target third load data set of the task through the output layer of the task. Among them, the hidden layer includes a GRU layer and a fully connected layer. It can be understood that there can be multiple hidden layers for each task. Figure 3 This is only an example and is not limited to this application.

[0078] For example, the structure of GRU can be as follows Figure 4 As shown. Among them, the GRU includes an update unit and a reset unit. The update unit is used to output an update data set corresponding to the update unit according to the output data set of the previous hidden layer. The reset unit is used to output a reset data set corresponding to the reset unit according to the common features. According to the update data set and the reset data set of the GRU, the output data set of the GRU can be determined. Exemplarily, Figure 4 The processing of the GRU shown can be expressed by the following formula (2): Formula (2) Among them, z1 represents the update data set output by the update unit, and r1 represents the reset data set output by the reset unit. Represents the activation function of GRU, such as Figure 4 Shown as " " represents the activation function, for example, the activation function can be a Sigmoid function. represents the weight matrix of the updated unit connection, Represents the weight matrix of the reset unit connection, wherein the weight matrix of the update unit connection and the weight matrix of the reset unit connection can be preset. h0 represents the output data set of the previous hidden layer, and x1 represents the common feature. Represents the output dataset of the next candidate hidden layer. Represents the weight matrix of the next candidate hidden layer connection. tanh() represents the calculation of the hyperbolic tangent value. h1 represents the output data set of GRU.

[0079] Based on this, the preset load forecasting model is trained through multiple training sets, and the GRU layer in the shared layer and multiple hidden layers can be trained to finally obtain a candidate load forecasting model.

[0080] Further, the load forecasting device inputs the n fourth load data sets in the test set into the above-mentioned candidate load forecasting model, and n expected load data sets can be obtained. According to the n expected load data sets and the n target fourth load data sets in the verification set, n mean square errors can be determined, wherein one expected load data set and one target fourth load data set determine one mean square error. The load forecasting device can use the sum of the n mean square errors as the model loss. According to the model loss, the model parameters are adjusted to obtain the load forecasting model. For example, the model parameters may include: learning rate, the number of GRU layers, and so on.

[0081] Therefore, the preset load forecasting model is trained through multiple training sets to obtain a candidate load forecasting model, and the model loss of the candidate load forecasting model is calculated through the test set and the validation set. The model parameters of the candidate load forecasting model can be adjusted according to the model loss to obtain the load forecasting model to improve the accuracy of load forecasting.

[0082] Based on this, by inputting n first load data sets into the load forecasting model, the target first load data set of each of the n electrical devices in the future time period can be obtained, and n target first load data sets can be obtained. Among them, the processing method of the n first load data sets in the load forecasting model is similar to the processing method of the n third load data sets in the preset load forecasting model, which will not be repeated here.

[0083] In summary, in an embodiment of the present application, first, T load data of each of the n electrical devices in the same physical space within a historical time period are obtained to obtain a load data. T environmental data of the n electrical devices within a historical time period are obtained through each of the m environmental sensors to obtain b environmental data. Then, based on the a load data, a basic measurement matrix is ​​constructed, and based on the b environmental data, a first augmented measurement matrix is ​​constructed. Based on the basic measurement matrix and the first augmented measurement matrix, a coupling analysis matrix can be determined. Further, based on the coupling analysis matrix, T linear eigenvalue statistical differences are determined, and based on the T linear eigenvalue statistical differences, n first load data sets are determined. Finally, the n first load data sets are input into the load prediction model to obtain the target first load data set of each of the n electrical devices in the future time period, and n target first load data sets are obtained. Therefore, a coupling analysis matrix can be determined through a basic measurement matrix constructed by load data of electrical equipment in the same physical space within a historical time period and a first augmented measurement matrix constructed by environmental data in the physical space. The linear eigenvalue statistic difference determined by the coupling analysis matrix can represent the influence index of environmental data on the load data of electrical equipment, thereby determining the first load data set considering the influence of environmental data. By inputting the first load data set into a load forecasting model and predicting the target first load data set of the electrical equipment in a future time period, the accuracy of load forecasting can be improved.

[0084] See also Figure 5 , Figure 5 A schematic diagram of a load prediction device provided in an embodiment of the present application. The load prediction device 500 may be the load prediction device of any of the above embodiments. The load prediction device 500 includes an acquisition unit 501 and a processing unit 502.

[0085] The acquisition unit 501 is used to acquire T load data of each of the n electrical devices in the historical time period to obtain a load data; acquire T environmental data of the n electrical devices in the historical time period through each of the m environmental sensors to obtain b environmental data; the n electrical devices are in the same physical space; n, m, T are all integers greater than 1, a=n T, b = m T; A processing unit 502 is used to construct a basic measurement matrix according to a load data; According to b environmental data, construct a first augmented measurement matrix; Determine a coupling analysis matrix according to the basic measurement matrix and the first augmented measurement matrix; According to the coupling analysis matrix, determine the statistical differences of T linear eigenvalues; Determine n first load data sets according to the statistical difference values ​​of the T linear eigenvalues; the n first load data sets correspond one to one to the n electrical equipment; The n first load data sets are input into the load prediction model to obtain a target first load data set of each of the n electrical devices in a future time period, thereby obtaining n target first load data sets.

[0086] In a possible embodiment, in determining the coupling analysis matrix according to the basic measurement matrix and the first augmented measurement matrix, the processing unit 502 is specifically configured to: Obtaining an initial white noise intensity control matrix when performing dimension expansion on the first augmented measurement matrix; Determining a first signal-to-noise ratio corresponding to a first augmented measurement matrix; According to the initial white noise intensity control matrix, the first augmented measurement matrix is ​​dimensionally expanded to obtain a second augmented measurement matrix; determining a second signal-to-noise ratio of a second augmented measurement matrix; If the second signal-to-noise ratio is consistent with the first signal-to-noise ratio, the basic measurement matrix and the second augmented measurement matrix are concatenated to obtain a coupling analysis matrix; If the second signal-to-noise ratio is inconsistent with the first signal-to-noise ratio, adjusting the initial white noise intensity control matrix according to the second signal-to-noise ratio and the first signal-to-noise ratio to obtain a target white noise intensity control matrix; According to the target white noise intensity control matrix, the first augmented measurement matrix is ​​dimensionally expanded to obtain a third augmented measurement matrix; The basic measurement matrix is ​​concatenated with the third augmented measurement matrix to obtain a coupling analysis matrix.

[0087] In a possible embodiment, in determining the second signal-to-noise ratio of the second augmented measurement matrix, the processing unit 502 is specifically configured to: The second signal-to-noise ratio is calculated by the following formula (1): Formula (1) Wherein, SNR represents the second signal-to-noise ratio, Tr() represents the trace of the calculation matrix, Y represents the second augmented measurement matrix, represents the transposed matrix of the second augmented measurement matrix, represents the signal-to-noise ratio adjustment parameter, represents the initial white noise intensity control matrix, Represents the transposed matrix of the initial white noise intensity control matrix.

[0088] In a possible embodiment, in determining T linear eigenvalue statistical difference values ​​according to the coupling analysis matrix, the processing unit 502 is specifically configured to: According to the dimension of the coupling analysis matrix, the dimension of the basic measurement matrix is ​​expanded to obtain a reference matrix; Get the size of the scroll window; According to the size of the rolling window, T first window data are obtained from the coupling analysis matrix; Determine a first eigenvalue set corresponding to each first window data in the T first window data to obtain T first eigenvalue sets; According to the T first eigenvalue sets, T first linear eigenvalue statistics are determined; the T first linear eigenvalue statistics correspond to the T first window data one by one; According to the T first window data, T second window data are obtained from the reference matrix; the T first window data correspond to the T second window data one by one; Determine a second eigenvalue set corresponding to each second window data in the T second window data to obtain T second eigenvalue sets; Determine T second linear eigenvalue statistics according to the T second eigenvalue sets; the T second linear eigenvalue statistics correspond one-to-one to the T second window data; T linear eigenvalue statistical differences are determined according to the T first linear eigenvalue statistics and the T second linear eigenvalue statistics.

[0089] In a possible embodiment, in determining n first load data sets according to T linear eigenvalue statistical difference values, the processing unit 502 is specifically configured to: Determine n second load data sets according to a load data; each second load data set corresponds to an electrical device; Determine the linear eigenvalue statistical difference values ​​that are less than the preset difference value among the T linear eigenvalue statistical difference values, and obtain c linear eigenvalue statistical difference values; c is an integer greater than 1 and less than or equal to T; Obtain c first window data from T first window data according to c linear eigenvalue statistical differences; Determine, according to the c linear eigenvalue statistical difference values, an influence index of the environmental data in each of the c first window data on the load data; According to the influence index of the environmental data in each of the c first window data on the load data, determine the sum of the influence index corresponding to each load data in the d load data of the c first window data, and obtain d total influence indexes; the d load data are all the load data in the c first window data; According to the d total impact indexes and the d load data, d adjusted load data are determined; According to the d adjusted load data, the n second load data sets are updated to obtain n first load data sets.

[0090] In a possible embodiment, before inputting the n first load data sets into the load forecasting model, the processing unit 502 is further configured to: A plurality of load association matrices are obtained from the coupling analysis matrix; the load association matrix includes load data corresponding to any two electrical devices among the n electrical devices; Determine an eigenvalue set corresponding to each load correlation matrix in a plurality of load correlation matrices to obtain a plurality of third eigenvalue sets; Any electric device corresponding to each load association matrix is ​​used as the associated electric device corresponding to the load association matrix, and the load data corresponding to the associated electric device of each load association matrix is ​​used as the associated load data of the load association matrix; Filling the associated load data of each load association matrix in the multiple load association matrices with preset white noise to obtain multiple associated reference matrices; Determine an eigenvalue set corresponding to each of the multiple correlation reference matrices to obtain multiple fourth eigenvalue sets; Determining the correlation between any two electrical devices among the n electrical devices according to the plurality of third eigenvalue sets and the plurality of fourth eigenvalue sets; According to the correlation degree between any two electric devices among the n electric devices, the n first load data sets are adjusted to obtain the adjusted n first load data sets.

[0091] In a possible embodiment, the processing unit 502 is further configured to: Obtaining a preset load forecasting model; Acquire multiple training sets, test sets, and validation sets; the training set includes n third load data sets of n electrical devices in a first time period and n target third load data sets in a second time period, and each electrical device corresponds to a third load data set and a target third load data set; the test set includes n fourth load data sets of n electrical devices in a third time period; the validation set includes n target fourth load data sets of n electrical devices in a fourth time period, and each electrical device corresponds to a fourth load data set and a target fourth load data set; the time length of the first time period and the time length of the third time period are equal to the time length of the historical time period, and the time length of the second time period and the time length of the fourth time period are equal to the time length of the future time period; Using n third load data sets of each training set in a plurality of training sets as input of a preset load forecasting model, using n target third load data sets of the training set as output of the preset load forecasting model, training the preset load forecasting model, and obtaining a candidate load forecasting model; Inputting the n fourth load data sets into the candidate load forecasting model to obtain n expected load data sets; Determining n mean square errors based on the n expected load data sets and the n target fourth load data sets; Determine the sum of n mean square errors as the model loss; According to the model loss, the model parameters of the candidate load forecasting model are adjusted to obtain the load forecasting model.

[0092] See also Figure 6 , Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 6 As shown, the electronic device 600 includes a transceiver 601, a processor 602 and a memory 603. They are connected via a bus 604. The memory 603 is used to store computer programs and data, and can transmit the data stored in the memory 603 to the processor 602. The electronic device 600 can be a load prediction device 500.

[0093] The processor 602 is used to read the computer program in the memory 603 and perform the following operations: Obtain T load data of each of the n electrical devices in the historical time period, and obtain a load data; obtain T environmental data of the n electrical devices in the historical time period through each of the m environmental sensors, and obtain b environmental data; the n electrical devices are in the same physical space; n, m, T are all integers greater than 1, a=n T, b = m T; According to a load data, construct a basic measurement matrix; According to b environmental data, construct a first augmented measurement matrix; Determine a coupling analysis matrix according to the basic measurement matrix and the first augmented measurement matrix; According to the coupling analysis matrix, determine the statistical differences of T linear eigenvalues; Determine n first load data sets according to the statistical difference values ​​of the T linear eigenvalues; the n first load data sets correspond one to one to the n electrical equipment; The n first load data sets are input into the load prediction model to obtain a target first load data set of each of the n electrical devices in a future time period, thereby obtaining n target first load data sets.

[0094] The above mainly introduces the scheme of the embodiment of the present application from the perspective of the execution process on the method side. It is understandable that, in order to realize the above functions, the electronic device includes a hardware structure and / or software module corresponding to the execution of each function. It should be easily appreciated by those skilled in the art that, in combination with the units and algorithm steps of each example described in the embodiments provided herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present application.

[0095] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. The computer program is executed by a processor to implement part or all of the steps of any one of the methods described in the above method embodiments.

[0096] An embodiment of the present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute part or all of the steps of any one of the methods recorded in the above method embodiments.

[0097] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.

[0098] In the above embodiments, 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.

[0099] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as 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, and the indirect coupling or communication connection of the device or unit can be electrical or other forms.

[0100] 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 network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0101] In addition, each functional unit in each embodiment of the present application 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 integrated unit may be implemented in the form of hardware or in the form of a software program module.

[0102] If the integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, 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. The computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0103] A person skilled in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable memory, and the memory may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0104] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A load forecasting method, characterized in that: include: Obtain T load data of each of n electrical devices in a historical time period to obtain a load data; obtain T environmental data of the n electrical devices in the historical time period through each of m environmental sensors to obtain b environmental data; the n electrical devices are in the same physical space; n, m, T are all integers greater than 1, a=n T, b = m T; According to the a load data, construct a basic measurement matrix; Constructing a first augmented measurement matrix according to the b environmental data; Determining a coupling analysis matrix according to the basic measurement matrix and the first augmented measurement matrix; Determining T linear eigenvalue statistical difference values ​​according to the coupling analysis matrix; Determining n first load data sets according to the T linear eigenvalue statistical difference values; The n first load data sets correspond one-to-one to the n electrical devices; The n first load data sets are input into a load prediction model to obtain a target first load data set for each of the n electrical devices in a future time period, thereby obtaining n target first load data sets.

2. The method according to claim 1, characterized in that The step of determining a coupling analysis matrix according to the basic measurement matrix and the first augmented measurement matrix comprises: Obtaining an initial white noise intensity control matrix when performing dimension expansion on the first augmented measurement matrix; Determining a first signal-to-noise ratio corresponding to the first augmented measurement matrix; According to the initial white noise intensity control matrix, dimensionally expand the first augmented measurement matrix to obtain a second augmented measurement matrix; determining a second signal-to-noise ratio of the second augmented measurement matrix; If the second signal-to-noise ratio is consistent with the first signal-to-noise ratio, concatenating the basic measurement matrix with the second augmented measurement matrix to obtain the coupling analysis matrix; If the second signal-to-noise ratio is inconsistent with the first signal-to-noise ratio, adjusting the initial white noise intensity control matrix according to the second signal-to-noise ratio and the first signal-to-noise ratio to obtain a target white noise intensity control matrix; According to the target white noise intensity control matrix, dimensionally expand the first augmented measurement matrix to obtain a third augmented measurement matrix; The basic measurement matrix and the third augmented measurement matrix are concatenated to obtain the coupling analysis matrix.

3. The method according to claim 2, characterized in that The determining a second signal-to-noise ratio of the second augmented measurement matrix includes: The second signal-to-noise ratio is calculated by the following formula, which is as follows: Wherein, SNR represents the second signal-to-noise ratio, Tr() represents the trace of the calculation matrix, Y represents the second augmented measurement matrix, represents the transposed matrix of the second augmented measurement matrix, represents the signal-to-noise ratio adjustment parameter, represents the initial white noise intensity control matrix, represents the transposed matrix of the initial white noise intensity control matrix.

4. The method according to any one of claims 1 to 3, characterized in that Determining T linear eigenvalue statistical difference values ​​according to the coupling analysis matrix includes: According to the dimension of the coupling analysis matrix, the dimension of the basic measurement matrix is ​​expanded to obtain a reference matrix; Get the size of the scroll window; According to the size of the rolling window, obtaining T first window data from the coupling analysis matrix; Determine a first eigenvalue set corresponding to each first window data in the T first window data to obtain T first eigenvalue sets; Determine T first linear eigenvalue statistics according to the T first eigenvalue sets; the T first linear eigenvalue statistics correspond one-to-one to the T first window data; According to the T first window data, T second window data are acquired from the reference matrix; the T first window data correspond to the T second window data one by one; Determine a second eigenvalue set corresponding to each second window data in the T second window data to obtain T second eigenvalue sets; Determine T second linear eigenvalue statistics according to the T second eigenvalue sets; the T second linear eigenvalue statistics correspond one-to-one to the T second window data; The T linear eigenvalue statistical differences are determined according to the T first linear eigenvalue statistics and the T second linear eigenvalue statistics.

5. The method according to claim 4, characterized in that The step of determining n first load data sets according to the T linear eigenvalue statistical difference values ​​comprises: Determine n second load data sets according to the a load data; each second load data set corresponds to an electrical device; Determine the linear eigenvalue statistical difference values ​​that are less than the preset difference value among the T linear eigenvalue statistical difference values, and obtain c linear eigenvalue statistical difference values; c is an integer greater than 1 and less than or equal to T; Obtaining c first window data from the T first window data according to the c linear eigenvalue statistical difference values; Determine, according to the c linear eigenvalue statistical difference values, an influence index of the environmental data in each of the c first window data on the load data; According to the influence index of the environmental data in each of the c first window data on the load data, determine the sum of the influence index corresponding to each load data in the d load data of the c first window data, and obtain d total influence indexes; the d load data are all the load data in the c first window data; Determining d adjusted load data according to the d total impact indexes and the d load data; The n second load data sets are updated according to the d adjusted load data to obtain the n first load data sets.

6. The method according to any one of claims 1 to 3, characterized in that: Before inputting the n first load data sets into the load forecasting model, the method further includes: Acquire multiple load association matrices from the coupling analysis matrix; the load association matrix includes load data corresponding to any two electrical devices among the n electrical devices; Determine an eigenvalue set corresponding to each load association matrix in the plurality of load association matrices to obtain a plurality of third eigenvalue sets; Any electric device corresponding to each load association matrix is ​​used as the associated electric device corresponding to the load association matrix, and the load data corresponding to the associated electric device of each load association matrix is ​​used as the associated load data of the load association matrix; Filling the associated load data of each load association matrix in the multiple load association matrices with preset white noise to obtain multiple associated reference matrices; Determine an eigenvalue set corresponding to each correlation reference matrix in the plurality of correlation reference matrices to obtain a plurality of fourth eigenvalue sets; Determining, according to the plurality of third eigenvalue sets and the plurality of fourth eigenvalue sets, a correlation degree between any two of the n electrical devices; According to the correlation degree between any two electrical devices among the n electrical devices, the n first load data sets are adjusted to obtain adjusted n first load data sets.

7. The method according to any one of claims 1 to 3, characterized in that: The method further comprises: Obtaining a preset load forecasting model; Acquire multiple training sets, test sets and validation sets; the training set includes n third load data sets of the n electrical devices in a first time period and n target third load data sets in a second time period, and each electrical device corresponds to a third load data set and a target third load data set; the test set includes n fourth load data sets of the n electrical devices in a third time period; the validation set includes n target fourth load data sets of the n electrical devices in a fourth time period, and each electrical device corresponds to a fourth load data set and a target fourth load data set; the time length of the first time period and the time length of the third time period are equal to the time length of the historical time period, and the time length of the second time period and the time length of the fourth time period are equal to the time length of the future time period; Taking n third load data sets of each training set in the multiple training sets as input of the preset load forecasting model, taking n target third load data sets of the training set as output of the preset load forecasting model, training the preset load forecasting model, and obtaining a candidate load forecasting model; Inputting the n fourth load data sets into the candidate load forecasting model to obtain n expected load data sets; Determining n mean square errors according to the n expected load data sets and the n target fourth load data sets; Determine the sum of the n mean square errors as the model loss; According to the model loss, the model parameters of the candidate load forecasting model are adjusted to obtain the load forecasting model.

8. A load forecasting device, characterized in that: include: an acquisition unit, configured to acquire T load data of each of n electrical devices in a historical time period, and obtain a load data; acquire T environmental data of the n electrical devices in the historical time period through each of m environmental sensors, and obtain b environmental data; the n electrical devices are in the same physical space; n, m, T are all integers greater than 1, a=n T, b = m T; A processing unit, used for constructing a basic measurement matrix according to the a load data; Constructing a first augmented measurement matrix according to the b environmental data; Determining a coupling analysis matrix according to the basic measurement matrix and the first augmented measurement matrix; Determining T linear eigenvalue statistical difference values ​​according to the coupling analysis matrix; Determining n first load data sets according to the T linear eigenvalue statistical difference values; The n first load data sets correspond one-to-one to the n electrical devices; The n first load data sets are input into a load prediction model to obtain a target first load data set for each of the n electrical devices in a future time period, thereby obtaining n target first load data sets.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the processor is connected to the memory, the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the electronic device executes the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method according to any one of claims 1 to 7.

Images