Power prediction method and device for new energy equipment, equipment and medium

Abstract

The embodiment of the invention discloses a power prediction method and device for new energy equipment, equipment and a medium, and the method comprises the steps: obtaining a preset fitting sequence, the preset fitting sequence is generated through the serialization of a fitting curve, and the fitting curve represents and sets the power change trend of the new energy equipment corresponding to environmental factors; according to a historical power sequence and a historical environment sequence of the new energy equipment, a historical operation sequence is generated, and the historical environment sequence comprises environment factors associated with the power of the new energy equipment; and determining the correlation between the historical operation sequence and a preset fitting sequence, and predicting the power of the new energy equipment according to the correlation. According to the technical scheme provided by the invention, the accuracy of power prediction can be improved in combination with the environmental factors of the new energy equipment when the power of the new energy equipment is predicted.

Description

Technical Field

[0001] The present invention relates to the field of deep learning, and in particular to a power prediction method, device, equipment and medium for new energy equipment. Background Art

[0002] With the continuous growth of global energy demand and the enhancement of environmental protection awareness, distributed new energy has gradually become one of the important energy supply methods. At the same time, the power of new energy equipment is one of the main technical parameters of new energy equipment. Therefore, in order to meet the current demand for the use of new energy equipment, power supervision and prediction of new energy equipment is extremely important.

[0003] However, the power of new energy equipment has significant volatility and uncertainty, which is mainly affected by multiple factors such as meteorological conditions and time factors. The current power prediction method cannot take into account the environmental factors of new energy equipment, which leads to low power prediction accuracy. Summary of the invention

[0004] The embodiments of the present invention provide a power prediction method, device, equipment and medium for new energy equipment. Through the technical solution of the present invention, when predicting the power of new energy equipment, the environmental factors of the new energy equipment can be combined to improve the accuracy of power prediction.

[0005] In a first aspect, an embodiment of the present invention provides a method for predicting power of a new energy device, comprising:

[0006] Acquire a preset fitting sequence, wherein the preset fitting sequence is generated by serializing a fitting curve, and the fitting curve represents a power change trend of the new energy equipment corresponding to a set environmental factor;

[0007] Generate a historical operation sequence according to a historical power sequence and a historical environment sequence of the new energy equipment, wherein the historical environment sequence includes environmental factors associated with the power of the new energy equipment;

[0008] The correlation between the historical operation sequence and the preset fitting sequence is determined, and the power of the new energy equipment is predicted according to the correlation.

[0009] In a second aspect, an embodiment of the present invention provides a power prediction device for new energy equipment, comprising:

[0010] An acquisition module, used for acquiring a preset fitting sequence, wherein the preset fitting sequence is generated by serializing a fitting curve, and the fitting curve represents a power change trend of the new energy equipment corresponding to a set environmental factor;

[0011] A splicing module, used to generate a historical operation sequence according to a historical power sequence and a historical environment sequence of the new energy equipment, wherein the historical environment sequence includes environmental factors associated with the power of the new energy equipment;

[0012] The prediction module is used to determine the correlation between the historical operation sequence and the preset fitting sequence, and predict the power of the new energy equipment according to the correlation.

[0013] In a third aspect, an embodiment of the present invention provides an electronic device, characterized in that the electronic device includes:

[0014] at least one processor; and,

[0015] a memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the power prediction method for new energy equipment described in any one of the embodiments of the present invention.

[0017] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the power prediction method for new energy equipment described in any one of the embodiments of the present invention when executed.

[0018] The embodiment of the present invention provides a power prediction method, device, equipment and medium for new energy equipment, the method comprising: obtaining a preset fitting sequence, wherein the preset fitting sequence is generated by serializing a fitting curve, the fitting curve characterizes the power change trend of the new energy equipment corresponding to the set environmental factors; generating a historical operation sequence according to the historical power sequence and the historical environmental sequence of the new energy equipment, wherein the historical environmental sequence includes the environmental factors associated with the power of the new energy equipment; determining the correlation between the historical operation sequence and the preset fitting sequence, and predicting the power of the new energy equipment according to the correlation. Specifically, the preset fitting sequence can characterize the power change trend of the new energy equipment corresponding to the environmental factors, and then predict the power of the new energy equipment by determining the correlation between the historical operation sequence of the new energy equipment and the preset fitting sequence, which can achieve the purpose of combining the environmental factors of the new energy equipment when predicting the power, thereby reducing the errors caused by the environmental factors and improving the accuracy of the power prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 A flowchart of a method for predicting power of new energy equipment provided in Embodiment 1 of the present invention;

[0021] Figure 2 A flowchart of a method for predicting power of new energy equipment provided in Embodiment 2 of the present invention;

[0022] Figure 3 A schematic diagram of power prediction of a new energy device provided by an embodiment of the present invention;

[0023] Figure 4 A schematic diagram of the structure of a power prediction device for new energy equipment provided in Embodiment 3 of the present invention;

[0024] Figure 5 A schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0025] 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.

[0026] 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.

[0027] It should be noted that the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in the technical solution of the present disclosure are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0028] Embodiment 1

[0029] Figure 1 A flowchart of a power prediction method for new energy equipment provided in Example 1 of the present invention. The method can be applied to situations where power prediction is performed on new energy equipment in combination with environmental data and power data of the new energy equipment. The method can be executed by a power prediction device for the new energy equipment, which can be composed of software and / or hardware and configured in a computer or server.

[0030] like Figure 1 As shown, including:

[0031] Step 110: Obtain a preset fitting sequence, wherein the preset fitting sequence is generated by serializing a fitting curve, and the fitting curve represents a power change trend of the new energy equipment corresponding to a set environmental factor.

[0032] The preset fitting sequence is a time series sequence, which is generated by serializing a fitting curve, and the fitting curve represents the power change trend of the new energy equipment corresponding to the set environmental factors.

[0033] Specifically, different environmental factors may affect the input / output power of new energy equipment. For example, strong winds may increase the input power of the generator fan, while rainy weather may reduce the input power of the generator fan. Therefore, for the power prediction of new energy equipment, it is necessary not only to refer to its own power data, but also to combine specific environmental factors, such as weather factors, so as to improve the accuracy of the power prediction of new energy equipment.

[0034] Optionally, the method for determining the fitting curve includes:

[0035] Acquire a power data set and an environmental data set of a new energy device; fit a preset curve according to the power data set and the environmental data set to determine candidate fitting parameters; if a candidate fitting curve corresponding to the candidate fitting parameters satisfies a preset fitting error, determine the candidate fitting curve as the fitting curve.

[0036] Among them, the power data set of new energy equipment can be the power data of new energy equipment in historical work, such as input power, output power and rated power, etc.; the environmental data set includes the environmental change data during the historical operation of new energy equipment, such as weather changes, temperature and humidity changes, etc. Specifically, the data of the power data set and environmental data set of new energy equipment can be a time series, representing the power changes and environmental changes of new energy equipment at different times.

[0037] Among them, the candidate fitting parameters are the curve parameters of the preset curve in the fitting process, such as the values ​​of each point of the curve, the slope and the intercept, etc. Specifically, different candidate fitting parameters will directly affect the accuracy of the fitting curve. Therefore, for the candidate fitting curve corresponding to the candidate fitting parameters, it is necessary to combine the real power data to determine the fitting error. If the fitting error is less than the preset fitting error, it indicates that the fitting is successful, and then the corresponding candidate fitting curve can be determined as the fitting curve. Exemplarily, the fitting algorithm can be the Prophet algorithm.

[0038] Optionally, fitting the preset curve according to the power data set and the environment data set to determine candidate fitting parameters includes:

[0039] Fitting the first curve, the second curve and the third curve according to the power data set and the environment data set to determine candidate curve parameters of the first curve, the second curve and the third curve;

[0040] The candidate curve parameters of the first curve are used to characterize the characteristics of non-periodic changes in power of the new energy equipment caused by environmental changes;

[0041] The candidate curve parameters of the second curve are used to characterize the characteristics of the periodic change of power of the new energy equipment caused by environmental changes;

[0042] The candidate curve parameters of the third curve are used to characterize the characteristics of irregular power changes of the new energy equipment caused by environmental changes.

[0043] Specifically, the candidate curve parameters of the first curve may characterize the characteristics of non-periodic changes in power of the new energy equipment caused by environmental changes, such as the overall change trend of power within a preset time period, such as an overall increasing trend or a decreasing trend.

[0044] Specifically, the candidate curve parameters of the second curve can characterize the characteristics of the periodic changes in power of new energy equipment caused by environmental changes. It can be understood that, for example, the periodic change trend of power can be the periodic fluctuation of power caused by seasonal changes. In winter and summer every year, the power demand increases and the output power of the new energy equipment increases.

[0045] Specifically, the candidate curve parameters of the third curve characterize the characteristics of irregular changes in the power of the new energy equipment caused by environmental changes. Specifically, the environment may suddenly change, thereby affecting the power input and output of the new energy equipment. For example, a sudden change in weather will affect the power input of the new energy equipment.

[0046] Furthermore, the first curve, the second curve and the third curve can characterize the power impact of the new energy equipment caused by environmental changes from multiple dimensions, thereby reducing the error caused by the environment during power prediction and improving the accuracy of the prediction.

[0047] Exemplarily, the fitting curve can be y(t)=g(t)+s(t)+h(t)+∈(t), where g(t) describes the long-term trend of change in time series data, captures the impact of non-periodic factors on the numerical value and the first curve; s(t) represents periodic fluctuations, weekly or annual seasonal changes, that is, the second curve; h(t) represents the impact of holidays with irregular schedules that may occur within one or more days, that is, the third curve; the error term ∈(t) represents random and unpredictable fluctuations.

[0048] Step 120: Generate a historical operation sequence according to the historical power sequence and the historical environment sequence of the new energy equipment, wherein the historical environment sequence includes environmental factors associated with the power of the new energy equipment.

[0049] Among them, the historical power series and the historical environment series can be the sequence data within the historical time period of the new energy equipment.

[0050] Specifically, since the present application needs to combine the power data and environmental data of new energy equipment when predicting power, the acquired historical power series and historical environmental series need to be preprocessed to generate a historical operation series in order to achieve the goal of improving the prediction accuracy. The specific method is as follows.

[0051] Step 130: Determine the correlation between the historical operation sequence and the preset fitting sequence, and predict the power of the new energy equipment according to the correlation.

[0052] Specifically, the correlation can characterize the association between the historical operation sequence and the preset fitting sequence. The correlation can reflect the power change trend of the new energy equipment corresponding to the historical operation sequence, thereby achieving the purpose of completing the power prediction of the new energy equipment through the power change trend.

[0053] Optionally, if the predicted power represented by the power prediction result is greater than the rated power of the new energy equipment, an alarm is issued.

[0054] An embodiment of the present invention provides a power prediction method for new energy equipment, the method comprising: obtaining a preset fitting sequence, wherein the preset fitting sequence is generated by serializing a fitting curve, the fitting curve characterizing the power change trend of the new energy equipment corresponding to a set environmental factor; generating a historical operation sequence according to a historical power sequence and a historical environmental sequence of the new energy equipment, wherein the historical environmental sequence includes environmental factors associated with the power of the new energy equipment; determining the correlation between the historical operation sequence and the preset fitting sequence, and predicting the power of the new energy equipment according to the correlation. Specifically, the preset fitting sequence can characterize the power change trend of the new energy equipment corresponding to the environmental factor, and then predict the power of the new energy equipment by determining the correlation between the historical operation sequence of the new energy equipment and the preset fitting sequence, so as to achieve the purpose of combining the environmental factors of the new energy equipment in the power prediction, thereby reducing the error caused by environmental factors in the power prediction and improving the accuracy of the power prediction.

[0055] Embodiment 2

[0056] Figure 2 This is a flow chart of a power prediction method for new energy equipment provided in the second embodiment of the present invention. Based on the above embodiments, this embodiment further defines a method for generating a historical operation sequence according to a historical power sequence and a historical environment sequence of the new energy equipment.

[0057] like Figure 2 As shown, including:

[0058] Step 210: Obtain a preset fitting sequence, wherein the preset fitting sequence is generated by serializing a fitting curve, and the fitting curve represents a power change trend of the new energy equipment corresponding to a set environmental factor.

[0059] Step 220: preprocess the historical power sequence and the historical environment sequence to obtain preprocessed historical power sequence and historical environment sequence, wherein the preprocessed historical power sequence has the same dimension as the historical environment sequence.

[0060] Specifically, before power prediction, the historical power sequence and the historical environment sequence need to be preprocessed so that they have the same format and correspond to each other. Furthermore, the historical power sequence and the historical environment sequence of the same period can be determined as sequences with a corresponding relationship. Furthermore, in order to ensure the accuracy of subsequent operations, it is necessary to ensure that the dimensions of the historical power sequence and the historical environment sequence are the same.

[0061] Optionally, step 220 includes:

[0062] Get the preset sequence element time interval and the preset sequence length;

[0063] Specifically, since different elements of the historical power sequence and the historical environmental sequence represent power data and environmental data at different times, in order to ensure the accuracy of subsequent calculations, it is necessary to unify the time intervals between the elements of the historical power sequence and the historical environmental sequence, that is, to determine the time intervals between sequence elements as preset sequence element time intervals, such as the time interval between each element in the historical power sequence and the historical environmental sequence is one hour. Furthermore, due to the deviation in data collection itself, the sequence lengths of different sequences may be different, such as sequence A represents data from 3 to 5 o'clock every day, and sequence B represents data from 3 to 6 o'clock. Therefore, it is necessary to unify the lengths of the sequences, that is, to unify the sequence lengths to the preset sequence lengths.

[0064] Adjusting the sequence elements of the historical power sequence and / or the historical environment sequence so that the time intervals of the sequence elements of the adjusted historical power sequence and / or the historical environment sequence are the preset sequence element time intervals;

[0065] Optionally, the least common multiple of the initial time intervals of the sequence elements of the historical power sequence and / or the historical environment sequence can be determined as the preset sequence element time interval, and then by adjusting the sequence elements of the historical power sequence and / or the historical environment sequence, only the elements of the preset sequence element time interval are retained in the sequence. Exemplarily, if the sequence A is (0, 1, 2, 3, 4, 5, 6) and the sequence B is (0, 2, 4, 6, 8), therefore, the least common multiple of the initial time intervals of the sequence A and the sequence B is 2, then the preset sequence element time interval can be set to 2, and the elements of the A and B sequences are adjusted, and after the adjustment, A is (0, 2, 4, 6) and B is (0, 2, 4, 6, 8).

[0066] If the length of the historical power sequence and the historical environment sequence is greater than the preset sequence length, deleting the sequence elements exceeding the length;

[0067] If the length of the historical power sequence and the historical environment sequence is less than the preset sequence length, the last element of the historical power sequence and the historical environment sequence is determined as a supplementary element, and the historical power sequence and the historical environment sequence are supplemented to the preset sequence length through the supplementary element.

[0068] Specifically, in order to ensure that the length of the historical power sequence and the historical environment sequence is the same as the preset sequence length, the overly long sequence can be deleted, or the overly short sequence can be supplemented. If the length of the historical power sequence and the historical environment sequence is greater than the preset sequence length, the sequence elements that exceed the length are deleted; if the length of the historical power sequence and the historical environment sequence is less than the preset sequence length, the last element of the historical power sequence and the historical environment sequence is determined as the supplementary element, and the historical power sequence and the historical environment sequence are supplemented to the preset sequence length through the supplementary element.

[0069] For example, if sequence A is (0, 2, 4, 6) and sequence B is (0, 2, 4, 6, 8), and the preset sequence length is 4, then 8 in sequence B can be deleted. If the preset sequence length is 5, 6 in sequence A can be determined as the complementary element, and sequence A can be supplemented to (0, 2, 4, 6, 6).

[0070] Through the above method, the dimensions of the historical power series and the historical environment series can be made the same, which is convenient for subsequent calculations and can improve the accuracy of prediction.

[0071] Step 230: splice the preprocessed historical power sequence and historical environment sequence to generate a historical operation sequence.

[0072] Specifically, the splicing method may be to splice the preprocessed historical power sequence and the historical environment sequence head to tail or to group the corresponding elements of the historical power sequence and the historical environment sequence into a vector group, which is not limited here.

[0073] Step 240: concatenate the historical operation sequence and the preset fitting sequence to generate a feature sequence, wherein the dimension of the feature sequence is determined by the number of environmental parameters in the historical operation sequence.

[0074] Specifically, the historical operation sequence and the preset fitting sequence may be spliced ​​together by connecting the beginning and the end or by forming corresponding elements of the historical power sequence and the historical environment sequence into a vector group, which is not limited here.

[0075] Exemplarily, the feature sequence may be in the following form: X = {X LMD ,X P}∈R T*(N+1) , where X LMD is the historical running sequence, X P is the preset fitting sequence, T is the time parameter, N is the number of parameter variables, and further, the feature sequence can contain the information of the values ​​of multiple variables at the same time step. Furthermore, the feature sequence can be mapped to a high dimension through the following formula To improve the generalization ability of the model.

[0076] Step 250: input the feature sequence into a pre-trained prediction model, and determine the query matrix, key matrix and value matrix through the prediction model based on the weight matrix and the feature sequence, wherein the prediction model includes a sparse self-attention layer, and the sparse self-attention layer is used to determine the correlation between the query matrix, key matrix and value matrix, and the matrix elements in the weight matrix are updated during the training process of the sparse self-attention layer.

[0077] Among them, the attention mechanism optimized by the sparse self-attention layer is used to calculate the query matrix, key matrix and value matrix corresponding to the feature sequence through the weight matrix.

[0078] Specifically, during the training process, the first weight matrix can be a unit matrix, and during the training process, the elements of the weight matrix are continuously updated through the sparse self-attention layer, and then after the prediction model is successfully trained, a weight matrix that meets the preset training conditions is determined. Optionally, the weight matrix can include a first matrix, a second matrix, and a third matrix, which are used to perform point multiplication operations with the feature sequence to generate a query matrix, a key matrix, and a value matrix corresponding to the feature sequence, respectively.

[0079] Specifically, by inputting the feature sequence into the pre-trained prediction model, the training model will perform calculations based on the feature sequence and the weight matrix to determine the query matrix, the key matrix, and the value matrix.

[0080] Optionally, the query matrix, key matrix, and value matrix may be determined by the following formula.

[0081] A=X*W_A

[0082] B=X*W_B

[0083] C=X*W_C

[0084] Among them, W_A, W_B, W_C are the first matrix, second matrix and third matrix that are successfully trained, A, B, C are the query matrix, key matrix and value matrix respectively.

[0085] Step 260: Determine the dependency relationship between power and environmental factors according to the correlation between the query matrix, the key matrix and the value matrix, and predict the power of the new energy device according to the dependency relationship between power and environmental factors.

[0086] Optionally, the correlation determination formula can be

[0087]

[0088] Among them, A, B, and C are query matrix, key matrix, and value matrix respectively. Bis the dimension of the key matrix vector, and Softmax is the activation function. Specifically, through this formula, the dot product range can be reduced, the gradient stability of softmax can be guaranteed, and the accuracy of correlation calculation can be improved.

[0089] Specifically, the correlation can represent the dependence between power and environmental factors. If the correlation is greater, it means that the current power is seriously affected by the environment, otherwise, the current power is not seriously affected by the environment.

[0090] Furthermore, by determining the dependency between power and environmental factors, the power of the new energy device can be predicted. The specific method is not limited here.

[0091] For example, Figure 3 A schematic diagram of power prediction of a new energy device provided in an embodiment of the present invention.

[0092] Specifically, Figure 3 It is mainly divided into two parts. The first part is the fitting of the prophet model, and the second part is to predict the power of new energy equipment through the sparse self-attention mechanism.

[0093] Specifically, in the first part, it is necessary to input the power data and meteorological data of the new energy equipment, and then preprocess the power data and meteorological data to unify their formats, generate power data sets and environmental data sets, and further, the prophet model can be used to decompose the samples in the data set to determine the trend term (first curve), seasonal term (second curve), holiday term (third curve) and residual term, that is, to determine the fitting result (fitting curve).

[0094] In the second part, it is necessary to first obtain the meteorological data and power data of the new energy equipment, and then perform normalization processing to generate the historical operation sequence. Furthermore, the historical operation sequence and the fitting results are input into the inverted embedding layer, which can learn the feature representation of the input sequence and improve the performance of the model by independently aggregating the global features of each input sequence. Furthermore, by inputting the sequence into the sparse self-attention layer, the query matrix, key matrix and value matrix of the input sequence are determined, and then the correlation is determined based on the query matrix, key matrix and value matrix, and then the power prediction is completed through the correlation.

[0095] An embodiment of the present invention provides a power prediction method for new energy equipment. According to the method, a pre-trained prediction model is input through a feature sequence to determine the query matrix, key matrix and value matrix corresponding to the feature sequence, and then the power can be predicted through the correlation between the query matrix, key matrix and value matrix. The method can effectively combine the environmental factors of the new energy equipment during power prediction, thereby reducing the error caused by environmental factors during power prediction and improving the accuracy of power prediction.

[0096] Embodiment 3

[0097] Figure 4 A schematic diagram of a power prediction device for a new energy device provided in the third embodiment of the present invention. The device can be used to execute any power prediction method for a new energy device described in the embodiments of the present invention.

[0098] like Figure 4 As shown, the device comprises:

[0099] An acquisition module 310 is used to acquire a preset fitting sequence, wherein the preset fitting sequence is generated by serializing a fitting curve, and the fitting curve represents a power change trend of the new energy device corresponding to a set environmental factor;

[0100] A splicing module 320, configured to generate a historical operation sequence according to a historical power sequence and a historical environment sequence of the new energy device, wherein the historical environment sequence includes environmental factors associated with the power of the new energy device;

[0101] The prediction module 330 is used to determine the correlation between the historical operation sequence and the preset fitting sequence, and predict the power of the new energy equipment according to the correlation.

[0102] An embodiment of the present invention provides a power prediction device for a new energy device, the device obtains a preset fitting sequence, wherein the preset fitting sequence is generated by serializing a fitting curve, and the fitting curve characterizes the power change trend of the new energy device corresponding to a set environmental factor; generates a historical operation sequence according to a historical power sequence and a historical environmental sequence of the new energy device, wherein the historical environmental sequence includes environmental factors associated with the power of the new energy device; determines the correlation between the historical operation sequence and the preset fitting sequence, and predicts the power of the new energy device according to the correlation. Specifically, the preset fitting sequence can characterize the power change trend of the new energy device corresponding to the environmental factor, and then predict the power of the new energy device by determining the correlation between the historical operation sequence of the new energy device and the preset fitting sequence, so as to achieve the purpose of combining the environmental factors of the new energy device during power prediction, thereby reducing the error caused by environmental factors during power prediction and improving the accuracy of power prediction.

[0103] Optionally, the device further includes: a fitting module, used to determine a fitting curve.

[0104] The fitting module comprises:

[0105] Acquisition unit, used to obtain power data set and environmental data set of new energy equipment

[0106] A fitting unit is used to fit a preset curve according to the power data set and the environmental data set to determine candidate fitting parameters

[0107] A determination unit is configured to determine the candidate fitting curve as the fitting curve if the candidate fitting curve corresponding to the candidate fitting parameter satisfies a preset fitting error.

[0108] The fitting unit is specifically used to fit the first curve, the second curve and the third curve according to the power data set and the environmental data set, and determine the candidate curve parameters of the first curve, the second curve and the third curve, and the candidate curve parameters of the first curve are used to characterize the characteristics of the non-periodic change of power of the new energy equipment caused by environmental changes;

[0109] The candidate curve parameters of the second curve are used to characterize the characteristics of the periodic change of power of the new energy equipment caused by environmental changes;

[0110] The candidate curve parameters of the third curve are used to characterize the characteristics of irregular power changes of the new energy equipment caused by environmental changes.

[0111] Optionally, the splicing module 320 includes:

[0112] A preprocessing unit, used for preprocessing the historical power sequence and the historical environment sequence to obtain the preprocessed historical power sequence and the historical environment sequence, wherein the preprocessed historical power sequence has the same dimension as the historical environment sequence;

[0113] The splicing unit is used to splice the pre-processed historical power sequence and historical environment sequence to generate a historical operation sequence.

[0114] Optionally, the preprocessing unit includes:

[0115] An acquisition subunit, used to acquire a preset sequence element time interval and a preset sequence length;

[0116] An adjusting unit, used for adjusting the sequence elements of the historical power sequence and / or the historical environment sequence so that the time interval of the sequence elements of the adjusted historical power sequence and / or the historical environment sequence is a preset sequence element time interval;

[0117] A judgment unit is used to delete the sequence elements that exceed the length if the length of the historical power sequence and the historical environment sequence is greater than the preset sequence length; if the length of the historical power sequence and the historical environment sequence is less than the preset sequence length, the last element of the historical power sequence and the historical environment sequence is determined as a supplementary element, and the historical power sequence and the historical environment sequence are supplemented to the preset sequence length through the supplementary element.

[0118] Optionally, the prediction module 330 includes:

[0119] A splicing unit, used for splicing the historical operation sequence and the preset fitting sequence to generate a feature sequence, wherein the dimension of the feature sequence is determined by the number of environmental parameters in the historical operation sequence;

[0120] a matrix determination unit, configured to input the feature sequence into a pre-trained prediction model, and determine a query matrix, a key matrix, and a value matrix through the prediction model based on a weight matrix and the feature sequence, wherein the prediction model includes a sparse self-attention layer, the sparse self-attention layer is configured to determine the correlation between the query matrix, the key matrix, and the value matrix, and the matrix elements in the weight matrix are updated during the training process of the sparse self-attention layer;

[0121] A prediction unit is used to determine the dependency relationship between power and environmental factors according to the correlation between the query matrix, the key matrix and the value matrix, and predict the power of the new energy device according to the dependency relationship between power and environmental factors.

[0122] Optionally, the power prediction device for new energy equipment further includes an alarm unit for issuing an alarm if the predicted power represented by the power prediction result is greater than the rated power of the new energy equipment.

[0123] The power prediction device for new energy equipment provided by the embodiment of the present invention can execute the power prediction method for new energy equipment provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0124] Embodiment 4

[0125] Figure 5 The present invention is a block diagram of an electronic device 10 that can be used to implement an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0126] like Figure 5As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0127] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0128] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The processor 11 executes the various methods and processes described above, such as a power prediction method for new energy equipment.

[0129] In some embodiments, the power prediction method of the new energy device can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the power prediction method of the new energy device described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute the power prediction method of the new energy device by any other appropriate means (for example, by means of firmware).

[0130] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0131] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0132] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0133] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0134] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0135] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0136] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0137] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A power prediction method for new energy equipment, characterized in that: include: Acquire a preset fitting sequence, wherein the preset fitting sequence is generated by serializing a fitting curve, and the fitting curve represents a power change trend of the new energy equipment corresponding to a set environmental factor; Generate a historical operation sequence according to a historical power sequence and a historical environment sequence of the new energy equipment, wherein the historical environment sequence includes environmental factors associated with the power of the new energy equipment; The correlation between the historical operation sequence and the preset fitting sequence is determined, and the power of the new energy equipment is predicted according to the correlation.

2. The method according to claim 1, characterized in that The method for determining the fitting curve comprises: Obtain power data sets and environmental data sets for new energy equipment; Fitting a preset curve according to the power data set and the environmental data set to determine candidate fitting parameters; If the candidate fitting curve corresponding to the candidate fitting parameter satisfies the preset fitting error, the candidate fitting curve is determined as the fitting curve.

3. The method according to claim 2, characterized in that The step of fitting the preset curve according to the power data set and the environment data set to determine candidate fitting parameters includes: Fitting the first curve, the second curve and the third curve according to the power data set and the environment data set to determine candidate curve parameters of the first curve, the second curve and the third curve; The candidate curve parameters of the first curve are used to characterize the characteristics of non-periodic changes in power of the new energy equipment caused by environmental changes; The candidate curve parameters of the second curve are used to characterize the characteristics of the periodic change of power of the new energy equipment caused by environmental changes; The candidate curve parameters of the third curve are used to characterize the characteristics of irregular power changes of the new energy equipment caused by environmental changes.

4. The method according to claim 1, characterized in that: The generating of the historical operation sequence according to the historical power sequence and the historical environment sequence of the new energy equipment includes: Preprocessing the historical power sequence and the historical environment sequence to obtain a preprocessed historical power sequence and a historical environment sequence, wherein the preprocessed historical power sequence has the same dimension as the historical environment sequence; The preprocessed historical power sequence and historical environment sequence are concatenated to generate a historical operation sequence.

5. The method according to claim 4, characterized in that The preprocessing of the historical power sequence and the historical environment sequence includes: Get the preset sequence element time interval and the preset sequence length; Adjusting the sequence elements of the historical power sequence and / or the historical environment sequence so that the time intervals of the sequence elements of the adjusted historical power sequence and / or the historical environment sequence are preset sequence element time intervals; If the length of the historical power sequence and the historical environment sequence is greater than the preset sequence length, deleting the sequence elements exceeding the length; If the length of the historical power sequence and the historical environment sequence is less than the preset sequence length, the last element of the historical power sequence and the historical environment sequence is determined as a supplementary element, and the historical power sequence and the historical environment sequence are supplemented to the preset sequence length through the supplementary element.

6. The method according to claim 1, characterized in that The determining the correlation between the historical operation sequence and the preset fitting sequence, and predicting the power of the new energy equipment according to the correlation, includes: The historical operation sequence and the preset fitting sequence are spliced ​​to generate a feature sequence, wherein the dimension of the feature sequence is determined by the number of environmental parameters in the historical operation sequence; Inputting the feature sequence into a pre-trained prediction model, determining a query matrix, a key matrix, and a value matrix through the prediction model based on a weight matrix and the feature sequence, wherein the prediction model includes a sparse self-attention layer, the sparse self-attention layer is used to determine the correlation between the query matrix, the key matrix, and the value matrix, and the matrix elements in the weight matrix are updated during the training process of the sparse self-attention layer; The dependency relationship between power and environmental factors is determined according to the correlation between the query matrix, the key matrix and the value matrix, and the power of the new energy device is predicted according to the dependency relationship between power and environmental factors.

7. The method according to claim 1, characterized in that Also includes: If the predicted power represented by the power prediction result is greater than the rated power of the new energy equipment, an alarm is issued.

8. A power prediction device for new energy equipment, characterized in that: include: An acquisition module, used for acquiring a preset fitting sequence, wherein the preset fitting sequence is generated by serializing a fitting curve, and the fitting curve represents a power change trend of the new energy equipment corresponding to a set environmental factor; A splicing module, used to generate a historical operation sequence according to a historical power sequence and a historical environment sequence of the new energy equipment, wherein the historical environment sequence includes environmental factors associated with the power of the new energy equipment; The prediction module is used to determine the correlation between the historical operation sequence and the preset fitting sequence, and predict the power of the new energy equipment according to the correlation.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the power prediction method for new energy equipment according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the power prediction method for new energy equipment according to any one of claims 1 to 7 when executed.

Images