Power measuring and calculating method, device and equipment and readable storage medium

Abstract

The invention provides a power measuring and calculating method, device and equipment and a readable storage medium. The power measuring and calculating method comprises the following steps: acquiring branch current data and serial number information of an inverter and meteorological data of a power station; inputting the branch current data, the number information and the meteorological data of the power station into a power measurement and calculation model; converting the number information into a corresponding embedded vector; splicing features corresponding to the embedded vector, the branch current data and the meteorological data of the power station to obtain a joint feature; and obtaining the measured power of the inverter according to the joint characteristics. Through the number information of the inverters, the difference of the operating parameters between different inverters can be accurately distinguished. The power measurement and calculation model is trained based on various data of each inverter, and the power of the inverter is measured and calculated based on the trained power measurement and calculation model, so that the accuracy and reliability of power measurement and calculation are improved.

Description

Technical Field

[0001] The present application belongs to the field of photovoltaic power generation technology and relates to a power measurement method, and in particular to a power measurement method, device, equipment and readable storage medium. Background Art

[0002] In the field of photovoltaic power generation, the accuracy of inverter power measurement is crucial to improving power generation efficiency and energy configuration. Traditional power measurement methods rely on manual work in feature selection and extraction, resulting in subjective and uncertain measurement results, as well as low efficiency and insufficient generalization when processing large-scale data. At the same time, traditional power measurement methods focus on conventional meteorological and physical parameters in the selection of input features, which fails to fully reflect the actual working status of the inverter, affecting the accuracy and reliability of power measurement. Therefore, how to improve the accuracy and reliability of inverter power measurement has become a technical problem that needs to be solved urgently. Summary of the invention

[0003] The present application provides a power measurement method, device, equipment and readable storage medium, which are used to solve the technical problem of poor accuracy of inverter power measurement in the prior art.

[0004] In a first aspect, an embodiment of the present application provides a power calculation method, the method comprising: obtaining branch current data, numbering information and meteorological data of the inverter; inputting the branch current data, the numbering information and the meteorological data of the power station into a power calculation model; converting the numbering information into a corresponding embedded vector; concatenating features corresponding to the embedded vector, the branch current data and the meteorological data of the power station to obtain a joint feature; and obtaining the calculated power of the inverter based on the joint feature.

[0005] In an implementation of the first aspect, the power measurement model includes: an input layer, an embedding layer, a feature combination layer, an attention layer, a residual structure and a fully connected layer.

[0006] In an implementation manner of the first aspect, the embedding vector includes semantic information corresponding to the numbering information.

[0007] In an implementation of the first aspect, the training method of the power measurement model includes: constructing a data sample set, wherein the data sample set includes branch current data, power data, numbering information of the inverter and meteorological data of the power station; and training the power measurement model based on the data sample set.

[0008] In an implementation of the first aspect, the power calculation model is trained based on the data sample set, including: obtaining a training set and a validation set based on the data sample set; inputting each group of training data in the training set into the power calculation model in turn, and updating the power calculation model according to the loss function value to obtain the power calculation model with the minimum loss function value; in the process of training the power calculation model, verifying the power calculation model based on the validation set within a preset time interval.

[0009] In an implementation manner of the first aspect, the branch current data, the power data, the numbering information, and the meteorological data of the power station in the data sample set are data at different times and under different meteorological conditions.

[0010] In an implementation of the first aspect, before inputting the branch current data, the numbering information and the meteorological data of the power station into the power measurement model, the method also includes: preprocessing the branch current data, the numbering information and the meteorological data of the power station, and the preprocessing includes: missing value processing, outlier processing and data normalization processing.

[0011] The embodiment of the present application provides a power measurement method, in which the differences in operating parameters between different inverters can be distinguished by obtaining the serial number information of the inverter, thereby improving the accuracy and reliability of power measurement. In addition, the branch current data in the operating parameters can directly reflect the actual working conditions of the inverter and its branches, providing a more accurate and comprehensive information basis for power measurement.

[0012] In a second aspect, an embodiment of the present application provides a power measuring device, which includes: a data acquisition module, used to obtain branch current data, numbering information and meteorological data of the inverter; a data input module, used to input the branch current data, the numbering information and the meteorological data of the power station into a power measuring model, and a vector conversion module, used to convert the numbering information into a corresponding embedded vector; a feature splicing module, used to splice the embedded vector with features corresponding to the branch current data, the numbering information and the meteorological data of the power station to obtain a joint feature; and a power measuring module, used to obtain the measured power of the inverter according to the joint feature.

[0013] In a third aspect, an embodiment of the present application provides an electronic device, comprising a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program and implement a power measurement method as described in any one of the first aspects of the embodiments of the present application when executing the computer program.

[0014] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the power measurement method described in any one of the first aspects of the embodiments of the present application is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 Shown is a schematic diagram of an application scenario of inverter power measurement provided by an embodiment of the present application.

[0016] Figure 2 Shown is a flow chart of a power measurement method provided by an embodiment of the present application.

[0017] Figure 3 Shown is a flow chart of a training method for a power measurement model in one embodiment of the present application.

[0018] Figure 4 Shown is a flow chart for determining a power measurement model in one embodiment of the present application.

[0019] Figure 5 Shown is a structural diagram of a power calculation model in one embodiment of the present application

[0020] Figure 6 Shown is a schematic diagram of a power measurement device in an embodiment of the present application.

[0021] Figure 7 Shown is a schematic diagram of the structure of an electronic device in an embodiment of the present application.

[0022] Component number description

[0023] Steps S21 to S25

[0024] Steps S31 to S32

[0025] Steps S41 to S43

[0026] 51 Input layer

[0027] 52 Embedding layer

[0028] 53 Feature combination layer

[0029] 54 Attention Layer

[0030] 55 Residual Structure

[0031] 56 Fully connected layers

[0032] 60 Power measurement device

[0033] 61 Data acquisition module

[0034] 62 Power measurement module

[0035] 70 Electronic equipment

[0036] 71 Processor

[0037] 72 Non-volatile storage media

[0038] 73 System Bus

[0039] 74 Internal memory

[0040] 75 Network Interface DETAILED DESCRIPTION

[0041] The following describes the embodiments of the present application through specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0042] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application, and thus the drawings only show components related to the present application rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the form, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0043] The embodiment of the present application provides a power calculation method. The power calculation method can obtain the branch current data, numbering information and meteorological data of the inverter; input the branch current data, numbering information and meteorological data of the power station into the power calculation model; convert the numbering information into a corresponding embedded vector; splice the features corresponding to the embedded vector, the branch current data and the meteorological data of the power station to obtain a joint feature; obtain the calculated power of the inverter according to the joint feature, which can solve the technical problem of low accuracy of inverter power calculation.

[0044] Figure 1 The following is a schematic diagram of an application scenario of inverter power calculation provided by an embodiment of the present application. Figure 1As shown, the application scenario includes a data acquisition system and electronic equipment. The data acquisition system is used to collect branch current data, numbering information and meteorological data of all inverters in the power station, and send the collected data to the electronic equipment. A power measurement model is deployed in the electronic equipment, and the power of the corresponding inverter can be measured by the power measurement model. The electronic equipment sends the measured power to the power station, and the power station optimizes the energy configuration according to the measured power of the inverter, thereby improving the power generation efficiency.

[0045] The technical solutions in the embodiments of the present application will be described in detail below in conjunction with the drawings in the embodiments of the present application.

[0046] Figure 2 The flowchart of the power measurement method provided by an embodiment of the present application is shown. Figure 2 As shown, the power measurement method provided in the embodiment of the present application includes the following steps S21 to S25.

[0047] S21, obtaining branch current data and numbering information of the inverter and meteorological data of the power station.

[0048] Specifically, the branch current data of the inverter may be obtained from the power station.

[0049] Among them, the branch current data specifically records the current changes of the inverter under different lighting conditions and load requirements, which directly reflects the dynamic response capability and performance status of the inverter. Based on the branch current data, the power data output by the inverter under different working conditions can be accurately calculated, significantly improving the accuracy of power measurement.

[0050] The meteorological data of the power station records the environmental status of the power station during operation. The meteorological data of the power station includes key parameters such as wind direction, wind speed, temperature, humidity and radiation. The meteorological data has a significant impact on the power data output by the inverter in the power station.

[0051] For example, in the field of photovoltaic power inverters, changes in meteorological data such as solar radiation will directly affect the power generation efficiency of photovoltaic panels, and thus have a direct impact on the power output of the inverter. Fluctuations in temperature and humidity will also affect the heat dissipation performance and overall working efficiency of the inverter. Therefore, meteorological data not only provides the necessary environmental basis for power station operation, but also simulates the operation of power stations under different meteorological conditions, and can more accurately calculate power values, providing a scientific basis for the efficient operation of power stations and the formulation of optimization strategies.

[0052] For example, the inverter number information can be obtained by numbering the inverters. Furthermore, when the inverters are numbered, each inverter number is unique, which can facilitate accurate distinction and identification of various data of each inverter.

[0053] In some embodiments, before inputting the branch current data, the numbering information and the meteorological data of the power station into the power measurement model, the method also includes: preprocessing the branch current data, the numbering information and the meteorological data of the power station, and the preprocessing includes: missing value processing, outlier processing and data normalization processing.

[0054] Exemplarily, the missing value processing includes: checking whether there are missing values ​​in the branch current data, numbering information of the inverter and the meteorological data of the power station. If there are missing values, the data row where the missing value is located is deleted to maintain the authenticity and reliability of the data. In the case of a small amount of data, interpolation or model-based methods (for example, using a machine learning model to calculate the missing values) can also be used to fill in the missing values, wherein the interpolation method includes linear interpolation, neighboring value interpolation, etc.

[0055] Exemplarily, outlier processing includes: performing outlier detection on all branch current data, the numbering information, and the meteorological data of the power station. If an outlier is detected, the data row where the outlier is located is deleted to avoid the outlier from adversely affecting the accuracy and stability of the calculated power output by the power calculation model. In the case of a small amount of data, boundary value replacement, smoothing processing, or a statistical-based method can be used to fill in outliers, wherein the method of filling in outliers includes a box plot method, a regression method, and the like.

[0056] Exemplarily, data normalization includes: scaling branch current data, number information, and meteorological data of the power station to a specific range to optimize feature weights and improve the performance and generalization ability of the power measurement model. The specific range may be [0, 1] or [0, 10], etc.

[0057] It should be noted that the specific methods or steps for missing value processing and data normalization mentioned in the above preprocessing are only for illustrative purposes. In practical applications, any suitable method can be selected according to actual needs to achieve the preprocessing of the above data, and this application does not impose any restrictions on this.

[0058] S22, inputting the branch current data, the numbering information and the meteorological data of the power station into a power calculation model.

[0059] Specifically, the branch current data, the numbering information and the meteorological data of the power station input into the power calculation model are pre-processed data.

[0060] Exemplarily, the branch current data, the numbering information and the meteorological data of the power station may be input into the power estimation model in batches or in real time.

[0061] In some embodiments, the power measurement model includes: an input layer, an embedding layer, a feature combination layer, an attention layer, a residual structure and a fully connected layer.

[0062] The input layer is used to input the branch current data, number information and meteorological data of the inverter.

[0063] After the number information of the inverter is input into the embedding layer, the embedding technology in the embedding layer can convert the number information of the inverter to obtain an embedding vector corresponding to the number information.

[0064] The feature joint layer is used to concatenate the embedded vector, branch current data and meteorological data of the power station to obtain joint features.

[0065] The attention layer includes a variety of attention mechanisms, for example, the attention layer includes self-attention mechanism, multi-head attention mechanism, external attention mechanism, hard attention mechanism, soft attention mechanism, etc. After receiving the joint features, the attention layer uses the corresponding attention mechanism to adaptively assign weights to each element in the joint features according to their importance.

[0066] Exemplarily, the specific process of the attention mechanism adaptively assigning weights to each element in the joint feature according to the importance of each element in the joint feature includes: calculating the attention score of each element, and applying the softmax function to convert the score into a probability distribution. And using the attention probability distribution as the weight, the joint feature is weighted and summed to obtain the weighted joint feature. Based on the weighted joint features obtained in the above steps, the power measurement model automatically focuses on the key information that has the greatest impact on the photovoltaic power measurement, and realizes the refined screening and efficient integration of information.

[0067] The residual structure includes multiple residual blocks, for example, three residual blocks can be stacked. By constructing direct connections across layers, the residual blocks can enable the weighted joint features to bypass some intermediate layers in the power measurement model and be directly transmitted to the output port of the subsequent layer of the power measurement model, and added with the output data of the subsequent layer. This significantly reduces the loss of the weighted joint features in the layer-by-layer transmission process and retains more original feature information of the weighted joint features.

[0068] Exemplarily, the residual block includes two layers of fully connected networks and a rectified linear unit (ReLU) activation function. The two layers of networks perform nonlinear transformations on the joint features to extract higher-level features. At the same time, the residual connection is used to maintain the continuous flow of information, that is, the joint features are directly transferred to the output of the residual block and added to the transformed joint features input into the residual block. This can effectively alleviate the gradient vanishing problem and maintain the stability and efficiency of the power measurement model training.

[0069] The fully connected layer is used to integrate the joint features after residual structure processing and output the power measurement results.

[0070] S23, converting the numbering information into a corresponding embedding vector.

[0071] Exemplarily, the number information is converted into a corresponding embedding vector based on the embedding technology in the embedding layer.

[0072] In some embodiments, the embedding vector includes semantic information corresponding to the numbering information.

[0073] Specifically, the embedding vector is a continuous vector containing semantic information, which retains the uniqueness of the number and can capture the potential connections, characteristic differences, and possible similarities between inverters in a low-dimensional space.

[0074] S24, concatenating the features corresponding to the embedding vector, the branch current data, and the meteorological data of the power station to obtain a joint feature.

[0075] For example, at the feature union layer, features corresponding to the embedded vector, branch current data, and meteorological data of the power station may be concatenated based on Python's pandas library or NumPy library to obtain a joint feature.

[0076] Specifically, after obtaining the joint feature, the attention mechanism adaptively assigns weights to each element in the joint feature according to the importance of each element in the joint feature.

[0077] Exemplarily, the specific process of the attention mechanism adaptively assigning weights to each element in the joint feature according to the importance of each element in the joint feature includes: calculating the attention score of each element, and applying the softmax function to convert the score into a probability distribution. And using the attention probability distribution as the weight, the joint feature is weighted and summed to obtain the weighted joint feature. Based on the weighted joint feature obtained in the above steps, the power measurement model automatically focuses on the key information that has the greatest impact on the photovoltaic power measurement, and realizes the refined screening and efficient integration of information.

[0078] S25: Obtain the measured power of the inverter according to the joint feature.

[0079] Specifically, in the power measurement model, the joint features are input into the attention layer, weights are assigned to each element in the joint features in the attention layer, and the joint features after the weights are assigned are input into the residual structure. The joint features after the weights are assigned after the residual structure processing retain more original feature information, and the joint features after the residual structure processing are input into the fully connected layer, and the joint features after the residual structure processing are integrated in the fully connected layer to obtain the measured power of the inverter.

[0080] The embodiment of the present application provides a power measurement method, in which, by obtaining the numbering information of the inverter, various data in different inverters can be accurately distinguished and identified, avoiding confusion of various data in different inverters, resulting in the possibility of reducing the accuracy and reliability of the power measurement of the inverter. The residual block in the power measurement model can bypass some intermediate layers in the power measurement model by constructing a cross-layer direct connection, and directly transmit the joint features to the output port of the subsequent layer of the power measurement model, and add it to the output data of the subsequent layer. The loss of the joint features in the layer-by-layer transmission process is significantly reduced, and more original feature information of the joint features is retained, providing a more accurate, comprehensive, and original feature information basis for power measurement, improving the accuracy and reliability of the inverter power measurement, and thus the accurate measurement of the inverter power plays a vital role in improving power generation efficiency and optimizing energy configuration.

[0081] Figure 3 Shown is a flow chart of a method for training a power calculation model in one embodiment of the present application. Figure 3 As shown, the process of the training method of the power measurement model in the embodiment of the present application includes the following steps S31 to S32.

[0082] S31, constructing a data sample set, wherein the data sample set includes branch current data, power data, numbering information of the inverter and meteorological data of the power station.

[0083] Specifically, according to the serial number information, the data of each inverter in the data sample set is placed at the position corresponding to the serial number information, and the data in different inverters are separated from each other.

[0084] Each data sample in the data sample set consists of two parts: input features and measurement targets. The input features consist of the branch current data, number information and meteorological data of the inverter obtained at the same time, and the measurement target represents the real power data output by the inverter. The power measurement model is trained based on the data sample set so that the power value calculated by the power measurement model is close to the real power data output by the inverter or the error between the power value calculated by the power measurement model and the real power data output by the inverter is minimized.

[0085] For example, at 2024 / 5 / 18:00:00, a certain inverter collected a set of data, including the branch current data, power data, and meteorological data of the inverter. Then a data sample can be constructed for this set of data. The input features of the data sample consist of the serial number information of the inverter, the branch current data at that moment, and the meteorological data at that moment. The measurement target of the data sample is: the power data at that moment. In the above manner, by collecting branch current data, power data, and meteorological data at different times and from different inverters, a data sample set can be constructed.

[0086] S32: Training the power measurement model based on the data sample set.

[0087] Based on the preset ratio, a training set corresponding to the data sample set is obtained, and based on the training set, a power measurement model is trained.

[0088] An embodiment of the present application provides a method for training a power measurement model by constructing a data sample set including branch current data, numbering information of inverters and meteorological data of power stations. The data in the data sample set are of various types, and multiple data can be distinguished based on the numbering information of the inverter, which facilitates accurate identification of the data of each inverter so as to further analyze their performance differences. The power measurement model is trained based on multiple data of each inverter, thereby improving the accuracy of the trained power measurement model.

[0089] Figure 4 Shown is a flow chart for determining a power measurement model in one embodiment of the present application. Figure 4 As shown, the process of the training method of the power measurement model in the embodiment of the present application includes the following steps S41 to S43.

[0090] S41, obtaining a training set and a validation set according to the data sample set.

[0091] Specifically, when a training set and a validation set are obtained based on a data sample set, a test set can also be obtained.

[0092] Specifically, the data sample set can be divided into a training set, a validation set and a test set based on a preset ratio, wherein the preset ratio may be 70%:15%:15% or 50%:35%:15% and the like.

[0093] Among them, the training set is used to train the power measurement model; the validation set is used to regularly verify the trained power measurement model during the training process; and the test set is used to verify the trained power measurement model after the training is completed.

[0094] Exemplarily, the performance of the power estimation model may be quantitatively evaluated by calculating the mean absolute error and the mean absolute percentage error.

[0095] In some embodiments, the branch current data, the power data, the numbering information and the meteorological data of the power station in the data sample set are data at different times and under different meteorological conditions.

[0096] Specifically, the branch current data, power data, numbering information and meteorological data of the power station at different times and under different meteorological conditions in the above data sample set provide rich data for training the power measurement model, and the various data in the inverter at different times and under different meteorological conditions are multifaceted and comprehensive.

[0097] S42, inputting each group of training data in the training set into the power calculation model in turn, and updating the power calculation model according to the loss function value to obtain the power calculation model with the minimum loss function value.

[0098] Specifically, each set of training data contains branch current data, power data, number information and meteorological data of the power station related to a specific inverter.

[0099] Exemplarily, the iterative optimization algorithm can be based on the gradient descent method, and the relevant parameters of the Adam optimizer can be configured. During the training process, each set of training data is input into the power measurement model in turn, the power measurement model is trained, and the parameters of the power measurement model are updated using the Adam optimizer to efficiently optimize the model and improve the training speed and accuracy. At the same time, the mean absolute error can be sampled as the loss function and set as the optimization target. By continuously iteratively adjusting the parameters of the power measurement model to minimize the loss function value, a power measurement model with the smallest loss function value is obtained.

[0100] S43, in the process of training the power calculation model, verifying the power calculation model based on the verification set within a preset time interval.

[0101] The preset time interval may be the time for training the power measurement model every N rounds.

[0102] For example, in order to monitor the training progress and performance of the power measurement model, the currently trained power measurement model can be evaluated using the validation set every 10 rounds of training. Calculate the loss value on the validation set and observe its changing trend. When the loss value on the validation set begins to rise, that is, when the performance of the power measurement model begins to decline, stop training in time to avoid overfitting the power measurement model on the training set. Regular verification of the power measurement model helps ensure the stability and reliability of the power measurement model.

[0103] In the process of determining the power measurement model, the embodiment of the present application provides a rich data basis for the power measurement model by constructing a data sample data set of the inverter under different times and different meteorological conditions, which helps the power measurement model to deeply explore the performance differences and response characteristics between the inverters, and provides an accurate model basis for the subsequent calculation of the power of the inverter in various scenarios based on the trained power measurement model. The power measurement model is trained in turn based on each group of training data until a power measurement model with the smallest loss function value is obtained, and the power measurement model is regularly verified based on the verification set, which improves the stability and reliability of the power measurement model and provides an accurate power measurement model for the subsequent power measurement of the inverter.

[0104] Figure 5 The structure diagram of the power calculation model in one embodiment of the present application is shown. Figure 5 As shown, the power measurement model includes an input layer 51, an embedding layer 52, a feature joint layer 53, an attention layer 54, a residual structure 55, and a fully connected layer 56. Among them, the input layer 51 is used to input the branch current data, numbering information and meteorological data of the inverter, the embedding layer 52 is used to obtain the embedding vector corresponding to the numbering information, the feature joint layer 53 is used to splice the branch current data, the meteorological data of the power station and the embedding vector to obtain the joint feature, and the attention mechanism in the attention layer 54 is used to adaptively assign weights to each element in the joint feature according to the importance of each element in the joint feature. The residual structure 55 is used to cross-layer transmit the joint features after the weights are assigned to reduce the feature loss of the joint features during the transmission process. The fully connected layer 56 is used to integrate the joint features after the residual structure is transmitted, and output the power measurement results. Its specific implementation process is similar to the steps in the above-mentioned methods. This application will not repeat this.

[0105] The protection scope of the power measurement method of the embodiment of the present application is not limited to the execution order of the steps listed in the present embodiment. All solutions implemented by adding, reducing or replacing steps in the prior art based on the principles of the present application are included in the protection scope of the present application.

[0106] The embodiment of the present application also provides a power measuring device, which can implement the power measuring method of the present application. However, the implementation device of the power measuring method of the present application includes but is not limited to the structure of the power measuring device listed in this embodiment. All structural deformations and replacements of the prior art made according to the principles of the present application are included in the protection scope of the present application.

[0107] like Figure 6 As shown, in one embodiment, the power measurement device 60 of the present application includes a data acquisition module 61 and a power measurement module 62 .

[0108] The data acquisition module 61 is used to acquire the branch current data, numbering information and meteorological data of the inverter, and input the branch current data, numbering information and meteorological data of the power station into the power measurement model.

[0109] The power calculation module 62 is used to convert the numbering information into a corresponding embedded vector; concatenate the embedded vector with the features corresponding to the branch current data, numbering information and meteorological data of the power station to obtain a joint feature; and obtain the calculated power of the inverter based on the joint feature.

[0110] The structures and principles of the data acquisition module 61 and the power calculation module 62 correspond to the steps in the above-mentioned power calculation method, so they will not be described in detail here.

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

[0112] The modules / units described as separate components may or may not be physically separated, and the components displayed as modules / units may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules / units may be selected according to actual needs to achieve the purpose of the embodiments of the present application. For example, the functional modules / units in the various embodiments of the present application may be integrated into one processing module, or each module / unit may exist physically separately, or two or more modules / units may be integrated into one module / unit.

[0113] Those of ordinary skill in the art should further appreciate that the units and steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software 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 this application.

[0114] The present application embodiment also provides a computer-readable storage medium. A person of ordinary skill in the art can understand that all or part of the steps in the method for implementing the above embodiment can be completed by instructing the processor through a program, and the program can be stored in a computer-readable storage medium, and the storage medium is a non-transitory medium, such as a random access memory, a read-only memory, a flash memory, a hard disk, a solid-state hard disk, a magnetic tape, a floppy disk, an optical disc, and any combination thereof. The above storage medium can be any available medium that a computer can access or a data storage device such as a server or a data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a digital video disc (DVD)), or a semiconductor medium (e.g., a solid-state disk (SSD)), etc.

[0115] An embodiment of the present application also provides an electronic device. Figure 7 The schematic diagram of the structure of the electronic device 70 in one embodiment of the present application is shown. The power measurement method provided in the embodiment of the present application can be applied to Figure 7 The electronic device 70 shown is, but not limited to, Figure 7 As shown, the electronic device 70 includes a processor 71 , a memory, a system bus 73 , and a network interface 75 , wherein the memory may include a non-volatile storage medium 72 and an internal memory 74 .

[0116] The non-volatile storage medium 72 can store an operating system and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can execute any power measurement method provided in the embodiments of the present application.

[0117] The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.

[0118] The internal memory 74 provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can execute any power measurement method provided in the embodiments of the present application.

[0119] The network interface 75 is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will appreciate that Figure 7The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0120] It should be understood that the processor 71 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0121] The electronic device 70 in the embodiment of the present application may include terminal devices such as tablet computers, laptop computers, mobile phones, supercomputers, smart wearable devices, etc., and can also be applied to databases, servers, and service response systems based on terminal artificial intelligence. The embodiment of the present application does not impose any restrictions on the specific type of electronic device.

[0122] For example, the electronic device can be a station (STAION, ST) in a WLAN, a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a Wireless Local Loop (WLL) station, a handheld device with wireless communication function, a computing device or other processing device connected to a wireless modem, a computer, a laptop computer, a handheld communication device, a handheld computing device, and / or other devices for communicating on wireless systems and next-generation communication systems, such as mobile terminals in 5G networks, mobile terminals in future evolved public land mobile networks (Public Land Mobile Network, PLMN) or mobile terminals in future evolved non-terrestrial networks (Non-terrestrial Network, NTN), etc.

[0123] As an example but not limitation, when the electronic device is a wearable device, the wearable device can also be a general term for wearable devices that are intelligently designed and developed using wearable technology for daily wear, such as gloves and watches equipped with near-field communication modules. A wearable device is a portable device that is worn directly on the body or integrated into the user's clothes or accessories. It is attached to the user and performs payment, authentication and other operations through a pre-bound electronic card. Wearable devices are not only hardware devices, but also powerful functions achieved through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are fully functional, large in size, and can achieve complete or partial functions without relying on smartphones, such as smart watches or smart glasses, as well as those that only focus on a certain type of application function and need to be used in conjunction with other devices such as smartphones, such as various types of smart watches and smart bracelets with display screens.

[0124] The descriptions of the processes or structures corresponding to the above-mentioned figures have different emphases. For parts that are not described in detail in a certain process or structure, please refer to the relevant descriptions of other processes or structures.

[0125] The above embodiments are merely illustrative of the principles and effects of the present application and are not intended to limit the present application. Anyone familiar with the technology may modify or change the above embodiments without violating the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by a person of ordinary skill in the art without departing from the spirit and technical ideas disclosed in the present application shall still be covered by the claims of the present application.

Claims

1. A power measurement method, characterized in that: The method comprises: Obtain the inverter's branch current data, number information and power station's meteorological data; Inputting the branch current data, the numbering information and the meteorological data of the power station into a power calculation model; Convert the numbering information into a corresponding embedding vector; Concatenating the features corresponding to the embedding vector, the branch current data, and the meteorological data of the power station to obtain a joint feature; According to the joint feature, the measured power of the inverter is obtained.

2. The power calculation method according to claim 1, characterized in that: The power measurement model includes an input layer, an embedding layer, a feature combination layer, an attention layer, a residual structure and a fully connected layer.

3. The power calculation method according to claim 1, characterized in that: The embedding vector includes semantic information corresponding to the numbering information.

4. The power calculation method according to claim 1, characterized in that: The training method of the power measurement model includes: Constructing a data sample set, wherein the data sample set includes branch current data, power data, numbering information of the inverter and meteorological data of the power station; Based on the data sample set, the power measurement model is trained.

5. The power calculation method according to claim 4, characterized in that: The step of training the power measurement model based on the data sample set includes: According to the data sample set, a training set and a validation set are obtained; Inputting each set of training data in the training set into the power calculation model in turn, and updating the power calculation model according to the loss function value to obtain the power calculation model with the minimum loss function value; During the training of the power calculation model, the power calculation model is verified based on the verification set within a preset time interval.

6. The power calculation method according to claim 4, characterized in that: The branch current data, the power data, the numbering information and the meteorological data of the power station in the data sample set are data at different times and under different meteorological conditions.

7. The power calculation method according to claim 1, characterized in that: Before inputting the branch current data, the numbering information and the meteorological data of the power station into the power estimation model, the method further includes: The branch current data, the numbering information and the meteorological data of the power station are preprocessed, and the preprocessing includes missing value processing, abnormal value processing and data normalization processing.

8. A power measurement device, characterized in that: The device comprises: A data acquisition module, used to acquire branch current data, numbering information and meteorological data of the inverter; input the branch current data, numbering information and meteorological data of the power station into a power measurement model; The power calculation module is used to convert the numbering information into a corresponding embedded vector; concatenate the features corresponding to the embedded vector, the branch current data and the meteorological data of the power station to obtain a joint feature; and obtain the calculated power of the inverter based on the joint feature.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: The electronic device comprises: A memory storing a computer program; A processor is communicatively connected to the memory, and executes the method according to any one of claims 1 to 7 when calling the computer program.

Images