CN117239743B - Electric energy meter electricity load acquisition method, device, equipment and medium - Google Patents
Electric energy meter electricity load acquisition method, device, equipment and medium Download PDFInfo
- Publication number
- CN117239743B CN117239743B CN202311514625.5A CN202311514625A CN117239743B CN 117239743 B CN117239743 B CN 117239743B CN 202311514625 A CN202311514625 A CN 202311514625A CN 117239743 B CN117239743 B CN 117239743B
- Authority
- CN
- China
- Prior art keywords
- load
- target
- data
- energy meter
- electric energy
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 70
- 230000005611 electricity Effects 0.000 title claims abstract description 67
- 238000013528 artificial neural network Methods 0.000 claims abstract description 29
- 238000012549 training Methods 0.000 claims description 49
- 238000012545 processing Methods 0.000 claims description 34
- 230000008569 process Effects 0.000 claims description 28
- 239000011159 matrix material Substances 0.000 claims description 27
- 230000006870 function Effects 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 16
- 238000010276 construction Methods 0.000 claims description 15
- 230000004931 aggregating effect Effects 0.000 claims description 10
- 238000010606 normalization Methods 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 9
- 238000001514 detection method Methods 0.000 claims description 8
- 230000002776 aggregation Effects 0.000 claims description 4
- 238000004220 aggregation Methods 0.000 claims description 4
- 238000002372 labelling Methods 0.000 claims description 4
- 230000007246 mechanism Effects 0.000 abstract description 6
- 238000007781 pre-processing Methods 0.000 description 14
- 238000010586 diagram Methods 0.000 description 6
- 230000009471 action Effects 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000013139 quantization Methods 0.000 description 2
- 238000009877 rendering Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a method, a device, equipment and a medium for acquiring an electric load of an electric energy meter, and relates to the technical field of electric power. The scheme constructs a load identification model through a time sequence transducer neural network, and has a multi-head attention mechanism; when the load type of the target electricity data is predicted by using the load identification model, the elements in the target electricity data can be fully focused and processed, so that the accuracy and the robustness of the model are improved, the problem that the accuracy of the current electric energy meter for identifying and acquiring the electricity load is low is solved, and the utilization efficiency of the electric load and the stability of a power grid are improved.
Description
Technical Field
The application relates to the technical field of electric power, in particular to a method, a device, equipment and a medium for acquiring an electric load for an electric energy meter.
Background
In daily life, an electric energy meter is one of key devices for measuring electricity consumption. The traditional electric energy meter is usually of an intelligent design, cannot obtain detailed information of a power grid, and can only obtain total power consumption information of a terminal user. In smart grid construction, it is necessary to precisely understand the power load conditions and analyze and utilize the power load. Therefore, the electric energy meter is added with a function of identifying and acquiring the electric load.
However, the current electric energy meter has the biggest defects of low identification accuracy rate for identifying the electric load, including low accuracy rate for identifying the class of electric equipment and low accuracy rate for identifying the numerical value of the consumed electric quantity of the equipment, which is not beneficial to monitoring and managing the electric network load by an electric company.
In view of the above problems, how to solve the problem that the accuracy of the current electric energy meter in identifying and acquiring the electric load is low is a urgent need for those skilled in the art.
Disclosure of Invention
The purpose of the application is to provide a method, a device, equipment and a medium for acquiring the electric load of an electric energy meter, so as to solve the problem that the accuracy of the electric load identification acquisition of the current electric energy meter is low.
In order to solve the technical problem, the application provides a method for acquiring an electric load of an electric energy meter, which comprises the following steps:
reading target electricity consumption data through an electric energy meter; wherein the electricity consumption data comprises target current data and target voltage data;
respectively carrying out differential processing on the target current data and the target voltage data;
inputting the processed target current data and the target voltage data into a load identification model to obtain a target load type and target power consumption;
the construction process of the load identification model comprises the following steps:
acquiring current data and voltage data stored by the electric energy meter;
preprocessing the current data and the voltage data respectively;
based on the preprocessed current data and the preprocessed voltage data, training the load identification model by using a time sequence transducer neural network to obtain the load identification model.
In one aspect, the preprocessing the current data and the voltage data, respectively, includes:
respectively carrying out normalization processing on the current data and the voltage data;
segmenting the normalized current data and the normalized voltage data according to time sequence to obtain a plurality of sequences of the current data and the voltage data;
labeling the current data and the voltage data of each sequence with a corresponding load type;
and dividing the current data and the voltage data marked with the load types into a training set and a testing set according to a preset proportion.
In another aspect, the training of the load identification model using a time series transducer neural network based on the preprocessed current data and the voltage data includes:
inputting the data in the training set into each multi-head attention model; the multi-head attention model comprises a first multi-head attention model and a second multi-head attention model, and the first multi-head attention model adopts shielding operation;
in each multi-head attention model, acquiring training feature matrixes of a preset number of load types according to data in the training set, and acquiring an initial weight matrix;
acquiring the weight of the corresponding self-attention layer according to the training feature matrix and the initial weight matrix to obtain an output result of the corresponding self-attention layer;
aggregating the output results of the self-attention layers corresponding to the load types to obtain an aggregate output result of the self-attention layer;
acquiring an output result of the corresponding multi-head attention model according to the weight coefficient and the aggregation output result;
processing the output results of the multi-head attention models respectively to obtain the corresponding final results of the multi-head attention models;
aggregating the final results of the multi-head attention models, and outputting the aggregated final results by using a normalized exponential function to obtain a classification result of the time sequence transducer neural network, thereby obtaining an initial load identification model;
acquiring a new weight matrix according to the classification result and the cross entropy loss function;
back-propagating according to the cross entropy loss function and the new weight matrix;
judging whether the load identification model meets preset requirements or not;
if yes, finishing the training of the load identification model.
On the other hand, the judging whether the load identification model meets the preset requirement comprises the following steps:
verifying the load identification model according to the data in the test set, and judging whether the accuracy of the load identification model is greater than a threshold;
if yes, confirming that the load identification model meets the preset requirement;
if not, confirming that the load identification model does not meet the preset requirement.
On the other hand, before the target electricity consumption data is read through the electric energy meter, the method further comprises the following steps:
deploying the load identification model in the electric energy meter;
and starting an electric energy meter electric signal detection sensor of the electric energy meter so as to obtain the target electricity utilization data through the electric energy meter electric signal detection sensor.
On the other hand, after the target load type and the target power consumption are obtained, the method further comprises:
generating a target load curve and target load statistical information according to the target load type and the target power consumption;
and storing the target load curve and the target load statistical information in a storage space of the electric energy meter.
On the other hand, after the target load type and the target power consumption are obtained, the method further comprises:
generating an acquisition log of the target load type and the target power consumption;
and storing the log in a storage space of the electric energy meter.
For solving above-mentioned technical problem, this application still provides an electric energy meter electricity load acquisition device, includes:
the reading module is used for reading the target electricity consumption data through the electric energy meter; wherein the electricity consumption data comprises target current data and target voltage data;
the differential processing module is used for respectively carrying out differential processing on the target current data and the target voltage data;
the prediction module is used for inputting the processed target current data and the target voltage data into a load identification model so as to obtain a target load type and target power consumption;
the construction process of the load identification model comprises the following steps:
acquiring current data and voltage data stored by the electric energy meter;
preprocessing the current data and the voltage data respectively;
based on the preprocessed current data and the preprocessed voltage data, training the load identification model by using a time sequence transducer neural network to obtain the load identification model.
For solving the technical problem, the application also provides electric energy meter electricity load acquisition equipment, including:
a memory for storing a computer program;
and the processor is used for realizing the steps of the method for acquiring the electric load of the electric energy meter when executing the computer program.
In order to solve the above technical problem, the present application further provides a computer readable storage medium, where a computer program is stored on the computer readable storage medium, and the steps of the method for obtaining the electric load of the electric energy meter are implemented when the computer program is executed by a processor.
According to the electric energy meter electricity load acquisition method, target electricity data are read through the electric energy meter; the power consumption data comprise target current data and target voltage data; respectively carrying out differential processing on the target current data and the target voltage data; inputting the processed target current data and target voltage data into a load identification model to obtain a target load type and target power consumption; the construction process of the load identification model comprises the following steps: acquiring current data and voltage data stored by an electric energy meter; preprocessing current data and voltage data respectively; based on the preprocessed current data and voltage data, training a load identification model by using a time sequence transducer neural network to obtain the load identification model. From this, the scheme builds a load recognition model through a time sequence transducer neural network, and has a multi-head attention mechanism; when the load type of the target electricity data is predicted by using the load identification model, the elements in the target electricity data can be fully focused and processed, so that the accuracy and the robustness of the model are improved, the problem that the accuracy of the current electric energy meter for identifying and acquiring the electricity load is low is solved, and the utilization efficiency of the electric load and the stability of a power grid are improved.
In addition, the application also provides an electric load acquisition device, equipment and medium for the electric energy meter, and the effects are the same as the above.
Drawings
For a clearer description of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described, it being apparent that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a method for obtaining an electric load of an electric energy meter according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a training process of a load recognition model according to an embodiment of the present application;
fig. 3 is a schematic diagram of an electric load obtaining device for an electric energy meter according to an embodiment of the present application;
fig. 4 is a schematic diagram of an electric load obtaining device for an electric energy meter according to an embodiment of the present application.
Detailed Description
The following description of the technical solutions in the embodiments of the present application will be made clearly and completely with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, but not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments herein without making any inventive effort are intended to fall within the scope of the present application.
The core of the application is to provide a method, a device, equipment and a medium for acquiring the electric load of the electric energy meter, which aim to solve the problem that the accuracy of the current electric energy meter for identifying and acquiring the electric load is low.
In order to provide a better understanding of the present application, those skilled in the art will now make further details of the present application with reference to the drawings and detailed description.
At present, the electric energy meter has the greatest defects of low identification accuracy for identifying the electric load, including low accuracy for identifying the class of electric equipment and low accuracy for identifying the numerical value of the consumed electric quantity of the equipment, which is not beneficial to monitoring and managing the electric network load by an electric company. In view of the above problems, the application provides a method for acquiring the electric load of an electric energy meter, which aims to solve the problem that the accuracy of the electric energy meter in identifying and acquiring the electric load is low at present.
Fig. 1 is a flowchart of a method for obtaining an electric load of an electric energy meter according to an embodiment of the present application. As shown in fig. 1, the method includes:
s10: and reading target electricity consumption data through an electric energy meter.
The electricity consumption data comprises target current data and target voltage data.
S11: and respectively carrying out differential processing on the target current data and the target voltage data.
S12: and inputting the processed target current data and target voltage data into a load identification model to obtain a target load type and target power consumption.
The construction process of the load identification model comprises the following steps: acquiring current data and voltage data stored by an electric energy meter; preprocessing current data and voltage data respectively; based on the preprocessed current data and voltage data, training a load identification model by using a time sequence transducer neural network to obtain the load identification model.
Specifically, in order to perform load identification and acquisition, first, target electricity consumption data is read through an electric energy meter. It is understood that the target electricity consumption data specifically includes target current data and target voltage data; the standard electric energy meter needs to output a plurality of voltage values and current values every second, and load identification is to read the data every second.
Further, differential processing is performed on the target current data and the target voltage data, respectively, so that the latest voltage and current data are obtained. And finally, inputting the processed target current data and target voltage data into a load identification model to obtain a target load type and target power consumption. It will be appreciated that the target load type is obtained by the load identification model, and the target power consumption may be directly calculated from the target current data and the target voltage data.
It should be noted that the load recognition model in this embodiment is a model trained by using a time-series transducer neural network based on current data and voltage data. Specifically, in the process of constructing the load identification model, current data and voltage data stored in the electric energy meter need to be acquired first. It will be appreciated that the Read-Only Memory (ROM) of the power meter stores current data and voltage data over a plurality of time periods, which can be used as sample data for model training. Further, because of the difference in data quality, it is not appropriate to directly use the current data and the voltage data for model training, and thus some necessary preprocessing, such as filtering, normalization, etc., needs to be performed on the original current data and the voltage data to make the quality of the two meet the model training. The data preprocessing process is not limited in this embodiment, and depends on the specific implementation. And finally, training a load identification model by utilizing a time sequence transducer neural network based on the preprocessed current data and voltage data to obtain the load identification model.
In this embodiment, the construction of the load recognition model is based on a time-series transducer neural network. It will be appreciated that since the load identification model is mainly used for the acquisition of load types, its tasks are mainly classification tasks. The time-series transducer neural network in this embodiment therefore eliminates the decoder (decoder) of the conventional transducer neural network. Only an encoder (encoder) is used for classification. In this embodiment, the specific construction process of the load identification model is not limited, and depends on the specific implementation situation.
In the embodiment, target electricity consumption data are read through an electric energy meter; the power consumption data comprise target current data and target voltage data; respectively carrying out differential processing on the target current data and the target voltage data; inputting the processed target current data and target voltage data into a load identification model to obtain a target load type and target power consumption; the construction process of the load identification model comprises the following steps: acquiring current data and voltage data stored by an electric energy meter; preprocessing current data and voltage data respectively; based on the preprocessed current data and voltage data, training a load identification model by using a time sequence transducer neural network to obtain the load identification model. From this, the scheme builds a load recognition model through a time sequence transducer neural network, and has a multi-head attention mechanism; when the load type of the target electricity data is predicted by using the load identification model, the elements in the target electricity data can be fully focused and processed, so that the accuracy and the robustness of the model are improved, the problem that the accuracy of the current electric energy meter for identifying and acquiring the electricity load is low is solved, and the utilization efficiency of the electric load and the stability of a power grid are improved.
In order to pre-process the current data and the voltage data, in some embodiments, the pre-processing the current data and the voltage data respectively includes:
s130: and respectively carrying out normalization processing on the current data and the voltage data.
S131: and carrying out segmentation processing on the normalized current data and the normalized voltage data according to the time sequence to obtain a plurality of sequences of current data and voltage data.
S132: and labeling the corresponding load type for the current data and the voltage data of each sequence.
S133: and dividing the current data and the voltage data marked with the load types into a training set and a testing set according to a preset proportion.
Specifically, the current data and the voltage data are firstly subjected to normalization processing and normalization processing, so that the data are on the same order of magnitude, and the training and the optimization of the neural network are facilitated. The time-series current data and voltage data are segmented to form a plurality of small sequences of current data and voltage data. And marking the correct load type for the data of each sequence, and finally dividing the current data and the voltage data into a training set and a testing set according to a preset proportion. In this embodiment, the preset ratio is not limited, and depends on the specific implementation. Thus, the preprocessing process of the current data and the voltage data is completed.
Fig. 2 is a schematic diagram of a load recognition model training process according to an embodiment of the present application. Based on the above embodiments, in some embodiments, as shown in fig. 2, training the load recognition model using the time series transducer neural network based on the preprocessed current data and voltage data includes:
s140: data in the training set is input into each multi-headed attention model.
The multi-head attention model comprises a first multi-head attention model and a second multi-head attention model, and the first multi-head attention model adopts shielding operation.
Specifically, data in the training set is input into each Multi-Head Attention (Multi-Head Attention) model. As shown in fig. 2, the multi-head attention model includes a first multi-head attention model and a second multi-head attention model, and the difference between the two models is that the first multi-head attention model adopts a mask (Masked) operation, and the information of the current moment is fed back through historical data, that is, future information is blocked, so that the Time characteristic of the data is reflected better, and the network focuses on the information of a Time Step (Time Step).
S141: in each multi-head attention model, training feature matrixes of a preset number of load types are obtained according to data in a training set, and an initial weight matrix is obtained.
S142: and acquiring the weight of the corresponding self-attention layer according to the training feature matrix and the initial weight matrix to obtain an output result of the corresponding self-attention layer.
Further, in each multi-head attention model, a preset number is obtained according to the data in the training setTraining feature matrix of load type +.>And obtain the initial weight matrix +.>. Where N is the number of samples. According to training feature matrix->And initial weight matrix->Acquiring the weight of the corresponding self-attention layer +.>To obtain the output result of the corresponding self-attention layer. The output result of the attention layer is specifically +.>，. Wherein (1)>The length of the training feature matrix X is characterized.
S143: and aggregating the output results of the self-attention layers corresponding to the load types to obtain the aggregate output result of the self-attention layers.
S145: and obtaining the output result of the corresponding multi-head attention model according to the weight coefficient and the aggregate output result.
Aggregating the output results of the self-attention layers corresponding to the load types to obtain an aggregate output result of the self-attention layer. Further by weight coefficient->Learning the Time sequence characteristics between different Time channels (Time channels) of the same Time layer, thereby according to the weight coefficient +.>And acquiring an output result of the corresponding multi-head attention model by aggregating the output result F: />。
S146: and processing the output results of the multi-head attention models respectively to obtain the corresponding final results of the multi-head attention models.
Then, to alleviate the gradient dissipation phenomenon, the output results of the multi-head attention models are respectively processed to obtain multi-head attention modelsThe attention model corresponds to the final result. Specifically, the purpose of focusing only on the current difference is achieved by normalizing and accumulating, and the output is:. Further, the feedback network layer is relatively simple, and is a two-layer fully connected layer, the activation function of the first layer is a Relu function, the second layer does not use the activation function, and the output is:wherein->And->Matrix and weights of the third layer, respectively, +.>Andthe matrix and the weight of the fourth layer respectively. The purpose of normalization and accumulation of the last layer is consistent with the purpose of normalization and accumulation, so that the final result corresponding to the multi-head attention model is: />。
S147: and aggregating the final results of the multiple attention models, and outputting the aggregated final results by using a normalized exponential function to obtain a classification result of the time sequence transducer neural network and obtain an initial load identification model.
Further, the final results of the multiple head attention models are aggregated through an output gate. It should be noted that, unlike the convolutional neural network (Convolutional Neural Networks, CNN) model processing time series, the present embodiment uses two-dimensional convolutional kernels to focus on both step-wise quantization (step-wise) and channel-level quantization (channel-wise), i.e., a double-tower model is used to calculate step- -The wise Attention and the channel-wise Attention. Finally, using normalized exponential functionAnd outputting the final result after aggregation to obtain a classification result of the time sequence transducer neural network, and obtaining an initial load identification model.
S148: and acquiring a new weight matrix according to the classification result and the cross entropy loss function.
S149: and back-propagating according to the cross entropy loss function and the new weight matrix.
S150: judging whether the load identification model meets the preset requirement or not; if yes, training of the load identification model is ended.
It will be appreciated that the above process is a model forward process. To improve the accuracy of classification, a process of reverse iterating the update parameters is added to the time series transducer neural network. The embodiment obtains a new weight matrix according to the classification result and the cross entropy loss function. And carrying out back propagation for a plurality of times according to the cross entropy loss function and the new weight matrix. Judging whether the load identification model meets the preset requirement or not; if yes, the model is considered to be built, and training of the load identification model is finished. In this embodiment, the specific process of determining whether the load identification model meets the preset requirement is not limited, and depends on the specific implementation situation. Thus, the construction of the load identification model is realized.
On the basis of the foregoing embodiments, in some embodiments, determining whether the load identification model meets the preset requirement includes:
s151: verifying the load identification model according to the data in the test set, and judging whether the accuracy of the load identification model is greater than a threshold value; if yes, go to step S152; if not, the process proceeds to step S153.
S152: and confirming that the load identification model meets the preset requirement.
S153: and confirming that the load identification model does not meet the preset requirement.
Specifically, in order to determine whether the load recognition model meets the requirement, the load recognition model may be verified according to data in the test set, and whether the accuracy of the load recognition model is greater than a threshold value may be determined. The threshold value in this embodiment is not limited, and may be set to 95% according to the specific implementation. And if the load identification model is larger than the threshold value, confirming that the load identification model meets the preset requirement. And if the load identification model is not greater than the threshold value, confirming that the load identification model does not meet the preset requirement. Thereby realizing the judgment of whether the model meets the requirement.
On the basis of the above embodiments, in some embodiments, before the target electricity consumption data is read by the electric energy meter, the method further includes:
s16: deploying the load identification model in the electric energy meter;
s17: and starting an electric energy meter electric signal detection sensor of the electric energy meter so as to acquire target electricity utilization data through the electric energy meter electric signal detection sensor.
In a specific implementation, in order to realize application of the load identification model, the load identification model is required to be deployed in the electric energy meter before target electricity consumption data are read through the electric energy meter; meanwhile, an electric energy meter electric signal detection sensor of the electric energy meter is started, so that target electricity utilization data can be conveniently obtained through the electric energy meter electric signal detection sensor, and the electricity utilization condition of a user can be accurately estimated and identified.
On the basis of the above embodiments, in some embodiments, after obtaining the target load type and the target power consumption amount, the method further includes:
s18: generating a target load curve and target load statistical information according to the target load type and the target electricity consumption;
s19: and storing the target load curve and the target load statistical information in a storage space of the electric energy meter.
In order to better analyze the electricity consumption condition of the user, in the implementation, a target load curve and target load statistical information can be generated according to the finally obtained target load type and target electricity consumption. It can be understood that the target load curve shows the electricity consumption condition of the user in the form of an image curve, and the target load statistical information shows the electricity consumption condition of the user in the form of a data table, so that the user can intuitively know the electricity consumption condition. And storing the target load curve and the target load statistical information in a storage space of the electric energy meter, so that the target load curve and the target load statistical information are better stored.
Further, in some embodiments, after obtaining the target load type and the target power consumption amount, further comprising:
s20: generating an acquisition log of the target load type and the target power consumption;
s21: the log is stored in a storage space of the electric energy meter.
It can be understood that after the target load type and the target electricity consumption are obtained, the current obtaining process of the target load type and the target electricity consumption can be generated into a log, and the log is stored in the storage space of the electric energy meter, so that a worker can obtain information related to the obtaining process of the target load type and the target electricity consumption from the storage space each time.
In the above embodiments, the method for acquiring the electric load of the electric energy meter is described in detail, and the application further provides a corresponding embodiment of the electric load acquiring device for the electric energy meter.
Fig. 3 is a schematic diagram of an electric load obtaining device for an electric energy meter according to an embodiment of the present application. As shown in fig. 3, the apparatus includes:
the reading module 10 is used for reading target electricity consumption data through an electric energy meter; the electricity consumption data comprises target current data and target voltage data.
The differential processing module 11 is configured to perform differential processing on the target current data and the target voltage data, respectively.
The prediction module 12 is configured to input the processed target current data and the target voltage data into the load identification model, so as to obtain a target load type and a target power consumption.
The construction process of the load identification model comprises the following steps: acquiring current data and voltage data stored by an electric energy meter; preprocessing current data and voltage data respectively; based on the preprocessed current data and voltage data, training a load identification model by using a time sequence transducer neural network to obtain the load identification model.
In this embodiment, the electric energy meter electrical load obtaining device includes a reading module, a differential processing module and a prediction module. The electric energy meter electricity load acquisition device can realize all the steps of the electric energy meter electricity load acquisition method when in operation. Reading target electricity consumption data through an electric energy meter; the power consumption data comprise target current data and target voltage data; respectively carrying out differential processing on the target current data and the target voltage data; inputting the processed target current data and target voltage data into a load identification model to obtain a target load type and target power consumption; the construction process of the load identification model comprises the following steps: acquiring current data and voltage data stored by an electric energy meter; preprocessing current data and voltage data respectively; based on the preprocessed current data and voltage data, training a load identification model by using a time sequence transducer neural network to obtain the load identification model. From this, the scheme builds a load recognition model through a time sequence transducer neural network, and has a multi-head attention mechanism; when the load type of the target electricity data is predicted by using the load identification model, the elements in the target electricity data can be fully focused and processed, so that the accuracy and the robustness of the model are improved, the problem that the accuracy of the current electric energy meter for identifying and acquiring the electricity load is low is solved, and the utilization efficiency of the electric load and the stability of a power grid are improved.
Fig. 4 is a schematic diagram of an electric load obtaining device for an electric energy meter according to an embodiment of the present application. As shown in fig. 4, the electric energy meter electric load acquisition apparatus includes:
a memory 20 for storing a computer program.
The processor 21 is configured to implement the steps of the electric load acquisition method for an electric energy meter as mentioned in the above embodiment when executing the computer program.
The electric energy meter electricity load obtaining device provided by the embodiment can include, but is not limited to, a smart phone, a tablet computer, a notebook computer, a desktop computer or the like.
Processor 21 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 21 may be implemented in hardware in at least one of a digital signal processor (Digital Signal Processor, DSP), a Field programmable gate array (Field-Programmable Gate Array, FPGA), a programmable logic array (Programmable Logic Array, PLA). The processor 21 may also comprise a main processor, which is a processor for processing data in an awake state, also called central processor (Central Processing Unit, CPU), and a coprocessor; a coprocessor is a low-power processor for processing data in a standby state. In some embodiments, the processor 21 may be integrated with a graphics processor (Graphics Processing Unit, GPU) for use in connection with rendering and rendering of content to be displayed by the display screen. In some embodiments, the processor 21 may also include an artificial intelligence (Artificial Intelligence, AI) processor for processing computing operations related to machine learning.
Memory 20 may include one or more computer-readable storage media, which may be non-transitory. Memory 20 may also include high-speed random access memory, as well as non-volatile memory, such as one or more magnetic disk storage devices, flash memory storage devices. In this embodiment, the memory 20 is at least used for storing a computer program 201, where the computer program, after being loaded and executed by the processor 21, can implement the relevant steps of the electric load acquisition method for an electric energy meter disclosed in any of the foregoing embodiments. In addition, the resources stored in the memory 20 may further include an operating system 202, data 203, and the like, where the storage manner may be transient storage or permanent storage. The operating system 202 may include Windows, unix, linux, among others. The data 203 may include, but is not limited to, data related to a method of acquiring an electrical load for an electrical energy meter.
In some embodiments, the electric energy meter electric load obtaining device may further include a display 22, an input/output interface 23, a communication interface 24, a power supply 25, and a communication bus 26.
It will be appreciated by those skilled in the art that the configuration shown in fig. 4 is not limiting of the electrical load acquisition device for an electrical energy meter and may include more or fewer components than shown.
In this embodiment, the electric energy meter electric load acquisition device includes a memory and a processor. The memory is used for storing a computer program. The processor is configured to implement the steps of the electric energy meter electric load acquisition method as mentioned in the above embodiments when executing the computer program. Reading target electricity consumption data through an electric energy meter; the power consumption data comprise target current data and target voltage data; respectively carrying out differential processing on the target current data and the target voltage data; inputting the processed target current data and target voltage data into a load identification model to obtain a target load type and target power consumption; the construction process of the load identification model comprises the following steps: acquiring current data and voltage data stored by an electric energy meter; preprocessing current data and voltage data respectively; based on the preprocessed current data and voltage data, training a load identification model by using a time sequence transducer neural network to obtain the load identification model. From this, the scheme builds a load recognition model through a time sequence transducer neural network, and has a multi-head attention mechanism; when the load type of the target electricity data is predicted by using the load identification model, the elements in the target electricity data can be fully focused and processed, so that the accuracy and the robustness of the model are improved, the problem that the accuracy of the current electric energy meter for identifying and acquiring the electricity load is low is solved, and the utilization efficiency of the electric load and the stability of a power grid are improved.
Finally, the present application also provides a corresponding embodiment of the computer readable storage medium. The computer-readable storage medium has stored thereon a computer program which, when executed by a processor, performs the steps as described in the method embodiments above.
It will be appreciated that the methods of the above embodiments, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored on a computer readable storage medium. With such understanding, the technical solution of the present application, or a part contributing to the prior art or all or part of the technical solution, may be embodied in the form of a software product stored in a storage medium, performing all or part of the steps of the method described in the various embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In this embodiment, a computer program is stored on a computer readable storage medium, and when the computer program is executed by a processor, the steps described in the above method embodiments are implemented. Reading target electricity consumption data through an electric energy meter; the power consumption data comprise target current data and target voltage data; respectively carrying out differential processing on the target current data and the target voltage data; inputting the processed target current data and target voltage data into a load identification model to obtain a target load type and target power consumption; the construction process of the load identification model comprises the following steps: acquiring current data and voltage data stored by an electric energy meter; preprocessing current data and voltage data respectively; based on the preprocessed current data and voltage data, training a load identification model by using a time sequence transducer neural network to obtain the load identification model. From this, the scheme builds a load recognition model through a time sequence transducer neural network, and has a multi-head attention mechanism; when the load type of the target electricity data is predicted by using the load identification model, the elements in the target electricity data can be fully focused and processed, so that the accuracy and the robustness of the model are improved, the problem that the accuracy of the current electric energy meter for identifying and acquiring the electricity load is low is solved, and the utilization efficiency of the electric load and the stability of a power grid are improved.
The method, the device, the equipment and the medium for acquiring the electric load of the electric energy meter are described in detail. In the description, each embodiment is described in a progressive manner, and each embodiment is mainly described by the differences from other embodiments, so that the same similar parts among the embodiments are mutually referred. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section. It should be noted that it would be obvious to those skilled in the art that various improvements and modifications can be made to the present application without departing from the principles of the present application, and such improvements and modifications fall within the scope of the claims of the present application.
It should also be noted that in this specification, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
Claims (8)
1. The method for acquiring the electric load of the electric energy meter is characterized by comprising the following steps of:
reading target electricity consumption data through an electric energy meter; wherein the electricity consumption data comprises target current data and target voltage data;
respectively carrying out differential processing on the target current data and the target voltage data;
inputting the processed target current data and the target voltage data into a load identification model to obtain a target load type and target power consumption; the construction process of the load identification model comprises the following steps: acquiring current data and voltage data stored by the electric energy meter; respectively carrying out normalization processing on the current data and the voltage data; segmenting the normalized current data and the normalized voltage data according to time sequence to obtain a plurality of sequences of the current data and the voltage data; labeling the current data and the voltage data of each sequence with a corresponding load type; dividing the current data and the voltage data marked with the load types into a training set and a testing set according to a preset proportion; inputting the data in the training set into each multi-head attention model; the multi-head attention model comprises a first multi-head attention model and a second multi-head attention model, and the first multi-head attention model adopts shielding operation; in each multi-head attention model, acquiring training feature matrixes of a preset number of load types according to data in the training set, and acquiring an initial weight matrix; acquiring the weight of the corresponding self-attention layer according to the training feature matrix and the initial weight matrix to obtain an output result of the corresponding self-attention layer; aggregating the output results of the self-attention layers corresponding to the load types to obtain an aggregate output result of the self-attention layer; acquiring an output result of the corresponding multi-head attention model according to the weight coefficient and the aggregation output result; processing the output results of the multi-head attention models respectively to obtain the corresponding final results of the multi-head attention models; aggregating the final results of the multi-head attention models, and outputting the aggregated final results by using a normalized exponential function to obtain a classification result of a time sequence transducer neural network, thereby obtaining an initial load identification model; acquiring a new weight matrix according to the classification result and the cross entropy loss function; back-propagating according to the cross entropy loss function and the new weight matrix; judging whether the load identification model meets preset requirements or not; if yes, finishing training of the load identification model to obtain the load identification model.
2. The method for obtaining an electric load of an electric energy meter according to claim 1, wherein the determining whether the load identification model meets a preset requirement comprises:
verifying the load identification model according to the data in the test set, and judging whether the accuracy of the load identification model is greater than a threshold;
if yes, confirming that the load identification model meets the preset requirement;
if not, confirming that the load identification model does not meet the preset requirement.
3. The electric energy meter electricity load acquisition method according to claim 1, characterized by further comprising, before the reading of the target electricity data by the electric energy meter:
deploying the load identification model in the electric energy meter;
and starting an electric energy meter electric signal detection sensor of the electric energy meter so as to obtain the target electricity utilization data through the electric energy meter electric signal detection sensor.
4. The electric energy meter electric load acquisition method according to claim 1, further comprising, after the obtaining the target load type and the target electric power consumption amount:
generating a target load curve and target load statistical information according to the target load type and the target power consumption;
and storing the target load curve and the target load statistical information in a storage space of the electric energy meter.
5. The electric energy meter electric load obtaining method according to any one of claims 1 to 4, characterized by further comprising, after the obtaining of the target load type and the target electric power consumption:
generating an acquisition log of the target load type and the target power consumption;
and storing the log in a storage space of the electric energy meter.
6. An electric energy meter electricity load acquisition device, characterized by comprising:
the reading module is used for reading the target electricity consumption data through the electric energy meter; wherein the electricity consumption data comprises target current data and target voltage data;
the differential processing module is used for respectively carrying out differential processing on the target current data and the target voltage data;
the prediction module is used for inputting the processed target current data and the target voltage data into a load identification model so as to obtain a target load type and target power consumption; the construction process of the load identification model comprises the following steps: acquiring current data and voltage data stored by the electric energy meter; respectively carrying out normalization processing on the current data and the voltage data; segmenting the normalized current data and the normalized voltage data according to time sequence to obtain a plurality of sequences of the current data and the voltage data; labeling the current data and the voltage data of each sequence with a corresponding load type; dividing the current data and the voltage data marked with the load types into a training set and a testing set according to a preset proportion; inputting the data in the training set into each multi-head attention model; the multi-head attention model comprises a first multi-head attention model and a second multi-head attention model, and the first multi-head attention model adopts shielding operation; in each multi-head attention model, acquiring training feature matrixes of a preset number of load types according to data in the training set, and acquiring an initial weight matrix; acquiring the weight of the corresponding self-attention layer according to the training feature matrix and the initial weight matrix to obtain an output result of the corresponding self-attention layer; aggregating the output results of the self-attention layers corresponding to the load types to obtain an aggregate output result of the self-attention layer; acquiring an output result of the corresponding multi-head attention model according to the weight coefficient and the aggregation output result; processing the output results of the multi-head attention models respectively to obtain the corresponding final results of the multi-head attention models; aggregating the final results of the multi-head attention models, and outputting the aggregated final results by using a normalized exponential function to obtain a classification result of a time sequence transducer neural network, thereby obtaining an initial load identification model; acquiring a new weight matrix according to the classification result and the cross entropy loss function; back-propagating according to the cross entropy loss function and the new weight matrix; judging whether the load identification model meets preset requirements or not; if yes, finishing training of the load identification model to obtain the load identification model.
7. An electric energy meter electricity load acquisition device, characterized by comprising:
a memory for storing a computer program;
a processor for implementing the steps of the electric energy meter electric load acquisition method according to any one of claims 1 to 5 when executing the computer program.
8. A computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, which when executed by a processor, implements the steps of the electric load acquisition method for an electric energy meter according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311514625.5A CN117239743B (en) | 2023-11-15 | 2023-11-15 | Electric energy meter electricity load acquisition method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311514625.5A CN117239743B (en) | 2023-11-15 | 2023-11-15 | Electric energy meter electricity load acquisition method, device, equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117239743A CN117239743A (en) | 2023-12-15 |
| CN117239743B true CN117239743B (en) | 2024-02-27 |
Family
ID=89093368
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311514625.5A Active CN117239743B (en) | 2023-11-15 | 2023-11-15 | Electric energy meter electricity load acquisition method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117239743B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118584232A (en) * | 2024-08-06 | 2024-09-03 | 青岛鼎信通讯股份有限公司 | Identification method, device, equipment and medium of electric equipment |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110889545A (en) * | 2019-11-20 | 2020-03-17 | 国网重庆市电力公司电力科学研究院 | Power load prediction method and device and readable storage medium |
| CN111080032A (en) * | 2019-12-30 | 2020-04-28 | 成都数之联科技有限公司 | Load prediction method based on Transformer structure |
| CN113434493A (en) * | 2021-06-28 | 2021-09-24 | 湘潭大学 | Non-invasive load decomposition method based on Transformer |
| CN114355275A (en) * | 2022-03-21 | 2022-04-15 | 青岛鼎信通讯股份有限公司 | Electric energy meter load monitoring method, system and device and computer readable storage medium |
| WO2022077693A1 (en) * | 2020-10-15 | 2022-04-21 | 中国科学院深圳先进技术研究院 | Load prediction model training method and apparatus, storage medium, and device |
| CN115018512A (en) * | 2022-04-21 | 2022-09-06 | 国网湖南省电力有限公司 | Electricity stealing detection method and device based on Transformer neural network |
| CN115381466A (en) * | 2022-08-11 | 2022-11-25 | 南京邮电大学 | Motor imagery electroencephalogram signal classification method based on AE and Transformer |
| WO2023284716A1 (en) * | 2021-07-15 | 2023-01-19 | 华为技术有限公司 | Neural network searching method and related device |
| CN115828091A (en) * | 2022-09-15 | 2023-03-21 | 国网江苏省电力有限公司信息通信分公司 | Non-invasive load identification method and system based on end-cloud cooperation |
| CN116151118A (en) * | 2023-02-27 | 2023-05-23 | 常州大学 | Non-invasive load decomposition method based on BERT and CNN |
| CN116486232A (en) * | 2023-04-24 | 2023-07-25 | 广东电网有限责任公司 | Load identification method and system based on deep learning theory |
| CN116523001A (en) * | 2023-05-06 | 2023-08-01 | 广西电网有限责任公司 | Method, device and computer equipment for constructing weak line identification model of power grid |
| CN116643949A (en) * | 2023-06-20 | 2023-08-25 | 派欧云计算(上海)有限公司 | Multi-model edge cloud load prediction method and device based on VaDE clustering |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113393025A (en) * | 2021-06-07 | 2021-09-14 | 浙江大学 | Non-invasive load decomposition method based on Informer model coding structure |
-
2023
- 2023-11-15 CN CN202311514625.5A patent/CN117239743B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110889545A (en) * | 2019-11-20 | 2020-03-17 | 国网重庆市电力公司电力科学研究院 | Power load prediction method and device and readable storage medium |
| CN111080032A (en) * | 2019-12-30 | 2020-04-28 | 成都数之联科技有限公司 | Load prediction method based on Transformer structure |
| WO2022077693A1 (en) * | 2020-10-15 | 2022-04-21 | 中国科学院深圳先进技术研究院 | Load prediction model training method and apparatus, storage medium, and device |
| CN113434493A (en) * | 2021-06-28 | 2021-09-24 | 湘潭大学 | Non-invasive load decomposition method based on Transformer |
| WO2023284716A1 (en) * | 2021-07-15 | 2023-01-19 | 华为技术有限公司 | Neural network searching method and related device |
| CN114355275A (en) * | 2022-03-21 | 2022-04-15 | 青岛鼎信通讯股份有限公司 | Electric energy meter load monitoring method, system and device and computer readable storage medium |
| CN115018512A (en) * | 2022-04-21 | 2022-09-06 | 国网湖南省电力有限公司 | Electricity stealing detection method and device based on Transformer neural network |
| CN115381466A (en) * | 2022-08-11 | 2022-11-25 | 南京邮电大学 | Motor imagery electroencephalogram signal classification method based on AE and Transformer |
| CN115828091A (en) * | 2022-09-15 | 2023-03-21 | 国网江苏省电力有限公司信息通信分公司 | Non-invasive load identification method and system based on end-cloud cooperation |
| CN116151118A (en) * | 2023-02-27 | 2023-05-23 | 常州大学 | Non-invasive load decomposition method based on BERT and CNN |
| CN116486232A (en) * | 2023-04-24 | 2023-07-25 | 广东电网有限责任公司 | Load identification method and system based on deep learning theory |
| CN116523001A (en) * | 2023-05-06 | 2023-08-01 | 广西电网有限责任公司 | Method, device and computer equipment for constructing weak line identification model of power grid |
| CN116643949A (en) * | 2023-06-20 | 2023-08-25 | 派欧云计算(上海)有限公司 | Multi-model edge cloud load prediction method and device based on VaDE clustering |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117239743A (en) | 2023-12-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7242101B2 (en) | Engine surge failure prediction system and method based on fusion neural network model | |
| CN117239743B (en) | Electric energy meter electricity load acquisition method, device, equipment and medium | |
| CN112114986A (en) | Data anomaly identification method and device, server and storage medium | |
| WO2023169274A1 (en) | Data processing method and device, and storage medium and processor | |
| CN108734216A (en) | Classification of power customers method, apparatus and storage medium based on load curve form | |
| CN111709548A (en) | Power consumer load prediction method, device, equipment and storage medium based on support vector machine | |
| CN110766236A (en) | Power equipment state trend prediction method based on statistical analysis and deep learning | |
| CN109754077B (en) | Network model compression method and device of deep neural network and computer equipment | |
| CN112215398A (en) | Power consumer load prediction model establishing method, device, equipment and storage medium | |
| CN115794578A (en) | Data management method, device, equipment and medium for power system | |
| CN112463848A (en) | Method, system, device and storage medium for detecting abnormal user behavior | |
| CN114358371A (en) | Photovoltaic short-term power prediction method and device based on deep learning | |
| CN117496269A (en) | Composite electric energy quality disturbance identification method | |
| CN116258167A (en) | Data detection method, device, electronic equipment and medium | |
| CN114462625A (en) | Decision tree generation method and device, electronic equipment and program product | |
| CN114492994A (en) | Power information processing system, method and device based on power big data | |
| CN112149743A (en) | Access control method, device, equipment and medium | |
| CN112183714A (en) | Automated data slicing based on artificial neural network | |
| CN113256328B (en) | Method, device, computer equipment and storage medium for predicting target clients | |
| CN117633615B (en) | Identification method, device, equipment and storage medium for power regulation sensitive data | |
| CN116071146A (en) | Credit data processing method, device and medium | |
| CN118154362B (en) | Power consumer classification method, device, electronic equipment and storage medium | |
| Chen et al. | Performance Assessment of Product Modules Based on Usage Data Collected Through Embedded Sensors | |
| CN116561701A (en) | Method, device and medium for monitoring state of main pump | |
| CN118096909A (en) | Text-to-image generation method and device, electronic equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |