Processing method and device of intelligent load identification model

The intelligent load identification model built by Bi-LSTM and MLP networks, combined with wavelet transform and weighted summation modules, solves the problem of insufficient generalization ability of linear prediction models under nonlinear electricity consumption characteristic data, and achieves more efficient load classification prediction.

CN118916803AActive Publication Date: 2024-11-08NANJING METER TECHNOLOGY CO LTD

Patent Information

Application Number
CN202410998469.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-24
Publication Date
2024-11-08
Estimated Expiration
2044-07-24

AI Technical Summary

Technical Problem

Existing linear prediction models do not perform well when dealing with nonlinear electricity consumption characteristic data, resulting in insufficient generalization ability of smart load identification models.

Method used

A smart load identification model is constructed using a Bi-LSTM model and an MLP network. The model dataset is built through big data collection and model training is performed. The model is classified and predicted by receiving time series of current, power and temperature. Wavelet transform and weighted summation modules are used to improve the nonlinear mapping capability of the model.

Benefits of technology

It improves the generalization ability of the intelligent load identification model and enhances the prediction accuracy for complex power consumption scenarios.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118916803A_ABST
    Figure CN118916803A_ABST
Patent Text Reader

Abstract

The embodiment of the invention relates to a processing method and device of an intelligent load identification model. The method comprises the steps of constructing the intelligent load identification model; constructing a model data set; carrying out model training on the intelligent load identification model based on the model data set; after the model training is finished, receiving a time sequence with current, power and temperature sampling data, and recording the time sequence as a corresponding first input sequence; and inputting the first sampling sequence into an intelligent load identification model to carry out load classification prediction processing so as to obtain a corresponding first prediction vector sequence. According to the invention, the model generalization ability of the intelligent load identification model can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a processing method and device for an intelligent load identification model. Background Art

[0002] The intelligent load identification model is an artificial intelligence model that can predict the type of power load in use in the power unit based on the power consumption characteristics of the power unit (such as current characteristics and power characteristics). The types of power loads mentioned here are usually fixed-frequency air conditioners, variable-frequency air conditioners, electric water heaters, electric heaters, electric kettles, small kitchen treasures, microwave ovens, induction cookers, rice cookers, electric ovens, dishwashers, washing machines, refrigerators, vacuum cleaners, hair dryers, power banks, electric vehicle battery packs and battery vehicles. At present, most of the commonly used intelligent load identification models on the market are based on a type of linear prediction model. The linear prediction models mentioned here are commonly used Support Vector Machine (SVM) models.

[0003] However, we have found in practical applications that the linear prediction model does not perform well when it is used to predict nonlinear power consumption characteristic data (such as current and power). In real scenarios, the power consumption characteristic data of each power consumption unit is often affected by a variety of nonlinear factors, such as time, temperature, and the simultaneous use of one or more types of power loads. The interaction between these factors is difficult to accurately describe with a simple linear relationship. In other words, the generalization ability of the intelligent load identification model based on the linear prediction model is poor in actual application scenarios.

[0004] In addition, we know that deep learning models, such as Multilayer Perceptron (MLP) network, Bi-LSTM network, etc., have powerful nonlinear mapping capabilities and can automatically learn complex nonlinear relationships from raw data. Therefore, if an intelligent load identification model can be built based on a deep learning model, the generalization ability of the model can be further improved. How to use one or more deep learning models to implement an intelligent load identification model is the technical problem to be solved by the present invention. Summary of the invention

[0005] The purpose of the present invention is to provide a processing method, device, electronic device and computer-readable storage medium for an intelligent load identification model in view of the defects of the prior art. The present invention uses two types of deep learning models, namely, the Bi-LSTM model and the MLP network, to construct an intelligent load identification model; and constructs a model data set through big data collection; and performs model training on the intelligent load identification model based on the model data set; and after the model training is completed, a time series sequence with current, power and temperature sampling data is received as a model input sequence, and the intelligent load identification model performs load classification prediction based on the model input sequence. The present invention can improve the model generalization ability of the intelligent load identification model.

[0006] To achieve the above object, a first aspect of an embodiment of the present invention provides a method for processing an intelligent load identification model, the method comprising:

[0007] Build intelligent load identification model;

[0008] Build model dataset;

[0009] Performing model training on the intelligent load identification model based on the model data set;

[0010] After the model training is completed, a time series sequence with current, power and temperature sampling data is received and recorded as the corresponding first input sequence; the first input sequence is formed by J first sequence data arranged in chronological order, and J is the preset model sequence input length; the first sequence data includes a first sampling time, a first sampling current, a first sampling power and a first sampling temperature;

[0011] The first sampling sequence is input into the intelligent load identification model for load classification prediction processing to obtain a corresponding first prediction vector sequence; the first prediction vector sequence includes J first prediction vectors, and the first prediction vectors correspond to the first sequence data one by one; each of the first prediction vectors includes K first load type flags, K is the total number of preset load types; the value of each first load type flag is 0 or 1; each first load type flag corresponds to a load type; the load types include at least fixed-frequency air conditioners, variable-frequency air conditioners, electric water heaters, electric heaters, electric kettles, small kitchen treasures, microwave ovens, induction cookers, rice cookers, electric ovens, dishwashers, washing machines, refrigerators, vacuum cleaners, hair dryers, power banks, electric vehicle battery packs and battery vehicles.

[0012] Preferably, the intelligent load identification model is used to perform load classification prediction processing according to the input sequence X of the model and output the corresponding prediction vector sequence Y; the model input end of the intelligent load identification model is used to receive the input sequence X, and the model output end is used to output the prediction vector sequence Y;

[0013] The input sequence X consists of multiple sequence data x j Sorted in chronological order, 1≤indexj≤J; the sequence data x j Including time T j 、Current I j , power P j and temperature W j ;

[0014] The prediction vector sequence Y is composed of multiple prediction vectors y i The prediction vector y is sorted in chronological order. i With the sequence data x j One-to-one correspondence; each of the prediction vectors y i Includes multiple load type flags j,k , 1≤index k≤K; each of the load type flags z j,k The value is 0 or 1; each load type flag z j,k Corresponds to a load type;

[0015] The intelligent load identification model includes a wavelet conversion module, a first classification prediction model, a second classification prediction model, a third classification prediction model, a weighted summation module and a classification output module;

[0016] The input end of the wavelet conversion module is connected to the input end of the model; the first output end of the wavelet conversion module is connected to the input end of the first classification prediction model, the second output end is connected to the input end of the second classification prediction model, and the third output end is connected to the input end of the third classification prediction model;

[0017] The wavelet transformation module is used to transform all the currents I j Extract and sort them in chronological order to form a corresponding current timing signal; and convert all the power P in the input sequence X into j The extracted data are sorted in chronological order to form a corresponding power time series signal; and based on a preset first wavelet basis, a low-frequency current feature and two high-frequency current features are extracted from the current time series signal to obtain a corresponding first current low-frequency feature sequence {I a,j}、The first current high frequency characteristic sequence {I b,j} and the second current high frequency characteristic sequence {I c,j}, I a,j ,I b,j ,I c,j The first current low-frequency feature, the first current high-frequency feature and the second current high-frequency feature are respectively corresponding; and based on the preset second wavelet basis, a low-frequency power feature and two high-frequency power features are extracted from the power time series signal to obtain the corresponding first power low-frequency feature sequence {Pa,j}, the first power high frequency characteristic sequence {P b,j} and the second power high frequency characteristic sequence {P c,j}, P a,j , P b,j , P c,j The first power low-frequency feature, the first power high-frequency feature and the second power high-frequency feature are respectively corresponding; and each current / power high-frequency feature sequence is subjected to high-frequency feature sequence denoising and smoothing processing; and after the high-frequency feature sequence denoising and smoothing processing is completed, the first current / power low-frequency feature sequence and the first and second current / power high-frequency feature sequences are subjected to sequence normalization processing; and after the sequence normalization processing is completed, all the time T j And all the temperatures W j The corresponding time and temperature normalization processing is also performed; and after the time and temperature normalization processing is completed, the normalized time, temperature, first current low-frequency feature and first power low-frequency feature corresponding to each of the indexes j form a corresponding normalized feature d a,j , and all the normalized features d are obtained a,j Sort by time to form a corresponding normalized feature sequence D A ; and the normalized time, temperature, first current high-frequency feature and first power high-frequency feature corresponding to each of the indexes j form a corresponding normalized feature d b,j , and all the normalized features d are obtained b,j Sort by time to form a corresponding normalized feature sequence D B ; and the normalized time, temperature, second current high-frequency feature and second power high-frequency feature corresponding to each of the indexes j form a corresponding normalized feature d c,j , and all the normalized features d are obtained c,j Sort by time to form a corresponding normalized feature sequence D C ; and the normalized feature sequence D A , D B , D C Output to the corresponding first, second and third classification prediction models; wherein the first wavelet basis includes at least the coif4 wavelet basis; the second wavelet basis includes at least the db4 wavelet basis;

[0018] The output end of the first classification prediction model is connected to the first input end of the weighted summation module; the first classification prediction model includes a first Bi-LSTM model and a first MLP network;

[0019] The first classification prediction model is used to transform the normalized feature sequence D AThe first Bi-LSTM model is input, and the first Bi-LSTM model performs the normalized feature sequence D A The time series features are extracted to obtain the corresponding time series feature vector H A ; and the time series feature vector H A The various time series characteristics h a,j The first MLP network is used to input the first MLP network according to the time series feature h a,j Perform load classification prediction and output the corresponding classification vector s a,j ; and all the classification vectors s are obtained a,j Sort by time to form a corresponding classification vector sequence S A ; and the classification vector sequence S A Output to the weighted summation module; wherein the time series feature vector H A Including a plurality of said timing characteristics h a,j , the timing characteristic h a,j With the normalized feature d a,j One-to-one correspondence; the classification vector sequence S A Including multiple classification vectors s a,j , the classification vector s a,j With the normalized feature d a,j One-to-one correspondence; each of the classification vectors s a,j The predicted probability p of the total number of load types K is a,j,k Composition; each of the classification prediction probability p a,j,k corresponding to one of the load types;

[0020] The output end of the second classification prediction model is connected to the second input end of the weighted summation module; the second classification prediction model includes a second Bi-LSTM model and a second MLP network;

[0021] The second classification prediction model is used to transform the normalized feature sequence D B The second Bi-LSTM model is input, and the second Bi-LSTM model performs the normalized feature sequence D B The time series features are extracted to obtain the corresponding time series feature vector H B ; and the time series feature vector H B The various time series characteristics h b,j The second MLP network is respectively inputted, and the second MLP network is used to generate the time series feature h according to the input time series feature h. b,j Perform load classification prediction and output the corresponding classification vector s b,j ; and all the classification vectors s are obtained b,jSort by time to form a corresponding classification vector sequence S B ; and the classification vector sequence S B Output to the weighted summation module; wherein the time series feature vector H B Including a plurality of said timing characteristics h b,j , the timing characteristic h b,j With the normalized feature d b,j One-to-one correspondence; the classification vector sequence S B Including multiple classification vectors s b,j , the classification vector s b,j With the normalized feature d b,j One-to-one correspondence; each of the classification vectors s b,j The predicted probability p of the total number of load types K is b,j,k Composition; each of the classification prediction probability p b,j,k corresponding to one of the load types;

[0022] The output end of the third classification prediction model is connected to the third input end of the weighted summation module; the third classification prediction model includes a third Bi-LSTM model and a third MLP network;

[0023] The third classification prediction model is used to transform the normalized feature sequence D C Input the third Bi-LSTM model, and the third Bi-LSTM model performs the normalized feature sequence D C The time series features are extracted to obtain the corresponding time series feature vector H C ; and the time series feature vector H C The various time series characteristics h c,j The third MLP network is used to input the time series features h of the input. c,j Perform load classification prediction and output the corresponding classification vector s c,j ; and all the classification vectors s are obtained c,j Sort by time to form a corresponding classification vector sequence S C ; and the classification vector sequence S C Output to the weighted summation module; wherein the time series feature vector H C Including a plurality of said timing characteristics h c,j , the timing characteristic h c,j With the normalized feature d c,j One-to-one correspondence; the classification vector sequence S C Including multiple classification vectors s c,j , the classification vector s c,j With the normalized feature dc,j One-to-one correspondence; each of the classification vectors s c,j The predicted probability p of the total number of load types K is c,j,k Composition; each of the classification prediction probability p c,j,k corresponding to one of the load types;

[0024] The output end of the weighted sum module is connected to the input end of the classification output module;

[0025] The weighted summation module is used to sum the classification vector sequence S A , S B , S C Perform weighted summation to obtain a corresponding weighted classification vector sequence S; and output the weighted classification vector sequence S to the classification output module; the weighted classification vector sequence S is composed of multiple weighted classification vectors s j The weighted classification vector s is sorted in chronological order. j With the sequence data x j One-to-one correspondence; each of the weighted classification vectors s j The weighted classification prediction probability p of the total number of load types K is j,k Composition, p j,k =w a ×p a,j,k +w b ×p b,j,k +w c ×p c,j,k , w a 、w b 、w c are the preset first, second and third weighting coefficients; each of the weighted classification prediction probabilities p j,k corresponding to one of the load types;

[0026] The output end of the classification output module is connected to the model output end;

[0027] The classification output module is used to convert each weighted classification vector s of the weighted classification vector sequence S into j as the corresponding current weighted classification vector; and for the K weighted classification prediction probabilities p in the current weighted classification vector j,k Perform a round of traversal; and in this round of traversal, the weighted classification prediction probability p of the current traversal is j,k As the corresponding current prediction probability; and the load type mark z corresponding to the current prediction probability j,k as the corresponding current load type mark; and the probability threshold value p corresponding to the current predicted probability in the preset probability threshold set hold,kas the corresponding current probability threshold; and identify whether the current predicted probability exceeds the current probability threshold, if it exceeds, the corresponding current load type flag is set to 1, if it does not exceed, the corresponding current load type flag is set to 0; and at the end of this round of traversal, the K load type flags z corresponding to the current weighted classification vector are j,k Form a corresponding prediction vector y i ; and composed of all the weighted classification vectors s j Corresponding to all the predicted vectors y i The corresponding prediction vector sequence Y is output; wherein the probability threshold set is composed of the probability threshold p of the total number K of load types hold,k Composition, each of the probability thresholds p hold,k Corresponding to one of the load types.

[0028] Preferably, the model data set includes a plurality of first data records;

[0029] The first data record includes a first training sequence and a first label vector sequence;

[0030] The first training sequence is formed by a plurality of first training sampling data arranged in chronological order; the first training sampling data includes a first training sampling time, a first training sampling current, a first training sampling power and a first training sampling temperature;

[0031] The first label vector sequence includes multiple first label prediction vectors, and the first label prediction vectors correspond one-to-one to the first training sample data; each of the first label prediction vectors includes K first label load type flags; the value of each first label load type flag is 0 or 1; each first label load type flag corresponds to one of the load types.

[0032] Preferably, the constructing of the model data set specifically includes:

[0033] Step 41, taking one or more power consumption scenarios including part or all of the loads in fixed-frequency air conditioners, variable-frequency air conditioners, electric water heaters, electric heaters, electric kettles, small kitchen treasures, microwave ovens, induction cookers, rice cookers, electric ovens, dishwashers, washing machines, refrigerators, vacuum cleaners, hair dryers, power banks, electric vehicle battery packs, and battery vehicles as corresponding sampling scenarios;

[0034] Step 42, continuously collecting data on the real-time power supply current, real-time power consumption, real-time temperature and real-time time of each sampling scene according to a preset first sampling duration to obtain a corresponding first collected data sequence; and marking the usage status of each load type in the current scene at each collection time point during the continuous data collection process of each sampling scene to obtain a corresponding first marked data sequence;

[0035] The total sampling time of the first acquisition data sequence matches the first sampling time; the first acquisition data sequence is formed by a plurality of first acquisition data arranged in chronological order; the first acquisition data includes a first acquisition time, a first acquisition current, a first acquisition power and a first acquisition temperature;

[0036] The first tag data sequence is formed by a plurality of first tag data arranged in chronological order, and the first tag data corresponds to the first collected data one by one; the first tag data includes K first load type tags; each of the first load type tags corresponds to one of the load types; the value of each of the first load type tags is 0 or 1, and the first load type tag is 0, indicating that the corresponding load type is not used at the corresponding first collection time, and the first load type tag is 1, indicating that the corresponding load type is in use at the corresponding first collection time;

[0037] Step 43, taking the model sequence input length as the corresponding first sequence length, performing sliding sequence extraction on each of the first collected data sequences with a preset first sliding step length and the first sequence length, and taking each extracted sliding sequence as a corresponding second collected data sequence; and extracting subsequences corresponding to each of the second collected data sequences in the first labeled data sequence as corresponding second labeled data sequences; and forming a corresponding first sequence pair by each of the second collected data sequences and the corresponding second labeled data sequence;

[0038] Step 44, taking each first sequence pair as the corresponding current sequence pair; and taking the second acquisition data sequence and the second label data sequence of the current sequence pair as the corresponding current acquisition data sequence and the current label data sequence; and taking the first acquisition time, the first acquisition current, the first acquisition power and the first acquisition temperature of each first acquisition data of the current acquisition data sequence as a group of corresponding first training sampling time, first training sampling current, first training sampling power and first training sampling temperature to form a corresponding first training sampling data; and taking K first load type marks of each first label data of the current label data sequence as K corresponding first label load type marks to form a corresponding first label prediction vector; and sorting all the first training sampling data corresponding to the current sequence pair in chronological order to form a corresponding first training sequence; and sorting all the first label prediction vectors corresponding to the current sequence pair in chronological order to form a corresponding first label vector sequence; and the first training sequence and the first label vector sequence corresponding to the current sequence pair to form a corresponding first data record;

[0039] Step 45: All the first data records obtained form the corresponding model data set.

[0040] Preferably, the performing model training on the intelligent load identification model based on the model data set specifically includes:

[0041] Step 51, randomly splitting the model data set into corresponding first training sets and first evaluation sets based on a preset first training evaluation ratio;

[0042] Wherein, the first training evaluation ratio is a preset ratio; the first training set and the first evaluation set both include a plurality of the first data records; the ratio of the total number of records in the first training set to the total number of records in the first evaluation set satisfies the first training evaluation ratio;

[0043] Step 52, extracting the first first data record of the first training set as the corresponding current training record;

[0044] Step 53, inputting the first training sequence of the current training record into the intelligent load identification model to perform load classification prediction processing to obtain a corresponding first training prediction vector sequence;

[0045] Step 54, bringing the first training prediction vector sequence and the first label vector sequence of the current training record into a preset first model loss function to calculate and obtain a corresponding first loss value;

[0046] Wherein, the first model loss function is implemented based on a multi-classification cross entropy loss function;

[0047] Step 55, identifying whether the first loss value satisfies a preset first loss value range; if the first loss value satisfies the first loss value range, identifying whether the current training record is the last first data record of the first training set, if so, turning to step 56, if not, extracting the next first data record of the first training set as the new current training record and returning to step 53; if the first loss value does not satisfy the first loss value range, performing a round of optimization on the model parameters of the first, second and third classification prediction models in the intelligent load identification model in the direction of minimizing the first model loss function based on a preset first model parameter optimizer, and returning to step 53 at the end of this round of optimization;

[0048] Wherein, the first model parameter optimizer includes an SGD optimizer and an ADAM optimizer;

[0049] Step 56, traverse all the first data records of the first evaluation set; and during the traversal, use the first data record currently traversed as the corresponding current evaluation record; and input the first training sequence of the current evaluation record into the intelligent load identification model for load classification prediction processing to obtain a corresponding second training prediction vector sequence; and form a corresponding first prediction label pair from the second training prediction vector sequence and the first label vector sequence of the current evaluation record;

[0050] Step 57, performing multi-classification precision and recall calculations on all the first predicted label pairs to obtain a corresponding first precision and first recall; and performing F1 score calculations on the precision and recall of the first predicted label pairs to obtain a corresponding first F1 score;

[0051] Step 58, identifying whether the first precision, the first recall and the first F1 score all satisfy the corresponding first preset precision range, the first preset recall range and the first preset F1 score range; if the first precision does not satisfy the corresponding first preset precision range or the first recall does not satisfy the corresponding first preset recall range or the first F1 score does not satisfy the corresponding first preset F1 score range, returning to step 51 to continue training; if the first precision satisfies the corresponding first preset precision range and the first recall satisfies the corresponding first preset recall range and the first F1 score satisfies the corresponding first preset F1 score range, stopping the model training, solidifying the model parameters of the intelligent load identification model, and confirming that the model training of the intelligent load identification model is completed.

[0052] A second aspect of an embodiment of the present invention provides a device for implementing the processing method of the intelligent load identification model described in the first aspect, the device comprising: a model construction module, a data set construction module, a model training module, a data receiving module and a model application module;

[0053] The model building module is used to build an intelligent load identification model;

[0054] The data set construction module is used to construct a model data set;

[0055] The model training module is used to perform model training on the intelligent load identification model based on the model data set;

[0056] The data receiving module is used to receive a time series sequence with current, power and temperature sampling data as the corresponding first input sequence after the model training is completed; the first input sequence is composed of J first sequence data arranged in chronological order, and J is the preset model sequence input length; the first sequence data includes a first sampling time, a first sampling current, a first sampling power and a first sampling temperature;

[0057] The model application module is used to input the first sampling sequence into the intelligent load identification model for load classification prediction processing to obtain a corresponding first prediction vector sequence; the first prediction vector sequence includes J first prediction vectors, and the first prediction vectors correspond to the first sequence data one by one; each of the first prediction vectors includes K first load type flags, K is the total number of preset load types; the value of each first load type flag is 0 or 1; each first load type flag corresponds to a load type; the load types include at least fixed-frequency air conditioners, variable-frequency air conditioners, electric water heaters, electric heaters, electric kettles, small kitchen treasures, microwave ovens, induction cookers, rice cookers, electric ovens, dishwashers, washing machines, refrigerators, vacuum cleaners, hair dryers, power banks, electric vehicle battery packs and battery vehicles.

[0058] A third aspect of an embodiment of the present invention provides an electronic device, including: a memory, a processor, and a transceiver;

[0059] The processor is used to couple with the memory, read and execute instructions in the memory, so as to implement the method steps described in the first aspect above;

[0060] The transceiver is coupled to the processor, and the processor controls the transceiver to send and receive messages.

[0061] A fourth aspect of an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions. When the computer instructions are executed by a computer, the computer executes the instructions of the method described in the first aspect above.

[0062] The embodiment of the present invention provides a processing method, device, electronic device and computer-readable storage medium for an intelligent load identification model. As can be seen from the above content, the embodiment of the present invention uses two types of deep learning models, namely, the Bi-LSTM model and the MLP network, to construct an intelligent load identification model; and constructs a model data set through big data collection; and performs model training on the intelligent load identification model based on the model data set; and after the model training is completed, receives a time series sequence with current, power and temperature sampling data as a model input sequence, and the intelligent load identification model performs load classification prediction based on the model input sequence. The model generalization capability of the intelligent load identification model is improved through the embodiment of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 A schematic diagram of a processing method of an intelligent load identification model provided in the first embodiment of the present invention;

[0064] Figure 2 A schematic diagram of a module of an intelligent load identification model provided in the first embodiment of the present invention;

[0065] Figure 3 A schematic diagram of a first / second / third classification prediction model provided in Example 1 of the present invention;

[0066] Figure 4 A module structure diagram of a processing device for an intelligent load identification model provided in the second embodiment of the present invention;

[0067] Figure 5 A schematic diagram of the structure of an electronic device provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0068] In order to make the purpose, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0069] Embodiment 1 of the present invention provides a method for processing an intelligent load identification model, such as Figure 1 As shown in the schematic diagram of a processing method of an intelligent load identification model provided in the first embodiment of the present invention, the method mainly includes the following steps:

[0070] Step 1: Build an intelligent load identification model.

[0071] Here, the intelligent load identification model of the embodiment of the present invention is used to perform load classification prediction processing according to the input sequence X of the model and output the corresponding prediction vector sequence Y; the model input end of the intelligent load identification model is used to receive the input sequence X, and the model output end is used to output the prediction vector sequence Y; wherein the input sequence X is composed of multiple sequence data x j Sorted in chronological order, 1≤indexj≤J, J is the preset model sequence input length; each sequence data x j Including time T j 、Current I j , power P j and temperature W j ; The prediction vector sequence Y is composed of multiple prediction vectors y i Sorted in chronological order, the prediction vector y i With sequence data x j One-to-one correspondence; each prediction vector y i Includes multiple load type flags j,k , 1≤index k≤K, K is the total number of preset load types; each load type is marked z j,k The value is 0 or 1; each load type flag z j,k Corresponding to a load type; the load types include at least fixed-frequency air conditioners, variable-frequency air conditioners, electric water heaters, electric heaters, electric kettles, small kitchen treasures, microwave ovens, induction cookers, rice cookers, electric ovens, dishwashers, washing machines, refrigerators, vacuum cleaners, hair dryers, power banks, electric vehicle battery packs and electric vehicle batteries.

[0072] like Figure 2 As shown in the module schematic diagram of the intelligent load identification model provided in the first embodiment of the present invention, the intelligent load identification model of the embodiment of the present invention includes a wavelet transformation module, a first classification prediction model, a second classification prediction model, a third classification prediction model, a weighted summation module and a classification output module; wherein:

[0073] 1) Wavelet transformation module:

[0074] like Figure 2 As shown, the input end of the wavelet conversion module is connected to the input end of the model; the first output end of the wavelet conversion module is connected to the input end of the first classification prediction model, the second output end is connected to the input end of the second classification prediction model, and the third output end is connected to the input end of the third classification prediction model;

[0075] The wavelet conversion module of the embodiment of the present invention is used for:

[0076] Step s1-1, input all currents I in sequence X jThe extracted data are sorted in chronological order to form the corresponding current timing signal;

[0077] Step s1-2, and input all the powers P in the sequence X j The extracted data are sorted in chronological order to form a corresponding power timing signal;

[0078] Step s1-3, and based on the preset first wavelet basis, extract a low-frequency current feature and two high-frequency current features from the current time series signal to obtain a corresponding first current low-frequency feature sequence {I a,j}、The first current high frequency characteristic sequence {I b,j} and the second current high frequency characteristic sequence {I c,j}; wherein the first wavelet basis at least includes the coif4 wavelet basis; the first current low-frequency characteristic sequence {I a,j}Based on a plurality of first current low-frequency characteristics I a,j The first current high frequency characteristic sequence {I b,j}Based on multiple first current high frequency characteristics I b,j The second current high frequency characteristic sequence {I c,j}By multiple second current high frequency characteristics I c,j composition;

[0079] Step s1-4, and based on the preset second wavelet basis, extract a low-frequency power feature and two high-frequency power features from the power time series signal to obtain a corresponding first power low-frequency feature sequence {P a,j}, the first power high frequency characteristic sequence {P b,j} and the second power high frequency characteristic sequence {P c,j}; wherein the second wavelet basis at least includes the db4 wavelet basis; the first power low-frequency characteristic sequence {P a,j} by a plurality of first power low frequency characteristics P a,j Composition, the first power high frequency characteristic sequence {P b,j} by a plurality of first power high frequency characteristics P b,j The second power high frequency characteristic sequence {P c,j} by a plurality of second power high frequency characteristics P c,j composition;

[0080] Step s1-5, and respectively perform high-frequency feature sequence noise reduction and smoothing processing on each current / power high-frequency feature sequence;

[0081] Step s1-6: After the high-frequency feature sequence denoising and smoothing processing is completed, the first current / power low-frequency feature sequence and the first and second current / power high-frequency feature sequences are respectively subjected to sequence normalization processing;

[0082] Step s1-7, after the sequence normalization process is completed, all time T j And all temperatures W j Corresponding time and temperature normalization processing is also performed;

[0083] Step s1-8, after the time and temperature normalization processing is completed, the normalized time, temperature, first current low-frequency feature and first power low-frequency feature corresponding to each index j form a corresponding normalized feature d a,j , and all the normalized features d a,j Sort by time to form a corresponding normalized feature sequence D A ;

[0084] Step s1-9, and the normalized time, temperature, first current high-frequency feature and first power high-frequency feature corresponding to each index j form a corresponding normalized feature d b,j , and all the normalized features d b,j Sort by time to form a corresponding normalized feature sequence D B ;

[0085] Step s1-10, and the normalized time, temperature, second current high-frequency feature and second power high-frequency feature corresponding to each index j form a corresponding normalized feature d c,j , and all the normalized features d c,j Sort by time to form a corresponding normalized feature sequence D C ;

[0086] Step s1-11, and normalize the feature sequence D A , D B , D C Output to the corresponding first, second, and third classification prediction models;

[0087] 2) First classification prediction model:

[0088] like Figure 2 As shown, the output end of the first classification prediction model is connected to the first input end of the weighted sum module; the first classification prediction model includes a first Bi-LSTM model and a first MLP network;

[0089] The first classification prediction model is used to:

[0090] Step s2-1, normalize the feature sequence D A Input the first Bi-LSTM model, and the first Bi-LSTM model normalizes the feature sequence D A The time series features are extracted to obtain the corresponding time series feature vector H A; Among them, the time series feature vector H A Including multiple time series features h a,j , time series feature h a,j With the normalized feature d a,j One to one correspondence;

[0091] Step s2-2, and transform the time series feature vector H A The various time series characteristics h a,j The first MLP network is used to input the time series features h of the input. a,j Perform load classification prediction and output the corresponding classification vector s a,j ; and all the classification vectors s are obtained a,j Sort by time to form a corresponding classification vector sequence S A ; Among them, the classification vector sequence S A Including multiple classification vectors s a,j , classification vector s a,j With the normalized feature d a,j One-to-one correspondence; each classification vector s a,j The classification prediction probability p of the total number of load types K a,j,k Composition; each classification prediction probability p a,j,k Corresponds to a load type;

[0092] Here, the processing flow of the first classification prediction model described in the above steps s2-1 to s2-2 can be referred to Figure 3 The first / second / third classification prediction model schematic diagram provided in the first embodiment of the present invention is used for understanding;

[0093] Step s2-3, and classify the vector sequence S A Output to the weighted summation module;

[0094] 3) Second classification prediction model:

[0095] like Figure 2 As shown, the output end of the second classification prediction model is connected to the second input end of the weighted sum module; the second classification prediction model includes a second Bi-LSTM model and a second MLP network;

[0096] The second classification prediction model is used to:

[0097] Step s3-1, normalize the feature sequence D B Input the second Bi-LSTM model, and the second Bi-LSTM model normalizes the feature sequence D B The time series features are extracted to obtain the corresponding time series feature vector H B ; Among them, the time series feature vector H B Including multiple time series features hb,j , time series feature h b,j With the normalized feature d b,j One to one correspondence;

[0098] Step s3-2, and transform the time series feature vector H B The various time series characteristics h b,j The second MLP network is used to input the time series features h of the input. b,j Perform load classification prediction and output the corresponding classification vector s b,j ; and all the classification vectors s are obtained b,j Sort by time to form a corresponding classification vector sequence S B ; Among them, the classification vector sequence S B Including multiple classification vectors s b,j , classification vector s b,j With the normalized feature d b,j One-to-one correspondence; each classification vector s b,j The classification prediction probability p of the total number of load types K b,j,k Composition; each classification prediction probability p b,j,k Corresponds to a load type;

[0099] Here, the processing flow of the second classification prediction model described in the above steps s3-1 to s3-2 can be referred to Figure 3 The first / second / third classification prediction model schematic diagram provided in the first embodiment of the present invention is used for understanding;

[0100] Step s3-3, and classify the vector sequence S B Output to the weighted summation module;

[0101] 4) Third classification prediction model:

[0102] like Figure 2 As shown, the output end of the third classification prediction model is connected to the third input end of the weighted sum module; the third classification prediction model includes a third Bi-LSTM model and a third MLP network;

[0103] The third classification prediction model is used for:

[0104] Step s4-1, normalize the feature sequence D C Input the third Bi-LSTM model, and the third Bi-LSTM model normalizes the feature sequence D C The time series features are extracted to obtain the corresponding time series feature vector H C ; Among them, the time series feature vector H C Including multiple time series features h c,j , time series feature h c,j With the normalized feature dc,j One to one correspondence;

[0105] Step s4-2, and transform the time series feature vector H C The various time series characteristics h c,j The third MLP network is used to input the time series features h of the input. c,j Perform load classification prediction and output the corresponding classification vector s c,j ; and all the classification vectors s are obtained c,j Sort by time to form a corresponding classification vector sequence S C ; Among them, the classification vector sequence S C Including multiple classification vectors s c,j , classification vector s c,j With the normalized feature d c,j One-to-one correspondence; each classification vector s c,j The classification prediction probability p of the total number of load types K c,j,k Composition; each classification prediction probability p c,j,k Corresponds to a load type;

[0106] Here, the processing flow of the third classification prediction model described in the above steps s4-1 to s4-2 can be referred to Figure 3 The first / second / third classification prediction model schematic diagram provided in the first embodiment of the present invention is used for understanding;

[0107] Step s4-3, and classify the vector sequence S C Output to the weighted summation module;

[0108] 5) Weighted summation module:

[0109] like Figure 2 As shown, the output end of the weighted sum module is connected to the input end of the classification output module;

[0110] The weighted sum module is used to:

[0111] Step s5-1, classify the vector sequence S A , S B , S C Perform weighted summation to obtain the corresponding weighted classification vector sequence S; wherein the weighted classification vector sequence S consists of multiple weighted classification vectors s j Sorted in chronological order, weighted classification vector s j With sequence data x j One-to-one correspondence; each weighted classification vector s j The weighted classification prediction probability p of the total number of load types K j,k Composition, p j,k =w a ×pa,j,k +w b ×p b,j,k +w c ×p c,j,k , w a 、w b 、w c are the preset first, second and third weighting coefficients; each weighted classification prediction probability p j,k Corresponds to a load type;

[0112] Step s5-2, and output the weighted classification vector sequence S to the classification output module;

[0113] 6) Classification output module:

[0114] like Figure 2 As shown, the output end of the classification output module is connected to the output end of the model;

[0115] The classification output module is used to: convert each weighted classification vector s of the weighted classification vector sequence S j As the corresponding current weighted classification vector; and predict the K weighted classification probabilities p in the current weighted classification vector j,k Perform a round of traversal; and in this round of traversal, the weighted classification prediction probability p of the current traversal is j,k As the corresponding current prediction probability; and the load type mark z corresponding to the current prediction probability j,k As the corresponding current load type mark; and the probability threshold p corresponding to the current predicted probability in the preset probability threshold set hold,k as the corresponding current probability threshold; and identify whether the current predicted probability exceeds the current probability threshold. If it exceeds, the corresponding current load type flag is set to 1; if it does not exceed, the corresponding current load type flag is set to 0; and at the end of this round of traversal, the K load type flags z corresponding to the current weighted classification vector are j,k To form a corresponding prediction vector y i ; and composed of all weighted classification vectors s j All corresponding prediction vectors y i The corresponding prediction vector sequence Y is output; the probability threshold set is composed of the probability threshold p of the total number of load types K hold,k Composition, each probability threshold p hold,k Corresponds to a load type.

[0116] Step 2, build a model dataset;

[0117] Wherein, the model data set includes a plurality of first data records; the first data record includes a first training sequence and a first label vector sequence; the first training sequence is formed by a plurality of first training sampling data arranged in chronological order; the first training sampling data includes a first training sampling time, a first training sampling current, a first training sampling power and a first training sampling temperature; the first label vector sequence includes a plurality of first label prediction vectors, and the first label prediction vectors correspond to the first training sampling data one by one; each first label prediction vector includes K first label load type flags; the value of each first label load type flag is 0 or 1; each first label load type flag corresponds to a load type;

[0118] Specifically, it includes: step 21, taking one or more power consumption scenarios of a part or all of the loads in the power loads including fixed-frequency air conditioners, variable-frequency air conditioners, electric water heaters, electric heaters, electric kettles, small kitchen treasures, microwave ovens, induction cookers, rice cookers, electric ovens, dishwashers, washing machines, refrigerators, vacuum cleaners, hair dryers, power banks, electric vehicle battery packs, and electric vehicle batteries as corresponding sampling scenarios;

[0119] Step 22, continuously collect data on the real-time power supply current, real-time power consumption, real-time temperature and real-time time of each sampling scene according to the preset first sampling time to obtain a corresponding first collected data sequence; and in the continuous data collection process of each sampling scene, mark the usage status of each load type in the current scene at each collection time point to obtain a corresponding first marked data sequence;

[0120] The first sampling duration is a preset time length, which is in months or years by default; the total sampling duration of the first acquisition data sequence matches the first sampling duration; the first acquisition data sequence is composed of a plurality of first acquisition data arranged in chronological order; the first acquisition data includes a first acquisition time, a first acquisition current, a first acquisition power and a first acquisition temperature;

[0121] The first tag data sequence is formed by a plurality of first tag data arranged in chronological order, and the first tag data corresponds to the first collection data one by one; the first tag data includes K first load type tags; each first load type tag corresponds to a load type; the value of each first load type tag is 0 or 1, and the first load type tag is 0, indicating that the corresponding load type is not used at the corresponding first collection time, and the first load type tag is 1, indicating that the corresponding load type is in use at the corresponding first collection time;

[0122] Step 23, taking the model sequence input length as the corresponding first sequence length, performing sliding sequence extraction on each first collected data sequence with a preset first sliding step length and the first sequence length, and taking each extracted sliding sequence as a corresponding second collected data sequence; and extracting the subsequences corresponding to each second collected data sequence in the first labeled data sequence as the corresponding second labeled data sequence; and forming a corresponding first sequence pair by each second collected data sequence and the corresponding second labeled data sequence;

[0123] Here, the first sliding step is a preset sequence step parameter;

[0124] For example, the first collected data sequence {data1, data2, data3, data4, data5} includes 5 first collected data, that is, the corresponding collected data sequence length is 5; assuming that the first sliding step is 2 and the first sequence length is 3; then based on the first sliding step = 2 and the first sequence length = 3, the two second collected data sequences that can be obtained by performing sliding sequence extraction on the first collected data sequence are {data1, data2, data3} and {data3, data4, data5} respectively;

[0125] Step 24, taking each first sequence pair as the corresponding current sequence pair; taking the second acquisition data sequence and the second label data sequence of the current sequence pair as the corresponding current acquisition data sequence and the current label data sequence; taking the first acquisition time, the first acquisition current, the first acquisition power and the first acquisition temperature of each first acquisition data of the current acquisition data sequence as a group of corresponding first training sampling time, first training sampling current, first training sampling power and first training sampling temperature to form a corresponding first training sampling data; taking the K first load type marks of each first label data of the current label data sequence as K corresponding first label load type marks to form a corresponding first label prediction vector; and sorting all the first training sampling data corresponding to the current sequence pair in chronological order to form a corresponding first training sequence; and sorting all the first label prediction vectors corresponding to the current sequence pair in chronological order to form a corresponding first label vector sequence; and the first training sequence and the first label vector sequence corresponding to the current sequence pair to form a corresponding first data record;

[0126] Step 25: compose a corresponding model data set from all the obtained first data records.

[0127] Step 3: training the intelligent load identification model based on the model data set;

[0128] Specifically comprising: step 31, randomly splitting the model data set into corresponding first training sets and first evaluation sets based on a preset first training evaluation ratio;

[0129] The first training evaluation ratio is a preset ratio, such as 8:2; the first training set and the first evaluation set both include a plurality of first data records; the ratio of the total number of records in the first training set to the total number of records in the first evaluation set satisfies the first training evaluation ratio;

[0130] Step 32, extracting the first first data record of the first training set as the corresponding current training record;

[0131] Step 33, inputting the first training sequence of the current training record into the intelligent load identification model to perform load classification prediction processing to obtain a corresponding first training prediction vector sequence;

[0132] Step 34, bringing the first training prediction vector sequence and the first label vector sequence of the current training record into a preset first model loss function to calculate and obtain a corresponding first loss value;

[0133] Among them, the first model loss function is implemented based on the multi-classification cross entropy loss function;

[0134] Step 35, identifying whether the first loss value satisfies a preset first loss value range; if the first loss value satisfies the first loss value range, identifying whether the current training record is the last first data record of the first training set, if so, turning to step 36, if not, extracting the next first data record of the first training set as a new current training record and returning to step 33; if the first loss value does not satisfy the first loss value range, then based on a preset first model parameter optimizer, a round of optimization is performed on the model parameters of the first, second and third classification prediction models in the intelligent load identification model in the direction of minimizing the first model loss function, and returning to step 33 at the end of this round of optimization;

[0135] The first loss value range is a preset loss value range; the first model parameter optimizer includes an SGD optimizer and an ADAM optimizer;

[0136] Step 36, traverse all first data records of the first evaluation set; and during the traversal, use the currently traversed first data record as the corresponding current evaluation record; and input the first training sequence of the current evaluation record into the intelligent load identification model for load classification prediction processing to obtain the corresponding second training prediction vector sequence; and form a corresponding first prediction label pair from the second training prediction vector sequence and the first label vector sequence of the current evaluation record;

[0137] Step 37, performing multi-classification precision and recall calculations on all first predicted label pairs to obtain corresponding first precision and first recall; and performing F1 score calculations on the precision and first recall to obtain corresponding first F1 scores;

[0138] Step 38, whether the first precision, the first recall rate and the first F1 score all satisfy the corresponding first preset precision range, the first preset recall rate range and the first preset F1 score range is identified; if the first precision does not satisfy the corresponding first preset precision range or the first recall rate does not satisfy the corresponding first preset recall rate range or the first F1 score does not satisfy the corresponding first preset F1 score range, then return to step 31 to continue training; if the first precision satisfies the corresponding first preset precision range and the first recall rate satisfies the corresponding first preset recall rate range and the first F1 score satisfies the corresponding first preset F1 score range, then stop model training, solidify the model parameters of the intelligent load identification model, and confirm that the model training of the intelligent load identification model is completed.

[0139] Here, the first preset precision range is a preset precision range, the first preset recall range is a preset recall range, and the first preset F1 score range is a preset F1 score range.

[0140] Step 4: After the model training is completed, a time series sequence with current, power and temperature sampling data is received and recorded as the corresponding first input sequence.

[0141] Here, the first input sequence is formed by J first sequence data arranged in chronological order; the first sequence data includes a first sampling time, a first sampling current, a first sampling power and a first sampling temperature.

[0142] Step 5: Input the first sampling sequence into the intelligent load identification model to perform load classification prediction processing to obtain a corresponding first prediction vector sequence.

[0143] Here, the obtained first prediction vector sequence includes J first prediction vectors, and the first prediction vectors correspond one-to-one to the first sequence data; each first prediction vector includes K first load type flags; the value of each first load type flag is 0 or 1; and each first load type flag corresponds to a load type.

[0144] It should be noted that the embodiment of the present invention can also assemble a corresponding load forecast report based on the first input sequence and the first prediction vector sequence, specifically: each first sequence data of the first input sequence and the corresponding first prediction vector form a corresponding first sampling time point prediction record; and all the obtained first sampling time point prediction records form a corresponding first time period prediction report. Based on the first time period prediction report, the use / unuse status of all power loads at each sampling time point in the time period can be intuitively displayed.

[0145] Figure 4 This is a module structure diagram of a processing device for an intelligent load identification model provided in the second embodiment of the present invention. The device is a terminal device or server that implements the aforementioned method embodiment, or can be a device that enables the aforementioned terminal device or server to implement the aforementioned method embodiment. For example, the device can be a device or chip system of the aforementioned terminal device or server. Figure 4 As shown, the device includes: a model construction module 201, a data set construction module 202, a model training module 203, a data receiving module 204 and a model application module 205.

[0146] The model building module 201 is used to build an intelligent load identification model.

[0147] The data set construction module 202 is used to construct a model data set.

[0148] The model training module 203 is used to perform model training on the intelligent load identification model based on the model data set.

[0149] The data receiving module 204 is used to receive a time series sequence with current, power and temperature sampling data as the corresponding first input sequence after the model training is completed; the first input sequence is composed of J first sequence data arranged in chronological order, and J is the preset model sequence input length; the first sequence data includes a first sampling time, a first sampling current, a first sampling power and a first sampling temperature.

[0150] The model application module 205 is used to input the first sampling sequence into the intelligent load identification model for load classification prediction processing to obtain the corresponding first prediction vector sequence; the first prediction vector sequence includes J first prediction vectors, and the first prediction vectors correspond to the first sequence data one by one; each first prediction vector includes K first load type flags, K is the total number of preset load types; the value of each first load type flag is 0 or 1; each first load type flag corresponds to a load type; the load types include at least fixed-frequency air conditioners, variable-frequency air conditioners, electric water heaters, electric heaters, electric kettles, small kitchen treasures, microwave ovens, induction cookers, rice cookers, electric ovens, dishwashers, washing machines, refrigerators, vacuum cleaners, hair dryers, power banks, electric vehicle battery packs and battery vehicles.

[0151] An embodiment of the present invention provides a processing device for an intelligent load identification model, which can execute the method steps in the above method embodiment. Its implementation principle and technical effects are similar and will not be repeated here.

[0152] It should be noted that it should be understood that the division of the various modules of the above device is only a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. And these modules can all be implemented in the form of software called by processing elements; they can also be all implemented in the form of hardware; some modules can also be implemented in the form of software called by processing elements, and some modules can be implemented in the form of hardware. For example, the model building module can be a separately established processing element, or it can be integrated in a chip of the above device. In addition, it can also be stored in the memory of the above device in the form of program code, and called and executed by a processing element of the above device. The function of the above-mentioned module is determined. The implementation of other modules is similar. In addition, these modules can be fully or partially integrated together, or they can be implemented independently. The processing element described here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each module above can be completed by an integrated logic circuit of hardware in the processor element or instructions in the form of software.

[0153] For example, the above modules may be one or more integrated circuits configured to implement the above methods, such as one or more application specific integrated circuits (ASIC), or one or more digital signal processors (DSP), or one or more field programmable gate arrays (FPGA). For another example, when a module above is implemented in the form of a processing element scheduling program code, the processing element may be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0154] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the above method embodiments are generated. The above computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The above-mentioned computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the above-mentioned computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, Bluetooth, microwave, etc.) methods. The above-mentioned computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media integrated. The above-mentioned available medium can be a magnetic medium (such as a floppy disk, a hard disk, a tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)), etc.

[0155] Figure 5 This is a schematic diagram of the structure of an electronic device provided in Embodiment 3 of the present invention. The electronic device may be a terminal device or a server for implementing the method of the aforementioned embodiment, or may be a terminal device or a server for implementing the method of the aforementioned embodiment connected to the aforementioned terminal device or server. Figure 5 As shown, the electronic device may include: a processor 301 (such as a CPU), a memory 302, and a transceiver 303; the transceiver 303 is coupled to the processor 301, and the processor 301 controls the transceiver 303. Various instructions may be stored in the memory 302 to complete various processing functions and implement the processing steps described in the aforementioned embodiment method. Preferably, the electronic device involved in the embodiment of the present invention also includes: a power supply 304, a system bus 305 and a communication port 306. The system bus 305 is used to realize the communication connection between components. The above-mentioned communication port 306 is used for connecting and communicating between the electronic device and other peripherals.

[0156] exist Figure 5The system bus 305 mentioned in the figure can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The system bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus. The communication interface is used to realize the communication between the database access device and other devices (such as clients, read-write libraries, and read-only libraries). The memory may include random access memory (RAM), and may also include non-volatile memory (Non-Volatile Memory), such as at least one disk storage.

[0157] The above-mentioned processor can be a general-purpose processor, including a central processing unit CPU, a network processor (Network Processor, NP), a graphics processing unit (Graphics Processing Unit, GPU), etc.; it can also be a digital signal processor DSP, an application-specific integrated circuit ASIC, a field programmable gate array FPGA or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0158] It should be noted that an embodiment of the present invention further provides a computer-readable storage medium, in which instructions are stored. When the computer-readable storage medium is run on a computer, the computer executes the method and processing process provided in the above embodiments.

[0159] An embodiment of the present invention further provides a chip for executing instructions, wherein the chip is used to execute the processing steps described in the aforementioned method embodiment.

[0160] The embodiment of the present invention provides a processing method, device, electronic device and computer-readable storage medium for an intelligent load identification model. As can be seen from the above content, the embodiment of the present invention uses two types of deep learning models, namely, the Bi-LSTM model and the MLP network, to construct an intelligent load identification model; and constructs a model data set through big data collection; and performs model training on the intelligent load identification model based on the model data set; and after the model training is completed, receives a time series sequence with current, power and temperature sampling data as a model input sequence, and the intelligent load identification model performs load classification prediction based on the model input sequence. The model generalization capability of the intelligent load identification model is improved through the embodiment of the present invention.

[0161] The professionals should further realize that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented by 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 the above description according to the function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0162] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0163] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A processing method for an intelligent load identification model, characterized in that: The method comprises: Build intelligent load identification model; Build model dataset; Performing model training on the intelligent load identification model based on the model data set; After the model training is completed, a time series sequence with current, power and temperature sampling data is received and recorded as the corresponding first input sequence; the first input sequence is formed by J first sequence data arranged in chronological order, and J is the preset model sequence input length; the first sequence data includes a first sampling time, a first sampling current, a first sampling power and a first sampling temperature; The first sampling sequence is input into the intelligent load identification model for load classification prediction processing to obtain a corresponding first prediction vector sequence; the first prediction vector sequence includes J first prediction vectors, and the first prediction vectors correspond to the first sequence data one by one; each of the first prediction vectors includes K first load type flags, K is the total number of preset load types; the value of each first load type flag is 0 or 1; each first load type flag corresponds to a load type; the load types include at least fixed-frequency air conditioners, variable-frequency air conditioners, electric water heaters, electric heaters, electric kettles, small kitchen treasures, microwave ovens, induction cookers, rice cookers, electric ovens, dishwashers, washing machines, refrigerators, vacuum cleaners, hair dryers, power banks, electric vehicle battery packs and battery vehicles.

2. The processing method of the intelligent load identification model according to claim 1 is characterized in that: The intelligent load identification model is used to perform load classification prediction processing according to the input sequence X of the model and output the corresponding prediction vector sequence Y; the model input end of the intelligent load identification model is used to receive the input sequence X, and the model output end is used to output the prediction vector sequence Y; The input sequence X consists of multiple sequence data x j Sorted in chronological order, 1≤indexj≤J; the sequence data x j Including time T j 、Current I j , power P j and temperature W j ; The prediction vector sequence Y is composed of multiple prediction vectors y i The prediction vector y is sorted in chronological order. i With the sequence data x j One-to-one correspondence; each of the prediction vectors y i Includes multiple load type flags j,k , 1≤index k≤K; each of the load type flags z j,k The value is 0 or 1; each load type flag z j,k Corresponds to a load type; The intelligent load identification model includes a wavelet conversion module, a first classification prediction model, a second classification prediction model, a third classification prediction model, a weighted summation module and a classification output module; The input end of the wavelet conversion module is connected to the input end of the model; the first output end of the wavelet conversion module is connected to the input end of the first classification prediction model, the second output end is connected to the input end of the second classification prediction model, and the third output end is connected to the input end of the third classification prediction model; The wavelet transformation module is used to transform all the currents I j Extract and sort them in chronological order to form a corresponding current timing signal; and convert all the power P in the input sequence X into j The extracted data are sorted in chronological order to form a corresponding power time series signal; and based on a preset first wavelet basis, a low-frequency current feature and two high-frequency current features are extracted from the current time series signal to obtain a corresponding first current low-frequency feature sequence {I a,j }、The first current high frequency characteristic sequence {I b,j } and the second current high frequency characteristic sequence {I c,j }, I a,j ,I b,j ,I c,j are respectively the corresponding first current low-frequency characteristic, the first current high-frequency characteristic, and the second current high-frequency characteristic; Based on the preset second wavelet basis, a low-frequency power feature and two high-frequency power features are extracted from the power time series signal to obtain a corresponding first power low-frequency feature sequence {P a,j }, the first power high frequency characteristic sequence {P b,j } and the second power high frequency characteristic sequence {P c,j }, P a,j , P b,j , P c,j The first power low-frequency feature, the first power high-frequency feature and the second power high-frequency feature are respectively corresponding; and each current / power high-frequency feature sequence is subjected to high-frequency feature sequence denoising and smoothing processing; and after the high-frequency feature sequence denoising and smoothing processing is completed, the first current / power low-frequency feature sequence and the first and second current / power high-frequency feature sequences are subjected to sequence normalization processing; and after the sequence normalization processing is completed, all the time T j And all the temperatures W j Corresponding time and temperature normalization processing is also performed; After the time and temperature normalization processing is completed, the normalized time, temperature, first current low-frequency feature and first power low-frequency feature corresponding to each index j form a corresponding normalized feature d a,j , and all the normalized features d are obtained a,j Sort by time to form a corresponding normalized feature sequence D A ; and the normalized time, temperature, first current high-frequency feature and first power high-frequency feature corresponding to each of the indexes j form a corresponding normalized feature d b,j , and all the normalized features d are obtained b,j Sort by time to form a corresponding normalized feature sequence D B ; and the normalized time, temperature, second current high-frequency feature and second power high-frequency feature corresponding to each of the indexes j form a corresponding normalized feature d c,j , and all the normalized features d are obtained c,j Sort by time to form a corresponding normalized feature sequence D C ; and the normalized feature sequence D A , D B , D C Output to the corresponding first, second and third classification prediction models; wherein the first wavelet basis includes at least the coif4 wavelet basis; the second wavelet basis includes at least the db4 wavelet basis; The output end of the first classification prediction model is connected to the first input end of the weighted summation module; the first classification prediction model includes a first Bi-LSTM model and a first MLP network; The first classification prediction model is used to transform the normalized feature sequence D A The first Bi-LSTM model is input, and the first Bi-LSTM model performs the normalized feature sequence D A The time series features are extracted to obtain the corresponding time series feature vector H A ; and the time series feature vector H A The various time series characteristics h a,j The first MLP network is used to input the first MLP network according to the time series feature h a,j Perform load classification prediction and output the corresponding classification vector s a,j ; and all the classification vectors s are obtained a,j Sort by time to form a corresponding classification vector sequence S A ; and the classification vector sequence S A Output to the weighted summation module; wherein the time series feature vector H A Including a plurality of said timing characteristics h a,j , the timing characteristic h a,j With the normalized feature d a,j One-to-one correspondence; the classification vector sequence S A Including multiple classification vectors s a,j , the classification vector s a,j With the normalized feature d a,j One-to-one correspondence; each of the classification vectors s a,j The predicted probability p of the total number of load types K is a,j,k Composition; each of the classification prediction probability p a,j,k corresponding to one of the load types; The output end of the second classification prediction model is connected to the second input end of the weighted sum module; the second classification prediction model includes a second Bi-LSTM model and a second MLP network; The second classification prediction model is used to transform the normalized feature sequence D B The second Bi-LSTM model is input, and the second Bi-LSTM model performs the normalized feature sequence D B The time series features are extracted to obtain the corresponding time series feature vector H B ; and the time series feature vector H B The various time series characteristics h b,j The second MLP network is respectively inputted, and the second MLP network is used to generate the time series feature h according to the input time series feature h. b,j Perform load classification prediction and output the corresponding classification vector s b,j ; and all the classification vectors s are obtained b,j Sort by time to form a corresponding classification vector sequence S B ; and the classification vector sequence S B Output to the weighted summation module; wherein the time series feature vector H B Including a plurality of said timing characteristics h b,j , the timing characteristic h b,j With the normalized feature d b,j One-to-one correspondence; the classification vector sequence S B Including multiple classification vectors s b,j , the classification vector s b,j With the normalized feature d b,j One-to-one correspondence; each of the classification vectors s b,j The predicted probability p of the total number of load types K is b,j,k Composition; each of the classification prediction probability p b,j,k corresponding to one of the load types; The output end of the third classification prediction model is connected to the third input end of the weighted sum module; the third classification prediction model includes a third Bi-LSTM model and a third MLP network; The third classification prediction model is used to transform the normalized feature sequence D C Input the third Bi-LSTM model, and the third Bi-LSTM model performs the normalized feature sequence D C The time series features are extracted to obtain the corresponding time series feature vector H C ; and the time series feature vector H C The various time series characteristics h c,j The third MLP network is used to input the time series features h of the input. c,j Perform load classification prediction and output the corresponding classification vector s c,j ; and all the classification vectors s are obtained c,j Sort by time to form a corresponding classification vector sequence S C ; and the classification vector sequence S C Output to the weighted summation module; wherein the time series feature vector H C Including a plurality of said timing characteristics h c,j , the timing characteristic h c,j With the normalized feature d c,j One-to-one correspondence; the classification vector sequence S C Including multiple classification vectors s c,j , the classification vector s c,j With the normalized feature d c,j One-to-one correspondence; each of the classification vectors s c,j The predicted probability p of the total number of load types K is c,j,k Composition; each of the classification prediction probability p c,j,k corresponding to one of the load types; The output end of the weighted summation module is connected to the input end of the classification output module; The weighted summation module is used to sum the classification vector sequence S A , S B , S C Perform weighted summation to obtain a corresponding weighted classification vector sequence S; and output the weighted classification vector sequence S to the classification output module; the weighted classification vector sequence S is composed of multiple weighted classification vectors s j The weighted classification vector s is sorted in chronological order. j With the sequence data x j One-to-one correspondence; each of the weighted classification vectors s j The weighted classification prediction probability p of the total number of load types K is j,k Composition, p j,k =w a ×p a,j,k +w b ×p b,j,k +w c ×p c,j,k , w a 、w b 、w c are the preset first, second and third weighting coefficients; each of the weighted classification prediction probabilities p j,k corresponding to one of the load types; The output end of the classification output module is connected to the model output end; The classification output module is used to convert each weighted classification vector s of the weighted classification vector sequence S into j as the corresponding current weighted classification vector; and for the K weighted classification prediction probabilities p in the current weighted classification vector j,k Perform a round of traversal; and in this round of traversal, the weighted classification prediction probability p of the current traversal is j,k As the corresponding current prediction probability; and the load type mark z corresponding to the current prediction probability j,k as the corresponding current load type mark; and the probability threshold value p corresponding to the current predicted probability in the preset probability threshold set hold,k as the corresponding current probability threshold; and identify whether the current predicted probability exceeds the current probability threshold, if it exceeds, the corresponding current load type flag is set to 1, if it does not exceed, the corresponding current load type flag is set to 0; and at the end of this round of traversal, the K load type flags z corresponding to the current weighted classification vector are j,k Form a corresponding prediction vector y i ; and composed of all the weighted classification vectors s j All the corresponding prediction vectors y i The corresponding prediction vector sequence Y is output; wherein the probability threshold set is composed of the probability threshold p of the total number K of load types hold,k Composition, each of the probability thresholds p hold,k Corresponding to one of the load types.

3. The processing method of the intelligent load identification model according to claim 2 is characterized in that: The model data set includes a plurality of first data records; The first data record includes a first training sequence and a first label vector sequence; The first training sequence is formed by a plurality of first training sampling data arranged in chronological order; the first training sampling data includes a first training sampling time, a first training sampling current, a first training sampling power and a first training sampling temperature; The first label vector sequence includes multiple first label prediction vectors, and the first label prediction vectors correspond one-to-one to the first training sample data; each of the first label prediction vectors includes K first label load type flags; the value of each first label load type flag is 0 or 1; each first label load type flag corresponds to one of the load types.

4. The processing method of the intelligent load identification model according to claim 3 is characterized in that: The constructing of the model data set specifically includes: Step 41, taking one or more power consumption scenarios including part or all of the loads in fixed-frequency air conditioners, variable-frequency air conditioners, electric water heaters, electric heaters, electric kettles, small kitchen treasures, microwave ovens, induction cookers, rice cookers, electric ovens, dishwashers, washing machines, refrigerators, vacuum cleaners, hair dryers, power banks, electric vehicle battery packs, and battery vehicles as corresponding sampling scenarios; Step 42, continuously collecting data on the real-time power supply current, real-time power consumption, real-time temperature and real-time time of each sampling scene according to a preset first sampling duration to obtain a corresponding first collected data sequence; and marking the usage status of each load type in the current scene at each collection time point during the continuous data collection process of each sampling scene to obtain a corresponding first marked data sequence; The total sampling time of the first acquisition data sequence matches the first sampling time; the first acquisition data sequence is formed by a plurality of first acquisition data arranged in chronological order; the first acquisition data includes a first acquisition time, a first acquisition current, a first acquisition power and a first acquisition temperature; The first tag data sequence is formed by a plurality of first tag data arranged in chronological order, and the first tag data corresponds to the first collected data one by one; the first tag data includes K first load type tags; each of the first load type tags corresponds to one of the load types; the value of each of the first load type tags is 0 or 1, and the first load type tag is 0, indicating that the corresponding load type is not used at the corresponding first collection time, and the first load type tag is 1, indicating that the corresponding load type is in use at the corresponding first collection time; Step 43, taking the model sequence input length as the corresponding first sequence length, performing sliding sequence extraction on each of the first collected data sequences with a preset first sliding step length and the first sequence length, and taking each extracted sliding sequence as a corresponding second collected data sequence; and extracting subsequences corresponding to each of the second collected data sequences in the first labeled data sequence as corresponding second labeled data sequences; and forming a corresponding first sequence pair by each of the second collected data sequences and the corresponding second labeled data sequence; Step 44, taking each first sequence pair as the corresponding current sequence pair; and taking the second acquisition data sequence and the second label data sequence of the current sequence pair as the corresponding current acquisition data sequence and the current label data sequence; and taking the first acquisition time, the first acquisition current, the first acquisition power and the first acquisition temperature of each first acquisition data of the current acquisition data sequence as a group of corresponding first training sampling time, first training sampling current, first training sampling power and first training sampling temperature to form a corresponding first training sampling data; and taking K first load type marks of each first label data of the current label data sequence as K corresponding first label load type marks to form a corresponding first label prediction vector; and sorting all the first training sampling data corresponding to the current sequence pair in chronological order to form a corresponding first training sequence; and sorting all the first label prediction vectors corresponding to the current sequence pair in chronological order to form a corresponding first label vector sequence; and the first training sequence and the first label vector sequence corresponding to the current sequence pair to form a corresponding first data record; Step 45: All the first data records obtained form the corresponding model data set.

5. The processing method of the intelligent load identification model according to claim 3 is characterized in that: The performing model training on the intelligent load identification model based on the model data set specifically includes: Step 51, randomly splitting the model data set into corresponding first training sets and first evaluation sets based on a preset first training evaluation ratio; Wherein, the first training evaluation ratio is a preset ratio; the first training set and the first evaluation set both include a plurality of the first data records; the ratio of the total number of records in the first training set to the total number of records in the first evaluation set satisfies the first training evaluation ratio; Step 52, extracting the first first data record of the first training set as the corresponding current training record; Step 53, inputting the first training sequence of the current training record into the intelligent load identification model to perform load classification prediction processing to obtain a corresponding first training prediction vector sequence; Step 54, bringing the first training prediction vector sequence and the first label vector sequence of the current training record into a preset first model loss function to calculate and obtain a corresponding first loss value; Wherein, the first model loss function is implemented based on a multi-classification cross entropy loss function; Step 55, identifying whether the first loss value satisfies a preset first loss value range; if the first loss value satisfies the first loss value range, identifying whether the current training record is the last first data record of the first training set, if so, turning to step 56, if not, extracting the next first data record of the first training set as the new current training record and returning to step 53; if the first loss value does not satisfy the first loss value range, performing a round of optimization on the model parameters of the first, second and third classification prediction models in the intelligent load identification model in the direction of minimizing the first model loss function based on a preset first model parameter optimizer, and returning to step 53 at the end of this round of optimization; Wherein, the first model parameter optimizer includes an SGD optimizer and an ADAM optimizer; Step 56, traverse all the first data records of the first evaluation set; and during the traversal, use the first data record currently traversed as the corresponding current evaluation record; and input the first training sequence of the current evaluation record into the intelligent load identification model for load classification prediction processing to obtain a corresponding second training prediction vector sequence; and form a corresponding first prediction label pair from the second training prediction vector sequence and the first label vector sequence of the current evaluation record; Step 57, performing multi-classification precision and recall calculations on all the first predicted label pairs to obtain a corresponding first precision and first recall; and performing F1 score calculations on the precision and recall of the first predicted label pairs to obtain a corresponding first F1 score; Step 58, identifying whether the first precision, the first recall and the first F1 score all satisfy the corresponding first preset precision range, the first preset recall range and the first preset F1 score range; if the first precision does not satisfy the corresponding first preset precision range or the first recall does not satisfy the corresponding first preset recall range or the first F1 score does not satisfy the corresponding first preset F1 score range, returning to step 51 to continue training; if the first precision satisfies the corresponding first preset precision range and the first recall satisfies the corresponding first preset recall range and the first F1 score satisfies the corresponding first preset F1 score range, stopping the model training, solidifying the model parameters of the intelligent load identification model, and confirming that the model training of the intelligent load identification model is completed.

6. A device for executing the processing method of the intelligent load identification model according to any one of claims 1 to 5, characterized in that: The device comprises: a model construction module, a data set construction module, a model training module, a data receiving module and a model application module; The model building module is used to build an intelligent load identification model; The data set construction module is used to construct a model data set; The model training module is used to perform model training on the intelligent load identification model based on the model data set; The data receiving module is used to receive a time series sequence with current, power and temperature sampling data as the corresponding first input sequence after the model training is completed; the first input sequence is composed of J first sequence data arranged in chronological order, and J is the preset model sequence input length; the first sequence data includes a first sampling time, a first sampling current, a first sampling power and a first sampling temperature; The model application module is used to input the first sampling sequence into the intelligent load identification model for load classification prediction processing to obtain a corresponding first prediction vector sequence; the first prediction vector sequence includes J first prediction vectors, and the first prediction vectors correspond to the first sequence data one by one; each of the first prediction vectors includes K first load type flags, K is the total number of preset load types; the value of each first load type flag is 0 or 1; each first load type flag corresponds to a load type; the load types include at least fixed-frequency air conditioners, variable-frequency air conditioners, electric water heaters, electric heaters, electric kettles, small kitchen treasures, microwave ovens, induction cookers, rice cookers, electric ovens, dishwashers, washing machines, refrigerators, vacuum cleaners, hair dryers, power banks, electric vehicle battery packs and battery vehicles.

7. An electronic device, characterized in that: include: memory, processors, and transceivers; The processor is used to couple with the memory, read and execute instructions in the memory, so as to implement the method according to any one of claims 1 to 5; The transceiver is coupled to the processor, and the processor controls the transceiver to send and receive messages.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a computer, the computer is enabled to execute the method according to any one of claims 1 to 5.

Citation Information

Patent Citations

  • Public building load identification method and device and computer readable storage medium

    CN115018052A

  • High-voltage cable partial discharge fault prediction method and system

    CN116027158A

  • Multi-LSTM power load short-term prediction method based on multi-scene recognition

    CN116937555A

  • Non-intrusive load monitoring method and system based on multi-task learning model

    CN117272230A

  • Load prediction method and device based on neural network, equipment and medium

    CN118017493A

Cited By

  • Processing method and device for predicting binding site of molecular fragment

    CN119673316A