CN116976472A - Method, system, equipment and storage medium for predicting residential electric energy consumption - Google Patents
Method, system, equipment and storage medium for predicting residential electric energy consumption Download PDFInfo
- Publication number
- CN116976472A CN116976472A CN202210384437.4A CN202210384437A CN116976472A CN 116976472 A CN116976472 A CN 116976472A CN 202210384437 A CN202210384437 A CN 202210384437A CN 116976472 A CN116976472 A CN 116976472A
- Authority
- CN
- China
- Prior art keywords
- data
- energy consumption
- preset
- time period
- electric energy
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000005265 energy consumption Methods 0.000 title claims abstract description 223
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000003860 storage Methods 0.000 title claims abstract description 20
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 37
- 238000004458 analytical method Methods 0.000 claims abstract description 9
- 230000004927 fusion Effects 0.000 claims description 51
- 238000012549 training Methods 0.000 claims description 43
- 238000009826 distribution Methods 0.000 claims description 36
- 230000006870 function Effects 0.000 claims description 25
- 238000000605 extraction Methods 0.000 claims description 24
- 238000012545 processing Methods 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 13
- 230000000737 periodic effect Effects 0.000 claims description 10
- 238000001228 spectrum Methods 0.000 claims description 10
- 230000009466 transformation Effects 0.000 claims description 7
- 239000010410 layer Substances 0.000 description 42
- 230000005611 electricity Effects 0.000 description 7
- 230000019771 cognition Effects 0.000 description 5
- 238000010219 correlation analysis Methods 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 230000000306 recurrent effect Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 230000001808 coupling effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 101001006892 Homo sapiens Krueppel-like factor 10 Proteins 0.000 description 1
- 102100027798 Krueppel-like factor 10 Human genes 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000002346 layers by function Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention provides a method, a system, equipment and a storage medium for predicting residential electric energy consumption, wherein the method comprises the following steps: acquiring electric energy consumption data in a first time period and at least one initial external data in the first time period, determining the initial external data with gray correlation degree not smaller than a first preset threshold value as final external data based on a preset gray correlation degree analysis algorithm, wherein the gray correlation degree is the correlation degree of the initial external data and the electric energy consumption data, extracting the input quantity of the electric energy consumption data in the first time period based on a preset empirical wavelet transform algorithm, acquiring a first subsequence set of the electric energy consumption data in the first time period, inputting the first subsequence set and the final external data into a preset energy consumption prediction model for energy consumption prediction, and acquiring electric energy consumption prediction data in a second time period. Therefore, the invention improves the accuracy of predicting the electric energy consumption of the residential building.
Description
Technical Field
The present invention relates to the field of energy consumption data processing, and in particular, to a method, system, device and storage medium for predicting residential power consumption.
Background
In recent years, as the proportion of the electric energy consumption of residents to the total social electric energy consumption is continuously increased, the load of the existing power grid is increased, even the phenomenon of switching off and limiting electricity occurs more frequently, and the social production and the life of residents are seriously affected. In the prior art, the electricity consumption data of the residential building are collected by the tail end sensor, and the electricity consumption is predicted by the electricity consumption data according to the experience of the person skilled in the relevant field. Because the electricity consumption data has the characteristics of uncertainty, gao Weixing, high nonlinearity and the like, the accuracy is low as a result of predicting the electric energy consumption of the residential building according to the electricity consumption data.
Disclosure of Invention
The embodiment of the invention aims to provide a method, a system, equipment and a storage medium for predicting residential electric energy consumption, so as to improve the accuracy of predicting residential electric energy consumption. The specific technical scheme is as follows:
a method of predicting residential power consumption, the method comprising:
the method comprises the steps of acquiring power consumption data in a first time period and at least one initial external data in the first time period.
And determining the initial external data with gray correlation degree not smaller than a first preset threshold value as final external data based on a preset gray correlation degree analysis algorithm, wherein the gray correlation degree is the correlation degree of the initial external data and the electric energy consumption data.
Performing an extraction operation on the power consumption data in the first time period based on a preset empirical wavelet transform algorithm, and obtaining a first subsequence set of the power consumption data in the first time period, wherein the first subsequence set comprises: a trend component sub-sequence and a periodic component sub-sequence of the power consumption data over the first period of time.
And inputting the first sub-sequence set and the final external data into a preset energy consumption prediction model to perform energy consumption prediction, and obtaining electric energy consumption prediction data in a second time period, wherein the second time period is a time period after the first time period.
Optionally, the preset energy consumption prediction model includes: a preset time sequence prediction layer and a preset attention distribution layer.
The process of obtaining the electric energy consumption prediction data in the second time period by the preset energy consumption prediction model according to the first subsequence set and the final external data includes:
For each subsequence in the first set of subsequences: and performing data splicing on the subsequence and the final external data in a vector dimension to obtain a first fusion characteristic sequence corresponding to the subsequence. And carrying out feature extraction on the first fusion feature sequence by using the preset time sequence prediction layer to obtain a first prediction similarity of the first fusion feature sequence. And according to the first prediction similarity, performing attention score distribution on each feature data in the first fusion feature sequence by using the preset attention distribution layer to obtain an electric energy consumption prediction parameter in a second time period, wherein the electric energy consumption prediction parameter has a corresponding relation with the subsequence.
For the first set of subsequences: and carrying out summation budget on the power consumption prediction parameters corresponding to the subsequences to obtain power consumption prediction data in the second time period.
Optionally, the training process of the preset energy consumption prediction model includes:
obtaining training data, wherein the training data comprises: a second set of subsequences within a first historical period, final external data for at least one of the first historical periods, and power consumption data for a second historical period, the second historical period being a period of time subsequent to the first historical period.
Training an initial energy consumption prediction model by using the training data to obtain the preset energy consumption prediction model, wherein the input of the preset energy consumption prediction model is a subsequence set in a preset time period and at least one final external data in the time period, and the output of the preset energy consumption prediction model is the electric energy consumption prediction data in a time period after the preset time period.
Optionally, the training the initial energy consumption prediction model by using the training data to obtain the preset energy consumption prediction model specifically includes:
for each subsequence in the second set of subsequences: and performing data splicing on the subsequence and final external data of at least one of the first historical time periods to obtain a second fusion characteristic sequence corresponding to the subsequence. And extracting the characteristics of the second fusion characteristic sequence by using an initial time sequence prediction layer to obtain a second prediction similarity. And according to the second prediction similarity, performing attention score distribution on each feature data in the second fusion feature sequence by using an initial attention distribution layer to obtain an electric energy consumption prediction parameter of a second historical time period, wherein the electric energy consumption prediction parameter of the second historical time period has a corresponding relation with the subsequence.
For the second set of subsequences: and carrying out summation budget on the power consumption prediction parameters corresponding to the subsequences to obtain power consumption prediction data in a second historical time period.
And performing parameter adjustment operation on the initial time sequence prediction layer and the initial attention distribution layer according to the electric energy consumption prediction data in the second historical time period and the electric energy consumption data in the second historical time period until the difference value between the electric energy consumption prediction data and the electric energy consumption data in the second historical time period meets a preset condition, so as to complete training of the initial energy consumption prediction model and obtain the preset energy consumption prediction model.
Optionally, the process of performing an extraction operation on the power consumption data in the first period based on a preset empirical wavelet transform algorithm to obtain a first subsequence set of the power consumption data in the first period includes:
and carrying out Fourier transform on the electric energy consumption data in the first time period by using a preset empirical wavelet transform algorithm to obtain a Fourier spectrum of the electric energy consumption data.
And constructing an empirical wavelet function and an empirical scale function according to the Fourier spectrum.
And carrying out data reconstruction on the electric energy consumption data by using the empirical wavelet function and the empirical scale function, and carrying out the component extraction operation to obtain a first subsequence set of the electric energy consumption data in the first time period.
A system for predicting residential power consumption, the system comprising:
the device comprises an initial data acquisition module, a data processing module and a data processing module, wherein the initial data acquisition module is used for acquiring electric energy consumption data in a first time period and at least one initial external data in the first time period.
The first data processing module is used for determining the initial external data with gray correlation degree not smaller than a first preset threshold value as final external data based on a preset gray correlation degree analysis algorithm, wherein the gray correlation degree is the correlation degree of the initial external data and the electric energy consumption data.
The second data processing module performs component extraction operation on the electric energy consumption data in the first time period based on a preset empirical wavelet transformation algorithm to obtain a first subsequence set of the electric energy consumption data in the first time period, wherein the first subsequence set comprises: a trend component sub-sequence and a periodic component sub-sequence of the power consumption data over the first period of time.
And the energy consumption prediction module is used for inputting the first sub-sequence set and the final external data into a preset energy consumption prediction model to perform energy consumption prediction to obtain electric energy consumption prediction data in a second time period, wherein the second time period is a time period after the first time period.
Optionally, a preset energy consumption prediction model in the energy consumption prediction module is configured with a preset time sequence prediction layer and a preset attention distribution layer. The energy consumption prediction module is configured to:
for each subsequence in the first set of subsequences:
and performing data splicing on the subsequence and the final external data in a vector dimension to obtain a first fusion characteristic sequence corresponding to the subsequence.
And carrying out feature extraction on the first fusion feature sequence by using the preset time sequence prediction layer to obtain a first prediction similarity of the first fusion feature sequence.
And according to the first prediction similarity, performing attention score distribution on each feature data in the first fusion feature sequence by using the preset attention distribution layer to obtain an electric energy consumption prediction parameter in a second time period, wherein the electric energy consumption prediction parameter has a corresponding relation with the subsequence.
For the first set of subsequences:
and carrying out summation budget on the power consumption prediction parameters corresponding to the subsequences to obtain power consumption prediction data in the second time period.
Optionally, the system further comprises:
the model training module is used for obtaining training data, wherein the training data comprises: a second set of subsequences within a first historical period, final external data for at least one of the first historical periods, and power consumption data for a second historical period, the second historical period being a period of time subsequent to the first historical period. Training an initial energy consumption prediction model by using the training data to obtain the preset energy consumption prediction model, wherein the input of the preset energy consumption prediction model is a subsequence set in a preset time period and at least one final external data in the time period, and the input of the preset energy consumption prediction model is electric energy consumption prediction data in a time period after the preset time period.
Optionally, the model training module is specifically configured to:
for each subsequence in the second set of subsequences: and performing data splicing on the subsequence and final external data of at least one of the first historical time periods to obtain a second fusion characteristic sequence corresponding to the subsequence. And extracting the characteristics of the second fusion characteristic sequence by using an initial time sequence prediction layer to obtain a second prediction similarity. And according to the second prediction similarity, performing attention score distribution on each feature data in the second fusion feature sequence by using an initial attention distribution layer to obtain an electric energy consumption prediction parameter of a second historical time period, wherein the electric energy consumption prediction parameter of the second historical time period has a corresponding relation with the subsequence.
For the second set of subsequences: and carrying out summation budget on the power consumption prediction parameters corresponding to the subsequences to obtain power consumption prediction data in a second historical time period.
And performing parameter adjustment operation on the initial time sequence prediction layer and the initial attention distribution layer according to the electric energy consumption prediction data in the second historical time period and the electric energy consumption data in the second historical time period until the difference value between the electric energy consumption prediction data and the electric energy consumption data in the second historical time period meets a preset condition, so as to complete training of the initial energy consumption prediction model and obtain the preset energy consumption prediction model.
Optionally, the second data processing module is configured to:
and carrying out Fourier transform on the electric energy consumption data in the first time period by using a preset empirical wavelet transform algorithm to obtain a Fourier spectrum of the electric energy consumption data.
And constructing an empirical wavelet function and an empirical scale function according to the Fourier spectrum.
And carrying out data reconstruction on the electric energy consumption data by using the empirical wavelet function and the empirical scale function, and carrying out the component extraction operation to obtain a first subsequence set of the electric energy consumption data in the first time period.
An apparatus for predicting residential power consumption, the apparatus comprising:
a processor;
a memory for storing the processor-executable instructions.
Wherein the processor is configured to execute the instructions to implement a method of predicting residential power consumption as claimed in any one of the preceding claims.
A computer storage medium, which when executed by a processor of an electronic device, causes the device to perform the method of predicting residential power consumption as claimed in any one of the preceding claims.
According to the method, the system, the equipment and the storage medium for predicting the residential electric energy consumption, provided by the embodiment of the invention, the electric energy consumption prediction data is objectively predicted from a mathematical operation angle according to the first subsequence set and the final external data by utilizing the preset energy consumption prediction model, so that compared with the mode of carrying out the energy consumption prediction according to subjective cognition of a person in the prior art, the influence of the subjective cognition on the finally obtained electric energy consumption prediction data is reduced, and the accuracy of predicting the residential electric energy consumption is improved. Meanwhile, the invention calculates the association degree between the power consumption data and the development trend of the initial external data by introducing a preset gray association degree analysis algorithm, and eliminates redundant data in the initial external data, thereby reducing the dimension of the input vector and improving the accuracy and the operation efficiency of the data. Finally, through introducing a preset empirical wavelet transformation algorithm, the trend component and the periodic component in the electric energy consumption data are identified and extracted, and the decoupling of the electric energy consumption data is realized, so that the accuracy of the finally obtained electric energy consumption prediction data is improved. Therefore, the invention improves the accuracy of predicting the electric energy consumption of the residential building.
Of course, it is not necessary for any one product or method of practicing the invention to achieve all of the advantages set forth above at the same time.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for predicting residential power consumption according to an embodiment of the present invention;
FIG. 2 is a flow chart of obtaining predicted data of power consumption over a second time period in accordance with an alternative embodiment of the present invention;
FIG. 3 is a block diagram of a system for predicting residential power consumption in accordance with another alternative embodiment of the present invention;
fig. 4 is a block diagram of an apparatus for predicting residential power consumption in accordance with another alternative embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The embodiment of the invention provides a method for predicting residential electric energy consumption, as shown in fig. 1, which comprises the following steps:
s101, acquiring the electric energy consumption data in a first time period and at least one initial external data in the first time period.
The types of the above-mentioned power consumption data include, but are not limited to: household energy consumption data and lighting energy consumption data. Types of the initial external data described above include, but are not limited to: temperature in a room, humidity in a room, latitude in a house, weather characteristics of an area in which the house is located, and the like.
Alternatively, in an alternative embodiment of the present invention, the acquired power consumption data and the initial external data may be data obtained after data preprocessing. The operation types of the data preprocessing include, but are not limited to: data denoising, missing value filling, normalization and the like. Since the above data preprocessing operation is a well known technology for those skilled in the art, the present invention is not repeated herein and limited thereto.
Optionally, in another optional embodiment of the present invention, the above electrical energy consumption data may be uploaded to a background database for storage by an intelligent electrical energy metering device or an intelligent home, where the electrical energy consumption data is collected in a period of time. The invention can acquire the electric energy consumption data through the background database.
Alternatively, in another optional embodiment of the present invention, the initial external data may be collected by a sensing device such as a temperature sensor, a humidity sensor, and an illumination intensity sensor, which are disposed indoors, and uploaded to the background database for storage. The invention can obtain the initial external data by reading the background database.
S102, determining initial external data with gray correlation degree not smaller than a first preset threshold value as final external data based on a preset gray correlation degree analysis algorithm, wherein the gray correlation degree is the correlation degree of the initial external data and the electric energy consumption data.
Alternatively, in an alternative embodiment of the present invention, the preset gray correlation analysis algorithm may be an Entropy-based gray correlation analysis algorithm (Entropy-based Grey Relation Analysis, EGRA). Since the above-mentioned power consumption data and initial external data are data belonging to different systems, respectively, there is no direct connection between them. Therefore, in order to ensure the accuracy of the data for predicting the power consumption of the house, it is necessary to calculate the degree of correlation between the power consumption data and the trend of the initial external data, so as to obtain the initial external data having the degree of correlation with the power consumption data satisfying the requirements. Meanwhile, since useless features or redundant features may exist in the initial external data, the operation efficiency is reduced. Therefore, the invention eliminates redundant data in the initial external data by introducing a preset gray correlation analysis algorithm, thereby realizing the purposes of reducing the dimension of the input vector and improving the calculation efficiency.
Optionally, in another optional embodiment of the present invention, the specific implementation manner of determining, based on the preset gray correlation analysis algorithm, the initial external data with the gray correlation not smaller than the first preset threshold as the final external data may be:
according to household energy consumption dataInitial external data->By the formula:
obtaining initial external data characterizing the mthAnd household appliance energy consumption data->Gray correlation coefficient of degree of correlation->Wherein t is the moment of corresponding data acquisition, ρ is a preset resolution coefficient, Δmin is the minimum absolute value of two poles of the household energy consumption data and the initial external data, and Δmin can be represented by the formula:
and (5) calculating to obtain the product. Wherein Δmax is the maximum absolute value of the two poles of the household energy consumption data and the initial external data. Δmax may be calculated by the formula:
and (5) calculating to obtain the product.
According to grey correlation coefficientBy the formula:
correlating grey coefficientsThe grey correlation density p (m, t) is converted.
According to the gray correlation density p (m, t), the following formula:
and calculating the maximum gray entropy E (m) corresponding to the gray correlation density p (m, t). Wherein,,gray entropy corresponding to mth initial external data, +.>Is a maximum value for limiting the maximum gray entropy E (m) to between 0 and 1.
According to the maximum gray entropy E (m) and gray correlation coefficient corresponding to the mth initial external dataBy the formula:
obtaining final characterization household electricity consumption dataAnd the mth initial external data->Gray degree of association GRG of degree of association;
and determining the initial external data with the gray correlation degree GRG not smaller than a first preset threshold value as final external data.
S103, performing component extraction operation on the electric energy consumption data in a first time period based on a preset empirical wavelet transformation algorithm, and obtaining a first subsequence set of the electric energy consumption data in the first time period, wherein the first subsequence set comprises: trend component sub-sequences and periodic component sub-sequences of the power consumption data over a first period of time.
Optionally, in an alternative embodiment of the present invention, the above-mentioned predetermined empirical wavelet transform algorithm (Empirical Wavelet Transform, EWT) is an adaptive signal decomposition method. The obtained power consumption data is multivariate time sequence data in a time period, and coupling effects are inevitably generated among the multivariate data, so that the accuracy of the finally obtained power consumption prediction data is reduced. Therefore, in order to eliminate the coupling effect between the polynomials, the accuracy of the finally obtained electric power consumption prediction data is improved. According to the invention, an EWT algorithm is introduced to identify and extract trend components and periodic components in the power consumption data, so that decoupling of the power consumption data is realized, and the accuracy of finally obtained power consumption prediction data is improved.
Alternatively, in another alternative embodiment of the present invention, the trend component sub-sequence may represent an internal trend of change in the power consumption data, and the period component sub-sequence may represent period change information of the power consumption data.
S104, inputting the first sub-sequence set and the final external data into a preset energy consumption prediction model to perform energy consumption prediction, and obtaining the energy consumption prediction data in a second time period, wherein the second time period is a time period after the first time period.
Optionally, in an optional embodiment of the present invention, the preset energy consumption prediction model may integrate the feature data in the first sub-sequence set and the final external data, and extract and calculate features affecting the obtaining of the final energy consumption prediction data in the feature data, so as to obtain the energy consumption prediction data characterizing the generation of the home appliance in the second period.
According to the invention, the electric energy consumption prediction data is objectively predicted from a mathematical operation angle according to the first subsequence set and the final external data by utilizing the preset energy consumption prediction model, so that compared with the mode of carrying out energy consumption prediction according to subjective cognition of people in the prior art, the influence of the subjective cognition on the finally obtained electric energy consumption prediction data is reduced, and the accuracy of predicting the electric energy consumption of residential houses is improved. Meanwhile, the invention calculates the association degree between the power consumption data and the development trend of the initial external data by introducing a preset gray association degree analysis algorithm, and eliminates redundant data in the initial external data, thereby reducing the dimension of the input vector and improving the accuracy and the operation efficiency of the data. Finally, through introducing a preset empirical wavelet transformation algorithm, the trend component and the periodic component in the electric energy consumption data are identified and extracted, and the decoupling of the electric energy consumption data is realized, so that the accuracy of the finally obtained electric energy consumption prediction data is improved. Therefore, the invention improves the accuracy of predicting the electric energy consumption of the residential building.
Optionally, the preset energy consumption prediction model includes: a preset time sequence prediction layer and a preset attention distribution layer.
The process of obtaining the electric energy consumption prediction data in the second time period by the preset energy consumption prediction model according to the first subsequence set and the final external data comprises the following steps:
for each sub-sequence in the first set of sub-sequences: and performing data splicing on the subsequence and final external data in a vector dimension to obtain a first fusion characteristic sequence corresponding to the subsequence. And carrying out feature extraction on the first fusion feature sequence by using a preset time sequence prediction layer to obtain a first prediction similarity of the first fusion feature sequence. And according to the first prediction similarity, performing attention score distribution on each feature data in the first fusion feature sequence by using a preset attention distribution layer to obtain an electric energy consumption prediction parameter in a second time period, wherein the electric energy consumption prediction parameter has a corresponding relation with the subsequence.
For a first set of subsequences: and carrying out summation budget on the power consumption prediction parameters corresponding to the subsequences to obtain power consumption prediction data in the second time period.
Alternatively, in an alternative embodiment of the present invention, the preset timing prediction layer may be a recurrent neural network based on gated recurrent units (Gate Recurrent Unit, GRU). According to the invention, by introducing the GRU neural network, the characteristic parameters representing the electric energy consumption in the second time period in the first fusion characteristic sequence are subjected to characteristic extraction, so that the first prediction similarity is obtained. Because the GRU neural network can memorize and excavate the characteristic parameters representing the electric energy consumption in the second time period in the first fusion characteristic sequence, compared with the existing data analysis mode through subjective cognition, the accuracy and objectivity of the intermediate link to data processing are improved.
Optionally, in another optional embodiment of the present invention, the above-mentioned data splicing between the sub-sequence and the final external data in the vector dimension, to obtain the first fusion feature sequence corresponding to the sub-sequence may be implemented by a fusion function (fusion). For example, it is assumed that in the above-described first sub-sequence, the data in the trend component sub-sequence of the power consumption data is: (1, 2), (3, 4), the data in the final external data are: (5, 6), (7, 8), the data in the first fusion feature sequence obtained after the data are spliced is: (1, 2,5, 6), (3, 4,7, 8). The examples in the present embodiment are merely illustrative. The specific operation steps of the data stitching are known to those skilled in the art, and the present invention is not repeated and limited in this respect.
Alternatively, in another alternative embodiment of the present invention, the preset attention distribution layer may be a neural network model based on an attention mechanism (attention mechanism). Since the AM model has a key information capturing and weight distribution mechanism. According to the invention, by introducing an AM model, attention degree prediction can be performed on the feature data at different moments in the first fusion feature sequence, and attention score distribution is performed on each feature data by combining the first prediction similarity. Thus, in the first fusion characteristic sequence, the proportion of characteristic data with promotion effect on obtaining final power consumption prediction data in the obtained power consumption prediction parameters is improved. And further improves the accuracy of the finally obtained power consumption prediction data.
Optionally, a training process of the energy consumption prediction model is preset, including:
obtaining training data, wherein the training data comprises: the second set of subsequences within the first historical period, final external data of at least one of the first historical period, and power consumption data within a second historical period, the second historical period being a period of time subsequent to the first historical period.
Training the initial energy consumption prediction model by using training data to obtain a preset energy consumption prediction model, wherein the input of the preset energy consumption prediction model is a subsequence set in a preset time period and at least one final external data in the time period, and the output of the preset energy consumption prediction model is the electric energy consumption prediction data in a time period after the preset time period.
Alternatively, in order to describe the process of obtaining the power consumption prediction data in the second period according to the first sub-sequence set and the final external data by using the preset power consumption prediction model, the description is specifically given herein with reference to an alternative embodiment of the present invention as shown in fig. 2:
for convenience of description, the first subsequence set includes an a subsequence 201 and a B subsequence 202. The final external data is set to include three types of data, namely, temperature 203, humidity 204, and light intensity 205. The predetermined timing prediction layer is replaced with a GRU layer 206, and the predetermined attention allocation layer is replaced with an AM layer 207.
And performing data stitching on the A sub-sequence 201, the temperature 203, the humidity 204 and the light intensity 205 in vector dimensions to obtain an A fusion characteristic sequence 208 corresponding to the A sub-sequence.
And performing data stitching on the B subsequence 202, the temperature 203, the humidity 204 and the light intensity 205 in vector dimensions to obtain a B fusion characteristic sequence 209 corresponding to the B subsequence.
The a fusion characteristic sequence 208 is sequentially input to the GRU layer 206 and the AM layer 207, and a first power consumption prediction parameter 210 is obtained.
The B fusion characteristic sequence 209 is sequentially input to the GRU layer 206 and the AM layer 207, and a second power consumption prediction parameter 211 is obtained.
The first power consumption prediction parameter 210 and the second power consumption prediction parameter 211 are summed 212 to obtain power consumption prediction data 213.
Optionally, training the initial energy consumption prediction model by using training data to obtain a preset energy consumption prediction model, which specifically includes:
for each sub-sequence in the second set of sub-sequences: and performing data splicing on the subsequence and final external data of at least one of the first historical time periods to obtain a second fusion characteristic sequence corresponding to the subsequence. And carrying out feature extraction on the second fusion feature sequence by using the initial time sequence prediction layer to obtain a second prediction similarity. And according to the second prediction similarity, performing attention score distribution on each feature data in the second fusion feature sequence by using the initial attention distribution layer to obtain an electric energy consumption prediction parameter in a second historical time period, wherein the electric energy consumption prediction parameter in the second historical time period has a corresponding relation with the subsequence.
For the second set of subsequences: and carrying out summation budget on the power consumption prediction parameters corresponding to the subsequences to obtain power consumption prediction data in the second historical time period.
And performing parameter adjustment operation on the initial time sequence prediction layer and the initial attention distribution layer according to the electric energy consumption prediction data in the second historical time period and the electric energy consumption data in the second historical time period until the difference value between the electric energy consumption prediction data and the electric energy consumption data in the second historical time period meets a preset condition, so as to complete training of the initial energy consumption prediction model and obtain the preset energy consumption prediction model.
Alternatively, in an alternative embodiment of the present invention, the parameter adjusting operation may be performed by obtaining a difference between the power consumption prediction data and the power consumption data in the second historical period, and determining a degree of difference between the difference and the preset threshold. And adjusting the parameters of the functional layers in the GRU neural network and the AM model according to the difference degree. It should be noted that the above parameter adjustment operation is a technology known to those skilled in the art, and the present invention does not make excessive restrictions and redundant descriptions for the specific parameter adjustment operation process.
Optionally, based on a preset empirical wavelet transform algorithm, performing an extraction operation on the power consumption data in the first period of time to obtain a first sub-sequence set of the power consumption data in the first period of time, where the process includes:
And carrying out Fourier transform on the electric energy consumption data in the first time period by using a preset empirical wavelet transform algorithm to obtain a Fourier spectrum of the electric energy consumption data.
From the fourier spectrum, an empirical wavelet function and an empirical scale function are constructed.
And carrying out data reconstruction on the electric energy consumption data by using an empirical wavelet function and an empirical scale function, and carrying out component extraction operation to obtain a first subsequence set of the electric energy consumption data in a first time period.
Optionally, in an optional embodiment of the present invention, the performing an extraction operation on the power consumption data in the first period based on the preset empirical wavelet transform algorithm, and a specific implementation manner of obtaining the first sub-sequence set of the power consumption data in the first period may be:
by the formula:
and reconstructing the household appliance energy consumption data to obtain converted household appliance energy consumption data f (t). Wherein,,trend component sub-sequence f for household energy consumption data 0 (t)，/>Periodic component sub-sequence f for household appliance energy consumption data i (t)。/>For the detail coefficients transformed by a pre-determined empirical wavelet transform algorithm, < > for>The detail coefficients are transformed by a preset empirical wavelet transform algorithm. />An empirical scale function phi constructed for a preset empirical wavelet transformation algorithm according to household energy consumption data n And (t) an empirical wavelet function constructed by a preset empirical wavelet transformation algorithm according to household energy consumption data.
It should be noted that, the above manner of obtaining the detail coefficients, the empirical scale function and the empirical wavelet function is a technique known to those skilled in the art, and the present invention is not described and limited herein in detail.
In accordance with the above method embodiment, the present invention further provides a system for predicting residential power consumption, as shown in fig. 3, where the system for predicting residential power consumption includes:
the initial data acquisition module 301 is configured to acquire power consumption data in a first period and at least one initial external data in the first period.
The first data processing module 302 determines, based on a preset gray correlation analysis algorithm, initial external data having a gray correlation not smaller than a first preset threshold as final external data, where the gray correlation is a correlation degree between the initial external data and the power consumption data.
The second data processing module 303 performs an extraction operation on the power consumption data in the first period based on a preset empirical wavelet transform algorithm, and obtains a first subsequence set of the power consumption data in the first period, where the first subsequence set includes: trend component sub-sequences and periodic component sub-sequences of the power consumption data over a first period of time.
The energy consumption prediction module 304 is configured to input the first sub-sequence set and the final external data into a preset energy consumption prediction model to perform energy consumption prediction, and obtain electric energy consumption prediction data in a second period of time, where the second period of time is a period of time after the first period of time.
Optionally, the preset energy consumption prediction model in the energy consumption prediction module 304 is configured with a preset time sequence prediction layer and a preset attention distribution layer. The energy consumption prediction module 304 is configured to:
for each sub-sequence in the first set of sub-sequences:
and performing data splicing on the subsequence and final external data in a vector dimension to obtain a first fusion characteristic sequence corresponding to the subsequence.
And carrying out feature extraction on the first fusion feature sequence by using a preset time sequence prediction layer to obtain a first prediction similarity of the first fusion feature sequence.
And according to the first prediction similarity, performing attention score distribution on each feature data in the first fusion feature sequence by using a preset attention distribution layer to obtain an electric energy consumption prediction parameter in a second time period, wherein the electric energy consumption prediction parameter has a corresponding relation with the subsequence.
For a first set of subsequences:
And carrying out summation budget on the power consumption prediction parameters corresponding to the subsequences to obtain power consumption prediction data in the second time period.
Optionally, the system for predicting residential electric energy consumption further includes:
the model training module is used for obtaining training data, wherein the training data comprises: the second set of subsequences within the first historical period, final external data of at least one of the first historical period, and power consumption data within a second historical period, the second historical period being a period of time subsequent to the first historical period. Training the initial energy consumption prediction model by using training data to obtain a preset energy consumption prediction model, wherein the input of the preset energy consumption prediction model is a subsequence set in a preset time period and at least one final external data in the time period, and the input of the preset energy consumption prediction model is the electric energy consumption prediction data in a time period after the preset time period.
Optionally, the model training module is specifically configured to:
for each sub-sequence in the second set of sub-sequences: and performing data splicing on the subsequence and final external data of at least one of the first historical time periods to obtain a second fusion characteristic sequence corresponding to the subsequence. And carrying out feature extraction on the second fusion feature sequence by using the initial time sequence prediction layer to obtain a second prediction similarity. And according to the second prediction similarity, performing attention score distribution on each feature data in the second fusion feature sequence by using the initial attention distribution layer to obtain an electric energy consumption prediction parameter in a second historical time period, wherein the electric energy consumption prediction parameter in the second historical time period has a corresponding relation with the subsequence.
For the second set of subsequences: and carrying out summation budget on the power consumption prediction parameters corresponding to the subsequences to obtain power consumption prediction data in the second historical time period.
And performing parameter adjustment operation on the initial time sequence prediction layer and the initial attention distribution layer according to the electric energy consumption prediction data in the second historical time period and the electric energy consumption data in the second historical time period until the difference value between the electric energy consumption prediction data and the electric energy consumption data in the second historical time period meets the preset condition, so as to complete training of the initial energy consumption prediction model and obtain the preset energy consumption prediction model.
Optionally, the second data processing module 303 is configured to:
and carrying out Fourier transform on the electric energy consumption data in the first time period by using a preset empirical wavelet transform algorithm to obtain a Fourier spectrum of the electric energy consumption data.
From the fourier spectrum, an empirical wavelet function and an empirical scale function are constructed.
And carrying out data reconstruction on the electric energy consumption data by using an empirical wavelet function and an empirical scale function, and carrying out component extraction operation to obtain a first subsequence set of the electric energy consumption data in a first time period.
The embodiment of the invention also provides a device for predicting the residential electric energy consumption, as shown in fig. 4, which comprises:
A processor 401.
A memory 402 for storing instructions executable by the processor 401.
Wherein the processor 401 is configured to execute instructions to implement a method of predicting residential power consumption as in any one of the above.
Embodiments of the present invention also provide a computer storage medium, which when executed by a processor of an electronic device, enables the device to perform a method of predicting residential power consumption as in any one of the above.
The memory may include volatile memory, random Access Memory (RAM), and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM), among other forms in computer readable media, the memory including at least one memory chip. Memory is an example of a computer-readable medium.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises an element.
In this specification, each embodiment is described in a related manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the application are to be included in the scope of the claims of the present application.
Claims (10)
1. A method of predicting residential power consumption, the method comprising:
acquiring electric energy consumption data in a first time period and at least one initial external data in the first time period;
determining the initial external data with gray correlation degree not smaller than a first preset threshold value as final external data based on a preset gray correlation degree analysis algorithm, wherein the gray correlation degree is the correlation degree of the initial external data and the electric energy consumption data;
Performing an extraction operation on the power consumption data in the first time period based on a preset empirical wavelet transform algorithm, and obtaining a first subsequence set of the power consumption data in the first time period, wherein the first subsequence set comprises: a trend component sub-sequence and a periodic component sub-sequence of the power consumption data over the first period of time;
and inputting the first sub-sequence set and the final external data into a preset energy consumption prediction model to perform energy consumption prediction, and obtaining electric energy consumption prediction data in a second time period, wherein the second time period is a time period after the first time period.
2. The method of claim 1, wherein the preset energy consumption prediction model comprises: a preset time sequence prediction layer and a preset attention distribution layer;
the process of obtaining the electric energy consumption prediction data in the second time period by the preset energy consumption prediction model according to the first subsequence set and the final external data includes:
for each subsequence in the first set of subsequences: performing data splicing on the subsequence and the final external data in a vector dimension to obtain a first fusion characteristic sequence corresponding to the subsequence; performing feature extraction on the first fusion feature sequence by using the preset time sequence prediction layer to obtain a first prediction similarity of the first fusion feature sequence; according to the first prediction similarity, performing attention score distribution on each feature data in the first fusion feature sequence by using the preset attention distribution layer to obtain an electric energy consumption prediction parameter in a second time period, wherein the electric energy consumption prediction parameter has a corresponding relation with the subsequence;
For the first set of subsequences: and carrying out summation budget on the power consumption prediction parameters corresponding to the subsequences to obtain power consumption prediction data in the second time period.
3. The method according to claim 1, wherein the training process of the preset energy consumption prediction model comprises:
obtaining training data, wherein the training data comprises: a second set of subsequences within a first historical period of time, final external data for at least one of the first historical period of time, and power consumption data for a second historical period of time, the second historical period of time being a period of time subsequent to the first historical period of time;
training an initial energy consumption prediction model by using the training data to obtain the preset energy consumption prediction model, wherein the input of the preset energy consumption prediction model is a subsequence set in a preset time period and at least one final external data in the time period, and the output of the preset energy consumption prediction model is the electric energy consumption prediction data in a time period after the preset time period.
4. A method according to claim 3, wherein the training the initial energy consumption prediction model using the training data to obtain the preset energy consumption prediction model specifically comprises:
For each subsequence in the second set of subsequences: performing data splicing on the subsequence and final external data of at least one of the first historical time periods to obtain a second fusion feature sequence corresponding to the subsequence; extracting features of the second fusion feature sequence by using an initial time sequence prediction layer to obtain a second prediction similarity; according to the second prediction similarity, performing attention score distribution on each feature data in the second fusion feature sequence by using an initial attention distribution layer to obtain an electric energy consumption prediction parameter of a second historical time period, wherein the electric energy consumption prediction parameter of the second historical time period has a corresponding relation with the subsequence;
for the second set of subsequences: carrying out summation budget on the power consumption prediction parameters corresponding to each subsequence to obtain power consumption prediction data in a second historical time period;
and performing parameter adjustment operation on the initial time sequence prediction layer and the initial attention distribution layer according to the electric energy consumption prediction data in the second historical time period and the electric energy consumption data in the second historical time period until the difference value between the electric energy consumption prediction data and the electric energy consumption data in the second historical time period meets a preset condition, so as to complete training of the initial energy consumption prediction model and obtain the preset energy consumption prediction model.
5. The method according to claim 1, wherein the step of obtaining the first sub-sequence set of the power consumption data in the first period of time by performing an extraction operation on the power consumption data in the first period of time based on a preset empirical wavelet transform algorithm comprises:
performing Fourier transform on the electric energy consumption data in the first time period by using a preset empirical wavelet transform algorithm to obtain a Fourier spectrum of the electric energy consumption data;
constructing an empirical wavelet function and an empirical scale function according to the Fourier spectrum;
and carrying out data reconstruction on the electric energy consumption data by using the empirical wavelet function and the empirical scale function, and carrying out the component extraction operation to obtain a first subsequence set of the electric energy consumption data in the first time period.
6. A system for predicting residential power consumption, the system comprising:
the device comprises an initial data acquisition module, a data processing module and a data processing module, wherein the initial data acquisition module is used for acquiring electric energy consumption data in a first time period and at least one initial external data in the first time period;
the first data processing module is used for determining the initial external data with gray correlation degree not smaller than a first preset threshold value as final external data based on a preset gray correlation degree analysis algorithm, wherein the gray correlation degree is the correlation degree of the initial external data and the electric energy consumption data;
The second data processing module performs component extraction operation on the electric energy consumption data in the first time period based on a preset empirical wavelet transformation algorithm to obtain a first subsequence set of the electric energy consumption data in the first time period, wherein the first subsequence set comprises: a trend component sub-sequence and a periodic component sub-sequence of the power consumption data over the first period of time;
and the energy consumption prediction module is used for inputting the first sub-sequence set and the final external data into a preset energy consumption prediction model to perform energy consumption prediction to obtain electric energy consumption prediction data in a second time period, wherein the second time period is a time period after the first time period.
7. The system of claim 6, wherein the energy consumption prediction module is configured to:
the preset energy consumption prediction model comprises the following steps: a preset time sequence prediction layer and a preset attention distribution layer;
for each subsequence in the first set of subsequences:
performing data splicing on the subsequence and the final external data in a vector dimension to obtain a first fusion characteristic sequence corresponding to the subsequence;
Performing feature extraction on the first fusion feature sequence by using the preset time sequence prediction layer to obtain a first prediction similarity of the first fusion feature sequence;
according to the first prediction similarity, performing attention score distribution on each feature data in the first fusion feature sequence by using the preset attention distribution layer to obtain an electric energy consumption prediction parameter in a second time period, wherein the electric energy consumption prediction parameter has a corresponding relation with the subsequence;
for the first set of subsequences:
and carrying out summation budget on the power consumption prediction parameters corresponding to the subsequences to obtain power consumption prediction data in the second time period.
8. The method of claim 6, wherein the system further comprises:
the model training module is used for obtaining training data, wherein the training data comprises: a second set of subsequences within a first historical period of time, final external data for at least one of the first historical period of time, and power consumption data for a second historical period of time, the second historical period of time being a period of time subsequent to the first historical period of time; training an initial energy consumption prediction model by using the training data to obtain the preset energy consumption prediction model, wherein the input of the preset energy consumption prediction model is a subsequence set in a preset time period and at least one final external data in the time period, and the input of the preset energy consumption prediction model is electric energy consumption prediction data in a time period after the preset time period.
9. An apparatus for predicting residential power consumption, the apparatus comprising:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement the method of predicting residential power consumption as claimed in any one of the preceding claims 1 to 5.
10. A computer storage medium, characterized in that instructions in the computer readable storage medium, when executed by a processor of an electronic device, enable the device to perform the method of predicting residential power consumption according to any one of the preceding claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210384437.4A CN116976472A (en) | 2022-04-13 | 2022-04-13 | Method, system, equipment and storage medium for predicting residential electric energy consumption |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210384437.4A CN116976472A (en) | 2022-04-13 | 2022-04-13 | Method, system, equipment and storage medium for predicting residential electric energy consumption |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116976472A true CN116976472A (en) | 2023-10-31 |
Family
ID=88471716
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210384437.4A Pending CN116976472A (en) | 2022-04-13 | 2022-04-13 | Method, system, equipment and storage medium for predicting residential electric energy consumption |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116976472A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117473275A (en) * | 2023-12-27 | 2024-01-30 | 芯知科技(江苏)有限公司 | Energy consumption detection method for data center |
-
2022
- 2022-04-13 CN CN202210384437.4A patent/CN116976472A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117473275A (en) * | 2023-12-27 | 2024-01-30 | 芯知科技(江苏)有限公司 | Energy consumption detection method for data center |
| CN117473275B (en) * | 2023-12-27 | 2024-03-26 | 芯知科技(江苏)有限公司 | Energy consumption detection method for data center |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110610280B (en) | Short-term prediction method, model, device and system for power load | |
| Dubey et al. | Study and analysis of SARIMA and LSTM in forecasting time series data | |
| Ji et al. | Prediction of hourly solar radiation using a novel hybrid model of ARMA and TDNN | |
| Cui et al. | Short‐term city electric load forecasting with considering temperature effects: An improved ARIMAX model | |
| CN111080032A (en) | Load prediction method based on Transformer structure | |
| Lv et al. | Short-term wind speed forecasting based on non-stationary time series analysis and ARCH model | |
| CN110333404B (en) | Non-invasive load monitoring method, device, equipment and storage medium | |
| Bansal et al. | Energy consumption forecasting for smart meters | |
| Chen et al. | An innovative method-based CEEMDAN–IGWO–GRU hybrid algorithm for short-term load forecasting | |
| CN116845874A (en) | Short-term prediction method and device for power load | |
| CN116321620A (en) | Intelligent lighting switch control system and method thereof | |
| CN116976472A (en) | Method, system, equipment and storage medium for predicting residential electric energy consumption | |
| Arpogaus et al. | Short-term density forecasting of low-voltage load using Bernstein-polynomial normalizing flows | |
| Zhang et al. | Accurate ultra-short-term load forecasting based on load characteristic decomposition and convolutional neural network with bidirectional long short-term memory model | |
| CN113807605A (en) | Power consumption prediction model training method, prediction method and prediction device | |
| CN117251724A (en) | Short-term wind power prediction method based on sequence correlation mechanism and Informar | |
| CN117495126A (en) | High-proportion new energy distribution network line loss prediction method and device | |
| CN111967652A (en) | Double-layer cooperative real-time correction photovoltaic prediction method | |
| Maalej et al. | Sensor data augmentation strategy for load forecasting in smart grid context | |
| El Bakali et al. | Data-Based Solar Radiation Forecasting with Pre-Processing Using Variational Mode Decomposition | |
| CN115936236A (en) | Method, system, equipment and medium for predicting energy consumption of cigarette factory | |
| Wei et al. | Using a model structure selection technique to forecast short-term wind speed for a wind power plant in North China | |
| CN115217152A (en) | Method and device for predicting opening and closing deformation of immersed tunnel pipe joint | |
| Marikkar et al. | Modified auto regressive technique for univariate time series prediction of solar irradiance | |
| CN113011674A (en) | Photovoltaic power generation prediction method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |