CN111080477A - Household power load prediction method and system - Google Patents
Household power load prediction method and system Download PDFInfo
- Publication number
- CN111080477A CN111080477A CN201911243132.6A CN201911243132A CN111080477A CN 111080477 A CN111080477 A CN 111080477A CN 201911243132 A CN201911243132 A CN 201911243132A CN 111080477 A CN111080477 A CN 111080477A
- Authority
- CN
- China
- Prior art keywords
- power load
- neural network
- network model
- convolutional neural
- data
- 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
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 61
- 238000012549 training Methods 0.000 claims abstract description 51
- 230000003044 adaptive effect Effects 0.000 claims abstract description 33
- 238000012360 testing method Methods 0.000 claims abstract description 29
- 238000012795 verification Methods 0.000 claims abstract description 26
- 238000007781 pre-processing Methods 0.000 claims description 9
- 238000013508 migration Methods 0.000 claims description 6
- 230000005012 migration Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 2
- 238000003062 neural network model Methods 0.000 claims description 2
- 238000002203 pretreatment Methods 0.000 claims description 2
- 230000006870 function Effects 0.000 description 5
- 238000010200 validation analysis Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012731 temporal analysis Methods 0.000 description 2
- 238000000700 time series analysis Methods 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
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
- 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
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Software Systems (AREA)
- Tourism & Hospitality (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- General Business, Economics & Management (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- Marketing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a system for predicting household power load, which are characterized in that basic data of the household power load are obtained and preprocessed to form a data set, an adaptive convolutional neural network model is constructed, the data set is divided into a training set, a verification set and a test set, a finally established adaptive convolutional neural network model is obtained through repeated training of the training set and fine adjustment of the verification set and the test set, the basic data of the household load is input into the finally established adaptive convolutional neural network model to predict the household power load in future unit time at any moment, and the precision of household load prediction can be effectively improved.
Description
Technical Field
The invention relates to the field, in particular to a method and a system for predicting household power load.
Background
With the popularization of smart meters, a large amount of fine-grained electricity utilization data is collected, so that load prediction at the home user level becomes possible. Compared with the total load of countries, regions and the like, the load prediction of the family users has unevenness and randomness. In response to this problem, various new power load prediction techniques have been proposed in the past few years. Due to uncertainty in user behavior and non-linearity of external influencing factors, home-level load prediction has become one of the most challenging tasks facing power market entities;
researchers provide different short-term load prediction methods, the historical load data and the weather data are used as input to predict the load of the whole system, a time series analysis method is usually adopted to predict, particularly, time series dynamic data are obtained and processed by a mathematical statistics method to predict the development of future family power load;
however, due to the fact that household-level load fluctuation is large, future household power loads of the time series analysis method tend to generate large deviation, and accuracy is low.
Disclosure of Invention
In view of the above, the present invention provides a method and a system for predicting a household power load.
The invention provides a household power load prediction method based on the above purpose, which comprises the following steps:
acquiring basic data of a household power load;
dividing basic data of the household power load into a training set, a verification set and a test set;
adding a kernel offset parameter in a preset self-adaptive convolution neural network model;
inputting the training set into a self-adaptive convolutional neural network model added with the kernel migration parameters, and repeatedly training the self-adaptive convolutional neural network model added with the kernel migration parameters until convergence;
carrying out fine adjustment on the trained self-adaptive convolutional neural network model by utilizing a verification set and a training set;
determining a target moment, and screening basic data before the initial moment from the obtained basic data of the household power load to serve as historical data;
inputting the historical data into the self-adaptive convolutional neural network model after fine tuning, and predicting the household power load in the future unit time of the target moment.
Preferably, the household electrical load base data includes individual household load data for a region, daily maximum and minimum air temperatures for the region, and holiday data.
Preferably, before dividing the basic data of the household power load into a training set, a verification set and a test set, the method further comprises:
preprocessing the basic data of the household power load;
such pre-treatments include, but are not limited to,
carrying out normalization processing on basic data of the household power load;
performing mean interpolation processing on missing values in the basic data of the household power load;
clearing redundant data;
and forming an input vector sequence by the basic data of the household power load according to the time sequence.
Preferably, the preset adaptive convolutional neural network model is as follows:
where K is the convolution kernel, y is the output sequence, d0Is the position on the output sequence, w is the weight, x is the input vector sequence, dnFor each location on the convolution kernel.
Preferably, the convolutional neural network model after adding the kernel offset parameter is as follows:
where is the convolution kernel,. DELTA.d is the kernel offset of the convolution kernel, y is the output sequence, d0Is the position on the output sequence, w is the weight, x is the input vector sequence, dnFor each location on the convolution kernel.
Preferably, before inputting the history data into the trimmed adaptive convolutional neural network model and predicting the household power load in a unit time in the future of the target time, the method further includes:
and correcting the self-adaptive convolutional neural network model after fine tuning by adopting a quantile loss function.
Preferably, the quantile loss function is:
where q is the quantile of the target,
representing the predicted value of the qth quantile at time t, n representing the length of the sequence, t representing any time, truetRepresenting the true load at time t, predtRepresenting the predicted value at time t。
Preferably, the dividing of the household electrical load base data into a training set, a validation set and a test set comprises:
dividing the basic data of the household power load into a training set, a verification set and a test set according to the division ratio of 0.8:0.1: 0.1.
A home electrical load prediction system comprising:
the data source module is used for acquiring basic data of the household power load;
the preprocessing module is used for preprocessing the basic data of the household power load to form a data set;
the data dividing module is used for dividing the data set into a training set, a verification set and a test set;
the model construction module is used for constructing a self-adaptive convolutional neural network model;
the model training module is used for inputting a training set into the self-adaptive convolutional neural network model and repeatedly training the self-adaptive convolutional neural network model until convergence;
the model correction module is used for finely adjusting the trained adaptive convolutional neural network model by utilizing the verification set and the test set to obtain a finally established adaptive convolutional neural network model;
and the prediction module is used for inputting the basic data of the family load before any time into the finally established adaptive convolutional neural network model and predicting the family power load in the future unit time at the time.
From the above, according to the method and system for predicting the household power load provided by the invention, the basic data of the household power load is obtained and is preprocessed to form the data set, the adaptive convolutional neural network model is constructed, the data set is divided into the training set, the verification set and the test set, the finally established adaptive convolutional neural network model is obtained through repeated training of the training set and fine adjustment of the verification set and the test set, the basic data of the household load is input into the finally established adaptive convolutional neural network model, the household power load in future unit time at any moment is predicted, and the precision of household load prediction can be effectively improved.
Drawings
Fig. 1 is a schematic flow chart of a method for predicting a household power load according to an embodiment of the present invention;
fig. 2 is a schematic diagram of an adaptive convolutional neural network according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to specific embodiments and the accompanying drawings.
It should be noted that all expressions using "first" and "second" in the embodiments of the present invention are used for distinguishing two entities with the same name but different names or different parameters, and it should be noted that "first" and "second" are merely for convenience of description and should not be construed as limitations of the embodiments of the present invention, and they are not described in any more detail in the following embodiments.
A method for predicting a household power load, as shown in fig. 1, includes the following steps:
s101, acquiring basic data of a household power load;
for example, home power load base data refers to individual home power load related data for a certain region.
S102, dividing basic data of the household power load into a training set, a verification set and a test set;
s103, adding a kernel offset parameter in a preset self-adaptive convolutional neural network model;
for example, adding a kernel offset parameter refers to adding a kernel offset parameter to a convolution kernel of an adaptive convolutional neural network.
S104, inputting the training set into the adaptive convolutional neural network model with the added nuclear offset parameters, and repeatedly training the adaptive convolutional neural network model with the added nuclear offset parameters until convergence;
for example, the process of repeatedly training the adaptive convolutional neural network model is to perform multiple iterations on the adaptive convolutional neural network model.
S105, carrying out fine adjustment on the trained adaptive convolutional neural network model by using a verification set and a test set;
for example, the fine tuning includes adjusting model parameters by comparing the accuracy and error of the training set and the validation set, selecting the model with the best performance of the validation set through multiple training, testing the model by using the testing set, and adding the latest data into the training set for training again if the training result is far from the testing set.
S106, determining a target moment, and screening basic data before the target moment from the obtained basic data of the household power load to serve as historical data;
for example, the target time may be an initial time of the target prediction period.
S107, inputting the historical data into the self-adaptive convolutional neural network model after fine adjustment, predicting the household power load in the future unit time at the moment, wherein the structure of the self-adaptive convolutional neural network model is shown in figure 2.
According to the method, the basic data of the household power load is obtained and divided into the training set, the verification set and the test set, the adaptive convolutional neural network model is repeatedly trained through the training set, the adaptive convolutional neural network model is finely adjusted through the verification set and the test set, the more optimized adaptive convolutional neural network model is obtained, the sensing field of the adaptive convolutional neural network model can be increased by adding the nuclear offset parameter in the adaptive convolutional neural network model, more comprehensive characteristics are learned in the repeated training, the more accurate household power load in the future unit time of the target time can be obtained by inputting the historical data through the finely adjusted adaptive convolutional neural network, and the prediction precision of the household power load is effectively improved.
As one embodiment, the home power load base data includes individual home load data for a region, daily maximum and minimum air temperatures for the region, and holiday data.
The inventor finds in practice that the weather condition and the holiday condition both have certain influence on the household power load, and the prediction accuracy can be improved by including the data in the basic data.
As an embodiment, before dividing the basic data of the home power load into a training set, a verification set and a test set, the method further includes:
pre-processing the household power load base data, wherein the pre-processing comprises but is not limited to: carrying out normalization processing on basic data of the household power load; performing mean interpolation processing on missing values in the basic data of the household power load; clearing redundant data; and forming an input vector sequence by the basic data of the household power load according to the time sequence.
Because the acquired basic data may be incomplete, inconsistent or repeated, and the low-quality data will result in a low-quality training result, the preprocessing of the family power conformity basic data can improve the training and fine-tuning effects of the adaptive convolutional neural network model.
As an embodiment, the preset adaptive convolutional neural network model is:
where K is the convolution kernel, y is the output sequence, d0Is the position on the output sequence, w is the weight, x is the input vector sequence, dnFor each location on the convolution kernel.
As an embodiment, the convolutional neural network model after adding the kernel offset parameter is
Where is the convolution kernel,. DELTA.d is the kernel offset of the convolution kernel, y is the output sequence, d0Is the position on the output sequence, w is the weight, x is the input vector sequence, dnFor each location on the convolution kernel.
The convolution kernels with the kernel offset parameters added are equivalent to all have telescopic changes, so that the scope of a receptive field is improved.
As an embodiment, before inputting the history data into the trimmed adaptive convolutional neural network model and predicting the household power load in a unit time in the future of the target time, the method further includes:
and correcting the self-adaptive convolutional neural network model after fine tuning by adopting a quantile loss function.
As another embodiment, the model may be modified by a mean square error function, such as
Where n represents the length of the sequence and t represents any time instant, truetRepresenting the true load at time t, predtRepresenting the predicted value at time t, but the mean square error can only provide the predicted value of future load, and in order to provide more information about future uncertainty, the mean square error is replaced by quantile loss.
As an embodiment, the quantile loss function is
Where q is the quantile of the target,
representing the predicted value of the qth quantile at time t, n representing the length of the sequence, t representing any time, truetRepresenting the true load at time t, predtRepresenting the predicted value at time t.
As one embodiment, dividing the home power load base data into a training set, a validation set, and a test set includes:
dividing the basic data of the household power load into a training set, a verification set and a test set according to the division ratio of 0.8:0.1: 0.1.
Practice shows that the division ratio can provide a more accurate adaptive convolutional neural network model.
For example, the obtained basic data of the home power load is single basic data of the home power load of 300 continuous hours, the first 80% of the basic data is selected as a training set according to the chronological order, the next 10% is used as a verification set, and the last 10% is used as a test set, then the first 80% of the basic data is input as a training set vector with the length of 240, and when prediction is performed, when the target time can be determined to be the beginning of the 241 th hour, the home power load of the 241 th hour in the 300 hours is predicted.
The invention also provides a system for predicting the household power load, which comprises the following components:
the data source module is used for acquiring basic data of the household power load;
the data dividing module is used for dividing the basic data of the household power load into a training set, a verification set and a test set;
the kernel migration module is used for adding kernel migration parameters in a preset self-adaptive convolutional neural network model;
the model training module is used for inputting a training set into a self-adaptive convolutional neural network model added with a nuclear offset parameter, and repeatedly training the self-adaptive convolutional neural network model added with the nuclear offset parameter until convergence;
the model correction module is used for finely adjusting the trained self-adaptive convolutional neural network model by utilizing the verification set and the test set;
the data screening module is used for determining a target moment, screening basic data before the initial moment from the obtained basic data of the household power load as historical data;
and the prediction module is used for inputting the historical data into the self-adaptive convolutional neural network model after fine adjustment and predicting the household power load in the future unit time of the target moment.
Those of ordinary skill in the art will understand that: the discussion of any embodiment above is meant to be exemplary only, and is not intended to intimate that the scope of the disclosure, including the claims, is limited to these examples; within the idea of the invention, also features in the above embodiments or in different embodiments may be combined, steps may be implemented in any order, and there are many other variations of the different aspects of the invention as described above, which are not provided in detail for the sake of brevity.
In addition, well known power/ground connections to Integrated Circuit (IC) chips and other components may or may not be shown within the provided figures for simplicity of illustration and discussion, and so as not to obscure the invention. Furthermore, devices may be shown in block diagram form in order to avoid obscuring the invention, and also in view of the fact that specifics with respect to implementation of such block diagram devices are highly dependent upon the platform within which the present invention is to be implemented (i.e., specifics should be well within purview of one skilled in the art). Where specific details (e.g., circuits) are set forth in order to describe example embodiments of the invention, it should be apparent to one skilled in the art that the invention can be practiced without, or with variation of, these specific details. Accordingly, the description is to be regarded as illustrative instead of restrictive.
While the present invention has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art in light of the foregoing description. For example, other memory architectures (e.g., dynamic ram (dram)) may use the discussed embodiments.
The embodiments of the invention are intended to embrace all such alternatives, modifications and variances that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, substitutions, improvements and the like that may be made without departing from the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (9)
1. A method for predicting a home electrical load, the method comprising:
acquiring basic data of a household power load;
dividing basic data of the household power load into a training set, a verification set and a test set;
adding a kernel offset parameter in a preset self-adaptive convolution neural network model;
inputting the training set into a self-adaptive convolutional neural network model added with the kernel migration parameters, and repeatedly training the self-adaptive convolutional neural network model added with the kernel migration parameters until convergence;
carrying out fine adjustment on the trained self-adaptive convolutional neural network model by utilizing a verification set and a training set;
determining a target moment, and screening basic data before the initial moment from the obtained basic data of the household power load to serve as historical data;
inputting the historical data into the self-adaptive convolutional neural network model after fine tuning, and predicting the household power load in the future unit time of the target moment.
2. A home power load prediction method according to claim 1, characterized in that: the household power load basic data comprises single household load data of a certain region, the daily maximum air temperature and the daily minimum air temperature of the region, and holiday data.
3. The method according to claim 1, wherein before dividing the basic data of the household power load into a training set, a verification set and a test set, the method further comprises:
preprocessing the basic data of the household power load;
such pre-treatments include, but are not limited to,
carrying out normalization processing on basic data of the household power load;
performing mean interpolation processing on missing values in the basic data of the household power load;
clearing redundant data;
and forming an input vector sequence by the basic data of the household power load according to the time sequence.
4. The home power load prediction method according to claim 1, wherein the preset adaptive convolutional neural network model is:
where K is the convolution kernel, y is the output sequence, d0Is the position on the output sequence, w is the weight, x is the input vector sequence, dnFor each location on the convolution kernel.
5. The home power load prediction method according to claim 1, wherein the convolutional neural network model after adding the kernel offset parameter is:
where is the convolution kernel,. DELTA.d is the kernel offset of the convolution kernel, y is the output sequence, d0Is the position on the output sequence, w is the weight, x is the input vector sequence, dnFor each location on the convolution kernel.
6. The method for predicting household power load according to claim 1, wherein the historical data is input into the trimmed adaptive convolutional neural network model, and before the household power load in the future unit time of the target time is predicted, the method further comprises:
and correcting the self-adaptive convolutional neural network model after fine tuning by adopting a quantile loss function.
7. The home power load prediction method of claim 6, wherein the quantile loss function is:
where q is the quantile of the target,
representing the predicted value of the qth quantile at time t, n representing the length of the sequence, t representing any time, truetRepresenting the true load at time t, predtRepresenting the predicted value at time t.
8. The method according to claim 1, wherein the dividing the home power load basic data into a training set, a verification set and a test set comprises:
dividing the basic data of the household power load into a training set, a verification set and a test set according to the division ratio of 0.8:0.1: 0.1.
9. A home electrical load prediction system, comprising:
the data source module is used for acquiring basic data of the household power load;
the preprocessing module is used for preprocessing the basic data of the household power load to form a data set;
the data dividing module is used for dividing the data set into a training set, a verification set and a test set;
the model construction module is used for constructing a self-adaptive convolutional neural network model;
the model training module is used for inputting a training set into the self-adaptive convolutional neural network model and repeatedly training the self-adaptive convolutional neural network model until convergence;
the model correction module is used for finely adjusting the trained adaptive convolutional neural network model by utilizing the verification set and the test set to obtain a finally established adaptive convolutional neural network model;
and the prediction module is used for inputting the basic data of the family load before any time into the finally established adaptive convolutional neural network model and predicting the family power load in the future unit time at the time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911243132.6A CN111080477A (en) | 2019-12-06 | 2019-12-06 | Household power load prediction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911243132.6A CN111080477A (en) | 2019-12-06 | 2019-12-06 | Household power load prediction method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111080477A true CN111080477A (en) | 2020-04-28 |
Family
ID=70313161
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911243132.6A Pending CN111080477A (en) | 2019-12-06 | 2019-12-06 | Household power load prediction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111080477A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111509810A (en) * | 2020-05-18 | 2020-08-07 | 广东电网有限责任公司东莞供电局 | Lithium battery charging state detection method and device and storage medium |
| CN112257928A (en) * | 2020-10-22 | 2021-01-22 | 国网山东省电力公司潍坊供电公司 | Short-term power load probability prediction method based on CNN and quantile regression |
| CN112508734A (en) * | 2020-11-27 | 2021-03-16 | 国网浙江省电力有限公司杭州供电公司 | Method and device for predicting power generation capacity of power enterprise based on convolutional neural network |
| CN114742258A (en) * | 2022-02-23 | 2022-07-12 | 吉林化工学院 | Migratable residential household power load scene prediction method |
| CN115640896A (en) * | 2022-10-25 | 2023-01-24 | 湖南工商大学 | Home user power load prediction method under multi-user scene and related equipment |
| CN116805157A (en) * | 2023-08-25 | 2023-09-26 | 中国人民解放军国防科技大学 | Unmanned cluster autonomous dynamic evaluation method and device |
| CN117407693A (en) * | 2023-10-20 | 2024-01-16 | 湖北大学 | Non-invasive load detection method based on partial domain self-adaption and quantile regression |
| CN117407693B (en) * | 2023-10-20 | 2024-05-24 | 湖北大学 | Non-invasive load detection method based on partial domain self-adaption and quantile regression |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104636822A (en) * | 2015-01-21 | 2015-05-20 | 广州市香港科大霍英东研究院 | Residential load prediction method of elman-based neural network |
| CN108416695A (en) * | 2018-02-24 | 2018-08-17 | 合肥工业大学 | Electric load probability density prediction technique based on deep learning and system, medium |
| CN108846517A (en) * | 2018-06-12 | 2018-11-20 | 清华大学 | A kind of probability short-term electric load prediction integrated approach of quantile |
| CN109543901A (en) * | 2018-11-20 | 2019-03-29 | 国网辽宁省电力有限公司经济技术研究院 | Short-Term Load Forecasting Method based on information fusion convolutional neural networks model |
| CN110197255A (en) * | 2019-04-29 | 2019-09-03 | 杰创智能科技股份有限公司 | A kind of deformable convolutional network based on deep learning |
-
2019
- 2019-12-06 CN CN201911243132.6A patent/CN111080477A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104636822A (en) * | 2015-01-21 | 2015-05-20 | 广州市香港科大霍英东研究院 | Residential load prediction method of elman-based neural network |
| CN108416695A (en) * | 2018-02-24 | 2018-08-17 | 合肥工业大学 | Electric load probability density prediction technique based on deep learning and system, medium |
| CN108846517A (en) * | 2018-06-12 | 2018-11-20 | 清华大学 | A kind of probability short-term electric load prediction integrated approach of quantile |
| CN109543901A (en) * | 2018-11-20 | 2019-03-29 | 国网辽宁省电力有限公司经济技术研究院 | Short-Term Load Forecasting Method based on information fusion convolutional neural networks model |
| CN110197255A (en) * | 2019-04-29 | 2019-09-03 | 杰创智能科技股份有限公司 | A kind of deformable convolutional network based on deep learning |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111509810A (en) * | 2020-05-18 | 2020-08-07 | 广东电网有限责任公司东莞供电局 | Lithium battery charging state detection method and device and storage medium |
| CN112257928A (en) * | 2020-10-22 | 2021-01-22 | 国网山东省电力公司潍坊供电公司 | Short-term power load probability prediction method based on CNN and quantile regression |
| CN112508734A (en) * | 2020-11-27 | 2021-03-16 | 国网浙江省电力有限公司杭州供电公司 | Method and device for predicting power generation capacity of power enterprise based on convolutional neural network |
| CN112508734B (en) * | 2020-11-27 | 2024-04-26 | 国网浙江省电力有限公司杭州供电公司 | Method and device for predicting power generation capacity of power enterprise based on convolutional neural network |
| CN114742258A (en) * | 2022-02-23 | 2022-07-12 | 吉林化工学院 | Migratable residential household power load scene prediction method |
| CN114742258B (en) * | 2022-02-23 | 2022-11-29 | 吉林化工学院 | Migratable residential household power load scene prediction method |
| CN115640896A (en) * | 2022-10-25 | 2023-01-24 | 湖南工商大学 | Home user power load prediction method under multi-user scene and related equipment |
| CN115640896B (en) * | 2022-10-25 | 2024-04-30 | 湖南工商大学 | Household user power load prediction method under multi-user scene and related equipment |
| CN116805157A (en) * | 2023-08-25 | 2023-09-26 | 中国人民解放军国防科技大学 | Unmanned cluster autonomous dynamic evaluation method and device |
| CN116805157B (en) * | 2023-08-25 | 2023-11-17 | 中国人民解放军国防科技大学 | Unmanned cluster autonomous dynamic evaluation method and device |
| CN117407693A (en) * | 2023-10-20 | 2024-01-16 | 湖北大学 | Non-invasive load detection method based on partial domain self-adaption and quantile regression |
| CN117407693B (en) * | 2023-10-20 | 2024-05-24 | 湖北大学 | Non-invasive load detection method based on partial domain self-adaption and quantile regression |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111080477A (en) | Household power load prediction method and system | |
| CN109242135B (en) | Model operation method, device and business server | |
| CN109342989B (en) | Error analysis method and device for electric energy meter | |
| KR102468316B1 (en) | Time series prediction method and apparatus based on past prediction data | |
| WO2011100255A2 (en) | Systems and methods for measuring and verifying energy savings in buildings | |
| CN113191564A (en) | Photovoltaic power prediction method and device and server | |
| CN114705990A (en) | Battery cluster state of charge estimation method and system, electronic equipment and storage medium | |
| CN114498619A (en) | Wind power prediction method and device | |
| WO2013167908A1 (en) | Method of operating a server apparatus for delivering website content, server apparatus and device in communication with server apparatus | |
| CN109816165A (en) | Wind-powered electricity generation ultra-short term power forecasting method and system | |
| CN112557905B (en) | Battery pack, data processing method thereof, computer device, medium, and vehicle | |
| CN113205230A (en) | Data prediction method, device and equipment based on model set and storage medium | |
| WO2024066902A1 (en) | Reservoir-inflow runoff correction optimization method and apparatus | |
| CN111461329B (en) | Model training method, device, equipment and readable storage medium | |
| CN110310476B (en) | Road congestion degree evaluation method and device, computer equipment and storage medium | |
| CN111323847A (en) | Method and apparatus for determining weight ratios for analog integration algorithms | |
| CN113627755A (en) | Test method, device, equipment and storage medium for intelligent terminal factory | |
| CN112508734A (en) | Method and device for predicting power generation capacity of power enterprise based on convolutional neural network | |
| JP2003121490A (en) | Sampling method, semiconductor characteristic computing device, and controlling method for it | |
| CN111768021A (en) | Order price adjustment method, device, server and storage medium | |
| CN114118855B (en) | CNN-based method for calculating benchmarking values of line loss rate of transformer area | |
| CN114386525B (en) | Adaptive adjustment method, device, equipment and storage medium for evaluation standard | |
| CN109409596B (en) | Processing method, device, equipment and computer-readable storage medium for predicting wind speed | |
| CN117293817A (en) | Power generation parameter prediction method and device | |
| WO2022156743A1 (en) | Feature construction method and apparatus, model training method and apparatus, and device and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200428 |