CN114372558A - Residential electricity load prediction method, medium and equipment based on multi-model fusion - Google Patents
Residential electricity load prediction method, medium and equipment based on multi-model fusion Download PDFInfo
- Publication number
- CN114372558A CN114372558A CN202111614636.1A CN202111614636A CN114372558A CN 114372558 A CN114372558 A CN 114372558A CN 202111614636 A CN202111614636 A CN 202111614636A CN 114372558 A CN114372558 A CN 114372558A
- Authority
- CN
- China
- Prior art keywords
- prediction
- model
- fusion
- electricity consumption
- residential
- 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 77
- 230000005611 electricity Effects 0.000 title claims abstract description 63
- 230000004927 fusion Effects 0.000 title claims abstract description 29
- 238000012549 training Methods 0.000 claims abstract description 9
- 238000007499 fusion processing Methods 0.000 claims abstract description 6
- 230000015654 memory Effects 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000013277 forecasting method Methods 0.000 claims 1
- 230000006403 short-term memory Effects 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000013136 deep learning model Methods 0.000 description 4
- 230000007787 long-term memory Effects 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 230000001174 ascending effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- 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
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Economics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Public Health (AREA)
- Mathematical Physics (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Water Supply & Treatment (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Power Engineering (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a residential electricity load prediction method, medium and equipment based on multi-model fusion, wherein the prediction method comprises the following steps: constructing a plurality of prediction models for predicting the electricity consumption of residents and acquiring the electricity consumption data x of the residentsiI-1, 2, a., t-1 as a training set, and respectively training each prediction model by using the training set; each prediction model is based on resident electricity consumption data xi1,2, the t-1 predicts and obtains predicted power consumption at the t moment, the t moment has known real power consumption, and corresponding relative errors of the prediction models are calculated based on the predicted power consumption and the real power consumption; calculating a confidence factor of each prediction model based on the relative error of each prediction model; each one ofPrediction model based on resident electricity consumption data xiT, predicting to obtain a prediction result of the resident electricity consumption at the moment of t + 1; and performing fusion processing based on the confidence factors of the prediction models and the prediction results of the resident electricity consumption to obtain the final prediction result at the moment t + 1. Compared with the prior art, the method has the advantages of wide application range, high prediction precision and the like.
Description
Technical Field
The invention relates to the technical field of resident electricity consumption prediction, in particular to a resident electricity load prediction method, medium and equipment based on multi-model fusion.
Background
The accurate prediction of the resident electricity consumption is of great significance to the guidance of the scheduling and optimization of the power flow.
Existing residential electricity prediction methods can be classified into a gray-scale prediction-based method, an autoregressive moving average model, an artificial intelligence method, and a deep learning model. It has the following disadvantages: the method based on the gray scale prediction is used for modeling a differential equation for historical data of the resident electricity consumption, so that prediction is carried out based on the differential equation, and the method is sensitive to abnormal data. The autoregressive moving average model is used for carrying out regression analysis on historical data of the resident electricity consumption and white noise of the resident electricity consumption and predicting according to the regression model, and the method can only represent the linear relation between the data. An artificial intelligence method, such as an artificial neural network (single hidden layer model) and a support vector machine model, trains by using historical electricity consumption data of residents, so that electricity consumption prediction is performed by using the trained model. The deep learning model, such as a recurrent neural network and a long-short term memory network method, is consistent with the idea that an artificial neural network (single hidden layer model) is used for predicting the electricity consumption of residents, the corresponding model is trained by using historical electricity consumption data of the residents, then the electricity consumption of the residents is predicted based on the trained model, and compared with the artificial neural network and a support vector machine, the deep learning model is higher in representation capability and correspondingly higher in calculated amount. The artificial intelligence method and the deep learning model are black box models, lack interpretability for predicted resident electricity consumption and are difficult to apply under the scene with high safety factor requirements. Meanwhile, due to the complexity and randomness of the electricity consumption behaviors of residents, the existing prediction method is difficult to be competent for accurately predicting the electricity consumption of different residents under different scenes.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a residential electrical load prediction method, medium and equipment based on multi-model fusion, which have wide application range and high prediction accuracy.
The purpose of the invention can be realized by the following technical scheme:
a residential electricity load prediction method based on multi-model fusion comprises the following steps:
constructing a plurality of prediction models for predicting the electricity consumption of residents and acquiring the electricity consumption data x of the residentsiI-1, 2., t-1 as a training set, each prediction model being trained separately using the training set;
each prediction model is based on resident electricity consumption data xiT-1 predicting to obtain predicted power consumption at t moment, wherein the t moment has known real power consumption, and calculating corresponding relative errors re of prediction models based on the predicted power consumption and the real power consumptionj(t), j ═ 1, 2.., n, n is the total number of prediction models;
calculating a confidence factor alpha for each prediction model based on the relative error of each prediction modelj(t)；
Each prediction model is based on resident electricity consumption data xiT prediction obtains a residential electricity consumption prediction result pre at the moment t +1j(t+1)；
The confidence factor alpha based on each prediction modelj(t) and residential electricity consumption prediction result prej(t +1) fusion processing is performed to obtain a final prediction result fusion (t +1) at time t + 1.
Further, the prediction model comprises a plurality of a gray scale prediction model, a Gaussian process regression model and a long-short term memory network model.
Further, the relative error rejThe formula for calculation of (t) is:
rej(t)＝(true_val(t)-prej(t))/(true_val(t))
where true _ val (t) is the real power consumption at time t, prej(t) is the predicted power consumption at time t of the jth prediction model.
Further, the confidence factor αjThe formula for calculation of (t) is:
further, the fusion process specifically comprises:
determine each relative error rej(t) relationship to 0 if all relative errors are present rej(t) > - < 0, fusion (t +1) > -max (pre)j(t +1)), max (·) represents taking the maximum value; if all relative errors exist rej(t) < 0, fusion (t +1) ═ min (pre)j(t +1)), min (·) represents taking the minimum value; if not, then,
further, the prediction model comprises a gaussian process regression model, and the prediction method further comprises:
and calculating a confidence interval of the residential electricity consumption prediction result at the t +1 moment based on the Gaussian process regression model.
Furthermore, the reliability of the prediction method is judged according to the absolute average value index of the relative error, and the weight of each prediction model is further fed back and adjusted.
The present invention also provides a computer readable storage medium comprising one or more programs for execution by one or more processors of an electronic device, the one or more programs including instructions for executing the residential electrical load prediction method as described above.
The present invention also provides an electronic device comprising:
one or more processors;
a memory; and
one or more programs stored in the memory, the one or more programs including instructions for executing the residential electric load prediction method as described above.
Compared with the prior art, the invention has the following beneficial effects:
1. the method disclosed by the invention integrates the results of multiple prediction methods, and sets the weight of each method, so that the prediction precision is effectively improved compared with that of a single method.
2. The method can be used for accurately predicting the power consumption under different scenes and different residential electricity consumption habits.
3. The method fuses a Grey Model (GM), a Gaussian Process Regression (GPR) and a Long Short-Term Memory network (LSTM), thereby accurately predicting the electricity consumption of residents. The invention gives the prediction result and the confidence coefficient (interval) of the prediction result, and has important significance for safe operation and regulation of the power grid. The gray scale prediction method can learn the differential (change) characteristic of the resident electricity consumption along with time, the Gaussian process regression reflects the random characteristic of the resident electricity consumption, and the long-term and short-term memory network can find and learn the potential characteristics and modes of the resident electricity consumption. The fusion method is based on gray level prediction, Gaussian process regression and historical expression of a long-term and short-term memory network, corresponding confidence factors are calculated, and the confidence factors are utilized to fuse the three methods, so that the electricity consumption of residents is accurately predicted in multiple scenes, and the problem that the electricity consumption is difficult to accurately predict due to complexity and randomness of electricity consumption behaviors of the residents is solved. Meanwhile, the confidence degree of the prediction result can be given by combining the confidence interval of the Gaussian process regression calculation, so that the safe scheduling and optimization of the power grid load flow are ensured.
Drawings
FIG. 1 is a schematic flow diagram of the present invention;
FIG. 2(a) is a diagram illustrating a fused prediction result in an embodiment;
FIG. 2(b) is a comparison of the effects of the respective methods in the examples;
FIG. 2(c) is the predicted Absolute Relative Error (ARE) for each method;
FIG. 2(d) is a schematic diagram illustrating the ascending order of the absolute relative error of the prediction in FIG. 2 (c).
Detailed Description
The invention is described in detail below with reference to the figures and specific embodiments. The present embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation manner and a specific operation process are given, but the scope of the present invention is not limited to the following embodiments.
As shown in the figure1, the invention provides a residential electricity load prediction method based on multi-model fusion, and the method fuses multiple prediction models, thereby effectively improving the application range and the prediction precision. In this embodiment, the prediction models used include a grayscale prediction model, a gaussian process regression model, and a long-term and short-term memory network model. To utilize the known resident electricity consumption xi1, 2., t, predicting the electricity consumption of the residents at the time of t +1 as an example, the method of the embodiment includes the following steps:
1) acquiring resident electricity consumption data xiT-1 is used to train a gray prediction model (GM), a gaussian process regression model (GPR), and a long-short term memory network model (LSTM);
2) and respectively predicting the resident electricity consumption at the t moment by using a gray prediction model, a Gaussian process regression model and a long-short term memory network model. Wherein the result of the grey scale prediction is pregm(t) the result of the Gaussian process regression prediction is pregpr(t) the result of the long-short term memory network prediction is prelstm(t)。
3) According to the real electricity consumption value true _ val (t) of the residents at the time t, calculating the corresponding relative error rej(t) in this embodiment, j is gm, gpr, lstm. Relative error re of each of the above prediction modelsjThe formula for calculation of (t) is:
rej(t)＝(true_val(t)-prej(t))/(true_val(t))
relative error of gray scale prediction is regm(t) the relative error predicted by the Gaussian regression process is regpr(t) the relative error of the long-short term memory network prediction is relstm(t)。
4) Calculating a confidence factor alpha for each prediction model based on the relative error of each prediction modelj(t)：
Wherein the confidence factor of the gray scale prediction is alphagm(t) the confidence factor of the Gaussian process regression is αgpr(t) a confidence factor for the long-short term memory network ofαlstm(t)。
5) Each prediction model is based on resident electricity consumption data xiT prediction obtains a residential electricity consumption prediction result pre at the moment t +1j(t +1) where the result of the gray prediction is pregm(t +1) the result of the Gaussian process regression prediction is pregpr(t +1), the result of the long-short term memory network prediction is prelstm(t+1)。
6) The confidence factor alpha based on each prediction modelj(t) and residential electricity consumption prediction result prej(t +1) fusion processing is performed to obtain a final prediction result fusion (t +1) at time t + 1. The fusion treatment specifically comprises the following steps:
determine each relative error rej(t) relationship to 0 if all relative errors are present rej(t) > - < 0, fusion (t +1) > -max (pre)j(t +1)), max (·) represents taking the maximum value; if all relative errors exist rej(t) < 0, fusion (t +1) ═ min (pre)j(t +1)), min (·) represents taking the minimum value; if not, then,
in a preferred embodiment, the prediction method further comprises the step of calculating a confidence interval of the prediction result of the residential electricity consumption at the time t +1 based on the gaussian process regression model, and the confidence of the prediction result can be given, so that the safe scheduling and optimization of the power flow of the power grid are ensured.
In a preferred embodiment, the reliability of the prediction method is determined by an absolute average indicator of relative errors, and the weight of each prediction model is adjusted by feedback.
The above method, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In the embodiment, experiments are carried out in a certain cell, and the method is used for predicting the electricity consumption of residents. And selecting the residential electricity consumption data from 8/month and 1 day in 2020 to 10/month and 30 days in 2020, wherein the 80-day electricity consumption data from 8/month and 1 day to 10/month and 19 days is set as a training set for training a gray scale model, a Gaussian regression model and a long-short term memory network model, and the 10-day electricity consumption data from 10/month and 20 days to 10/month and 30 days is used as a test set for testing the prediction effect of the residential electricity consumption. Fig. 2(a) shows the fusion prediction result, fig. 2(b) shows the comparison of the effects of the methods, fig. 2(c) shows the Absolute Relative Error (ARE) of the prediction of each method, and fig. 2(d) sorts the Absolute Relative Error of the prediction in fig. 2(c) in ascending order.
As can be seen from fig. 2, the fusion algorithm is better than the gray scale prediction, the gaussian process regression, and the long-short term memory network. Fig. 2(d) shows the predicted absolute relative errors of the respective methods in ascending order, and the area under the curve represents the total absolute relative error of the corresponding method over the entire prediction set. As shown, the area under the curve of the fusion algorithm is minimal, and the total error is minimal.
Table 1 gives the prediction error for each method. As can be seen from table 1, the fusion algorithm has the smallest average absolute relative error.
TABLE 1 error comparison
| Method | Maximum ARE | Minimum ARE | Average ARE |
| Gray scale prediction | 0.5077 | 0.0441 | 0.1964 |
| Gauss process regression | 0.4196 | 0.0086 | 0.2027 |
| Long and short term memory network | 0.3549 | 0.0012 | 0.2001 |
| Fusion algorithm | 0.4177 | 0.0012 | 0.1658 |
The foregoing detailed description of the preferred embodiments of the invention has been presented. It should be understood that numerous modifications and variations could be devised by those skilled in the art in light of the present teachings without departing from the inventive concepts. Therefore, the technical solutions available to those skilled in the art through logic analysis, reasoning and limited experiments based on the prior art according to the concept of the present invention should be within the scope of protection defined by the claims.
Claims (9)
1. A residential electricity load prediction method based on multi-model fusion is characterized by comprising the following steps:
constructing a plurality of prediction models for predicting the electricity consumption of residents and acquiring the electricity consumption data x of the residentsiI-1, 2., t-1 as a training set, each prediction model being trained separately using the training set;
each prediction model is based on resident electricity consumption data xiT-1 predicting to obtain predicted power consumption at t moment, wherein the t moment has known real power consumption, and calculating corresponding relative errors re of prediction models based on the predicted power consumption and the real power consumptionj(t), j ═ 1, 2.., n, n is the total number of prediction models;
calculating a confidence factor alpha for each prediction model based on the relative error of each prediction modelj(t)；
Each prediction model is based on resident electricity consumption data xiT prediction obtains a residential electricity consumption prediction result pre at the moment t +1j(t+1)；
The confidence factor alpha based on each prediction modelj(t) and residential electricity consumption prediction result prej(t +1) fusion processing is performed to obtain a final prediction result fusion (t +1) at time t + 1.
2. The residential electrical load prediction method based on multi-model fusion as claimed in claim 1, wherein the prediction model comprises a plurality of a gray scale prediction model, a gaussian process regression model, and a long-short term memory network model.
3. The residential power load prediction method based on multi-model fusion as claimed in claim 1, wherein said relative error rejThe formula for calculation of (t) is:
rej(t)＝(true_val(t)-prej(t))/(true_val(t))
where true _ val (t) is the real power consumption at time t, prej(t) is the predicted power consumption at time t of the jth prediction model.
4. According toThe residential electrical load forecasting method based on multi-model fusion as claimed in claim 1, wherein the confidence factor α isjThe formula for calculation of (t) is:
5. the residential electrical load prediction method based on multi-model fusion as claimed in claim 1, wherein the fusion process is specifically:
determine each relative error rej(t) relationship to 0 if all relative errors are present rej(t) > - < 0, fusion (t +1) > -max (pre)j(t +1)), max (·) represents taking the maximum value; if all relative errors exist rej(t) < 0, fusion (t +1) ═ min (pre)j(t +1)), min (·) represents taking the minimum value; if not, then,
6. the residential electrical load prediction method based on multi-model fusion as claimed in claim 1, wherein the prediction model comprises a gaussian process regression model, the prediction method further comprising:
and calculating a confidence interval of the residential electricity consumption prediction result at the t +1 moment based on the Gaussian process regression model.
7. The residential power load prediction method based on multi-model fusion as claimed in claim 1, wherein the reliability of the prediction method is determined by an absolute average indicator of relative errors, and the weight of each prediction model is adjusted by feedback.
8. A computer-readable storage medium, characterized by comprising one or more programs for execution by one or more processors of an electronic device, the one or more programs including instructions for executing the residential electrical load prediction method according to any one of claims 1 to 7.
9. An electronic device, comprising:
one or more processors;
a memory; and
one or more programs stored in the memory, the one or more programs including instructions for executing the residential electric load prediction method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111614636.1A CN114372558A (en) | 2021-12-27 | 2021-12-27 | Residential electricity load prediction method, medium and equipment based on multi-model fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111614636.1A CN114372558A (en) | 2021-12-27 | 2021-12-27 | Residential electricity load prediction method, medium and equipment based on multi-model fusion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114372558A true CN114372558A (en) | 2022-04-19 |
Family
ID=81142169
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111614636.1A Pending CN114372558A (en) | 2021-12-27 | 2021-12-27 | Residential electricity load prediction method, medium and equipment based on multi-model fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114372558A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115166619A (en) * | 2022-05-27 | 2022-10-11 | 云南电网有限责任公司 | Intelligent electric energy meter operation error monitoring system |
| WO2024145396A1 (en) * | 2022-12-29 | 2024-07-04 | Tyco Fire & Security Gmbh | Net zero energy facilities with uncertainty handling |
-
2021
- 2021-12-27 CN CN202111614636.1A patent/CN114372558A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115166619A (en) * | 2022-05-27 | 2022-10-11 | 云南电网有限责任公司 | Intelligent electric energy meter operation error monitoring system |
| CN115166619B (en) * | 2022-05-27 | 2023-03-10 | 云南电网有限责任公司 | Intelligent electric energy meter running error monitoring system |
| WO2024145396A1 (en) * | 2022-12-29 | 2024-07-04 | Tyco Fire & Security Gmbh | Net zero energy facilities with uncertainty handling |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110298501B (en) | Electrical load prediction method based on long-time and short-time memory neural network | |
| CN106874581B (en) | Building air conditioner energy consumption prediction method based on BP neural network model | |
| CN111563706A (en) | Multivariable logistics freight volume prediction method based on LSTM network | |
| CN109146162B (en) | A kind of probability wind speed forecasting method based on integrated Recognition with Recurrent Neural Network | |
| CN111860658A (en) | Transformer fault diagnosis method based on cost sensitivity and integrated learning | |
| CN114372558A (en) | Residential electricity load prediction method, medium and equipment based on multi-model fusion | |
| CN112751345B (en) | LSTM and phase trajectory based electric power system low-frequency oscillation mode identification method | |
| CN112686481A (en) | Runoff forecasting method and processor | |
| CN114492922A (en) | Medium-and-long-term power generation capacity prediction method | |
| CN114595861A (en) | MSTL (modeling, transformation, simulation and maintenance) and LSTM (least Square TM) model-based medium-and-long-term power load prediction method | |
| CN111428419A (en) | Suspended sediment concentration prediction method and device, computer equipment and storage medium | |
| CN111697560B (en) | Method and system for predicting load of power system based on LSTM | |
| CN111191823A (en) | Production logistics prediction method based on deep learning | |
| CN113111592A (en) | Short-term wind power prediction method based on EMD-LSTM | |
| Chen et al. | Short-term wind power forecasting using mixed input feature-based cascade-connected artificial neural networks | |
| CN115759415A (en) | Power consumption demand prediction method based on LSTM-SVR | |
| CN115358437A (en) | Power supply load prediction method based on convolutional neural network | |
| Köhnen et al. | The potential of deep learning to reduce complexity in energy system modeling | |
| CN116303786A (en) | Block chain financial big data management system based on multidimensional data fusion algorithm | |
| CN115907131A (en) | Method and system for building electric heating load prediction model in northern area | |
| CN111680712A (en) | Transformer oil temperature prediction method, device and system based on similar moments in the day | |
| CN118364963A (en) | Building material price prediction method based on LSTM neural network | |
| CN118017482A (en) | Flexible climbing capacity demand analysis method based on prediction error feature extraction | |
| CN117522066A (en) | Combined optimization method and system based on peak shaving power supply equipment combination prediction | |
| CN113762591A (en) | Short-term electric quantity prediction method and system based on GRU and multi-core SVM counterstudy |
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 |