CN110175416A - Three Gorges Reservoir water temperature prediction method based on principal component analysis and neural network - Google Patents
Three Gorges Reservoir water temperature prediction method based on principal component analysis and neural network Download PDFInfo
- Publication number
- CN110175416A CN110175416A CN201910463939.4A CN201910463939A CN110175416A CN 110175416 A CN110175416 A CN 110175416A CN 201910463939 A CN201910463939 A CN 201910463939A CN 110175416 A CN110175416 A CN 110175416A
- Authority
- CN
- China
- Prior art keywords
- water temperature
- neural network
- reservoir water
- gorges reservoir
- principal component
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The Three Gorges Reservoir water temperature prediction method based on principal component analysis and neural network that the invention discloses a kind of, comprising: collect the Three Gorges Reservoir water temperature data collection of multivariable；Judge the integrality of Three Gorges Reservoir water temperature data collection；Feature selecting is carried out to water temperature data；Feature extraction is carried out, new data set is carried out using Principal Component Analysis to do Feature Dimension Reduction processing, treated that data set is divided into training set and test set by Feature Dimension Reduction；It establishes neural network prediction model and carries out parameter optimization, input training set, carry out sample learning；Input test collection carries out model evaluation；Three Gorges Reservoir water temperature and characteristic are measured, after carrying out feature selecting and feature extraction, as the input of neural network prediction model, Three Gorges Reservoir water temperature is predicted using neural network prediction model.Method of the invention effectively improves precision of prediction, the calculation amount for reducing prediction model, the reasonability for promoting data.
Description
Technical field
The invention belongs to hydroelectric project hydrologic monitoring fields, and in particular to a kind of based on principal component analysis and neural network
Three Gorges Reservoir water temperature prediction method.
Background technique
When the problems such as considering water quality of river and biotic factor, water temperature has economic and ecological double meaning.Water temperature is to determine
One of the river ecology parameter for determining aquatic ecosystem holistic health has aquatile or even aquatic ecosystem extremely heavy
The influence wanted.Therefore, water temperature is carried out effectively and accurate prediction is particularly important.
Currently, the research method predicted in reservoir area of Three Gorges to water temperature is less.Mainly pass through biography in the prior art
The empirical method of system or the numerical prediction based on mathematical model, such as consider that the relationship between water temperature and water flow movement is built
The method that vertical two dimension k- ε model carries out water temperature prediction.The real-time of these prediction techniques is not high, although to a certain extent can be with
Reflect the distribution situation of local airflow, temperature field, but since the simplification of itself has dispensed many important physical phenomenons, essence
It spends not high.
Summary of the invention
Technical problem of the invention be the reservoir area of Three Gorges water temperature prediction method data volume of the prior art is big, data redundancy and lead
The model running time of cause is long, prediction effect is bad, precision of prediction is not high.The object of the present invention is to provide one kind to be based on principal component
The Three Gorges Reservoir water temperature prediction method of analysis and neural network, using LightGBM method, Principal Component Analysis to water temperature data
Feature selecting and feature extraction are carried out, data set is formed and neural network prediction model is trained, it is pre- using neural network
Model is surveyed to predict reservoir area of Three Gorges water temperature.
The technical scheme is that the Three Gorges Reservoir water temperature prediction method based on principal component analysis and neural network, including
Following steps,
Step 1: collecting the Three Gorges Reservoir water temperature data collection of multivariable；
Step 2: judging the integrality of Three Gorges Reservoir water temperature data collection, rejecting outliers are carried out to data set, to data set
In missing values or exceptional value, use corresponding feature average value substitute；
Step 3: feature selecting being carried out to water temperature data, importance analysis is carried out to characteristic parameter, has been selected compared with Gao Chong
The feature set and water temperature for the property wanted are combined into new data set；
Step 4: feature extraction is carried out, new data set is carried out using Principal Component Analysis to do Feature Dimension Reduction processing, it will
Treated that data set is divided into training set and test set for Feature Dimension Reduction；
Step 5: establishing neural network prediction model and carry out parameter optimization, input training set, carry out sample learning；
Step 6: after the completion of neural network prediction model training, input test collection carries out neural network prediction model assessment；
Step 7: measuring Three Gorges Reservoir water temperature and characteristic, feature choosing is carried out using the importance analysis method of step 3
It selects, after carrying out feature extraction using the Principal Component Analysis of step 4, as the input of neural network prediction model, using nerve
Network Prediction Model predicts Three Gorges Reservoir water temperature.
Further, in step 1, the Three Gorges Reservoir water temperature data collection of the multivariable includes rainfall, output flow, defeated
Inbound traffics, wind speed, relative humidity, temperature, radiation and water temperature.
Further, described that importance analysis is carried out using LightGBM method to characteristic parameter in step 3.
Further, in step 3, the new data set includes output flow, input flow rate, wind speed, relative humidity, gas
Temperature, radiation and water temperature.
Further, in step 5, the neural network prediction model uses LSTM neural network.
Further, the LSTM neural network includes the double-deck hidden layer, and batch processing size is 72, and hidden layer dimension is
150。
Further, the LSTM neural network includes input layer, hidden layer, dropout layers and output layer.
Further, the LSTM neural network uses ReLU activation primitive, MSE loss function, adam optimizer.
Compared with prior art, the beneficial effects of the invention are as follows methods of the invention to effectively improve reservoir area of Three Gorges water temperature prediction
Precision, the calculation amount for reducing water temperature prediction model, the reasonability for promoting data.
Detailed description of the invention
Present invention will be further explained below with reference to the attached drawings and examples.
Fig. 1 is the flow diagram of the Three Gorges Reservoir water temperature prediction method based on principal component analysis and neural network.
Fig. 2 is the feature importance of accumulation and the relational graph of feature quantity.
Specific embodiment
As shown in Figure 1, the Three Gorges Reservoir water temperature prediction method based on principal component analysis and neural network, including following step
Suddenly,
Step 1: collecting the Three Gorges Reservoir water temperature data collection of multivariable；
Step 2: judging the integrality of Three Gorges Reservoir water temperature data collection, rejecting outliers are carried out to data set, to data set
In missing values or exceptional value, use corresponding feature average value substitute；
Step 3: feature selecting being carried out to water temperature data using LightGBM method, importance point is carried out to characteristic parameter
Analysis, the feature set and water temperature for selecting higher significant are combined into new data set；
Step 4: feature extraction is carried out, new data set is carried out using Principal Component Analysis to do Feature Dimension Reduction processing, it will
Treated that data set is divided into training set and test set for Feature Dimension Reduction；
Step 5: establishing LSTM neural network prediction model and carry out parameter optimization, input training set, carry out sample learning；
After the completion of the training of step 6:LSTM neural network prediction model, input test collection carries out neural network prediction model
Assessment；
Step 7: measuring Three Gorges Reservoir water temperature and characteristic, feature choosing is carried out using the importance analysis method of step 3
It selects, after carrying out feature extraction using the Principal Component Analysis of step 4, as the input of LSTM neural network prediction model, uses
LSTM neural network prediction model predicts Three Gorges Reservoir water temperature.
Different environmental factors generates different influences to water temperature, therefore predicts in the water temperature to Three Gorges Reservoir reservoir area
When, consider various Water Temperature factors, collect the water temperature data collection of the multivariable of 9 years Three Gorges Reservoirs, content includes rainfall
Amount, output flow, input flow rate, wind speed, relative humidity, temperature, radiation and water temperature.The water temperature at prediction current time needs to consider
The influence at previous moment or former moment belongs to time series problem, has good result to long-term Dependence Problem is handled
LSTM neural network has unique advantage for water temperature prediction.
In step 2, feature selecting refers to selects several features of high importance to form new number from existing feature
Enhanced with reducing the difficulty and speed of neural network prediction model training mission to the understanding between feature and characteristic value according to collection.
The feature importance of each characteristic parameter is calculated using LightGBM method, calculated result is as shown in table 1, is arranged after normalization
Sequence simultaneously adds up, as a result as shown in Fig. 2: when feature quantity is 6, the feature importance of accumulation has reached 0.998667,
The feature importance of rainfall is lower, therefore remaining 6 parameter and water temperature is selected to be combined into new data set.
The feature importance of 1 parameters of table
In step 3, in order to reduce the redundancy of data information, feature is carried out using Principal Component Analysis to new data set and is mentioned
It takes.KMO (Kaiser-Meyer-Olkin) value and Bartlett sphericity inspection result are as shown in table 2, KMO value and Barlett
Sphericity inspection is all satisfied requirement；The population variance of explanation is as shown in table 3, it can be seen that and the characteristic value of ingredient 1 and ingredient 2 is greater than 1,
And their total methods that can explain 78.252%, therefore two principal components are extracted, according to composition matrix and composition score
Coefficient matrix determines the correlativity between extraction factor and original parameter, the characteristic parameter collection after obtaining dimensionality reduction.It collects
The water temperature data of the multivariable of 9 years Three Gorges Reservoirs is concentrated, and the data of the first five years is divided into training set, rear 4 years data are drawn
It is divided into test set, is used as experimental data after normalizing respectively.
2 KMO value of table and Bartlett sphericity examination table
The population variance table that table 3 is explained
The LSTM neural network prediction model that the present invention uses includes input layer, hidden layer, dropout layers and output layer,
Output layer uses linear convergent rate.
The neuron activation functions that hidden layer is chosen use ReLU function
F (x)=max (0, x)
When inputting x<0, exporting is 0, as x>0, is exported as x.The activation primitive makes LSTM neural network more quickly
It restrains and fights gradient disappearance problem.
The target error function of LSTM neural network prediction model uses MAE function
In formula, N is data sample number, and y is true value,For predicted value.
LSTM neural network prediction model uses Adam optimizer, and Adam optimizer, which is used to update and calculate, influences model instruction
The network parameter of experienced and model output, makes it approach or be optimal value, to minimize or maximize loss function.
The optimized parameter of LSTM neural network prediction model: the double-deck hidden layer, batch processing size are 72, hidden layer
Dimension is 150, cycle of training 300.
The present embodiment uses the water temperature data collection of step 1 and the new data set of step 3 respectively, in 4 groups of neural network models
On carry out analysis comparison, for experimental result as shown in table 4, table 5,4 groups of neural network models are respectively CNN neural network model, RNN
Neural network model, GRU neural network model, LSTM neural network model.
Experimental result table of 4 original data set of table on different models
| Evaluation index | CNN | RNN | GRU | LSTM |
| MAE | 2.027 | 0.392 | 0.304 | 0.275 |
| RMSE | 2.601 | 0.491 | 0.407 | 0.37 |
| R2_score | 0.73097 | 0.99040 | 0.99342 | 0.99421 |
Experimental result table of the treated data set of table 5 on different models
| Evaluation index | CNN | RNN | GRU | LSTM |
| MAE | 0.791 | 0.269 | 0.259 | 0.254 |
| RMSE | 1.034 | 0.387 | 0.383 | 0.335 |
| R2_score | 0.95750 | 0.99404 | 0.99416 | 0.99538 |
As shown in table 4, table 5, analysis comparison result shows feature selecting proposed by the present invention, at the feature of feature extraction
Reason method can effectively promote the reasonability, the calculation amount for reducing model, the precision of prediction for improving model of data.Meanwhile number
It is better than other neural network models according to performance of the collection in optimized LSTM neural network.
Claims (8)
1. the Three Gorges Reservoir water temperature prediction method based on principal component analysis and neural network, which is characterized in that include the following steps,
Step 1: collecting the Three Gorges Reservoir water temperature data collection of multivariable；
Step 2: judging the integrality of Three Gorges Reservoir water temperature data collection, rejecting outliers are carried out to data set, data are concentrated
Missing values or exceptional value are substituted using corresponding feature average value；
Step 3: feature selecting being carried out to water temperature data, importance analysis is carried out to characteristic parameter, has selected higher significant
Feature set and water temperature be combined into new data set；
Step 4: carrying out feature extraction, new data set is carried out using Principal Component Analysis to do Feature Dimension Reduction processing, by feature
Data set after dimension-reduction treatment is divided into training set and test set；
Step 5: establishing neural network prediction model and carry out parameter optimization, input training set, carry out sample learning；
Step 6: after the completion of neural network prediction model training, input test collection carries out neural network prediction model assessment；
Step 7: measuring Three Gorges Reservoir water temperature and characteristic, feature selecting is carried out using the importance analysis method of step 3, is adopted
It is pre- using neural network as the input of neural network prediction model after carrying out feature extraction with the Principal Component Analysis of step 4
Model is surveyed to predict Three Gorges Reservoir water temperature.
2. the Three Gorges Reservoir water temperature prediction method according to claim 1 based on principal component analysis and neural network, special
Sign is, in step 1, the Three Gorges Reservoir water temperature data collection of the multivariable includes rainfall, output flow, input flow rate, wind
Speed, relative humidity, temperature, radiation and water temperature.
3. the Three Gorges Reservoir water temperature prediction method according to claim 1 based on principal component analysis and neural network, special
Sign is, described to carry out importance analysis using LightGBM method to characteristic parameter in step 3.
4. the Three Gorges Reservoir water temperature prediction method according to claim 1 based on principal component analysis and neural network, special
Sign is, in step 3, the new data set include output flow, input flow rate, wind speed, relative humidity, temperature, radiation and
Water temperature.
5. the Three Gorges Reservoir water temperature prediction method according to claim 1 based on principal component analysis and neural network, special
Sign is, in step 5, the neural network prediction model uses LSTM neural network.
6. the Three Gorges Reservoir water temperature prediction method according to claim 5 based on principal component analysis and neural network, special
Sign is that the LSTM neural network includes the double-deck hidden layer, and batch processing size is 72, and hidden layer dimension is 150.
7. the Three Gorges Reservoir water temperature prediction method according to claim 5 based on principal component analysis and neural network, special
Sign is that the LSTM neural network includes input layer, hidden layer, dropout layers and output layer.
8. the Three Gorges Reservoir water temperature prediction according to claim 5-7 any one based on principal component analysis and neural network
Method, which is characterized in that the LSTM neural network uses ReLU activation primitive, MSE loss function, adam optimizer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910463939.4A CN110175416A (en) | 2019-05-30 | 2019-05-30 | Three Gorges Reservoir water temperature prediction method based on principal component analysis and neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910463939.4A CN110175416A (en) | 2019-05-30 | 2019-05-30 | Three Gorges Reservoir water temperature prediction method based on principal component analysis and neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110175416A true CN110175416A (en) | 2019-08-27 |
Family
ID=67696779
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910463939.4A Pending CN110175416A (en) | 2019-05-30 | 2019-05-30 | Three Gorges Reservoir water temperature prediction method based on principal component analysis and neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110175416A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110672804A (en) * | 2019-09-30 | 2020-01-10 | 华南师范大学 | Intelligent detection method for typical organic pollutants in urban river water body |
| CN111027893A (en) * | 2019-12-31 | 2020-04-17 | 山东琢瑜清泉智能软件科技有限公司 | Intelligent evaluation early warning system and method for river and lake water environment health |
| CN111553394A (en) * | 2020-04-20 | 2020-08-18 | 中国长江三峡集团有限公司 | Reservoir water level prediction method based on cyclic neural network and attention mechanism |
| CN112001556A (en) * | 2020-08-27 | 2020-11-27 | 华中科技大学 | Reservoir downstream water level prediction method based on deep learning model |
| CN112116147A (en) * | 2020-09-16 | 2020-12-22 | 南京大学 | River water temperature prediction method based on LSTM deep learning |
| CN112182709A (en) * | 2020-09-28 | 2021-01-05 | 中国水利水电科学研究院 | Rapid prediction method for let-down water temperature of large-scale reservoir stop log door layered water taking facility |
| WO2021120787A1 (en) * | 2019-12-20 | 2021-06-24 | 华中科技大学 | Simulation operation method for large-scale reservoir group in main stream and tributaries of river basin |
| CN113033618A (en) * | 2021-03-03 | 2021-06-25 | 四川大学 | Layered reservoir water taking and discharging water temperature prediction model and prediction method based on support vector regression |
| CN113610217A (en) * | 2021-07-14 | 2021-11-05 | 中国铁道科学研究院集团有限公司电子计算技术研究所 | Passenger station environment temperature prediction method and device |
| CN114575827A (en) * | 2022-04-11 | 2022-06-03 | 中国地质大学(北京)郑州研究院 | Intelligent processing system and method for measurement while drilling data |
| CN117196313A (en) * | 2023-09-25 | 2023-12-08 | 华设设计集团股份有限公司 | Tunnel construction collapse accident coupling risk source identification method |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109711592A (en) * | 2018-03-27 | 2019-05-03 | 江苏信息职业技术学院 | A kind of pond water temperature prediction technique based on genetic algorithm optimization extreme learning machine |
-
2019
- 2019-05-30 CN CN201910463939.4A patent/CN110175416A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109711592A (en) * | 2018-03-27 | 2019-05-03 | 江苏信息职业技术学院 | A kind of pond water temperature prediction technique based on genetic algorithm optimization extreme learning machine |
Non-Patent Citations (1)
| Title |
|---|
| 杨昆等: "湖泊表面水温预测与可视化方法研究", 《仪器仪表学报》 * |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110672804B (en) * | 2019-09-30 | 2022-05-06 | 华南师范大学 | Intelligent detection method for typical organic pollutants in urban river water body |
| CN110672804A (en) * | 2019-09-30 | 2020-01-10 | 华南师范大学 | Intelligent detection method for typical organic pollutants in urban river water body |
| WO2021120787A1 (en) * | 2019-12-20 | 2021-06-24 | 华中科技大学 | Simulation operation method for large-scale reservoir group in main stream and tributaries of river basin |
| CN111027893A (en) * | 2019-12-31 | 2020-04-17 | 山东琢瑜清泉智能软件科技有限公司 | Intelligent evaluation early warning system and method for river and lake water environment health |
| CN111553394A (en) * | 2020-04-20 | 2020-08-18 | 中国长江三峡集团有限公司 | Reservoir water level prediction method based on cyclic neural network and attention mechanism |
| CN112001556A (en) * | 2020-08-27 | 2020-11-27 | 华中科技大学 | Reservoir downstream water level prediction method based on deep learning model |
| CN112001556B (en) * | 2020-08-27 | 2022-07-15 | 华中科技大学 | Reservoir downstream water level prediction method based on deep learning model |
| CN112116147A (en) * | 2020-09-16 | 2020-12-22 | 南京大学 | River water temperature prediction method based on LSTM deep learning |
| CN112182709A (en) * | 2020-09-28 | 2021-01-05 | 中国水利水电科学研究院 | Rapid prediction method for let-down water temperature of large-scale reservoir stop log door layered water taking facility |
| CN112182709B (en) * | 2020-09-28 | 2024-01-16 | 中国水利水电科学研究院 | Method for rapidly predicting water drainage temperature of large reservoir stoplog gate layered water taking facility |
| CN113033618B (en) * | 2021-03-03 | 2022-03-15 | 四川大学 | Layered reservoir water taking and discharging water temperature prediction model and prediction method based on support vector regression |
| CN113033618A (en) * | 2021-03-03 | 2021-06-25 | 四川大学 | Layered reservoir water taking and discharging water temperature prediction model and prediction method based on support vector regression |
| CN113610217A (en) * | 2021-07-14 | 2021-11-05 | 中国铁道科学研究院集团有限公司电子计算技术研究所 | Passenger station environment temperature prediction method and device |
| CN113610217B (en) * | 2021-07-14 | 2024-04-02 | 中国铁道科学研究院集团有限公司电子计算技术研究所 | Method and device for predicting ambient temperature of passenger station |
| CN114575827A (en) * | 2022-04-11 | 2022-06-03 | 中国地质大学(北京)郑州研究院 | Intelligent processing system and method for measurement while drilling data |
| CN114575827B (en) * | 2022-04-11 | 2024-06-04 | 中国地质大学(北京)郑州研究院 | Intelligent processing system and method for measurement while drilling data |
| CN117196313A (en) * | 2023-09-25 | 2023-12-08 | 华设设计集团股份有限公司 | Tunnel construction collapse accident coupling risk source identification method |
| CN117196313B (en) * | 2023-09-25 | 2024-07-26 | 华设设计集团股份有限公司 | Tunnel construction collapse accident coupling risk source identification method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110175416A (en) | Three Gorges Reservoir water temperature prediction method based on principal component analysis and neural network | |
| CN110619360A (en) | Ultra-short-term wind power prediction method considering historical sample similarity | |
| CN113554466B (en) | Short-term electricity consumption prediction model construction method, prediction method and device | |
| CN106022954B (en) | Multiple BP neural network load prediction method based on grey correlation degree | |
| CN107220498B (en) | Mechanical material evaluation method and system | |
| CN106251001A (en) | A kind of based on the photovoltaic power Forecasting Methodology improving fuzzy clustering algorithm | |
| CN110987436B (en) | Bearing fault diagnosis method based on excitation mechanism | |
| CN111369070A (en) | Envelope clustering-based multimode fusion photovoltaic power prediction method | |
| CN109143408B (en) | Dynamic region combined short-time rainfall forecasting method based on MLP | |
| CN115456460A (en) | Multi-quality index output prediction method and system for tobacco shred loosening and conditioning process | |
| CN113344288B (en) | Cascade hydropower station group water level prediction method and device and computer readable storage medium | |
| CN114444378A (en) | Short-term power prediction method for regional wind power cluster | |
| CN106896219A (en) | The identification of transformer sub-health state and average remaining lifetime method of estimation based on Gases Dissolved in Transformer Oil data | |
| CN105404926A (en) | Aluminum electrolytic production technology optimization method based on BP neural network and MBFO algorithm | |
| CN105321000A (en) | Aluminum electrolytic process parameter optimization method based on BP neural network and MOBFOA algorithm | |
| CN114298134A (en) | Wind power prediction method and device and electronic equipment | |
| CN116245227A (en) | Daily weather drought prediction method, device, storage medium and equipment | |
| CN104865827A (en) | Oil pumping unit oil extraction optimization method based on multi-working-condition model | |
| CN116187835A (en) | Data-driven-based method and system for estimating theoretical line loss interval of transformer area | |
| CN114596726A (en) | Parking position prediction method based on interpretable space-time attention mechanism | |
| CN110533249B (en) | Metallurgical enterprise energy consumption prediction method based on integrated long-term and short-term memory network | |
| CN112288157A (en) | Wind power plant power prediction method based on fuzzy clustering and deep reinforcement learning | |
| CN114118401A (en) | Neural network-based power distribution network flow prediction method, system, device and storage medium | |
| CN116826745B (en) | Layered and partitioned short-term load prediction method and system in power system background | |
| CN111028086A (en) | Enhanced index tracking method based on clustering and LSTM network |
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 |