CN114611778B - Reservoir water level early warning method and system based on warehousing flow - Google Patents
Reservoir water level early warning method and system based on warehousing flow Download PDFInfo
- Publication number
- CN114611778B CN114611778B CN202210207734.1A CN202210207734A CN114611778B CN 114611778 B CN114611778 B CN 114611778B CN 202210207734 A CN202210207734 A CN 202210207734A CN 114611778 B CN114611778 B CN 114611778B
- Authority
- CN
- China
- Prior art keywords
- reservoir
- water level
- model
- reservoir water
- 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.)
- Active
Links
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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/17—Function evaluation by approximation methods, e.g. inter- or extrapolation, smoothing, least mean square method
-
- 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
- G06N3/045—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
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
- Y02A10/40—Controlling or monitoring, e.g. of flood or hurricane; Forecasting, e.g. risk assessment or mapping
Abstract
The invention relates to a reservoir water level early warning method and system based on warehousing flow, the system comprises a data acquisition module, a data transmission module, a reservoir capacity calculation module, a reservoir water level prediction module and an early warning module, the steps are S1 acquisition of historical and real-time reservoir capacity and reservoir water level data, S2 calculation of a reservoir capacity value in a future time period, S3 construction of a reservoir water level prediction model through multi-layer sensor model training, S4 prediction of a reservoir water level value in the future days, and S5 comparison of the predicted reservoir water level value and a water level warning value is carried out for early warning. The method has the advantages that the accuracy of the prediction result is high, the water level change data of the next several days can be predicted, the method has trend, the training model has strong prediction capability, the characteristics such as geographical environment and the like are fully considered, the hidden characteristics are trained and merged into the prediction model, and the fitting effect is very good.
Description
Technical Field
The invention relates to the technical field of multivariate time series information mining and reservoir safety early warning, in particular to a reservoir water level early warning method and system based on warehousing traffic.
Background
With the rapid development of society, China gradually starts large-scale flood control construction, flood control projects are enhanced, and flood is controlled to a certain degree. However, in China, medium and small rivers are numerous and have the characteristics of rapid increase of river water level, rapid water flow and the like, once strong rainfall occurs, flood can be caused, reservoir flow is rapidly increased, and bank breaking and dam collapse of the reservoir can be caused under the more serious condition. How to predict the reservoir water level change condition in the next few days is of great significance to the flood control dispatching department.
In the prior art, a single-feature-based time training model is used for water level prediction, although modal decomposition is carried out, the model has strong dependence on time series data, and if the predicted reservoir engineering changes a little, the prediction capability of the prediction model is greatly reduced. And the water level prediction time is short and has no tendency.
Disclosure of Invention
The invention aims to overcome the defects and provides a reservoir water level early warning method and system based on warehousing flow.
The technical scheme adopted by the invention is as follows:
a reservoir water level early warning method based on warehousing traffic comprises the following steps:
s1, collecting historical and real-time reservoir capacity and reservoir water level data, transmitting the data and storing the data in a reservoir water regime database;
s2, acquiring warehousing flow in the next few days based on a known warehousing flow forecasting model, acquiring current reservoir capacity data from a reservoir water regime database, and calculating a reservoir capacity value in the future time period;
s3, obtaining historical reservoir capacity and reservoir water level data from a database, dividing the historical reservoir capacity and reservoir water level data into a training set and a verification set, constructing a multilayer sensor model for predicting the reservoir water level based on the training set, verifying the performance of the model by using the verification set, adjusting model parameters according to the value obtained by the Root Mean Square Error (RMSE) of an evaluation function, and circularly iterating the training model to obtain the optimal parameters and the model structure of the model as a reservoir water level prediction model until the RMSE value predicted by the model is minimum;
s4, predicting the reservoir water level value of the future days by using the reservoir water level prediction model obtained in the step S3 according to the reservoir capacity value of the future time period obtained in the step S2;
and S5, determining the disaster situation according to the comparison between the predicted reservoir water level value and the water level warning value, and thus linking the visual platform to perform early warning.
In the method for early warning of the water level of the reservoir based on the warehousing traffic, the method for calculating the volume value of the reservoir in the step S2 is as follows:
wherein b is t The storage capacity of the reservoir at the current moment is shown, t shows the time of the current moment, and n is the time length; x T Representing the forecast warehousing flow on the Tth day; f. of n Indicating the reservoir capacity on day n.
The specific case of reservoir capacity of t +1, t +2, …, t + n days can be calculated respectively, n is preferably 5 in the present invention.
The multilayer perceptron model multilayer perceptron network described in step S3 has three structures, namely an input layer, a hidden layer and an output layer, and the corresponding network input X ═ X 1 ,x 2 ,x 3 ,…,x d ]The corresponding net output O ═ O 1 ,o 2 ,o 3 ,…,o q ]The output of the hidden layer is H, and the weight parameter and the deviation parameter of the hidden layer are W respectively h And b h Weight and bias of output layerThe difference parameters are respectively W o And b o The objective function of the network model is:
O=(XW h +b h )W o +b o =XW h W o +b h W o +b o 。
the evaluation function is as follows:
where RMSE denotes the root mean square error, a i Representing true value, p i Representing the predicted value, and m representing the number of predicted data samples.
A reservoir water level early warning system based on warehousing flow comprises a data acquisition module, a data transmission module, a reservoir capacity calculation module, a reservoir water level prediction module and an early warning module, wherein the data acquisition module is used for collecting water level and reservoir capacity data measured by a hydrological monitoring station, the data transmission module is used for transmitting a measurement result to a remote server and storing the measurement result into a reservoir water situation database, the reservoir capacity calculation module is used for calculating the reservoir capacity change condition in the next several days, the reservoir water level prediction module is used for predicting the reservoir water level based on the reservoir capacity, and the early warning module is used for sending out early warning information according to the predicted water level when the water level exceeds a water warning value.
The invention has the beneficial effects that:
(1) on the basis of forecasting the warehousing flow, the invention combines the research of the relation between the reservoir water regime data and the reservoir geographical features, fully excavates the relation between the reservoir capacity and the reservoir water level, and constructs a future reservoir water level forecasting model by using a multilayer sensor algorithm technology.
(2) The method can predict water level change data of several days in the future, has trend, has strong prediction capability of the training model, fully considers the characteristics of geographic environment and the like, trains and integrates the hidden characteristics into the prediction model, has very good fitting effect, and also has good performance on sparse data.
Drawings
Fig. 1 is a flow chart of a reservoir water level early warning method based on warehousing traffic according to the present invention.
Fig. 2 is a block diagram of the early warning system according to the present invention.
Fig. 3 is a diagram showing the effect of fitting the predicted value and the observed value of the water level of the space reservoir in embodiment 3 of the present invention.
Detailed Description
The invention is described in further detail below with reference to the figures and specific examples.
Example 1
The embodiment is a method for predicting the storage capacity of a flood season reservoir, namely a method for calculating the capacity value of the reservoir in a future time period, and comprises the following steps:
(1) the method comprises the steps that a reservoir hydrological monitoring station for measuring reservoir capacity and reservoir water level is arranged on a reservoir, historical and real-time reservoir capacity and reservoir water level data are collected and stored in a reservoir water regime database;
(2) acquiring warehousing flow in the next several days based on a known warehousing flow forecasting model (such as a hydrodynamic model in the prior art), and then transmitting the forecasted warehousing flow data to a storage capacity calculation module under the condition that the warehousing flow at the future moment is known; meanwhile, statistical analysis is carried out on the capacity data of the reservoir capacity of the historical site reservoir stored in the database, and the data are preprocessed, so that the capacity data of the reservoir on the same day are obtained and transmitted to the capacity calculation module;
(3) based on the current reservoir capacity and the warehousing flow in the next few days, the reservoir capacity calculation module is used for calculating the reservoir capacity change condition in the next few days, and the calculation method of the reservoir capacity calculation module is as follows:
wherein b is t Indicating the storage capacity of the reservoir at the time of the day, t indicating the time of the day,n is a time length; x T Representing the forecast warehousing flow on the Tth day; f. of n Representing the reservoir capacity on day n;
(4) according to the specific situation that the storage capacity calculation module can calculate the storage capacity of t +1, t +2, …, t + n days, respectively, n is set to 5 in the present embodiment.
Example 2
The embodiment is a flood season reservoir water level prediction method, which comprises the following steps:
(1) reading historical reservoir capacity and reservoir water level data from a reservoir water regime database, analyzing the data, cleaning abnormal or missing data, perfecting the data, storing the perfected data into a training file in a corresponding format, and acquiring training data from the training file, wherein the training data comprises N pieces of data, each piece of data is represented as V n ={v 1 ,v 2 N denotes the nth sample in the training data, v 1 Indicating reservoir capacity, v 2 Representing the reservoir water level, and dividing the training data into a training set and a verification set;
(2) the method comprises the steps of constructing an initialized multi-layer sensor network, wherein the multi-layer sensor network has three structures, namely an input layer, a hidden layer and an output layer, and the corresponding network input X is [ X ] 1 ,x 2 ,x 3 ,…,x d ]The corresponding network output O ═ O 1 ,o 2 ,o 3 ,…,o q ]The output of the hidden layer is H, and the weight parameter and the deviation parameter of the hidden layer are W respectively h And b h The weight and deviation parameters of the output layer are W o And b o The objective function of the network model is: o ═ X (XW) h +b h )W o +b o =XW h W o +b h W o +b o
Relu is used as an activation function of the network model, and the definition of the activation function is as follows:
ReLU(x)=max(x,0);
(3) training an initial network model by using a training set which is normalized by a linear function to obtain a prediction model of reservoir water level, verifying the performance of the model by using a normalized verification set, adjusting model parameters according to a value obtained by an evaluation function Root Mean Square Error (RMSE), and iteratively training the model in a circulating manner until the RMSE value of the prediction model is minimum, so that the optimal parameters and the model structure of the model are obtained, a hidden layer is three layers, and the number of neurons in each layer is 20;
(4) obtaining optimal model parameters and model structures according to model training, and constructing a multilayer sensor model for predicting the reservoir water level; on the basis of obtaining the capacity of the reservoir in the future time period in the embodiment 1, predicting the water level condition of the reservoir in the future days by using a reservoir water level prediction model;
(5) performing disaster situation determination according to the comparison of the predicted water level value and the warning water level value, and linking a visual platform to perform display early warning; when the reservoir water level prediction module predicts that the reservoir water level value in the next several days exceeds the warning value, immediately issuing early warning; and acquiring early warning information, and making corresponding scheduling treatment, such as opening a gate to discharge water, by combining the change trend of the water level prediction value within the next several days, so that the reservoir can bear a certain amount of flood after water discharge.
Example 3
As shown in fig. 2, the reservoir water level early warning system based on the warehousing flow comprises a data acquisition module, a data transmission module, a reservoir capacity calculation module, a reservoir water level prediction module and an early warning module, wherein the data acquisition module is used for collecting water level and reservoir capacity data measured by a hydrological monitoring station, the data transmission module is used for transmitting a measurement result to a remote server and storing the measurement result in a reservoir water situation database, the reservoir capacity calculation module is used for calculating the reservoir capacity conversion condition in the next several days, the reservoir water level prediction module is used for predicting the reservoir water level based on the reservoir capacity, and the early warning module is used for sending out early warning information according to the predicted water level when the predicted water level exceeds the water area warning value.
The simulation of the early warning system in this embodiment is executed in a hardware environment with a CPU and a memory of 16GB at a master frequency of 1.6GHZ and a software environment with python3.6, keras2.2.4 and Pycharm 2016.
The operation early warning method comprises the steps of embodiment 1 and embodiment 2.
The reservoir to be tested is a Taihe reservoir, historical water situation data of a basin of the Taihe reservoir are adopted, the historical data are 1994-01-10 to 2021-02-01, 2000-01-01 to 2021-02-01 are selected as data sets through screening, and then the data sets are segmented according to the proportion of 4:1 and are respectively used as a training set and a testing set.
FIG. 3 is a graph of the effect of fitting the predicted value and observed value of the level of the Taihe reservoir by the method of the present invention;
in this embodiment, the method proposed by the present invention is compared with the following model prediction methods, and the estimation index (RMSE) is used to measure the prediction capability of the model, and the comparison results are shown in the following table:
TABLE 1 two model prediction comparisons
As can be seen from Table 1, the prediction of the reservoir level of the Taihe river is more accurate than the prediction capability of the integrated model.
The present invention has been described in detail with reference to the embodiments, and it should be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit of the invention.
Claims (4)
1. A reservoir water level early warning method based on warehousing traffic is characterized by comprising the following steps:
s1, collecting historical and real-time reservoir capacity and reservoir water level data, transmitting the data and storing the data in a reservoir water regime database;
s2, acquiring warehousing flow in a future time period based on a known warehousing flow forecasting model, acquiring current reservoir capacity data from a reservoir water regime database, and calculating a reservoir capacity value in the future time period; the calculation method of the capacity value of the reservoir comprises the following steps:
wherein b is t The storage capacity of the reservoir at the current moment is shown, t shows the time of the current moment, and n is the time length; x T Representing the forecast warehousing flow on the Tth day; f. of n Indicating the reservoir capacity on day n;
s3, obtaining historical reservoir capacity and reservoir water level data from a database, dividing the historical reservoir capacity and the reservoir water level data into a training set and a verification set, constructing a multilayer sensor model for predicting the reservoir water level based on the training set, verifying the performance of the model by using the verification set, adjusting model parameters according to the value obtained by the Root Mean Square Error (RMSE) of an evaluation function, and circularly iterating the training model until the RMSE value predicted by the model is minimum, and obtaining the optimal parameters and the model structure of the model as a reservoir water level prediction model; the multilayer perceptron model has three structures, namely an input layer, a hidden layer and an output layer, and the corresponding network input X ═ X 1 ,x 2 ,x 3 ,…,x d ]The corresponding network output O ═ O 1 ,o 2 ,o 3 ,…,o q ]The output of the hidden layer is H, and the weight parameter and the deviation parameter of the hidden layer are W respectively h And b h The weight and deviation parameters of the output layer are W o And b o The objective function of the network model is:
O=(XW h +b h )W o +b o =XW h W o +b h W o +b o ;
s4, predicting the reservoir capacity value of the future time period obtained in the step S2 by using the reservoir water level prediction model in the step S3;
and S5, determining the disaster situation according to the comparison between the predicted reservoir water level value and the water level warning value, and thus linking the visual platform to perform early warning.
2. The reservoir water level early warning method based on warehousing traffic as claimed in claim 1, wherein n is 5.
3. The reservoir water level early warning method based on warehousing traffic as claimed in claim 1, wherein the evaluation function is as follows:
where RMSE denotes the root mean square error, a i Representing true value, p i Representing the predicted value, and m representing the number of predicted data samples.
4. A reservoir water level early warning system based on warehousing traffic for realizing the method of claim 1 is characterized by comprising a data acquisition module, a data transmission module, a reservoir capacity calculation module, a reservoir water level prediction module and an early warning module, wherein the data acquisition module is used for collecting water level and reservoir capacity data measured by a hydrological monitoring station, the data transmission module is used for transmitting a measurement result to a remote server and storing the measurement result in a reservoir water situation database, the reservoir capacity calculation module is used for calculating the reservoir capacity change condition in a future time period, the reservoir water level prediction module is used for predicting the reservoir water level based on the reservoir capacity, and the early warning module is used for sending early warning information when the predicted water level exceeds a water warning value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210207734.1A CN114611778B (en) | 2022-03-04 | 2022-03-04 | Reservoir water level early warning method and system based on warehousing flow |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210207734.1A CN114611778B (en) | 2022-03-04 | 2022-03-04 | Reservoir water level early warning method and system based on warehousing flow |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114611778A CN114611778A (en) | 2022-06-10 |
CN114611778B true CN114611778B (en) | 2022-09-06 |
Family
ID=81861877
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210207734.1A Active CN114611778B (en) | 2022-03-04 | 2022-03-04 | Reservoir water level early warning method and system based on warehousing flow |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114611778B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115330088A (en) * | 2022-10-11 | 2022-11-11 | 广东广宇科技发展有限公司 | Flood control fine prediction method for small reservoir |
CN115713165B (en) * | 2022-11-28 | 2024-01-02 | 中国长江电力股份有限公司 | Reservoir ultra-short-term water level prediction method, system and storage medium considering dynamic reservoir capacity influence |
CN116258278A (en) * | 2023-05-10 | 2023-06-13 | 青岛研博数据信息技术有限公司 | Method, system and equipment for deducing constructed water level reservoir capacity |
CN117689501A (en) * | 2024-02-03 | 2024-03-12 | 深圳市广汇源环境水务有限公司 | Reservoir flood prevention dynamic forecasting and early warning method and system platform |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104613943A (en) * | 2013-11-04 | 2015-05-13 | 中国水利水电科学研究院 | Reservoir water storage amount remote sensing and ground concurrent monitoring method |
CN104883406A (en) * | 2015-06-17 | 2015-09-02 | 山东锋士自动化系统有限公司 | Water conservancy internet of things system based on cloud computing and monitoring method thereof |
CN109492802A (en) * | 2018-10-30 | 2019-03-19 | 河海大学 | A kind of year-end level of multi-year regulating storage reservoir for timed position preferred method based on expert system |
JP2019095240A (en) * | 2017-11-20 | 2019-06-20 | 日本無線株式会社 | Water level prediction method, water level prediction program, and water level prediction device |
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 |
CN112966570A (en) * | 2021-02-07 | 2021-06-15 | 山东锋士信息技术有限公司 | Reservoir water storage capacity metering method based on satellite remote sensing and DEM data |
CN112966445A (en) * | 2021-03-15 | 2021-06-15 | 河海大学 | Reservoir flood control optimal scheduling method based on reinforcement learning model FQI |
CN113256005A (en) * | 2021-05-28 | 2021-08-13 | 国能大渡河沙坪发电有限公司 | Power station water level process prediction method and device based on neural network model |
WO2022024009A1 (en) * | 2020-07-30 | 2022-02-03 | Inttrust S.A. - Information Technology Trust | Cloud platform for underground water reservoirs |
CN114048679A (en) * | 2021-11-11 | 2022-02-15 | 国网新源控股有限公司 | Neural network-based refined monitoring method for water level of each area of reservoir |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110910004A (en) * | 2019-11-18 | 2020-03-24 | 国电湖南巫水水电开发有限公司 | Reservoir dispatching rule extraction method and system with multiple uncertainties |
-
2022
- 2022-03-04 CN CN202210207734.1A patent/CN114611778B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104613943A (en) * | 2013-11-04 | 2015-05-13 | 中国水利水电科学研究院 | Reservoir water storage amount remote sensing and ground concurrent monitoring method |
CN104883406A (en) * | 2015-06-17 | 2015-09-02 | 山东锋士自动化系统有限公司 | Water conservancy internet of things system based on cloud computing and monitoring method thereof |
JP2019095240A (en) * | 2017-11-20 | 2019-06-20 | 日本無線株式会社 | Water level prediction method, water level prediction program, and water level prediction device |
CN109492802A (en) * | 2018-10-30 | 2019-03-19 | 河海大学 | A kind of year-end level of multi-year regulating storage reservoir for timed position preferred method based on expert system |
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 |
WO2022024009A1 (en) * | 2020-07-30 | 2022-02-03 | Inttrust S.A. - Information Technology Trust | Cloud platform for underground water reservoirs |
CN112966570A (en) * | 2021-02-07 | 2021-06-15 | 山东锋士信息技术有限公司 | Reservoir water storage capacity metering method based on satellite remote sensing and DEM data |
CN112966445A (en) * | 2021-03-15 | 2021-06-15 | 河海大学 | Reservoir flood control optimal scheduling method based on reinforcement learning model FQI |
CN113256005A (en) * | 2021-05-28 | 2021-08-13 | 国能大渡河沙坪发电有限公司 | Power station water level process prediction method and device based on neural network model |
CN114048679A (en) * | 2021-11-11 | 2022-02-15 | 国网新源控股有限公司 | Neural network-based refined monitoring method for water level of each area of reservoir |
Non-Patent Citations (6)
Title |
---|
Neural network application in reservoir water level forecasting and release decision;Wan Hussain Wan Ishak 等;《International Journal of New Computer Architectures and their Applications》;20111231;第1卷(第2期);第265-274页 * |
Reservoir Level Forecasting using Neural Networks: Lake Naivasha;S.Ondimu 等;《Biosystems Engineering》;20061113;第96卷(第1期);第135-138页 * |
基于Copula函数的桃林口水库防洪风险分析;李大鸣 等;《水利水电技术》;20170320;第48卷(第03期);第158-164、170页 * |
基于LSTM模型的水库监测预警与风险评估;王茂洋 等;《水利技术监督》;20210913(第09期);第140-146、161页 * |
疏勒河中游梯级水库库容和库水位关系模型优化;郑宗倩 等;《农业工程》;20201220;第10卷(第12期);第50-56页 * |
距离度量学习法在水库静库容调洪演算中的应用;纪国良 等;《水电能源科学》;20200807;第33卷(第08期);第62-65、13页 * |
Also Published As
Publication number | Publication date |
---|---|
CN114611778A (en) | 2022-06-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN114611778B (en) | Reservoir water level early warning method and system based on warehousing flow | |
JP2007205001A (en) | Discharge forecasting apparatus | |
CN102360468B (en) | Flood forecasting system | |
CN102682573A (en) | Time sequence analysis-based storm surge disaster early warning system | |
CN109886456B (en) | Debris flow prediction method based on PCA and mixed kernel function LSSVR | |
CN105069537A (en) | Constructing method of combined air quality forecasting model | |
CN107423857B (en) | A kind of long-term water multiple target joint probability Forecasting Methodology in region | |
CN113962465A (en) | Precipitation forecasting method, equipment, device and storage medium | |
CN114399193A (en) | Method for detecting runoff events in data-deficient areas based on depth time sequence point process and LSTM | |
CN117556197B (en) | Typhoon vortex initialization method based on artificial intelligence | |
CN114357670A (en) | Power distribution network power consumption data abnormity early warning method based on BLS and self-encoder | |
CN113988655A (en) | Power transmission line running state evaluation method considering multiple meteorological factors | |
Rohaimi et al. | 3 Hours ahead of time flood water level prediction using NNARX structure: Case study pahang | |
Chen et al. | Rainfall forecasting in sub-Sahara Africa-Ghana using LSTM deep learning approach | |
Lu et al. | Uncertainty quantification of machine learning models to improve streamflow prediction under changing climate and environmental conditions | |
Lin et al. | Hurricane freshwater flood risk assessment model for residential buildings in southeast US coastal states considering climate change | |
CN114935759A (en) | Wave field missing value filling method and system based on high-frequency ground wave radar observation | |
CN105023060A (en) | Production qualified rate prediction method by fusing degradation information of manufacturing equipment | |
CN115829150A (en) | Accumulated water prediction system | |
Sene et al. | Hydrological forecasting | |
CN113487069B (en) | Regional flood disaster risk assessment method based on GRACE daily degradation scale and novel DWSDI index | |
Chinforoush et al. | A novel method for forecasting surface wind speed using wind-direction based on hierarchical markov model | |
CN115049013A (en) | Short-term rainfall early warning model fusion method combining linearity and SVM | |
CN113011657A (en) | Method and device for predicting typhoon water level, electronic equipment and storage medium | |
CN113065700A (en) | Short-time heavy rainfall forecasting method based on significance and sensitivity factor analysis method |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CB03 | Change of inventor or designer information |
Inventor after: Sun Qiyu Inventor after: Lu Ke Inventor after: Yu Jinzhong Inventor after: Shang Lina Inventor before: Sun Qiyu Inventor before: Lu Ke Inventor before: Yu Jinzhong Inventor before: Shang Lina |
|
CB03 | Change of inventor or designer information |