CN109447336B - Optimized control method for water level between upstream reservoir and reverse regulation reservoir dam thereof - Google Patents
Optimized control method for water level between upstream reservoir and reverse regulation reservoir dam thereof Download PDFInfo
- Publication number
- CN109447336B CN109447336B CN201811228536.3A CN201811228536A CN109447336B CN 109447336 B CN109447336 B CN 109447336B CN 201811228536 A CN201811228536 A CN 201811228536A CN 109447336 B CN109447336 B CN 109447336B
- Authority
- CN
- China
- Prior art keywords
- water level
- reservoir
- dam
- upstream
- interval
- 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
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 116
- 238000011144 upstream manufacturing Methods 0.000 title claims abstract description 71
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000013528 artificial neural network Methods 0.000 claims abstract description 22
- 238000012549 training Methods 0.000 claims description 9
- 238000003062 neural network model Methods 0.000 claims description 8
- 238000003064 k means clustering Methods 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 4
- 230000001105 regulatory effect Effects 0.000 claims description 4
- 230000002787 reinforcement Effects 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 abstract description 8
- 238000010248 power generation Methods 0.000 abstract description 4
- 238000005457 optimization Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 10
- 238000004590 computer program Methods 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 4
- 238000007418 data mining Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000005192 partition Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000003860 storage Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000007621 cluster analysis Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000000638 solvent extraction Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Primary Health Care (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Feedback Control In General (AREA)
Abstract
The invention discloses an optimization control method for water level between an upstream reservoir and a counter-regulation reservoir dam thereof, which is characterized in that a plurality of neural networks are trained based on historical operation data, the working condition matching closest to the historical working condition is searched according to the current working condition, the neural network corresponding to the working condition matching is selected, and the prediction of the water level after the upstream reservoir is loaded on the dam and the water level before the counter-regulation reservoir dam is realized; and on the basis of forecasting the water level behind the upper reservoir dam and the water level in front of the reverse regulation reservoir dam, performing optimal control trial calculation on the water level between the cascade reservoirs by taking the flow of the upper reservoir dam as a variable, and realizing the maximum total output of the cascade. The cascade hydropower station cascade power generation control method fully utilizes the historical operation data of the cascade hydropower station, solves the complex problem of water level control between the reverse regulation reservoir and the upper reservoir dam, and can provide a solution for optimizing and controlling the water level between the dams to provide cascade power generation benefits.
Description
Technical Field
The invention relates to the technical field of water affair calculation, in particular to an optimal control method for water level between an upstream reservoir and a counter-regulation reservoir dam thereof.
Background
The relationship between the front water level of the counter regulation reservoir dam and the outlet flow and tail water of the superior reservoir in the cascade reservoir is a complex hydraulics problem essentially. To clear up the relationship between the three, theoretically, the modeling calculation needs to be carried out by adopting methods such as a one-dimensional or two-dimensional hydraulic model and the like on the hydraulic characteristics of the riverway between the cascade reservoirs. However, in production practice, the section data and the like of the river channel mostly lack sufficient precision, so the calculation result of the hydraulic model often lacks practicability, more, the artificial experience is adopted, rough quantitative estimation is given, and reservoir scheduling decision is restricted.
Disclosure of Invention
The invention aims to overcome the defects in the prior art, provides an optimal control method for the water level between an upstream reservoir and a counter-regulation reservoir dam thereof, and solves the problem that the calculation result of a hydraulic model is often lack of practicability.
In order to solve the technical problem, the invention provides an optimal control method for the water level between an upstream reservoir and a reverse regulation reservoir dam thereof, which is characterized by comprising the following steps of:
s1, extracting historical data of four types of influence factors including the outlet flow of the upstream reservoir, the post-dam water level of the upstream reservoir, the interval flow and the pre-dam water level of the back-regulation reservoir, and forming the historical data of each influence factor in the same time period into a historical data set of the time period;
s2, clustering the historical data sets of each time interval according to the water level interval division of the dam front water level of the counter regulation reservoir so as to distribute the historical data sets to corresponding water level intervals;
s3, constructing the same neural network model for each water level interval, inputting the neural network model into the reservoir outlet flow of the upstream reservoir at the beginning of the time interval, the water level of the upstream reservoir at the beginning of the time interval, the interval flow and the water level of the upstream reservoir at the beginning of the time interval, outputting the water level of the upstream reservoir at the end of the time interval and the water level of the upstream reservoir at the end of the time interval, and training the neural network model belonging to the water level interval by using historical data in each water level interval;
s4, obtaining the outlet flow of the upstream reservoir at the beginning of the time interval, the dam front water level of the upstream reservoir, the interval flow and the dam front water level of the back regulation reservoir, determining the water level interval to which the upstream reservoir belongs, pre-measuring the back water level of the upstream reservoir at the end of the time interval and the dam front water level of the back regulation reservoir at the end of the time interval through a neural network model of the water level interval, and calculating the total output of the cascade reservoir at the time interval; and continuously adjusting the outlet flow of the upstream reservoir, and repeatedly performing neural network prediction until the total output of the cascade reservoir in the current time period is not increased, wherein the corresponding upstream reservoir dam rear water level and the reverse adjustment reservoir dam front water level are the optimal dam-to-dam control water level.
Preferably, the historical data sets of the respective time periods are normalized before clustering the historical data sets of the respective time periods.
Preferably, the normalization method converts each type of data into standard data between 0 and 1 for maximum-minimum normalization.
Preferably, the clustering method is K-means clustering.
Preferably, when clustering the historical data sets of each time period, the similarity between the historical data sets of each time period is measured by the euclidean distance.
Preferably, the optimal inter-dam control water level is compared with actual values of upstream reservoir dam back water level and back regulation reservoir dam front water level at corresponding time intervals, the deviation is recorded, and the prediction network is finely adjusted by a reinforcement learning method on the basis of the deviation.
Compared with the prior art, the invention has the following beneficial effects:
1) a clustering analysis method in data mining is adopted to provide proper training samples for neural network training;
2) the method is independent of fine river section data, can establish the flow and water level relation between the upstream reservoir and the back regulation reservoir according to historical operation data, can calculate, and is suitable for water level prediction and control between any cascade reservoirs with the back regulation reservoir;
3) by adopting the reinforcement learning method, the neural network can be retrained according to the deviation between the predicted value and the measured value, the prediction precision is continuously improved, and the self-learning capability is realized.
Drawings
FIG. 1 is a schematic flow diagram of the process of the present invention;
FIG. 2 is a single neural network structure for dam water level prediction;
FIG. 3 is a flow chart of neural network updating in the method of the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
The invention relates to an optimal control method for the water level between an upstream reservoir and a counter-regulation reservoir dam thereof, which comprises the following processes:
and step S1, extracting historical data of the influence factors influencing the upstream reservoir and the counter regulating reservoir water level, and forming the historical data of each influence factor in the same time interval into a historical data set of the time interval.
And extracting historical data of influence factors related to the upstream reservoir and the counter-regulated reservoir water level from the reservoir scheduling database. In the embodiment of the invention, the following 4 types of historical data need to be extracted: 1) the flow of the upstream reservoir out of the reservoir, 2) the water level of the upstream reservoir behind the dam, 3) the interval flow, and 4) the water level of the reservoir before the dam is reversely adjusted.
The data volume of the historical data is related to the time granularity of the data collected in the reservoir scheduling database, generally 5 minutes, 15 minutes or 1 hour, and the time granularity of each reservoir may be different without influencing the implementation of the method disclosed by the invention.
The 4 types of basic data all need to unify the time interval length, and if the 4 types of basic data are different, an interpolation method needs to be adopted to unify the data format with the minimum time granularity. Then the upstream reservoir outlet flow, the upstream reservoir dam rear water level, the interval flow and the reverse regulation reservoir dam corresponding to the same time intervalAnd (5) the former water level is spliced into a data set, so that a historical data set D with a uniform format is constructed. If in a certain time t, the delivery flow of the upstream reservoir is Q1tThe upstream reservoir dam rear water level is Z1tAnd the interval flow rate is Q2tAnd the front water level of the reservoir dam is regulated to be Z2tThen the historical data set for that period is denoted as Dt=（Q1t,Z1t,Q2t,Z2t) And the rest periods are analogized, the historical data set D = (D) of n periods1,D2,D3…Dn）。
And step S2, dividing the dam front water level of the back regulation reservoir into a plurality of regions, and clustering and distributing the historical data sets of each time period to each water level region.
And (2) performing preliminary analysis on the historical data set D sorted in the step 1) by adopting a cluster analysis method in a data mining method, wherein the preliminary analysis aims at classifying similar scheduling conditions in the historical data and improving the pertinence of subsequent calculation, and the adopted cluster analysis method is K-means clustering.
The K-means clustering principle is as follows: given a set of n objects, the partitioning method is to construct k partitions of the data, where each partition represents a family, and given the number of k partitions to be constructed, the partitioning method first creates an initial partition, and then relocates the samples using an iterative relocation technique until the condition is met.
The method comprises the following specific steps:
a) cleaning abnormal data in the historical data set, wherein the abnormal data comprises negative values, data obviously exceeding a normal range and the like;
b) normalizing the washed historical data set, namely converting various data into standard data between 0 and 1 by adopting maximum-minimum standardization;
c) measuring the similarity between the historical data sets Dt in each time period by Euclidean distance;
d) dividing the front water level of the counter regulation reservoir into a plurality of sections according to requirements, carrying out sample clustering on historical data sets in each time section by using a K-means clustering algorithm, and distributing the historical data to each divided water level section to be used as the training sample data of the neural network in the future.
And step S3, constructing a corresponding neural network for each water level interval, and training the neural network based on the historical data set in each water level interval.
And searching potential rules in historical data by adopting an artificial intelligence method, and improving the prediction level by accumulating the actually measured data.
The invention adopts an artificial neural network algorithm to search the height nonlinear relation among the outlet flow of the upstream reservoir, the water level behind the dam of the upstream reservoir, the interval flow and the water level in front of the back-regulating reservoir dam, and makes prediction.
And (4) respectively training the neural networks corresponding to the water level intervals by using the clustering analysis result obtained in the last step as a training sample, namely training the neural networks according to the water level intervals, wherein the neural networks are in parallel relation.
The neural network structure in each water level interval is the same. The schematic diagram of the input and output of the neural network structure is shown in fig. 2, and the input layer is 4 nodes: the reservoir outlet flow of the initial upstream reservoir in the time interval, the water level behind the dam of the initial upstream reservoir in the time interval, the interval flow and the water level before the dam of the initial upstream reservoir in the time interval are adjusted. The output layer is 2 nodes: and the upstream reservoir dam rear water level at the end of the time interval and the reservoir dam front water level at the end of the time interval are reversely adjusted. The number of hidden layer nodes is 2 times the number of input layer nodes.
And step S4, performing optimal control trial calculation on the water level between the cascade reservoirs by taking the flow of the reservoir as a variable, and realizing the maximum total output of the cascade.
Under the background discussed by the invention, the main purpose of the water level optimization control between the upstream reservoir and the reverse regulation reservoir is to obtain larger step power generation benefit, and the method comprises the following steps:
1) acquiring an upstream reservoir dam front water level Zs at the beginning of the time interval, an upstream reservoir dam rear water level Ze at the beginning of the time interval, interval flow Q at the time interval and an initial reverse regulation reservoir dam front water level Zd at the time interval from reservoir monitoring data;
2) selecting a prediction neural network which is most matched with the current scheduling working condition;
the working condition matching mode is as follows:
a) acquiring the reservoir outlet flow of the initial upstream reservoir in time interval, the post-dam water level of the initial upstream reservoir in time interval, the interval flow and the pre-dam water level of the initial reverse regulation reservoir in time interval from the reservoir monitoring data to form a current cascade reservoir working condition data set, wherein the forming mode is the same as that in the step S1 and is used as a judgment parameter of the cascade reservoir working condition;
b) converting various data into standard data between 0 and 1 by adopting min-max standardization;
c) respectively calculating the distance between the current cascade reservoir working condition data set and the center of each cluster data set in the data mining result of the step S2, and finding out the data set closest to the current working condition distance as a matching data set by Euclidean distance measurement;
d) matching a corresponding prediction neural network according to the water level interval where the matching data set is located;
3) assuming an upstream reservoir outlet flow Qt, taking the upstream reservoir dam rear water level Ze at the beginning of the time interval, the interval flow Q at the time interval and the downstream reservoir dam front water level Zd at the beginning of the time interval in the step 1) as input, and calculating the upstream reservoir dam rear water level Z1 and the reverse regulation reservoir dam front water level Z2 at the end of the time interval by using the matched neural network obtained in the last step;
4) based on the basic information of Qt, Zs, Ze, Zd, Z1 and the like, calculating the output N1 of the upstream reservoir in the current time period according to the hydroelectric power generation principle, and calculating the output N2 of the back regulation reservoir by utilizing a relation curve of the dam front water level-output of the back regulation reservoir based on Z2; calculating the total output N1+ N2 of the step reservoir;
5) returning to the step 3), adjusting the delivery flow of the upstream reservoir according to a certain step length, performing trial calculation and optimization according to a dichotomy until the total output of the cascade reservoir in the period is not increased, and the delivery flow of the upstream reservoir at the moment is Qopt. And the corresponding upstream reservoir dam rear water level and the reverse regulation reservoir dam front water level are the optimal inter-dam control water level.
Step S5, automatic updating of the neural network.
And after the step S4 is finished, recording the time interval corresponding to the optimal dam-to-dam control water level, the upstream dam rear water level, the counter-regulation reservoir dam front water level value and the adopted prediction neural network. And comparing the actual values of the upstream water level behind the reservoir dam and the upstream water level in front of the back-regulating reservoir dam in the corresponding time period, recording the deviation of the actual values, corresponding the deviation to the input condition in the prediction according to the time period, and further finely adjusting the prediction network by using a reinforcement learning method on the basis of the deviation, thereby achieving the purpose of improving the effect of the prediction network.
The method utilizes a data mining and artificial intelligence method to obtain the potential law of the association between the outlet flow of the upstream reservoir, the water level behind the dam of the upstream reservoir and the water level in front of the counter regulation reservoir from a large amount of historical operating data, has wide applicability, can be supported by certain historical operating data, and can continuously improve the accuracy of prediction along with the accumulation of the operating data.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.
Claims (6)
1. An optimal control method for water level between an upstream reservoir and a counter-regulation reservoir dam thereof is characterized by comprising the following steps:
s1, extracting historical data of four types of influence factors including the outlet flow of the upstream reservoir, the post-dam water level of the upstream reservoir, the interval flow and the pre-dam water level of the back-regulation reservoir, and forming the historical data of each influence factor in the same time period into a historical data set of the time period;
s2, clustering the historical data sets of each time interval according to the water level interval division of the dam front water level of the counter regulation reservoir so as to distribute the historical data sets to corresponding water level intervals;
s3, constructing the same neural network model for each water level interval, inputting the neural network model into the reservoir outlet flow of the upstream reservoir at the beginning of the time interval, the water level of the upstream reservoir at the beginning of the time interval, the interval flow and the water level of the upstream reservoir at the beginning of the time interval, outputting the water level of the upstream reservoir at the end of the time interval and the water level of the upstream reservoir at the end of the time interval, and training the neural network model belonging to the water level interval by using historical data in each water level interval;
s4, obtaining the outlet flow of the upstream reservoir at the beginning of the time interval, the dam front water level of the upstream reservoir, the interval flow and the dam front water level of the back regulation reservoir, determining the water level interval to which the upstream reservoir belongs, pre-measuring the back water level of the upstream reservoir at the end of the time interval and the dam front water level of the back regulation reservoir at the end of the time interval through a neural network model of the water level interval, and calculating the total output of the cascade reservoir at the time interval; and continuously adjusting the outlet flow of the upstream reservoir, and repeatedly performing neural network prediction until the total output of the cascade reservoir in the current time period is not increased, wherein the corresponding upstream reservoir dam rear water level and the reverse adjustment reservoir dam front water level are the optimal dam-to-dam control water level.
2. The method as claimed in claim 1, wherein the historical data sets of each time period are normalized before clustering the historical data sets of each time period.
3. The method as claimed in claim 2, wherein the normalization means converts each type of data into standard data between 0 and 1 for maximum-minimum normalization.
4. The optimal control method for the water level between the upstream reservoir and the counter-regulated reservoir dam of claim 1, wherein the clustering method is K-means clustering.
5. The method as claimed in claim 1, wherein the similarity between the historical data sets of the time intervals is measured in terms of Euclidean distance when clustering the historical data sets of the time intervals.
6. The method as claimed in claim 1, wherein the optimal inter-dam control water level is compared with the actual values of the upstream post-dam water level and the upstream pre-dam water level of the back-regulation reservoir at the corresponding time interval, and the deviation is recorded, and the prediction network is finely adjusted by a reinforcement learning method based on the deviation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811228536.3A CN109447336B (en) | 2018-10-22 | 2018-10-22 | Optimized control method for water level between upstream reservoir and reverse regulation reservoir dam thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811228536.3A CN109447336B (en) | 2018-10-22 | 2018-10-22 | Optimized control method for water level between upstream reservoir and reverse regulation reservoir dam thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109447336A CN109447336A (en) | 2019-03-08 |
| CN109447336B true CN109447336B (en) | 2021-11-05 |
Family
ID=65548363
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811228536.3A Active CN109447336B (en) | 2018-10-22 | 2018-10-22 | Optimized control method for water level between upstream reservoir and reverse regulation reservoir dam thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109447336B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110930016A (en) * | 2019-11-19 | 2020-03-27 | 三峡大学 | Cascade reservoir random optimization scheduling method based on deep Q learning |
| CN115130679A (en) * | 2022-02-11 | 2022-09-30 | 希望知舟技术(深圳)有限公司 | Data management and control method, related device and medium program product |
| CN115712800B (en) * | 2022-11-24 | 2023-07-28 | 国能大渡河流域水电开发有限公司 | Reservoir water level fluctuation treatment method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103971198A (en) * | 2014-04-02 | 2014-08-06 | 四川大学 | System for distributing loads among plants of cascade hydropower stations in real time and implementation method of system |
| CN106202978A (en) * | 2016-08-18 | 2016-12-07 | 黄河勘测规划设计有限公司 | Fully-loaded stream multiple purpose reservoir flood regulation by level and stages optimization method and system thereof |
| JP2017091124A (en) * | 2015-11-09 | 2017-05-25 | 三菱電機株式会社 | Monitoring controller of water-supply-facilities plant and method for managing water level of distribution reservoir using monitoring controller |
| CN107423258A (en) * | 2017-06-30 | 2017-12-01 | 华电电力科学研究院 | Energy utilization improvement rate innovatory algorithm and step power station scheduling benefit evaluation system |
| CN108321806A (en) * | 2018-03-09 | 2018-07-24 | 贵州电网有限责任公司 | The multi-period tide optimization method of cascade hydropower water level control based on Real-time Feedback |
-
2018
- 2018-10-22 CN CN201811228536.3A patent/CN109447336B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103971198A (en) * | 2014-04-02 | 2014-08-06 | 四川大学 | System for distributing loads among plants of cascade hydropower stations in real time and implementation method of system |
| JP2017091124A (en) * | 2015-11-09 | 2017-05-25 | 三菱電機株式会社 | Monitoring controller of water-supply-facilities plant and method for managing water level of distribution reservoir using monitoring controller |
| CN106202978A (en) * | 2016-08-18 | 2016-12-07 | 黄河勘测规划设计有限公司 | Fully-loaded stream multiple purpose reservoir flood regulation by level and stages optimization method and system thereof |
| CN107423258A (en) * | 2017-06-30 | 2017-12-01 | 华电电力科学研究院 | Energy utilization improvement rate innovatory algorithm and step power station scheduling benefit evaluation system |
| CN108321806A (en) * | 2018-03-09 | 2018-07-24 | 贵州电网有限责任公司 | The multi-period tide optimization method of cascade hydropower water level control based on Real-time Feedback |
Non-Patent Citations (1)
| Title |
|---|
| 中小型电站水库日常发电调度的优化研究;梁汉华;《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》;20050615;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109447336A (en) | 2019-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108846517B (en) | Integration method for predicating quantile probabilistic short-term power load | |
| CN106251625B (en) | Three-dimensional urban road network global state prediction technique under big data environment | |
| CN109447336B (en) | Optimized control method for water level between upstream reservoir and reverse regulation reservoir dam thereof | |
| CN108399748B (en) | Road travel time prediction method based on random forest and clustering algorithm | |
| CN111709134B (en) | Multi-water-source cross-basin scheduling method and device based on gate pump station group control | |
| CN110717535B (en) | Automatic modeling method and system based on data analysis processing system | |
| CN113096388B (en) | Short-term traffic flow prediction method based on gradient lifting decision tree | |
| CN109615124B (en) | SCADA master station load prediction method based on deep learning | |
| CN109800898A (en) | A kind of intelligence short-term load forecasting method and system | |
| CN103745273A (en) | Semiconductor fabrication process multi-performance prediction method | |
| CN109670650A (en) | The method for solving of Cascade Reservoirs scheduling model based on multi-objective optimization algorithm | |
| CN104865827B (en) | Oil pumping unit oil extraction optimization method based on multi-working-condition model | |
| CN104992244A (en) | Airport freight traffic prediction analysis method based on SARIMA and RBF neural network integration combination model | |
| CN108985577B (en) | Reservoir group real-time flood control dispatching significant reservoir intelligent identification method based on inference machine | |
| CN112016723B (en) | Time granularity adjustable high-frequency power grid load prediction method | |
| CN110163429A (en) | A kind of short-term load forecasting method based on similar day optimal screening | |
| CN112987666A (en) | Power plant unit operation optimization regulation and control method and system | |
| CN111525587B (en) | Reactive load situation-based power grid reactive voltage control method and system | |
| CN101808339A (en) | Telephone traffic subdistrict self-adaptive classification method applying K-MEANS and prior knowledge | |
| CN104538993B (en) | A kind of Hydropower Stations automatic power generation control method | |
| CN113255986A (en) | Multi-step daily runoff forecasting method based on meteorological information and deep learning algorithm | |
| CN112163723B (en) | Hydropower station medium-long-term runoff prediction method, medium and equipment based on scene division | |
| CN111882114B (en) | Short-time traffic flow prediction model construction method and prediction method | |
| CN113344288A (en) | Method and device for predicting water level of cascade hydropower station group and computer readable storage medium | |
| CN108154003B (en) | Blasting vibration prediction method based on Spark gene expression optimization |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: Sichuan city of Chengdu province Shu 610094 West Road No. 366 Applicant after: State Grid Sichuan Electric Power Corporation Applicant after: NARI Group Co. Ltd. Address before: 211106, No. 19, good faith Road, Jiangning District, Jiangsu, Nanjing Applicant before: NARI Group Co. Ltd. Applicant before: State Grid Sichuan Electric Power Corporation |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |