CN211628271U - Cascade hydropower station group combined dispatching device based on machine learning - Google Patents
Cascade hydropower station group combined dispatching device based on machine learning Download PDFInfo
- Publication number
- CN211628271U CN211628271U CN202020613701.3U CN202020613701U CN211628271U CN 211628271 U CN211628271 U CN 211628271U CN 202020613701 U CN202020613701 U CN 202020613701U CN 211628271 U CN211628271 U CN 211628271U
- Authority
- CN
- China
- Prior art keywords
- hydropower station
- control unit
- cascade
- station group
- machine learning
- 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
-
- 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 utility model relates to a step hydropower station crowd combined dispatching device based on machine learning to the effect of full play historical optimization dispatch law improves the dispatch level and the comprehensive benefit of step hydropower station crowd. The device comprises a working condition acquisition sensor, a data acquisition module and a data processing module, wherein the working condition acquisition sensor is used for acquiring real-time working condition data of each hydropower station of the cascade; the forecasting and collecting terminal is used for collecting medium and long term runoff forecasting of each reservoir of the cascade; the main control unit is connected with the working condition acquisition sensor and the forecast acquisition terminal and is used for generating a cascade hydropower station group scheduling scheme; the mobile control unit is connected with the main control unit and used for checking the scheduling scheme of the cascade hydropower station group and inputting manual intervention information of the scheduling scheme; the equipment control unit is connected with the main control unit and is used for automatically controlling the hydroelectric generating sets, the flood discharge gates, the water supply gates and the ecological management gates of all the cascade hydropower stations according to the scheduling scheme of the cascade hydropower station group; the communication management unit is connected with each module and used for realizing remote signal exchange among the modules and automatically generating logs.
Description
Technical Field
The utility model relates to a step hydropower station crowd combined dispatching device based on machine learning. Belongs to the application device in the technical field of hydropower station dispatching.
Background
The cascade hydropower station group combined optimization scheduling is implemented, hydrological compensation, water conservancy compensation and electric power compensation among reservoirs can be performed, the overall potential of the cascade is fully excavated on the premise that the safety risk of engineering and downstream protection objects is not improved, and the comprehensive benefit of the cascade is improved.
The medium-and-long-term deterministic combined optimization scheduling can theoretically realize optimal overall cascade benefit, but depends too much on medium-and-long-term runoff forecasting precision, so that the practical application is limited. The hidden random optimization scheduling provides another way, a rule containing the joint optimization scheduling is extracted from a long series historical optimization simulation result, and the dependence on the medium and long term prediction accuracy can be effectively reduced.
The traditional hidden random scheduling method includes a scheduling graph and the like, which has clear logic, is easy to operate, but is not flexible. The machine learning technology has the characteristics of flexible structure, strong nonlinear mapping capability and the like, and is particularly suitable for the combined dispatching of the cascade hydropower station group.
Disclosure of Invention
The to-be-solved technical problem of the utility model is: aiming at the existing problems, the cascade hydropower station group joint scheduling decision device based on machine learning is provided to fully play the role of a history optimization scheduling rule and improve the scheduling level and the comprehensive benefit of the cascade hydropower station group.
The utility model adopts the technical proposal that: the utility model provides a step hydropower station crowd combined dispatching device based on machine learning which characterized in that: the system comprises a work condition acquisition sensor, a forecast acquisition terminal, a main control unit, a mobile control unit, an equipment control unit, a communication management unit and a power supply management unit;
the working condition acquisition sensor is used for acquiring real-time working condition data of each hydropower station of the cascade;
the forecasting and collecting terminal is used for collecting medium and long term runoff forecasting of each reservoir of the cascade;
the main control unit is connected with the working condition acquisition sensor and the forecast acquisition terminal and is used for generating a cascade hydropower station group scheduling scheme;
the mobile control unit is connected with the main control unit and used for checking a scheduling scheme of the cascade hydropower station group and inputting manual intervention information of the scheduling scheme;
the equipment control unit is connected with the main control unit and is used for automatically controlling the hydroelectric generating sets, the flood discharge gates, the water supply gates and the ecological pipe gates of all the cascade hydropower stations according to the scheduling scheme of the cascade hydropower station group;
and the communication management unit is connected with each module and used for realizing remote signal exchange among the modules and automatically generating logs.
The work condition acquisition sensor comprises: the device is arranged in all hydropower stations of the cascade, and each hydropower station comprises a water turbine guide vane opening sensor, a flood discharge gate opening sensor, a dam front water level sensor, a water supply pipe flowmeter and an ecological discharge pipe flowmeter.
The forecast acquisition terminal: the method comprises a third-party hydrological forecast access terminal and a manual entry terminal.
The main control unit is a cloud server and is internally provided with a cascade hydropower station group joint dispatching model containing a machine learning model.
The movement control unit: being a mobile phone or a tablet or a combination of both.
The device manipulation unit: the system comprises a hydroelectric generating set control facility, a flood discharge gate control facility, a water supply gate control facility and an ecological gate control facility of each hydropower station in the cascade.
The utility model has the advantages that: the utility model discloses simple structure, preparation convenience, cost are lower, the utility model discloses utilize the non-linear mapping ability strong, to the machine learning technique that hydropower station dispatch rule generalization ability is strong, based on step hydropower station crowd real-time perception information, combine historical information and middle stage hydrology forecast information, rely on the experience of scheduling technical staff, implement the joint optimization scheduling of step hydropower station scientifically, rationally, intelligently.
Drawings
Fig. 1 is a schematic structural diagram of the embodiment.
Detailed Description
As shown in fig. 1, the present embodiment is a stair hydropower station group combined dispatching device based on machine learning, and the device includes a work condition acquisition sensor 3, a forecast acquisition terminal 2, a main control unit 1, a mobile control unit 5, an equipment control unit 4, a communication management unit, and a power management unit.
The condition of a worker gathers the sensor and installs in each hydropower station of step in this embodiment, and every hydropower station all includes hydraulic turbine stator opening sensor, flood discharge gate opening sensor, dam front water level sensor, delivery pipe flowmeter, ecological discharge pipe flowmeter, installs in dam, flood discharge gate, ecological gate, water supply gate and the generating set of all step hydropower stations, gathers real-time water level, flood discharge flow, ecological flow, water supply flow, the current generation volume data of each hydropower station.
The forecast acquisition terminals in the embodiment are provided with one or more than one, and comprise a third-party hydrological forecast access terminal and a manual entry terminal, and are used for acquiring the medium-term and long-term runoff forecast of each reservoir of the cascade.
In this embodiment, the master control unit 1 is a cloud server, is provided with a cascade hydropower station group joint scheduling model 101 including a machine learning model, is connected with the working condition acquisition sensor and the forecast acquisition terminal 2, and is used for generating a cascade hydropower station group scheduling scheme, and the scheduling model is obtained by training related data such as medium-long term joint optimization scheduling calculation results of past cascade hydropower stations, dynamic data of each reservoir and each power station at that time, and medium-long term runoff numerical forecast of each reservoir.
In this embodiment, the mobile control unit 5 is a mobile phone or a tablet or a combination of the two, is connected to the main control unit 1, and is configured to check a scheduling scheme of the cascade hydropower station group and input manual intervention information for the scheduling scheme.
In this embodiment, the device control unit 4 is connected to the main control unit 1, and is configured to automatically control the flow discharge of the hydroelectric generating sets, the flood discharge gates, the water supply gates, and the ecological pipe gates of the cascade hydropower stations according to a scheduling scheme of the cascade hydropower station group, including the hydroelectric generating set control facilities, the flood discharge gate control facilities, the water supply gate control facilities, and the ecological gate control facilities of the cascade hydropower stations.
In this embodiment, the communication management unit is connected to each module, and is configured to implement remote signal exchange between the modules and automatically generate a log.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (6)
1. The utility model provides a step hydropower station crowd combined dispatching device based on machine learning which characterized in that: the system comprises a work condition acquisition sensor (3), a forecast acquisition terminal (2), a main control unit (1), a mobile control unit (5), an equipment control unit (4), a communication management unit and a power management unit;
the working condition acquisition sensor (3) is used for acquiring real-time working condition data of each hydropower station of the cascade;
the forecast acquisition terminal (2) is used for acquiring the medium-long term runoff forecast of each reservoir of the cascade;
the main control unit (1) is connected with the working condition acquisition sensor (3) and the forecast acquisition terminal (2) and is used for generating a cascade hydropower station group scheduling scheme;
the mobile control unit (5) is connected with the main control unit (1) and is used for checking the scheduling scheme of the cascade hydropower station group and inputting manual intervention information of the scheduling scheme;
the equipment control unit (4) is connected with the main control unit (1) and is used for automatically controlling the hydroelectric generating sets, the flood discharge gates, the water supply gates and the ecological management gates of all the hydropower stations of the cascade according to the scheduling scheme of the cascade hydropower station group;
and the communication management unit is connected with each module and used for realizing remote signal exchange among the modules and automatically generating logs.
2. The machine learning based step hydropower station group combined dispatching device of claim 1, wherein: the work condition acquisition sensor comprises: the device is arranged in all hydropower stations of the cascade, and each hydropower station comprises a water turbine guide vane opening sensor, a flood discharge gate opening sensor, a dam front water level sensor, a water supply pipe flowmeter and an ecological discharge pipe flowmeter.
3. The machine learning based step hydropower station group combined dispatching device of claim 1, wherein: the forecast acquisition terminal (2): the method comprises a third-party hydrological forecast access terminal and a manual entry terminal.
4. The machine learning based step hydropower station group combined dispatching device of claim 1, wherein: the main control unit (1) is a cloud server, and a cascade hydropower station group joint scheduling model (101) containing a machine learning model is arranged in the main control unit.
5. The machine learning based step hydropower station group combined dispatching device of claim 1, wherein: the movement control unit (5): being a mobile phone or a tablet or a combination of both.
6. The machine learning based step hydropower station group combined dispatching device of claim 1, wherein: the device control unit (4): the system comprises a hydroelectric generating set control facility, a flood discharge gate control facility, a water supply gate control facility and an ecological gate control facility of each hydropower station in the cascade.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202020613701.3U CN211628271U (en) | 2020-04-22 | 2020-04-22 | Cascade hydropower station group combined dispatching device based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202020613701.3U CN211628271U (en) | 2020-04-22 | 2020-04-22 | Cascade hydropower station group combined dispatching device based on machine learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN211628271U true CN211628271U (en) | 2020-10-02 |
Family
ID=72622448
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202020613701.3U Active CN211628271U (en) | 2020-04-22 | 2020-04-22 | Cascade hydropower station group combined dispatching device based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN211628271U (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116011733A (en) * | 2022-12-08 | 2023-04-25 | 河海大学 | Multi-scale cooperative control intelligent scheduling method and system for cascade hydropower station group |
-
2020
- 2020-04-22 CN CN202020613701.3U patent/CN211628271U/en active Active
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116011733A (en) * | 2022-12-08 | 2023-04-25 | 河海大学 | Multi-scale cooperative control intelligent scheduling method and system for cascade hydropower station group |
| CN116011733B (en) * | 2022-12-08 | 2023-11-28 | 河海大学 | Multi-scale cooperative control intelligent scheduling method and system for cascade hydropower station group |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhang et al. | Optimal sizing of the grid-connected hybrid system integrating hydropower, photovoltaic, and wind considering cascade reservoir connection and photovoltaic-wind complementarity | |
| Su et al. | Optimization model for long-distance integrated transmission of wind farms and pumped-storage hydropower plants | |
| CN110991687B (en) | Water resource scheduling optimization method based on empirical model | |
| CN104458316B (en) | Overall physical model test platform for transient process of hydropower station | |
| CN101705671A (en) | Yellow River upstream cascade hydroelectric station operation design and optimized dispatching method as well as equipment | |
| CN103714426A (en) | Integrated scheduling system for small and medium radial flow type hydropower station group | |
| CN105243502A (en) | Hydropower station scheduling risk assessment method and system based on runoff interval prediction | |
| CN112101818B (en) | Sponge city flood optimal scheduling method suitable for complex hydraulic connection | |
| CN113489003B (en) | Source network coordination planning method considering wind-light-water integrated complementary operation | |
| CN211628271U (en) | Cascade hydropower station group combined dispatching device based on machine learning | |
| CN104200289A (en) | Distributed photovoltaic installed capacity prediction method based on investment return rate | |
| Kumar et al. | Data-driven internet of things and cloud computing enabled hydropower plant monitoring system | |
| Hamann et al. | Real-time optimization of a hydropower cascade using a linear modeling approach | |
| Zhang et al. | Assessing the integration potential of new energy in river basin clean energy corridors considering energy-power coupled complementary operation modes | |
| Lerede et al. | Might future electricity generation suffice to meet the global demand? | |
| CN110570628A (en) | Power transmission line pole tower geological disaster monitoring, early warning and analyzing system and using method | |
| CN206205105U (en) | City intelligent drainage control system based on heterarchical architecture | |
| Thomas et al. | A study of energy conversion at the Jebba Hydroelectric power station | |
| Huang et al. | Wind prediction based on improved bp artificial neural network in wind farm | |
| CN104977855A (en) | Emulated data simulation method for reservoir operation automatic system | |
| Twaróg | Modelling of the Solina-Myczkowce pumped storage power plant | |
| CN202705984U (en) | Combined flood-preventing optimized scheduling system for cascade reservoir group | |
| de Almeida et al. | OPAH a model for optimal design of multipurpose small hydropower plants | |
| Gbadamosi et al. | Evaluation of operational efficiency of Shiroro hydro-electric plant in Nigeria | |
| CN113239642A (en) | Method for calculating reservoir warehousing flow |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant |