Intelligent reservoir scheduling system and method based on model-free adaptive control

Through the model-free adaptive control algorithm and incremental model, the reservoir scheduling strategy is dynamically adjusted, which solves the accuracy and response problems of traditional reservoir scheduling methods, real-time adjustment and efficient management of reservoir water levels are realized, adapting to complex hydrological environments, and responding to extreme weather in advance. .

CN119180528AInactive Publication Date: 2024-12-24SHAANXI WATER CONSERVANCY & ELECTRIC POWER SURVEY & DESIGN INSTITUTE (GROUP) CO LTD

Patent Information

Application Number
CN202411690882.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-25
Publication Date
2024-12-24
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Traditional reservoir scheduling methods rely on manual experience or fixed rules, have low scheduling accuracy and flexibility, making them difficult to deal with complex hydrological environments and emergencies, and establishing accurate models is time-consuming and labor-intensive and prone to failure, making them unable to respond quickly and make full use of real-time data.

Method used

Adopt the reservoir intelligent scheduling system based on model-free adaptive control, obtain real-time and historical hydrological data through data acquisition and storage modules, build incremental models using model-free adaptive control algorithms, dynamically adjust scheduling strategies, get rid of precise model dependence, and realize real-time Scheduling and fast response.

Benefits of technology

It improves the flexibility and adaptability of reservoir scheduling, ensures that the water level is within a safe range, achieves efficient utilization and intelligent management, can quickly respond to sudden changes, respond to extreme weather in advance, and improves scheduling accuracy and response speed.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119180528A_ABST
    Figure CN119180528A_ABST
Patent Text Reader

Abstract

The invention discloses an intelligent reservoir scheduling system and method based on model-free adaptive control, belongs to the technical field of water conservancy scheduling, and can solve the problems that time and labor are consumed when a precise model is established in a traditional scheduling system, the risk of model failure exists, and quick response cannot be achieved in the face of sudden hydrological changes. The system comprises a data acquisition module used for acquiring real-time hydrological data of a reservoir; the data storage module is used for storing historical hydrological data of the reservoir; the scheduling strategy determination module is connected with the data acquisition module and the data storage module, and is used for determining a scheduling strategy of the reservoir by using a model-free adaptive control algorithm according to the real-time hydrological data and the historical hydrological data; and the scheduling execution module is connected with the scheduling strategy determination module and is used for scheduling the reservoir according to the scheduling strategy of the reservoir. The method is used for intelligent scheduling of the reservoir.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to a reservoir intelligent dispatching system and method based on model-free adaptive control, belonging to the technical field of water conservancy dispatching. Background Art

[0002] With the continuous advancement of science and technology, reservoirs, as an important tool for water resource scheduling, are facing increasingly complex challenges in scheduling and management. Existing reservoir scheduling methods usually rely on manual experience or control systems based on fixed rules. These methods have low scheduling accuracy and flexibility, especially when dealing with complex hydrological environments and emergencies. Traditional scheduling strategies are often difficult to adapt. With the increase in climate change and extreme weather events, reservoir scheduling systems need to have stronger real-time response capabilities to ensure that reservoir water levels can remain within a safe range under different conditions.

[0003] Traditional model-based reservoir operation methods rely on accurate mathematical modeling of reservoir systems. However, due to the complexity and variability of reservoir systems, establishing accurate models is not only time-consuming and laborious, but also has the risk of model failure, especially when faced with sudden hydrological changes, the operation system cannot respond quickly. In addition, existing operation systems often lack effective use of real-time data and cannot fully utilize the real-time hydrological information provided by modern sensor networks for dynamic operation. Summary of the invention

[0004] The present invention provides a reservoir intelligent dispatching system and method based on model-free adaptive control, which can solve the problems that the traditional dispatching system is time-consuming and labor-intensive to establish an accurate model, has the risk of model failure, and cannot respond quickly to sudden hydrological changes.

[0005] In one aspect, the present invention provides a reservoir intelligent dispatching system based on model-free adaptive control, the system comprising:

[0006] Data acquisition module, used to collect real-time hydrological data of the reservoir;

[0007] Data storage module, used to store historical hydrological data of the reservoir;

[0008] A dispatching strategy determination module, connected to both the data acquisition module and the data storage module, for determining a dispatching strategy of a reservoir according to the real-time hydrological data and the historical hydrological data and using a model-free adaptive control algorithm;

[0009] The scheduling execution module is connected to the scheduling strategy determination module and is used to schedule the reservoir according to the scheduling strategy of the reservoir.

[0010] Optionally, the real-time hydrological data includes real-time input data and real-time output data; the real-time input data includes the real-time water inflow, real-time water outflow, real-time evaporation and real-time precipitation of the reservoir area; the real-time output data includes the real-time water level of the reservoir;

[0011] The historical hydrological data include historical input data and historical output data; the historical input data include the historical inflow, historical outflow, historical evaporation and historical precipitation of the reservoir area; the historical output data include the historical water level of the reservoir.

[0012] Optionally, the scheduling strategy determination module specifically includes:

[0013] A model building unit, used to build an incremental model between incremental input data and incremental output data; the incremental input data is the increment of the real-time input data collected at the current moment compared to the historical input data stored at the previous moment; the incremental output data is the increment of the real-time output data collected at the current moment compared to the historical output data stored at the previous moment;

[0014] The strategy determination unit is used to determine the scheduling strategy of the reservoir at the next moment according to the incremental model, the incremental input data at the previous moment, the incremental output data at the current moment and the real-time hydrological data.

[0015] Optionally, the strategy determination unit specifically includes:

[0016] A matrix updating subunit, used to determine the incremental linearization matrix at the current moment according to the incremental input data at the previous moment, the incremental linearization matrix in the incremental model, and the incremental output data at the current moment;

[0017] The strategy generation subunit is used to determine the reservoir scheduling strategy at the next moment according to the incremental linearization matrix, real-time input data, real-time output data and the expected water level of the reservoir at the current moment.

[0018] Optionally, the real-time input data and the historical input data also include weather forecast data for the area where the reservoir is located.

[0019] Optionally, the weather forecast data includes predicted precipitation and predicted evaporation for the next 24 hours.

[0020] Optionally, the scheduling execution module includes:

[0021] An instruction generating unit, used for generating a dispatch instruction according to a dispatch strategy of the reservoir;

[0022] An instruction execution unit is used to control the opening of the water inlet valve and the water outlet valve of the reservoir according to the dispatching instruction.

[0023] Optionally, the system further includes:

[0024] A data backup module is connected to both the data storage module and the instruction generation unit, and is used to regularly back up the historical hydrological data and the scheduling instructions.

[0025] On the other hand, the present invention provides a reservoir intelligent scheduling method based on model-free adaptive control, the method comprising:

[0026] Collect real-time hydrological data of reservoirs;

[0027] Determining a reservoir dispatching strategy based on historical hydrological data and the real-time hydrological data and using a model-free adaptive control algorithm;

[0028] The reservoir is dispatched according to the dispatching strategy of the reservoir.

[0029] Optionally, the reservoir dispatching strategy is determined based on the historical hydrological data and the real-time hydrological data and using a model-free adaptive control algorithm, specifically including:

[0030] Constructing an incremental model between incremental input data and incremental output data; the incremental input data is the increment of the real-time input data collected at the current moment compared to the historical input data stored at the previous moment; the incremental output data is the increment of the real-time output data collected at the current moment compared to the historical output data stored at the previous moment;

[0031] The dispatching strategy of the reservoir at the next moment is determined according to the incremental model, the incremental input data at the previous moment, the incremental output data at the current moment and the real-time hydrological data.

[0032] The beneficial effects that the present invention can produce include:

[0033] The reservoir intelligent dispatching system based on model-free adaptive control provided by the present invention collects hydrological data such as reservoir water level, inflow flow, outflow flow, precipitation, evaporation, etc. in real time, and dynamically adjusts the reservoir dispatching strategy in combination with a model-free adaptive control algorithm to ensure that the reservoir water level is within a safe range, thereby achieving efficient utilization and intelligent management of water resources.

[0034] The reservoir intelligent dispatching system based on model-free adaptive control provided by the present invention can effectively prevent water level fluctuations caused by extreme weather by combining future weather forecast information and make dispatching decisions in advance. At the same time, the data storage module can also be used to record historical dispatching data, continuously optimize the model-free adaptive control algorithm, and improve the response speed and dispatching accuracy of the system.

[0035] The reservoir intelligent dispatching system based on model-free adaptive control provided by the present invention performs adaptive adjustment of control input through real-time input and output data, gets rid of the dependence on precise mathematical models, and greatly improves the flexibility and adaptability of dispatching. At the same time, the model-free adaptive control algorithm can realize real-time regulation of reservoir water level, quickly respond to sudden hydrological changes, and ensure the safety and efficiency of reservoir operation. The system can self-learn and optimize dispatching strategies based on historical hydrological data and real-time hydrological data, significantly improving the intelligent management level of reservoirs. And combined with meteorological forecast data and real-time hydrological data for dispatching decisions, it can achieve early response to extreme weather events and further improve the accuracy of dispatching. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 This is a structural block diagram of a reservoir intelligent dispatching system based on model-free adaptive control provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0037] The present invention is described in detail below in conjunction with embodiments, but the present invention is not limited to these embodiments.

[0038] The embodiment of the present invention provides a reservoir intelligent dispatching system based on model-free adaptive control, such as Figure 1 As shown, the system comprises:

[0039] Data acquisition module, used to collect real-time hydrological data of the reservoir.

[0040] Among them, real-time hydrological data include real-time input data and real-time output data; real-time input data include the real-time inflow, real-time outflow, real-time evaporation and real-time precipitation in the reservoir area; real-time output data include the real-time water level of the reservoir.

[0041] In practical applications, the data acquisition module may include radar level gauges, hydrological stations, flow meters, rain gauges and evaporation ponds to monitor various hydrological parameters of the reservoir in real time.

[0042] Specifically, radar level gauges are used to monitor reservoir water levels in real time to ensure that the system obtains accurate water level data. This data is the basis for system scheduling decisions and needs to be collected and uploaded in real time.

[0043] The hydrological station is used to detect and transmit the inflow flow of the reservoir, and the flow meter at the gate is used to measure the outflow flow to ensure that the changes in the inflow and outflow of the reservoir can be controlled in real time. The flow data will be used as one of the input parameters of the model-free adaptive control module to generate the scheduling strategy.

[0044] Rain gauges are used to measure precipitation in the area where the reservoir is located, helping the system estimate water level changes in the reservoir.

[0045] The evaporation pond is used to estimate the evaporation of the reservoir water surface using the existing water temperature model, helping the system to estimate the water level changes in the reservoir.

[0046] The data storage module is used to store the historical hydrological data of the reservoir.

[0047] Among them, historical hydrological data include historical input data and historical output data; historical input data include the historical inflow, historical outflow, historical evaporation and historical precipitation of the reservoir area; historical output data include the historical water level of the reservoir.

[0048] In practical applications, the data storage module may be a data storage server.

[0049] The dispatching strategy determination module is connected to both the data acquisition module and the data storage module, and is used to determine the dispatching strategy of the reservoir based on real-time hydrological data and historical hydrological data and using a model-free adaptive control algorithm.

[0050] Model-free adaptive control algorithms have been widely used in the field of complex system control due to their advantage of not requiring precise mathematical models. The algorithm can dynamically optimize the control strategy through adaptive adjustment algorithms based on the real-time input and output data of the system, so that the system can still achieve precise control in the face of uncertain environments. Therefore, applying model-free adaptive control to reservoir operation can not only improve the accuracy and real-time performance of operation, but also reduce dependence on mathematical models and improve the level of intelligent operation of reservoirs.

[0051] Specifically, the scheduling strategy determination module includes:

[0052] A model building unit is used to build an incremental model between incremental input data and incremental output data; the incremental input data is the increment of the real-time input data collected at the current moment compared to the historical input data stored at the previous moment; the incremental output data is the increment of the real-time output data collected at the current moment compared to the historical output data stored at the previous moment.

[0053] First, define the input data of the reservoir as (including inlet flow, outlet flow, precipitation, evaporation), the output data is (Water level in the reservoir).

[0054] Then, a dynamic linearized incremental model is constructed by using the real-time input and output data and historical input and output data through a model-free adaptive control algorithm, which is specifically described as:

[0055] (1)

[0056] in, Indicates incremental input data, Indicates incremental output data, is the incremental linearization matrix of the system.

[0057] The strategy determination unit is used to determine the scheduling strategy of the reservoir at the next moment according to the incremental model, the incremental input data at the previous moment, the incremental output data at the current moment and the real-time hydrological data.

[0058] Specifically, the strategy determination unit includes:

[0059] The matrix updating subunit is used to determine the incremental linearization matrix at the current moment according to the incremental input data at the previous moment, the incremental linearization matrix in the incremental model, and the incremental output data at the current moment.

[0060] Specifically, the incremental linearization matrix can be dynamically updated through historical data ,However It cannot be obtained directly through the formula, but its estimated value can be calculated Make the substitution and use the following formula:

[0061] (2)

[0062] in, is the step size factor, is the regularization parameter, is an estimate of the incremental linearization matrix.

[0063] The model-free adaptive control module calculates and updates the historical input and output data and the real-time input and output data, and gradually optimizes the incremental linearization matrix. , which represents the impact of the system input on the output at the current moment, and adjusts it by dynamically updating the formula.

[0064] The strategy generation subunit is used to determine the reservoir scheduling strategy at the next moment according to the incremental linearization matrix, real-time input data, real-time output data and the expected water level of the reservoir at the current moment.

[0065] Specifically, based on the incremental model and output data, the input data for the next moment is generated. (It includes the inflow and outflow at the next moment, which constitute the reservoir scheduling strategy at the next moment):

[0066] (3)

[0067] in, is the expected water level, is the regularization parameter, is the step factor, and the control input is continuously adjusted through this formula to achieve accurate control of the reservoir water level.

[0068] The dispatching execution module is connected to the dispatching strategy determination module and is used to dispatch the reservoir according to the reservoir's dispatching strategy.

[0069] Specifically, it includes: an instruction generation unit, which is used to generate a dispatch instruction according to the dispatch strategy of the reservoir.

[0070] The instruction generation unit can automatically generate specific dispatching instructions according to the dispatching strategy generated by the strategy generation subunit, including operations such as adjusting the opening of the reservoir gate and the discharge volume, so as to ensure accurate control of the reservoir water level.

[0071] The instruction execution unit is used to control the opening of the water inlet valve and the water outlet valve of the reservoir according to the dispatching instruction.

[0072] The instruction execution unit executes specific reservoir scheduling operations according to the scheduling plan generated by the instruction generation unit, adjusts the water inlet flow and the water outlet flow, and ensures that the reservoir water level remains within the set range.

[0073] Furthermore, the real-time input data and historical input data also include weather forecast data for the area where the reservoir is located.

[0074] Among them, weather forecast data includes predicted precipitation and predicted evaporation for the next 24 hours.

[0075] The embodiment of the present invention receives future weather forecast data, including forecast precipitation and evaporation, through a weather forecast interface, and uses it as input for a scheduling strategy determination module. These data are combined with real-time hydrological data to further optimize the scheduling strategy, respond to possible extreme weather events in advance, avoid reservoir overflow or low water level, and ensure that the reservoir water level is within a safe range.

[0076] In the embodiment of the present invention, the data storage module is used to store historical hydrological data and dispatch operation records. The system continuously optimizes the dispatch strategy by analyzing historical data, and uses these data to adjust the parameters of the model-free adaptive control algorithm to further improve the dispatch efficiency of the system.

[0077] Furthermore, the system also includes:

[0078] The data backup module is connected to both the data storage module and the instruction generation unit, and is used for regularly backing up historical hydrological data and dispatching instructions.

[0079] Regularly back up important hydrological data and dispatching operation records to ensure that data can be restored in the event of a failure or emergency, thereby ensuring the long-term stable operation of the system.

[0080] The reservoir intelligent dispatching system based on model-free adaptive control provided by the present invention has achieved the following technical progress compared with the prior art:

[0081] (1) No need to rely on precise models: The system adaptively adjusts the control input through real-time input and output data, eliminating the reliance on precise mathematical models and greatly improving the flexibility and adaptability of scheduling.

[0082] (2) Real-time dynamic scheduling: The system can achieve real-time regulation of reservoir water level through a model-free adaptive control algorithm, quickly respond to sudden hydrological changes, and ensure the safety and efficiency of reservoir operation.

[0083] (3) High level of intelligence: The system can self-learn and optimize scheduling strategies based on historical data and real-time data, significantly improving the intelligent management level of the reservoir.

[0084] (4) Multi-dimensional data integration: Combine meteorological forecast data and real-time hydrological data to make scheduling decisions, achieve early response to extreme weather events, and further improve the accuracy of scheduling.

[0085] Another embodiment of the present invention provides a reservoir intelligent scheduling method based on model-free adaptive control, the method comprising:

[0086] Collect real-time hydrological data of reservoirs;

[0087] Determine the reservoir operation strategy based on historical and real-time hydrological data and using a model-free adaptive control algorithm;

[0088] The reservoir is dispatched according to the reservoir dispatching strategy.

[0089] Among them, the reservoir dispatching strategy is determined based on historical hydrological data and real-time hydrological data, and using a model-free adaptive control algorithm, including:

[0090] Construct an incremental model between incremental input data and incremental output data; the incremental input data is the increment of the real-time input data collected at the current moment compared to the historical input data stored at the previous moment; the incremental output data is the increment of the real-time output data collected at the current moment compared to the historical output data stored at the previous moment;

[0091] The reservoir dispatching strategy at the next moment is determined based on the incremental model, the incremental input data of the previous moment, the incremental output data of the current moment and the real-time hydrological data.

[0092] The specific description of each step in the above scheduling method can refer to the description of each module in the scheduling system, which will not be repeated here. The above scheduling method can achieve the same function as the scheduling system side.

[0093] The present invention uses a model-free adaptive control algorithm to dynamically adjust the reservoir dispatching strategy based on real-time collected hydrological data. The algorithm does not need to establish an accurate mathematical model, but instead uses the input-output relationship of the system to perform incremental dynamic linearization estimation, and uses real-time data to adjust the system control input, thereby optimizing the reservoir dispatching decision and ensuring that the water level is always kept within a safe range.

[0094] The reservoir intelligent dispatching system based on model-free adaptive control proposed by the present invention collects key hydrological parameters such as water level, inflow, outflow, precipitation and estimated evaporation of the reservoir in real time, and combines meteorological forecast data to dynamically generate the optimal dispatching strategy using a model-free adaptive control algorithm. The system can effectively solve the problems of relying on accurate mathematical models and lacking real-time adaptive capabilities in the existing dispatching system, and greatly improve the intelligence and automation level of reservoir dispatching. The core of the system is the dispatching strategy determination module, which determines the dispatching strategy of the reservoir based on the model-free adaptive control algorithm. It does not need to rely on complex mathematical models, but dynamically adjusts the dispatching strategy of the reservoir according to the real-time collected hydrological data and meteorological forecast data to ensure that the reservoir water level is always within a safe range, avoiding the phenomenon of unsafe operation of the reservoir or too low water level. Through the self-learning function, the system can dynamically adjust according to historical data and real-time data when dealing with complex and changeable hydrological environments, ensuring that the system can make flexible dispatching responses according to environmental changes. This system is particularly suitable for reservoir scenarios that require efficient water level regulation. Under extreme weather conditions, it can optimize the scheduling strategy in advance through weather forecast data to ensure the safe operation of the reservoir and the effective use of resources.

[0095] The above are only a few embodiments of the present application and do not constitute any form of limitation to the present application. Although the present application is disclosed as above with preferred embodiments, it is not intended to limit the present application. Any technician familiar with the profession, without departing from the scope of the technical solution of the present application, using the technical content disclosed above to make slight changes or modifications are equivalent to equivalent implementation cases and fall within the scope of the technical solution.

Claims

1. A reservoir intelligent dispatching system based on model-free adaptive control, characterized in that: The system comprises: Data acquisition module, used to collect real-time hydrological data of the reservoir; Data storage module, used to store historical hydrological data of the reservoir; A dispatching strategy determination module, connected to both the data acquisition module and the data storage module, for determining a dispatching strategy of a reservoir according to the real-time hydrological data and the historical hydrological data and using a model-free adaptive control algorithm; The scheduling execution module is connected to the scheduling strategy determination module and is used to schedule the reservoir according to the scheduling strategy of the reservoir.

2. The system according to claim 1, characterized in that The real-time hydrological data includes real-time input data and real-time output data; the real-time input data includes the real-time water inflow, real-time water outflow, real-time evaporation and real-time precipitation in the area where the reservoir is located; the real-time output data includes the real-time water level of the reservoir; The historical hydrological data include historical input data and historical output data; the historical input data include the historical inflow, historical outflow, historical evaporation and historical precipitation of the reservoir area; the historical output data include the historical water level of the reservoir.

3. The system according to claim 2, characterized in that The scheduling strategy determination module specifically includes: A model building unit, used to build an incremental model between incremental input data and incremental output data; the incremental input data is the increment of the real-time input data collected at the current moment compared to the historical input data stored at the previous moment; the incremental output data is the increment of the real-time output data collected at the current moment compared to the historical output data stored at the previous moment; The strategy determination unit is used to determine the scheduling strategy of the reservoir at the next moment according to the incremental model, the incremental input data at the previous moment, the incremental output data at the current moment and the real-time hydrological data.

4. The system according to claim 3, characterized in that The strategy determination unit specifically includes: A matrix updating subunit, used to determine the incremental linearization matrix at the current moment according to the incremental input data at the previous moment, the incremental linearization matrix in the incremental model, and the incremental output data at the current moment; The strategy generation subunit is used to determine the reservoir scheduling strategy at the next moment according to the incremental linearization matrix, real-time input data, real-time output data and the expected water level of the reservoir at the current moment.

5. The system according to claim 2, characterized in that The real-time input data and the historical input data also include weather forecast data for the area where the reservoir is located.

6. The system according to claim 5, characterized in that The weather forecast data includes the forecast precipitation and forecast evaporation in the next 24 hours.

7. The system according to claim 1, characterized in that The scheduling execution module includes: An instruction generating unit, used for generating a dispatch instruction according to a dispatch strategy of the reservoir; An instruction execution unit is used to control the opening of the water inlet valve and the water outlet valve of the reservoir according to the dispatching instruction.

8. The system according to claim 7, characterized in that The system further comprises: A data backup module is connected to both the data storage module and the instruction generation unit, and is used to regularly back up the historical hydrological data and the scheduling instructions.

9. A reservoir intelligent dispatching method based on model-free adaptive control, characterized in that: The method comprises: Collect real-time hydrological data of reservoirs; Determining a reservoir dispatching strategy based on historical hydrological data and the real-time hydrological data and using a model-free adaptive control algorithm; The reservoir is dispatched according to the dispatching strategy of the reservoir.

10. The method according to claim 9, characterized in that According to the historical hydrological data and the real-time hydrological data, a reservoir dispatching strategy is determined by using a model-free adaptive control algorithm, specifically including: Constructing an incremental model between incremental input data and incremental output data; the incremental input data is the increment of the real-time input data collected at the current moment compared to the historical input data stored at the previous moment; the incremental output data is the increment of the real-time output data collected at the current moment compared to the historical output data stored at the previous moment; The dispatching strategy of the reservoir at the next moment is determined according to the incremental model, the incremental input data at the previous moment, the incremental output data at the current moment and the real-time hydrological data.

Citation Information

Patent Citations

  • Cascade reservoir random optimization scheduling method based on deep Q learning

    CN110930016A

  • Reservoir flood prevention water level early warning system and method

    CN118430190A

  • Cascade reservoir optimal dispatching system

    CN118485261A

  • Reservoir flood control scheduling method and system

    CN118536766A

  • Simulation operation method for large-scale reservoir group in main stream and tributaries of river basin

    WO2021120787A1

Cited By

  • Water conservancy project scheduling system based on artificial intelligence

    CN120146539A

  • Dynamic optimization and adaptive learning method of water conservancy system large model and storage medium

    CN120218183A

  • Model-free adaptive control reservoir scheduling method and terminal equipment

    CN120706842A