Reservoir dispatching strategy calculation method, device, equipment, medium and product

Abstract

The invention relates to the technical field of hydrology and hydraulic power, and discloses a reservoir scheduling strategy calculation method, device and equipment, a medium and a product, and the method comprises the steps: building a digital twinborn body according to a real physical entity environment of a target drainage basin; future medium and long-term weather forecast data is obtained, the medium and long-term weather forecast data is input into the digital twinborn body, the digital twinborn body is combined with the medium and long-term weather forecast data to predict the medium and long-term runoff process of the reservoir in the target drainage basin, and different reservoir dispatching strategies are simulated in combination with the medium and long-term runoff process; obtaining a simulation result of each reservoir scheduling strategy; and determining an optimal scheduling strategy according to the simulation result of each reservoir scheduling strategy. According to the method, the digital twinborn is constructed through the medium and long term weather forecast data, the future medium and long term runoff is predicted through the digital twinborn, and the optimal scheduling strategy is simulated according to the prediction result.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of hydrology and hydraulics, and particularly relates to a reservoir scheduling strategy calculation method and device, an electronic device, a storage medium and a program product. BACKGROUND

[0002] Current medium and long-term inflow forecasts are mainly based on statistical methods, conceptual hydrological models or physical hydrological models. Although these methods can provide a certain accuracy of the forecast results, the statistical method has limited prediction accuracy and is difficult to achieve dynamic adjustment and real-time update. SUMMARY

[0003] The present application provides a reservoir scheduling strategy calculation method to solve the problem of limited prediction accuracy and difficulty in dynamic adjustment and real-time update of the statistical method.

[0004] In a first aspect, the present application provides a reservoir scheduling strategy calculation method, comprising: constructing a digital twin according to the real physical entity environment of the target basin; obtaining future medium and long-term weather forecast data, inputting the medium and long-term weather forecast data into the digital twin, so that the digital twin combines the medium and long-term weather forecast data to predict the medium and long-term runoff process of the reservoir in the target basin, and combines the medium and long-term runoff process to simulate different reservoir scheduling strategies, and obtains the simulation results of each reservoir scheduling strategy; determining the optimal scheduling strategy according to the simulation results of each reservoir scheduling strategy.

[0005] The present application constructs a digital twin according to the actual entity environment, constructs a digital twin of the target basin, and can real-time depict the hydro-meteorological conditions, the basin underlying surface characteristics and the reservoir operation state in the target basin through the digital twin, so as to dynamically capture the comprehensive change characteristics of the basin and the reservoir, significantly improve the accuracy and adaptability of the inflow forecast, and simulate the results after executing different scheduling strategies on the reservoir through the digital twin, so as to facilitate selecting the optimal scheduling strategy according to the simulation results of different scheduling strategies.

[0006] In an optional embodiment, the digital twin is constructed according to the real physical entity environment of the target basin, comprising: constructing a basin geometric structure model, the basin geometric structure model is used to extract the main river structure information, the tributary network structure information, the reservoir boundary and the lake shoreline within the basin range by using the global digital elevation model and the basic geographic information database, and generate a terrain-landscape spatial grid model; constructing a hydrological-hydraulic physical process model, the hydrological-hydraulic physical process model is used to operate the basin characteristics and the hydrological and hydrodynamic process data within the basin range; The reservoir regulation behavior model is used to combine hydrological and hydrodynamic process data to obtain simulation results of different reservoir regulation strategies.

[0007] The embodiment provides a method for calculating state variables according to calculations in three aspects of physical terrain modeling, hydrological and hydrodynamic modeling, and reservoir regulation modeling. Data basis is provided for subsequent prediction.

[0008] In an optional embodiment, the hydrological and hydrodynamic physical process model comprises: a runoff sub-model for simulating a time and space distribution of a surface runoff coefficient according to input rainfall data, land use data, soil type data, and slope information data; a soil moisture sub-model for fusing profile water dynamics, effective root zone water capacity, and evaporation and transpiration coefficient to calculate an evaporation and transpiration coefficient; a groundwater sub-model for fusing groundwater storage and discharge, river-groundwater mutual feeding, and time and space delay effects by using a two-dimensional unsteady equation to simulate groundwater level data and river-groundwater exchange data; a lake and reservoir sub-model for linking tributary supply data and gate water diversion boundary conditions to obtain a corresponding relationship between water surface evaporation and reservoir capacity change.

[0009] In an optional embodiment, different reservoir regulation strategies are simulated in combination with a medium and long-term runoff process to obtain simulation results of the reservoir regulation strategies, including: determining a regulation result observation value of the reservoir, the regulation result observation value being an actual observation value after the reservoir is regulated according to the optimal regulation strategy; constructing an error vector by using a deviation between the simulation result of the optimal regulation strategy and the regulation result observation value; obtaining a weight correction term by using a covariance matrix of the error vector, correcting the digital twin by using the weight correction term, and obtaining a corrected digital twin.

[0010] The embodiment provides a comparison between a prediction result and an actual result. After the digital twin is used to complete prediction, the simulation result of the optimal regulation strategy is compared with an actual observation value after the optimal regulation strategy is executed. An error vector is constructed according to a deviation between the two, and the digital twin is corrected according to the error vector. A “simulation-observation-prediction” closed loop framework is established. A state reset and parameter update mechanism is triggered when an error is detected, and long-term stable operation of the simulation system is ensured.

[0011] In an optional embodiment, different reservoir regulation strategies are simulated in combination with a medium and long-term runoff process to obtain simulation results of the reservoir regulation strategies, including: According to the simulation results of the digital twin and the scheduling result observation values corresponding to the simulation results, a historical prediction database is constructed; A residual learning model is constructed by using the simulation results in the historical prediction database and the corresponding scheduling result observation values, so that the residual learning model identifies the deviation law of the digital twin, and outputs a dynamic correction factor according to the deviation law; The digital twin is corrected by using the dynamic correction factor, and a corrected digital twin is obtained.

[0012] Another method for correcting the digital twin is given in the embodiment. After the prediction is completed by using the digital twin, the simulation result data of the optimal scheduling strategy is collected, and a database is established according to the simulation result data. The simulation results in the database are compared with the actual observation values after the optimal scheduling strategy is executed, a residual learning model is constructed according to the deviation between the two, the deviation law is learned and a dynamic correction factor is output according to the deviation law, an updating mechanism that learns and corrects is established, and the accuracy of the prediction data is ensured.

[0013] In an optional embodiment, future medium and long term weather forecast data is obtained, and the medium and long term weather forecast data is input into the digital twin, including: Obtaining future medium and long term weather forecast data; The medium and long term weather forecast data is spatially registered to the model topography-landform spatial grid model by using an interpolation algorithm.

[0014] A method for importing weather forecast data into a spatial grid model is disclosed, which realizes accurate matching of weather data and a topography-landform spatial grid model.

[0015] In a second aspect, the present application provides a reservoir scheduling strategy calculation device, including: A model building module is configured to build a digital twin. A simulation calculation module is configured to calculate simulation results of each reservoir scheduling strategy.

[0016] In a third aspect, the present application provides an electronic device, including a memory and a processor, which are communicatively connected to each other, and the memory stores computer instructions, and the processor executes the computer instructions to perform the reservoir scheduling strategy calculation method of the first aspect or any of the corresponding embodiments thereof.

[0017] In a fourth aspect, the present application provides a computer readable storage medium, which stores computer instructions for causing a computer to execute the reservoir scheduling strategy calculation method of the first aspect or any of the corresponding embodiments thereof.

[0018] In a fifth aspect, the present application provides a computer program product comprising computer instructions for causing a computer to execute the reservoir scheduling strategy calculation method of the first aspect or any of its possible implementation forms. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the specific embodiments of the present application or the technical solutions in the prior art, the drawings needed in the specific embodiments or prior art description will be briefly introduced as follows. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0020] Figure 1 is a schematic diagram of an application scenario according to an embodiment of the present application; Figure 2 is a first flowchart of a reservoir scheduling strategy calculation method according to an embodiment of the present application; Figure 3 is a second flowchart of a reservoir scheduling strategy calculation method according to an embodiment of the present application; Figure 4 is a third flowchart of a reservoir scheduling strategy calculation method according to an embodiment of the present application; Figure 5 is a fourth flowchart of a reservoir scheduling strategy calculation method according to an embodiment of the present application; Figure 6 is a fifth flowchart of a reservoir scheduling strategy calculation method according to an embodiment of the present application; Figure 7 is a structural block diagram of a reservoir scheduling strategy calculation device according to an embodiment of the present application; Figure 8 is a hardware structure schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application will be described clearly and completely in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0022] It can be understood that before using the technical solutions disclosed in the embodiments of the present application, the type, use range, use scenario and the like of the personal information involved in the present application should be informed to the user and the authorization of the user should be obtained through appropriate means according to relevant laws and regulations.

[0023] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0024] As an optional application scenario of this invention, such as Figure 1 As shown, the reservoir scheduling strategy calculation system may include at least one terminal device and at least one server. Figure 1 The system is illustrated in the example, which includes a computer 101, a mobile terminal 102, and a server 103, and the terminal devices such as the computer 101 and the mobile terminal 102 are connected to the server 103 through a network 110.

[0025] Specifically, the terminal device can be a smartphone, tablet, laptop, PDA, desktop computer, game console, smart TV, smart wearable device, in-vehicle terminal, VR (Virtual Reality) device, AR (Augmented Reality) device, etc. Server 103 can be a standalone physical server, a server cluster, a distributed system, or a cloud server providing cloud services. Network 110 can be a wired or wireless network, examples of which include, but are not limited to, the Internet, corporate intranet, local area network, wide area network, mobile communication network, and combinations thereof.

[0026] This invention provides a method for calculating reservoir scheduling strategies. By constructing a digital twin and combining it with medium- and long-term meteorological forecast data, the method predicts future runoff processes to achieve higher accuracy in long-term inflow forecasts.

[0027] According to an embodiment of the present invention, a method for calculating reservoir scheduling strategies is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0028] This embodiment provides a method for calculating reservoir scheduling strategies, which can be used on mobile terminals such as mobile phones and tablets. Figure 2 This is a flowchart of a reservoir scheduling strategy calculation method according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps: Step S201, a digital twin is constructed according to a real physical entity environment of a target basin.

[0029] The real physical environment of the target basin refers to geographical conditions and ecological environment characteristics of the basin. It includes specific construction conditions of the topography of the basin, types of soil in the basin, and hydrological characteristics, etc. The digital twin refers to a virtual model corresponding to an entity in the real world constructed by data modeling. The digital twin can simulate, predict and optimize the running conditions of the entity by means of data and algorithm analysis.

[0030] Step S202, future medium and long term weather forecast data is obtained, the medium and long term weather forecast data is input into the digital twin, so that the digital twin combines the medium and long term weather forecast data to predict the medium and long term runoff process of the reservoir in the target basin, and combines the medium and long term runoff process to simulate different reservoir scheduling strategies to obtain simulation results of each reservoir scheduling strategy.

[0031] The medium and long term weather forecast data refers to the weather prediction results in a long period of time in the future calculated according to current weather observation data and historical climate data, etc. The medium and long term runoff process refers to the change process of flowing water bodies formed by water bodies on the ground surface and underground in the basin. The reservoir scheduling strategy refers to a series of plans and measures for efficient management and optimal allocation of water resources of the reservoir by planning water storage, water release and other operations. By importing the medium and long term weather forecast data into the digital twin, the prediction of the medium and long term runoff process can be obtained, and different reservoir scheduling strategies can be simulated to find the optimal scheduling strategy.

[0032] Exemplarily, the medium and long term can refer to 6 months, 1 year or 2 years, etc., which is not limited here.

[0033] Step S203, the optimal scheduling strategy is determined according to the simulation results of each reservoir scheduling strategy.

[0034] By comparing and analyzing the simulation running results under each reservoir scheduling strategy, the optimal scheduling strategy scheme that can be realized under certain conditions is determined.

[0035] In an optional embodiment, the inflow of each scheduling strategy can be input into a reservoir scheduling simulation platform, and simulation is performed by using the reservoir scheduling simulation platform to obtain key evaluation indexes such as water storage utilization rate, benefit increase, and water loss of different scheduling strategies, and the optimal scheduling strategy is selected based on the above evaluation indexes.

[0036] The reservoir scheduling strategy calculation method provided in this embodiment constructs a digital twin of the target watershed. Through the digital twin, the hydrological and meteorological conditions, underlying surface characteristics, and reservoir operation status within the target watershed can be plotted in real time, thereby dynamically capturing the comprehensive changing characteristics of the watershed and the reservoir, significantly improving the accuracy and adaptability of inflow forecasts. Furthermore, the digital twin can simulate the results of implementing different scheduling strategies on the reservoir, thus facilitating the selection of the optimal scheduling strategy based on the simulation results of different scheduling strategies.

[0037] This embodiment provides a method for calculating reservoir scheduling strategies. Figure 3 This is a flowchart of a reservoir scheduling strategy calculation method according to an embodiment of the present invention, such as... Figure 3 As shown, the process includes the following steps: Step S301: Construct a digital twin based on the real physical environment of the target watershed.

[0038] Specifically, step S301 includes: Step S3011: Construct a watershed geometric structure model. The watershed geometric structure model is used to extract the main river channel structure information, tributary network structure information, reservoir boundaries and lake shorelines within the watershed using the global digital elevation model and basic geographic information database, and generate a topographic-geomorphic spatial grid model.

[0039] In one optional embodiment, the watershed geometric structure model refers to a mathematical model obtained by modeling the topographic features of the reservoir to be measured.

[0040] In one alternative embodiment, the data required to construct the watershed geometry model is obtained from the Global Digital Elevation Model and a basic geographic information database.

[0041] In one alternative embodiment, the main channel structure information is used to describe the morphology of the main channel. The tributary network structure information refers to the channel morphology of the tributaries downstream of the main channel.

[0042] In one alternative embodiment, the reservoir boundary refers to the boundary line data of the reservoir under study. The lake shoreline refers to the shoreline data of the lake under study. The topographic-geomorphic spatial grid model is a digital model that expresses topographic and geomorphic features through grid cells.

[0043] In one optional embodiment, information such as cross-sectional morphology, reservoir outline, water level change characteristics, main channel structure information, tributary network structure information, reservoir boundary and lake shoreline can be acquired through high-resolution remote sensing imagery, lidar measurement and UAV oblique photography. The geomorphic features at different locations are then mapped into a topographic-geomorphic spatial grid model, which facilitates subsequent simulation based on the mapping of medium- and long-term meteorological forecast data to the topographic-geomorphic spatial grid model.

[0044] Step S3012: Construct a hydrological-hydraulic physical process model. The hydrological-hydraulic physical process model is used to calculate the watershed characteristics within the watershed area and obtain hydrological and hydrodynamic process data within the watershed area.

[0045] Hydrological-hydraulic physical process models are used to simulate physical processes such as water volume and flow in the water cycle. Hydrological and hydrodynamic process data are then used to combine different scheduling strategies.

[0046] Step S3013: Construct a reservoir regulation behavior model. The reservoir regulation behavior model is used to combine hydrological and hydrodynamic process data to simulate different reservoir scheduling strategies and obtain the simulation results of each reservoir scheduling strategy.

[0047] In one optional implementation, a reservoir regulation behavior model is constructed based on scheduling procedures. Reservoir regulation behavior refers to the scheduling and management of water storage and release in a reservoir. For example, inputting water level data, inflow data, and gate opening data into the reservoir regulation behavior model yields outflow data. Introducing a "scheduling memory factor" and a "regulation response function" calculated from historical operational data creates a computable mapping of historical scheduling behavior, resulting in state variables.

[0048] Step S302: Obtain future medium- and long-term meteorological forecast data, input the medium- and long-term meteorological forecast data into the digital twin, so that the digital twin, in conjunction with the medium- and long-term meteorological forecast data, predicts the medium- and long-term runoff processes of reservoirs in the target watershed, and simulates different reservoir scheduling strategies based on the medium- and long-term runoff processes, obtaining the simulation results of each reservoir scheduling strategy. For details, please refer to... Figure 2 Step S202 of the illustrated embodiment will not be described again here.

[0049] Step S303: Determine the optimal scheduling strategy based on the simulation results of each reservoir's scheduling strategy. For details, please refer to [link to relevant documentation]. Figure 2 Step S203 of the illustrated embodiment will not be described again here.

[0050] The reservoir scheduling strategy calculation method provided in this embodiment offers a method for obtaining state variables based on three aspects: physical terrain modeling, hydrological and hydraulic modeling, and reservoir regulation modeling. This provides a data foundation for subsequent predictions.

[0051] In an optional embodiment, the constructed hydrological-hydraulic physical process model includes: The runoff generation and sinking sub-model is used to simulate the surface runoff coefficient and spatiotemporal distribution data based on input rainfall data, land use data, soil type data, and slope information data; A soil moisture sub-model is used to integrate profile moisture dynamics, effective root zone water carrying capacity, and evapotranspiration coefficient to calculate the evapotranspiration coefficient. The groundwater sub-model is used to integrate groundwater storage and release, river-groundwater interaction and spatiotemporal delay effects using two-dimensional unsteady-state equations to simulate groundwater level data and river-groundwater exchange data. The lake and reservoir sub-models are used to link tributary replenishment data and sluice gate water diversion boundary conditions to obtain the correspondence between water surface evaporation and reservoir capacity changes.

[0052] For example, the runoff generation and sinking sub-model can adopt the SCS-CN or Green-Ampt model; the soil moisture sub-model can output the effective root zone water content based on the profile water dynamics and balance equations for evapotranspiration calculation; the groundwater sub-model can introduce the two-dimensional unsteady Boussinesq equation to output the groundwater level and river-groundwater exchange volume; the lake and reservoir sub-model can dynamically simulate volume changes, water surface evaporation, and hydraulic connections, and handle boundary conditions such as tributary recharge and gate water intake in conjunction with the model, outputting water surface evaporation and reservoir capacity changes.

[0053] This embodiment provides a method for calculating reservoir scheduling strategies. Figure 4 This is a flowchart of a reservoir scheduling strategy calculation method according to an embodiment of the present invention, such as... Figure 4 As shown, the process includes the following steps: Step S401: Construct a digital twin based on the actual physical environment of the target watershed. For details, please refer to [link to relevant documentation]. Figure 2 Step S201 of the illustrated embodiment will not be described again here.

[0054] Step S402: Obtain future medium- and long-term meteorological forecast data, input the medium- and long-term meteorological forecast data into the digital twin, so that the digital twin combines the medium- and long-term meteorological forecast data to predict the medium- and long-term runoff process of reservoirs in the target watershed, and combines the medium- and long-term runoff process to simulate different reservoir scheduling strategies, and obtain the simulation results of each reservoir scheduling strategy.

[0055] Specifically, in step S402 above, different reservoir scheduling strategies are simulated in conjunction with medium- and long-term runoff processes to obtain simulation results for each reservoir scheduling strategy, including: Step S4021: Determine the observed values ​​of the reservoir's scheduling results. The observed values ​​of the scheduling results are the actual observed values ​​after scheduling the reservoir according to the optimal scheduling strategy.

[0056] The scheduling results are observed and compared with subsequent predictions to obtain the deviation between the prediction and the actual values.

[0057] Step S4022: Construct an error vector by comparing the simulation results of the optimal scheduling strategy with the observed values ​​of the scheduling results.

[0058] For example, an error vector can be constructed using ensemble Kalman filtering.

[0059] Step S4023: Obtain the weight correction term through the covariance matrix of the error vector, and use the weight correction term to correct the digital twin to obtain the corrected digital twin.

[0060] By using weight adjustment terms, adjustments are made to the digital twin to make it closer to the expected goal, thereby improving overall performance.

[0061] Step S403: Determine the optimal scheduling strategy based on the simulation results of each reservoir's scheduling strategy. For details, please refer to [link to relevant documentation]. Figure 2 Step S203 of the illustrated embodiment will not be described again here.

[0062] The reservoir scheduling strategy calculation method provided in this embodiment compares the simulation results of the optimal scheduling strategy with the actual observed values ​​after the optimal scheduling strategy is executed, constructs an error vector based on the deviation between the two, and corrects the digital twin based on the error vector, thus establishing a closed-loop framework of "simulation-observation-prediction". When error is detected, a state reset and parameter update mechanism is triggered to ensure the long-term stable operation of the simulation system.

[0063] This embodiment provides a method for calculating reservoir scheduling strategies. Figure 5 This is a flowchart of a reservoir scheduling strategy calculation method according to an embodiment of the present invention, such as... Figure 5 As shown, the process includes the following steps: Step S501: Construct a digital twin based on the actual physical environment of the target watershed. For details, please refer to [link to relevant documentation]. Figure 2 Step S201 of the illustrated embodiment will not be described again here.

[0064] Step S502: Obtain future medium- and long-term meteorological forecast data, input the medium- and long-term meteorological forecast data into the digital twin, so that the digital twin combines the medium- and long-term meteorological forecast data to predict the medium- and long-term runoff process of reservoirs in the target watershed, and combines the medium- and long-term runoff process to simulate different reservoir scheduling strategies, and obtain the simulation results of each reservoir scheduling strategy.

[0065] Specifically, in step S502 above, different reservoir scheduling strategies are simulated in conjunction with medium- and long-term runoff processes to obtain simulation results for each reservoir scheduling strategy, including: Step S5021: Construct a historical prediction database based on the simulation results of the digital twin and the scheduling result observations corresponding to each simulation result.

[0066] A historical prediction database is constructed from multiple simulation results for comparison with actual observations, providing a sufficient sample size for subsequent bias analysis.

[0067] Step S5022: Construct a residual learning model using simulation results and corresponding scheduling result observations from the historical prediction database, so that the residual learning model can identify the deviation patterns of the digital twin and output a dynamic correction factor based on the deviation patterns.

[0068] The residual refers to the difference between the simulated output of the twin and the actual scheduled observations. This process captures the systematic bias of the twin and transforms the patterns into dynamically callable correction factors.

[0069] Step S5023: The digital twin is corrected using a dynamic correction factor to obtain the corrected digital twin.

[0070] The correction factor obtained in the above process is used to reverse-correct the simulation results of the digital twin, offsetting the deviation. This achieves the correction between the simulation results and the actual values ​​of the digital twin.

[0071] Step S503: Determine the optimal scheduling strategy based on the simulation results of each reservoir's scheduling strategy. For details, please refer to [link to relevant documentation]. Figure 2 Step S203 of the illustrated embodiment will not be described again here.

[0072] The reservoir scheduling strategy calculation method provided in this embodiment collects multiple simulation results of the optimal scheduling strategy after completing the prediction using a digital twin. A database is established based on the multiple simulation results. The simulation results in the database are compared with the actual observations after executing the optimal scheduling strategy. A residual learning model is constructed based on the deviation between the two, the deviation pattern is learned, and a dynamic correction factor is output based on the deviation pattern. An update mechanism from learning to correction is established to ensure the accuracy of the prediction data.

[0073] This embodiment provides a method for calculating reservoir scheduling strategies. Figure 6 This is a flowchart of a reservoir scheduling strategy calculation method according to an embodiment of the present invention, such as... Figure 6 As shown, the process includes the following steps: Step S601: Construct a digital twin based on the actual physical environment of the target watershed. For details, please refer to [link to relevant documentation]. Figure 2 Step S201 of the illustrated embodiment will not be described again here.

[0074] Step S602: Obtain future medium- and long-term meteorological forecast data, input the medium- and long-term meteorological forecast data into the digital twin, so that the digital twin combines the medium- and long-term meteorological forecast data to predict the medium- and long-term runoff process of reservoirs in the target watershed, and combines the medium- and long-term runoff process to simulate different reservoir scheduling strategies, and obtain the simulation results of each reservoir scheduling strategy.

[0075] Specifically, step S602 above, which involves acquiring future medium- and long-term weather forecast data and inputting it into the digital twin, includes: Step S6021: Obtain future medium- and long-term weather forecast data.

[0076] For example, methods for obtaining future medium- and long-term weather forecast data may include accessing global / regional medium- and long-term weather forecast data such as ECMWF, GFS, and NMME, and automatically downloading daily variables such as rainfall, temperature, and wind speed for the next 6 months.

[0077] Step S6022: Spatial registration of medium- and long-term meteorological forecast data to the model topography-geomorphology spatial grid model is performed using an interpolation algorithm.

[0078] Interpolation algorithms can be used to combine medium- and long-term meteorological forecast data with the constructed topographic-geomorphic spatial grid model.

[0079] For example, interpolation algorithms can use bilinear interpolation, inverse distance weighted interpolation, or kriging interpolation. Large-scale climate indices such as sea surface temperature, ENSO, and PDO can also be embedded as prior factors to improve regional forecasting capabilities and seasonal abrupt change response capabilities.

[0080] Step S603: Determine the optimal scheduling strategy based on the simulation results of each reservoir's scheduling strategy. For details, please refer to [link to relevant documentation]. Figure 2 Step S203 of the illustrated embodiment will not be described again here.

[0081] The reservoir scheduling strategy calculation method provided in this embodiment discloses a method for importing meteorological forecast data into a spatial grid model to achieve accurate matching between meteorological data and topographic-geomorphic spatial grid model.

[0082] This embodiment also provides a reservoir scheduling strategy calculation device, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0083] This embodiment provides a reservoir scheduling strategy calculation device, such as...Figure 7 As shown, it includes: Model building module 701 is used to build digital twins.

[0084] The simulation calculation module 702 is used to calculate the simulation results of the scheduling strategies for each reservoir.

[0085] The reservoir scheduling strategy calculation device provided in this embodiment of the invention can execute the reservoir scheduling strategy calculation method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method execution. Further functional descriptions of the above modules and units are the same as in the corresponding embodiments described above, and will not be repeated here.

[0086] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0087] The following is a detailed reference. Figure 8 This diagram illustrates a suitable structural schematic for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 801, which can perform various appropriate actions and processes based on a program stored in read-only memory (ROM) 802 or a program loaded from memory 808 into random access memory (RAM) 803. The RAM 803 also stores various programs and data required for the operation of the electronic device. The processor 801, ROM 802, and RAM 803 are interconnected via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0088] Typically, the following devices can be connected to I / O interface 805: input devices 806 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 807 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 808 including, for example, magnetic tapes, hard disks, etc.; and communication devices 809. Communication device 809 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 8 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0089] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 809, or installed from a memory 808, or installed from a ROM 802. When the computer program is executed by the processor 801, it performs the functions defined in the reservoir scheduling strategy calculation method of the embodiments of the present invention.

[0090] Figure 8 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0091] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the reservoir scheduling strategy calculation method shown in the above embodiments is implemented.

[0092] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0093] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for calculating reservoir scheduling strategies, characterized in that, The method includes: Construct a digital twin based on the real physical environment of the target watershed; Obtain future medium- and long-term meteorological forecast data, input the medium- and long-term meteorological forecast data into the digital twin, so that the digital twin combines the medium- and long-term meteorological forecast data to predict the medium- and long-term runoff process of reservoirs in the target watershed, and combines the medium- and long-term runoff process to simulate different reservoir scheduling strategies, and obtain the simulation results of each reservoir scheduling strategy. The optimal scheduling strategy is determined based on the simulation results of the scheduling strategies for each reservoir.

2. The method according to claim 1, characterized in that, Construct a digital twin based on the real physical environment of the target watershed, including: A watershed geometric structure model is constructed. This model is used to extract the main river channel structure information, tributary network structure information, reservoir boundaries and lake shorelines within the watershed using the Global Digital Elevation Model and a basic geographic information database, and to generate a topographic-geomorphic spatial grid model. A hydrological-hydraulic physical process model is constructed, which is used to calculate the watershed characteristics within the watershed area, and the hydrological and hydrodynamic process data within the watershed area are used. A reservoir regulation behavior model is constructed, which is used to combine the hydrological and hydrodynamic process data to simulate different reservoir scheduling strategies and obtain the simulation results of each reservoir scheduling strategy.

3. The method according to claim 2, characterized in that, The hydrological-hydraulic physical process model includes: The runoff generation and sinking sub-model is used to simulate the surface runoff coefficient and spatiotemporal distribution data based on input rainfall data, land use data, soil type data, and slope information data; A soil moisture sub-model is used to integrate profile moisture dynamics, effective root zone water carrying capacity, and evapotranspiration coefficient to calculate the evapotranspiration coefficient. The groundwater sub-model is used to integrate groundwater storage and release, river-groundwater interaction and spatiotemporal delay effects using two-dimensional unsteady-state equations to simulate groundwater level data and river-groundwater exchange data. The lake and reservoir sub-models are used to link tributary replenishment data and sluice gate water diversion boundary conditions to obtain the correspondence between water surface evaporation and reservoir capacity changes.

4. The method according to claim 1, characterized in that, Simulations of different reservoir scheduling strategies were conducted based on the aforementioned medium- and long-term runoff processes, yielding simulation results for each strategy, including: Determine the observed values ​​of the reservoir's scheduling results, which are the actual observed values ​​after scheduling the reservoir according to the optimal scheduling strategy; The deviation between the simulation results of the optimal scheduling strategy and the observed values ​​of the scheduling results is constructed as an error vector; The weight correction term is obtained by calculating the covariance matrix of the error vector, and the digital twin is corrected using the weight correction term to obtain the corrected digital twin.

5. The method according to claim 1, characterized in that, Simulations of different reservoir scheduling strategies were conducted based on the aforementioned medium- and long-term runoff processes, yielding simulation results for each strategy, including: A historical prediction database is constructed based on the simulation results of the digital twin and the scheduling result observations corresponding to each simulation result. A residual learning model is constructed using simulation results and corresponding scheduling result observations from the historical prediction database, so that the residual learning model can identify the deviation patterns of the digital twin and output a dynamic correction factor based on the deviation patterns. The digital twin is corrected using the dynamic correction factor to obtain the corrected digital twin.

6. The method according to claim 2, characterized in that, Acquiring future medium- and long-term weather forecast data and inputting the medium- and long-term weather forecast data into the digital twin includes: Obtain future medium- and long-term weather forecast data; The medium- and long-term meteorological forecast data are spatially registered to the topographic-geomorphic spatial grid model described in the model using an interpolation algorithm.

7. A reservoir scheduling strategy calculation device, characterized in that, The device includes: The model building module is used to build digital twins; The simulation calculation module is used to calculate the simulation results of the scheduling strategies for each reservoir.

8. An electronic device, characterized in that, include: The system includes a memory and a processor, which are interconnected. The memory stores computer instructions, and the processor executes the computer instructions to perform a reservoir scheduling strategy calculation method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions, which are used to cause the computer to execute a reservoir scheduling strategy calculation method according to any one of claims 1 to 6.

10. A computer program product, characterized in that, It includes computer instructions, which are used to cause a computer to execute a reservoir scheduling strategy calculation method according to any one of claims 1 to 6.

Images