A river network gate pump station dispatching method, device, equipment and storage medium

Abstract

The present invention discloses a river network gate pump station scheduling method, device, electronic device and storage medium. The method comprises: determining the hydrological data, meteorological data and scheduling constraints of the target area; determining the inflow water flow data of the river network gate pump station in the target area according to the hydrological data and meteorological data; and outputting the gate pump station scheduling data according to the inflow water flow data and scheduling constraints using a preset scheduling large model. The technical solution of the present application determines the inflow water flow data of the river network gate pump station in the target area through the hydrological data and meteorological data of the target area, and obtains the gate pump station scheduling data of the target area according to the inflow water flow data and the scheduling constraints on the water level of the target area and the operating capacity of the river network gate pump station using a pre-trained scheduling large model, so as to realize the efficient allocation of water resources in the target area and the stable control of the water power of the river network gate pump station.

Description

Technical Field

[0001] The present invention relates to the technical field of water area management, and in particular to a method, device, equipment and storage medium for dispatching a river network gate pump station. Background Art

[0002] The river network gate pump station dispatching realizes multiple functions such as flood control, drainage, irrigation, and water supply through the rational use of water resources, ensuring regional water demand and flood control safety. For example, in the rainy season, the gate pump station is dispatched to drain water in time to prevent the river network water level from being too high and causing flood disasters; in the dry season, the pump station is used to pump water to irrigate farmland to ensure agricultural production.

[0003] At present, the scheduling of many river network sluice pump stations relies on preset plans and lacks flexibility. Each sluice pump station operates independently and needs to be manually scheduled, which reduces management efficiency and increases operating costs.

[0004] In addition, the existing river network gate pump station scheduling scheme based on numerical models cannot process massive historical data and data generated by real-time operation for rapid analysis, and cannot extract the corresponding nonlinear relationship between the data. In addition, when facing the integrated scheduling of river network gate pump stations of different scales, the model needs to be constantly verified, resulting in the model algorithm not being effective for the integrated scheduling of regional river network gate pump stations of all scales. Summary of the invention

[0005] The present invention provides a river network sluice pump station scheduling method, device, equipment and storage medium to achieve efficient allocation of water resources in a target area and stable control of the water power of the river network sluice pump station.

[0006] In a first aspect, an embodiment of the present invention provides a method for scheduling a river network gate pump station, the method comprising:

[0007] Determine hydrological data, meteorological data and dispatching constraints of the target area, wherein the dispatching constraints are used to constrain the water level and the operating capacity of the river network gate pump station in the target area;

[0008] Determine the inflow water flow data of the river network sluice pump station in the target area according to the hydrological data and meteorological data; the inflow water flow data is the time series data of the inflow water flow of the river network sluice pump station;

[0009] The preset large scheduling model is used to output the gate pump station scheduling data according to the inflow water flow data and scheduling constraints. The gate pump station scheduling data is the equipment status time series data of the river network gate pump station.

[0010] In a second aspect, an embodiment of the present invention further provides a river network gate pump station dispatching device, the device comprising:

[0011] A target area information determination module, used to determine the hydrological data, meteorological data and dispatching constraints of the target area, wherein the dispatching constraints are used to constrain the water level and the operating capacity of the river network gate pump station in the target area;

[0012] An inflow water flow determination module is used to determine the inflow water flow data of the river network gate pump station in the target area according to the hydrological data and meteorological data; the inflow water flow data is the inflow flow time series data of the river network gate pump station;

[0013] The scheduling data determination module is used to output the gate pump station scheduling data according to the inflow water flow data and scheduling constraints using a preset scheduling large model, wherein the gate pump station scheduling data is the equipment status time series data of the river network gate pump station.

[0014] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a river network gate pump station scheduling method as described in any one of the embodiments of the present invention is implemented.

[0015] In a fourth aspect, an embodiment of the present invention further provides a storage medium storing computer executable instructions, which, when executed by a computer processor, are used to execute a river network gate pump station scheduling method as described in any one of the embodiments of the present invention.

[0016] The technical solution of the embodiment of the present invention determines the inflow water flow data of the river network sluice pump station in the target area through the hydrological data and meteorological data of the target area, and uses the pre-trained scheduling large model to obtain the sluice pump station scheduling data of the target area according to the inflow water flow data and the scheduling constraints on the water level of the target area and the operating capacity of the river network sluice pump station, so as to realize the efficient allocation of water resources in the target area and the stable control of the water dynamics of the river network sluice pump station.

[0017] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 It is a flow chart of a river network gate pump station scheduling method provided by the first embodiment of the present invention;

[0020] Figure 2 It is a structural schematic diagram of a river network gate pump station dispatching device provided in Embodiment 3 of the present invention;

[0021] Figure 3 It is a structural schematic diagram of an electronic device for implementing the river network gate pump station scheduling method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0023] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0024] Embodiment 1

[0025] Figure 1 A flow chart of a river network gate pump station scheduling method is provided for the first embodiment of the present invention. This embodiment is applicable to the river network gate pump station scheduling situation. The method can be executed by a river network gate pump station scheduling device. The river network gate pump station scheduling device can be implemented in the form of hardware and / or software. The river network gate pump station scheduling device can be configured in any electronic device with network communication and computing. Figure 1 As shown, the method includes:

[0026] S110, determining the hydrological data, meteorological data, gate pump station operation data and dispatch constraint conditions of the target area.

[0027] In this embodiment, the hydrological data includes precipitation, precipitation frequency, evaporation, and groundwater flow, and the meteorological data includes temperature, humidity, and wind speed.

[0028] The dispatching constraints are used to constrain the water level in the target area and the operating capacity of the river network gate pump station. The dispatching constraints include upstream and downstream water level constraints and gate flow constraints of the river network gate pump station.

[0029] In practical applications, the dispatching constraints are determined based on the equipment operation data of the gate pump station, the upstream and downstream water level boundary data of the river network gate pump station, and the water demand data. Among them, the equipment operation data of the gate pump station includes the water level height of the pump station inlet, the water level height of the pump station outlet, the pump flow, the number of pumps, etc. The upstream and downstream water level boundary data of the river network gate pump station include the highest water level upstream of the river network gate pump station and the lowest water level upstream of the river network gate pump station.

[0030] In actual scenarios, there are specific water level control requirements for the upstream and downstream of the river network where the sluice pump station is located. The upstream water level cannot exceed a certain set value to prevent flooding, and the downstream water level must also be maintained within a certain range to ensure water supply, shipping and other needs. These water level restrictions require specific values, such as the upstream water level must not be higher than 50 meters, and the downstream water level should be maintained between 30 meters and 40 meters. In addition, in order to ensure the downstream ecological water demand, a certain minimum flow rate needs to pass through the sluice pump station. Under normal circumstances, the minimum flow rate requirement can be 10 cubic meters per second.

[0031] It should be noted that the hydrological data of a region, including precipitation, precipitation frequency, evaporation, groundwater flow, temperature, humidity and wind speed, are important data for understanding the water resources status, hydrological cycle process and water resources management of the region.

[0032] S120. Determine the inflow water flow data of the river network sluice pump station in the target area according to the hydrological data and meteorological data.

[0033] In this embodiment, the inflow water flow data is used to represent the inflow flow time series data of the river network gate pump station.

[0034] Specifically, the hydrological data of the target area can be monitored by hydrological stations. Many hydrological stations will conduct long-term monitoring of the water level and flow rate of the river. Through these measured data, appropriate flow calculation formulas can be selected, such as the velocity area method, to calculate the flow of the river, and then obtain the inflow water flow data of the river network gate pump station. For example, it is known that the average flow velocity of a certain section of the river monitored by a hydrological station is v, and the cross-sectional area of ​​the water is A. According to the formula Q=v·A (Q is the water flow), the flow of the section can be calculated. If this section is located upstream of the river network gate pump station and there is no influence from other tributaries, the flow can be approximated as the inflow water flow data. Furthermore, the inflow water flow data of the target time series can be determined according to the average flow velocity of adjacent time periods.

[0035] In addition, this embodiment can also use a float-type water level gauge to drive a recording device to record water level changes in the target area by using the float to rise and fall with the water surface, so as to determine the inflow water flow data within the target time series.

[0036] Optionally, determining the inflow water flow data of the river network sluice pump station in the target area according to the hydrological data and meteorological data includes:

[0037] The hydrological data and meteorological data are preprocessed, and the inflow water flow data of the river network gate pump station is determined according to the processed hydrological data and meteorological data, wherein the preprocessing includes data cleaning and format normalization.

[0038] In this embodiment, the data types of the collected hydrological data and meteorological data may include images, texts, videos, etc. This embodiment unifies data from different sources and formats by preprocessing the data, thereby facilitating the determination of the inflow water flow data of the river network gate pump station.

[0039] The data cleaning step includes removing outliers (such as obviously unreasonable hydrological or meteorological data due to instrument failure, etc.). For example, if the hydrological or meteorological data at a certain moment far exceeds the normal range of the same period in the history of the region, and it is verified that it is caused by measurement errors, it needs to be removed.

[0040] Furthermore, when the hydrological data or meteorological data is standardized, it conforms to the format requirements for calculating the water flow data entering the reservoir. For example, the units of the flow data are uniformly converted into specific units (such as cubic meters per second, etc.), and the data is normalized so that it can be better calculated and analyzed.

[0041] Specifically, a water flow prediction model for the target area can be constructed based on the historical time series of the hydrological data and meteorological data of the target area and the time series data of the inflow water flow in the corresponding lag period. The inflow water flow time series data consists of the inflow water flow corresponding to multiple different time points. The inflow water flow data of the river network gate pump station in the target area can be determined according to the acquired hydrological data and meteorological data through the constructed water flow prediction model.

[0042] Furthermore, the inflow water flow at any time point is selected as the inflow water flow at the current moment according to the inflow water flow data, and the inflow water flow at the next moment is predicted using the water flow prediction model, thereby determining the inflow water flow data within the target time period of the river network gate pump station in the target area.

[0043] S130. Determine the sluice pump station dispatching data of the target area according to the inflow water flow data and dispatching constraints using a preset large dispatching model.

[0044] In this embodiment, the scheduling model is used to determine the sluice pump station scheduling data of the target area according to the inflow water flow data and scheduling constraints of the target area. The sluice pump station scheduling data is the equipment status time series data of the river network sluice pump station. Among them, the equipment status time series data is the number of pump openings and closings, pump opening degree and pump rotation speed at different times. The equipment status time series data ensures the water resource management and stable control of the target area.

[0045] This embodiment uses a pre-trained scheduling model to perform complex calculations and analyses on relevant input data (such as inflow water flow data, scheduling constraints, etc.), simulates the operating status of the sluice pump station under different conditions, and outputs reasonable sluice pump station scheduling data to regulate and manage water resources under different conditions.

[0046] Optionally, schedule the construction of a large model, including:

[0047] Determine the historical data of the river network sluice pump station in the target area; the historical data includes historical inflow water flow data and historical sluice pump station dispatching data; the historical sluice pump station dispatching data is a historical sluice pump station equipment status time series;

[0048] The historical data is used as the input and output of the neural network model for deep simulation training to obtain a large scheduling model for the river network gate pump station.

[0049] It should be noted that this embodiment includes a pre-training process for the scheduling large model, first determining the historical inflow data and historical sluice station scheduling data of the river network sluice station in the target area. The historical data can be obtained through historical records of hydrological stations and meteorological stations.

[0050] The historical inflow water flow data and the historical sluice pump station dispatching data are integrated according to the input format specified by the neural network model and used as the input and output of the neural network model for deep simulation training. It should be noted that the historical inflow water flow data and the historical sluice pump station dispatching data can be a pair of array input and output.

[0051] The neural network model in this embodiment can be a multi-layer perceptron, a recurrent neural network, a convolutional neural network, etc. In this embodiment, a large scheduling model can be obtained by training the recurrent neural network model.

[0052] Specifically, during the training process of the recurrent neural network model, the various parameters of the recurrent neural network model are determined. For a river network sluice pump station scheduling problem involving multiple factors (hydrological data, meteorological data, sluice pump station operation data, etc.) and complex interrelationships, 3-5 hidden layers may be set, and the corresponding activation function and the number of neurons in each layer may be determined.

[0053] Furthermore, during the training process of the recurrent neural network model, the recurrent neural network model will analyze and simulate various possible operating states of the gate pump station according to its internally set algorithms and rules, combined with the principles of hydrodynamics and the experience learned from historical data. For example, under different inflow conditions, the recurrent neural network model can meet the scheduling constraints such as water level restrictions and flow restrictions by adjusting the gate opening of the gate pump station and the pumping power of the pump station. After the training is completed, a large scheduling model of the river network gate pump station is obtained.

[0054] The large dispatching model of this embodiment can process and analyze massive amounts of historical data, which is beneficial for accurate prediction and control of sluice pump station dispatching data and early warning of disasters based on inflow water flow data.

[0055] Optionally, the historical data is used as the input and output of a neural network model for deep simulation training to obtain a large scheduling model for a river network gate pump station, including:

[0056] Dividing the historical data into a training set and a test set;

[0057] Using the historical inflow water flow data of the training set as the input of the neural network model, and using the historical sluice pump station scheduling data of the training set as the output of the neural network model for deep simulation training;

[0058] Inputting the historical inflow water flow data of the test set into the trained neural network model to obtain the reference sluice pump station dispatch result;

[0059] According to the reference sluice pump station scheduling results and the historical sluice pump station scheduling data of the test set, the parameters of the neural network model are adjusted until the reference sluice pump station scheduling results and the historical sluice pump station scheduling data of the test set meet the matching conditions to obtain a large model of river network sluice pump station scheduling.

[0060] It should be noted that the training set of this embodiment is used to train the neural network model, and the test set is used to update the parameters of the trained neural network model. The training set includes historical inflow water flow data and historical sluice pump station scheduling data for training the neural network model, and the test set includes historical inflow water flow data and historical sluice pump station scheduling data for updating the parameters of the trained neural network model.

[0061] The neural network model is deeply simulated and trained based on historical data to obtain a large scheduling model for the river network gate pump station. Specifically, in this embodiment, the historical data can be divided into a training set and a test set. First, a batch of historical data is taken from the training set and input into the recurrent neural network model for training. The historical inflow water flow data of the test set is input into the trained recurrent neural network model, and the predicted reference gate pump station scheduling results (such as pump gate opening, pump opening and closing number, etc.) are calculated through forward propagation.

[0062] Next, the difference between the reference sluice pump station scheduling results and the historical sluice pump station scheduling data in the test set, i.e., the loss value, is calculated according to the selected loss function.

[0063] Furthermore, an optimization algorithm is selected to update the parameters of the recurrent neural network model according to the difference (loss value) between the reference sluice station scheduling result and the historical sluice station scheduling data in the test set, until the reference sluice station scheduling result and the historical sluice station scheduling data in the test set meet the matching condition. For example, the matching condition may be that the difference between the reference sluice station scheduling result and the historical sluice station scheduling data converges to a preset threshold, or reaches a set number of training rounds, thereby obtaining a large scheduling model of the river network sluice station.

[0064] Optionally, after outputting the gate pump station dispatching data according to the inflow water flow data and dispatching constraints using a preset dispatching large model, the method further includes:

[0065] The large scheduling model is iteratively updated according to the inflow water flow data and the sluice pump station scheduling data.

[0066] In this embodiment, the current inflow water flow data is input into the scheduling model, and the model will output the corresponding gate pump station scheduling data (such as pump gate opening, pump opening and closing quantity, etc.), which can provide a reference for the actual scheduling operation.

[0067] It should be noted that in practical applications, on the one hand, new historical data can be collected, the training set and the test set can be re-divided, and the scheduling model can be retrained according to the above training steps to improve the performance of the scheduling model. On the other hand, the input data, model architecture, loss function, optimization algorithm, etc. of the scheduling model can be adjusted according to the actual sluice pump station scheduling data in the target area, so that the scheduling model can better adapt to the actual scheduling needs of the target area.

[0068] The scheduling model in this embodiment can dynamically adjust the future gate pump station scheduling data based on historical data and real-time data, continuously optimize the scheduling strategy plan, and achieve flexibility and real-time performance of gate pump station scheduling.

[0069] Optionally, after outputting the gate pump station dispatching data according to the inflow water flow data and the dispatching constraint conditions using the preset dispatching large model, the method further includes:

[0070] Evaluate the gate pump station dispatching data according to the evaluation index to obtain the gate pump station dispatching data evaluation result;

[0071] Generate a dispatching plan for the target area based on the inflow water flow data, the sluice pump station dispatching data, and the evaluation results of the sluice pump station dispatching data;

[0072] The scheduling plan is visually displayed on the terminal.

[0073] In this embodiment, the evaluation index is used to evaluate the water level control of the target area according to the sluice pump station scheduling data, wherein the evaluation index includes a water level control index or a sluice pump station flow regulation index, and the like.

[0074] Specifically, determine whether the upstream and downstream water levels of the river network gate pump station can be maintained within the set range before and after the target area is operated according to the gate pump station dispatching data. For example, the upstream water level fluctuation range of the river network gate pump station should be within ±0.5 meters above and below the target water level value, and the downstream water level fluctuation range of the river network gate pump station should be within ±0.3 meters above and below the target water level value. By comparing the actual water level data with the target water level value, the water level fluctuation range is determined, and the effect of the gate pump station dispatching data on water level control is further evaluated.

[0075] If the water level fluctuation range of the upstream and downstream of the river network gate pump station is less than the target water level value, the gate pump station dispatching data evaluation result is greater than the preset threshold value. If the water level fluctuation range of the upstream and downstream of the river network gate pump station is less than the target water level value, the gate pump station dispatching data evaluation result is less than the preset threshold value. The larger the gate pump station dispatching data evaluation result, the more accurate the gate pump station dispatching data in the target area is, and the more stable the water resources control capacity in the target area is.

[0076] Furthermore, a scheduling plan for the target area can be generated according to the natural language processing large model based on the reservoir water flow data, the gate pump station scheduling data, and the evaluation results of the gate pump station scheduling data. The scheduling plan of this embodiment can be visualized on the terminal in the form of pictures, videos or texts.

[0077] Specifically, the powerful semantic understanding and feature extraction capabilities of the natural language processing large model are used to mine key features and potential relationships in the data. For example, qualitative descriptions of water level control effects, flow regulation accuracy, equipment operating status, etc. are extracted from the text-based evaluation results and converted into feature vectors that can be understood by the model.

[0078] Analyze the dynamic relationship between the inflow data and the sluice pump station dispatch data, such as the combination of sluice pump station openings and the change rules of opening degrees at different flow levels, as well as the impact of these operations on subsequent flow and water levels. Through data mining technology, find out possible causal relationships or related patterns to provide a basis for the generation of dispatch plans.

[0079] The technical solution of the embodiment of the present invention determines the inflow water flow data of the river network sluice pump station in the target area through the hydrological data and meteorological data of the target area, and uses the pre-trained scheduling large model to obtain the sluice pump station scheduling data of the target area according to the inflow water flow data and the scheduling constraints on the water level of the target area and the operating capacity of the river network sluice pump station, so as to realize the efficient allocation of water resources in the target area and the stable control of the water dynamics of the river network sluice pump station.

[0080] Embodiment 2

[0081] Figure 2 This is a schematic diagram of the structure of a river network gate pump station dispatching device provided in the second embodiment of the present invention. This embodiment can be applied to the dispatching of river network gate pump stations. The river network gate pump station dispatching device can be implemented in the form of hardware and / or software. The river network gate pump station dispatching device can be configured in any electronic device with network communication and computing. Figure 2 As shown, the device comprises:

[0082] The target area information determination module 310 is used to determine the hydrological data, meteorological data and dispatching constraints of the target area, wherein the dispatching constraints are used to constrain the water level and the operating capacity of the river network gate pump station in the target area;

[0083] The inflow water flow determination module 320 is used to determine the inflow water flow data of the river network gate pump station in the target area according to the hydrological data and meteorological data; the inflow water flow data is the inflow flow time series data of the river network gate pump station;

[0084] The scheduling data determination module 330 is used to determine the sluice pump station scheduling data of the target area according to the inflow water flow data and scheduling constraints using a preset scheduling large model, wherein the sluice pump station scheduling data is the equipment status time series data of the river network sluice pump station.

[0085] Optionally, determining the inflow water flow data of the river network sluice pump station in the target area according to the hydrological data and meteorological data includes:

[0086] The hydrological data and meteorological data are preprocessed, and the inflow water flow data of the river network gate pump station is determined according to the processed hydrological data and meteorological data. The preprocessing includes data cleaning and format normalization.

[0087] Optionally, schedule the construction of a large model, including:

[0088] Determine the historical data of the river network sluice pump station in the target area; the historical data includes historical inflow water flow data and historical sluice pump station dispatching data; the historical sluice pump station dispatching data is a historical sluice pump station equipment status time series;

[0089] The historical data is used as the input and output of the neural network model for deep simulation training to obtain a large model for river network gate pump station scheduling.

[0090] Optionally, the historical data is used as the input and output of a neural network model for deep simulation training to obtain a large model for river network gate pump station scheduling, including:

[0091] Dividing the historical data into a training set and a test set;

[0092] Using the historical inflow water flow data of the training set as the input of the neural network model, and using the historical sluice pump station scheduling data of the training set as the output of the neural network model for deep simulation training;

[0093] Inputting the historical inflow water flow data of the test set into the trained neural network model to obtain the reference sluice pump station dispatch result;

[0094] According to the reference sluice pump station scheduling results and the historical sluice pump station scheduling data of the test set, the parameters of the neural network model are adjusted until the reference sluice pump station scheduling results and the historical sluice pump station scheduling data of the test set meet the matching conditions to obtain a large model of river network sluice pump station scheduling.

[0095] Optionally, after determining the sluice pump station dispatching data of the target area according to the inflow water flow data and dispatching constraints using a preset dispatching large model, the method further includes:

[0096] The large scheduling model is iteratively updated according to the inflow water flow data and the sluice pump station scheduling data.

[0097] Optionally, after determining the sluice pump station dispatching data of the target area according to the inflow water flow data and the dispatching constraint conditions using a preset dispatching large model, the method further includes:

[0098] The gate pump station dispatching data is evaluated according to the evaluation index to obtain the gate pump station dispatching data evaluation result; the evaluation index is used to evaluate the water level control of the target area according to the gate pump station dispatching data;

[0099] Generate a dispatching plan for the target area based on the inflow water flow data, the sluice pump station dispatching data, and the evaluation results of the sluice pump station dispatching data;

[0100] The scheduling plan is visually displayed on the terminal.

[0101] Optionally, the hydrological data include precipitation, precipitation frequency, evaporation and groundwater flow; the meteorological data include temperature, humidity and wind speed; and the scheduling constraints include upstream and downstream water level constraints of the river network gate pump station and gate flow constraints.

[0102] The technical solution of the embodiment of the present application determines the inflow water flow data of the river network sluice pump station in the target area through the hydrological data and meteorological data of the target area, and uses the pre-trained scheduling large model to obtain the sluice pump station scheduling data of the target area according to the inflow water flow data and the scheduling constraints on the water level of the target area and the operating capacity of the river network sluice pump station, so as to realize the efficient allocation of water resources in the target area and the stable control of the water dynamics of the river network sluice pump station.

[0103] The river network gate pump station scheduling device provided in the embodiment of the present invention can execute the river network gate pump station scheduling method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0104] Embodiment 3

[0105] Figure 3 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0106] like Figure 3 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0107] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0108] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The processor 11 executes the various methods and processes described above, such as a river network gate pump station scheduling method.

[0109] In some embodiments, the river network gate pump station scheduling method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the river network gate pump station scheduling method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute the river network gate pump station scheduling method in any other appropriate manner (for example, by means of firmware).

[0110] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0111] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0112] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0113] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0114] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0115] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0116] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0117] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for dispatching a river network sluice pump station, characterized in that: include: Determine hydrological data, meteorological data and dispatching constraints of the target area, wherein the dispatching constraints are used to constrain the water level and the operating capacity of the river network gate pump station in the target area; Determine the inflow water flow data of the river network sluice pump station in the target area according to the hydrological data and meteorological data; the inflow water flow data is the time series data of the inflow water flow of the river network sluice pump station; The preset large-scale dispatching model is used to determine the sluice pump station dispatching data of the target area according to the inflow water flow data and dispatching constraints. The sluice pump station dispatching data is the equipment status time series data of the river network sluice pump station.

2. The method according to claim 1, characterized in that Determine the inflow water flow data of the river network sluice pump station in the target area based on the hydrological data and meteorological data, including: The hydrological data and meteorological data are preprocessed, and the inflow water flow data of the river network gate pump station is determined according to the processed hydrological data and meteorological data. The preprocessing includes data cleaning and format normalization.

3. The method according to claim 1, characterized in that Scheduling the construction process of a large model, including: Determine the historical data of the river network sluice pump station in the target area; the historical data includes historical inflow water flow data and historical sluice pump station dispatching data; the historical sluice pump station dispatching data is a historical sluice pump station equipment status time series; The historical data is used as the input and output of the neural network model for deep simulation training to obtain a large model for river network gate pump station scheduling.

4. The method according to claim 3, characterized in that The historical data is used as the input and output of the neural network model for deep simulation training to obtain a large model for river network gate pump station scheduling, including: Dividing the historical data into a training set and a test set; Using the historical inflow water flow data of the training set as the input of the neural network model, and using the historical sluice pump station scheduling data of the training set as the output of the neural network model to perform deep simulation training; Inputting the historical inflow water flow data of the test set into the trained neural network model to obtain the reference sluice pump station dispatch result; According to the reference sluice pump station scheduling results and the historical sluice pump station scheduling data of the test set, the parameters of the neural network model are adjusted until the reference sluice pump station scheduling results and the historical sluice pump station scheduling data of the test set meet the matching conditions to obtain a large model of river network sluice pump station scheduling.

5. The method according to claim 1, characterized in that After determining the sluice pump station dispatching data of the target area according to the inflow water flow data and dispatching constraints using the preset dispatching large model, it includes: The large scheduling model is iteratively updated according to the inflow water flow data and the sluice pump station scheduling data.

6. The method according to claim 1, characterized in that After determining the sluice pump station dispatching data of the target area according to the inflow water flow data and dispatching constraints using the preset dispatching large model, the method further includes: The gate pump station dispatching data is evaluated according to the evaluation index to obtain the gate pump station dispatching data evaluation result; the evaluation index is used to evaluate the water level control of the target area according to the gate pump station dispatching data; Generate a dispatching plan for the target area based on the inflow water flow data, the sluice pump station dispatching data, and the evaluation results of the sluice pump station dispatching data; The scheduling plan is visually displayed on the terminal.

7. The method according to claim 1, characterized in that The hydrological data include precipitation, precipitation frequency, evaporation and groundwater flow; the meteorological data include temperature, humidity and wind speed; the scheduling constraints include upstream and downstream water level constraints of the river network gate pump station and gate flow constraints.

8. A river network gate pump station dispatching device, characterized in that: include: A target area information determination module, used to determine the hydrological data, meteorological data and dispatching constraints of the target area, wherein the dispatching constraints are used to constrain the water level and the operating capacity of the river network gate pump station in the target area; An inflow water flow determination module is used to determine the inflow water flow data of the river network gate pump station in the target area according to the hydrological data and meteorological data; the inflow water flow data is the inflow flow time series data of the river network gate pump station; The scheduling data determination module is used to output the gate pump station scheduling data according to the inflow water flow data and scheduling constraints using a preset scheduling large model, wherein the gate pump station scheduling data is the equipment status time series data of the river network gate pump station.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method for scheduling a river network gate pump station as described in any one of claims 1-7 is implemented.

10. A storage medium storing computer executable instructions, characterized in that: When the computer executable instructions are executed by a computer processor, they are used to execute the method for scheduling a river network gate pump station as described in any one of claims 1-7.

Images