Method and device for coordinated dispatching of composite water network, electronic equipment and storage medium

Abstract

The present application relates to the technical field of water regulation, and provides a method and device for coordinated regulation of a composite water network, an electronic device and a storage medium, the method comprising: obtaining real-time habitat state data of each grid unit in the composite water network; calculating a habitat suitability index deviation of each grid unit based on the real-time habitat state data; determining an abnormal grid unit if the habitat suitability index deviation exceeds a first preset deviation threshold; adjusting a weight coefficient of an ecological gain target term of the abnormal grid unit in an initial objective function to obtain an updated objective function; performing optimization calculation based on the updated objective function to generate a regulation scheme for the composite water network, and controlling the composite water network based on the regulation scheme. The method provided by the present application realizes fine and adaptive coordinated regulation for local ecological crisis by constructing a habitat suitability dynamic feedback mechanism and a target weight dynamic correction, thereby improving flood control safety and realizing coordinated growth of ecological service functions.

Description

Technical Field

[0001] This invention relates to the field of water conservancy scheduling technology, and in particular to a method, apparatus, electronic device and storage medium for the coordinated scheduling of a composite water network. Background Technology

[0002] Complex water networks typically consist of interconnected rivers, lakes, and reservoirs. Their daily management and scheduling are crucial for ensuring flood control safety, meeting regional water supply demands, and maintaining aquatic ecological balance. With increasingly stringent modern ecological protection requirements, balancing the rational allocation of water resources with the stable growth of the aquatic ecosystem during water network scheduling has become a significant technical challenge in water management. To meet this need, existing complex water network scheduling schemes primarily employ a goal-oriented, single-scheduling approach. Specifically, this approach typically sets an upper limit for water levels based on actual flood control safety needs, or a lower limit for flow rates based on societal water supply demands. Regarding ecological protection, existing scheduling schemes usually treat ecological baseflow as a static, rigid constraint, maintaining the basic water volume within the river and lake system by controlling the opening and closing of gates or pumping stations in the water network, thereby ensuring basic ecological water requirements.

[0003] However, existing complex water network scheduling schemes have significant shortcomings in practical applications. Because they only maintain basic water volume as a static constraint and usually adopt unified scheduling commands for the entire basin or large area, water conservancy scheduling often comes at the cost of biodiversity, and cannot accurately and adaptively allocate flow to meet the differentiated needs of different habitat units in the complex water network. Summary of the Invention

[0004] This invention provides a method, apparatus, electronic device, and storage medium for the coordinated scheduling of a complex water network, which addresses the shortcomings of existing water conservancy scheduling that often sacrifices biodiversity and fails to provide accurate and adaptive flow allocation for the differentiated needs of different habitat units in a complex water network.

[0005] This invention provides a method for the coordinated scheduling of a composite water network, comprising: Acquire real-time habitat status data for each grid unit in the composite water network; Based on the real-time habitat status data of each grid cell, the habitat suitability index deviation of each grid cell is calculated; If the habitat suitability index deviation exceeds a first preset deviation threshold, abnormal grid cells are identified, and the weight coefficients of the ecological gain objective term of the abnormal grid cells in the initial objective function are adjusted to obtain an updated objective function. Based on the updated objective function, an optimization calculation is performed to generate a scheduling scheme for the composite water network, so as to control the composite water network based on the scheduling scheme.

[0006] According to the collaborative scheduling method of a composite water network provided by the present invention, the ecological gain target includes a water quality improvement sub-item and a biodiversity gain sub-item; The step of adjusting the weight coefficients of the ecological gain objective term in the initial objective function for the abnormal grid cells to obtain the updated objective function includes: The weight coefficients of the abnormal grid cells in the water quality improvement sub-item and the biodiversity gain sub-item are adjusted to obtain the updated objective function; The step of performing optimization calculations based on the updated objective function to generate a scheduling scheme for the composite water network includes: Multiple scheduling candidate schemes are obtained, and the simulated water quality improvement and simulated biodiversity gain of each grid unit under the scheduling candidate schemes are simulated. Based on the updated objective function, the simulated water quality improvement and simulated biodiversity gain of each grid cell are applied to calculate the target evaluation value of each scheduling candidate scheme. The scheduling scheme is obtained by performing global iterative optimization based on the target evaluation value.

[0007] According to the collaborative scheduling method of a composite water network provided by the present invention, the initial objective function further includes a safety constraint term; the safety constraint term is used to output a preset penalty extreme value when the simulated water level value under the scheduling candidate scheme exceeds the preset warning water level. The step of adjusting the weight coefficients of the abnormal grid cells in the water quality improvement sub-item and the biodiversity gain sub-item to obtain the updated objective function includes: Adjusting the weight coefficients of the abnormal grid cells corresponding to the water quality improvement sub-item and the biodiversity gain sub-item yields the ecological gain objective function. The update objective function is constructed based on the ecological gain objective function and the security constraint term.

[0008] According to the present invention, a collaborative scheduling method for a composite water network, wherein controlling the composite water network based on the scheduling scheme includes: Obtain the feedback habitat suitability index of each grid unit in the composite water network after executing the current action parameters corresponding to the scheduling scheme; Based on the feedback habitat suitability index of each grid cell, the feedback index deviation of each grid cell is calculated. If the feedback index deviation of any grid cell exceeds a second preset deviation threshold, the feedback adjustment amount of the arbitrary grid cell is calculated based on the feedback index deviation of the arbitrary grid cell. Based on the feedback adjustment amount of the arbitrary grid cell, the current action parameters corresponding to the arbitrary grid cell are adjusted to obtain the updated action parameters; The updated action parameters are used as the current action parameters, and the process is repeated to obtain the feedback habitat suitability index of each grid cell after executing the current action parameters, until the deviation of the feedback index of each grid cell is calculated to be no greater than the second preset deviation threshold.

[0009] According to a collaborative scheduling method for a composite water network provided by the present invention, the step of calculating the habitat suitability index deviation of each grid cell based on the real-time habitat status data of each grid cell includes: Determine the ideal habitat suitability index for each grid cell; Based on the real-time habitat status data of each grid cell, the actual habitat suitability index of each grid cell is calculated. Based on the actual habitat suitability index and the ideal habitat suitability index of each grid cell, the habitat suitability index deviation of each grid cell is calculated.

[0010] According to the collaborative scheduling method of a composite water network provided by the present invention, determining the ideal habitat suitability index of each grid unit includes: The ecological function corresponding to each grid unit is obtained; the ecological function includes at least one of spawning ground, wetland purification, and migration corridor. Based on the ecological function of each grid unit, the ideal habitat suitability index of each grid unit is determined.

[0011] According to the collaborative scheduling method of a composite water network provided by the present invention, the real-time habitat status data includes flow velocity parameters, water level parameters, dissolved oxygen parameters, and biomass parameters.

[0012] The present invention also provides a coordinated scheduling device for a composite water network, comprising: The acquisition unit acquires real-time habitat status data for each grid unit in the composite water network; The deviation calculation unit calculates the habitat suitability index deviation for each grid cell based on the real-time habitat status data for each grid cell. The objective function update unit identifies abnormal grid cells when the habitat suitability index deviation exceeds a first preset deviation threshold, adjusts the weight coefficient of the abnormal grid cells in the ecological gain objective term of the initial objective function, and obtains the updated objective function. The collaborative scheduling unit performs optimization calculations based on the updated objective function to generate a scheduling scheme for the composite water network, and controls the composite water network based on the scheduling scheme.

[0013] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the collaborative scheduling method of the composite water network as described above.

[0014] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the collaborative scheduling method for the composite water network as described above.

[0015] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the collaborative scheduling method for the composite water network as described above.

[0016] The present invention provides a method, apparatus, electronic device, and storage medium for the coordinated scheduling of a composite water network. By acquiring the habitat status of the grid units of the composite water network in real time, the habitat suitability index deviation is calculated. When abnormal grid units are identified due to excessive deviation, the weight coefficient of the ecological gain term of the abnormal grid units in the objective function is dynamically adjusted to obtain an updated objective function. Then, the optimal scheduling scheme is generated for closed-loop control. This effectively overcomes the defect of traditional water conservancy scheduling that only focuses on water level and ignores the habitat of aquatic organisms. It constructs a dynamic feedback mechanism for habitat suitability, ensuring that the water resources of the entire network can be adaptively and precisely allocated in response to local ecological crises. This greatly improves the coordinated protection capability and automated response level of the ecological service functions in the operation of water conservancy projects. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating the collaborative scheduling method for a composite water network provided by the present invention. Figure 2 This is a schematic diagram of the grid unit division of the composite water network provided by the present invention; Figure 3 This is a schematic diagram of the collaborative scheduling system architecture for the composite water network and aquatic-biological system provided by the present invention; Figure 4 This is a flowchart illustrating the collaborative scheduling method for a composite water network based on habitat feedback provided by the present invention. Figure 5 This is a comparative diagram showing the effects of the collaborative scheduling method for composite water networks provided by the present invention; Figure 6 This is a schematic diagram of the structure of the collaborative scheduling device for the composite water network provided by the present invention; Figure 7 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0020] It should be understood that 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. Therefore, features defined with "first" and "second" may explicitly or implicitly include one or more of the stated features. In the description of embodiments of the present invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0021] It should be noted that all actions involving the acquisition of signals, information, or data in this application are carried out in compliance with the relevant data protection laws and regulations of the locality and with permission from the owner of the relevant device.

[0022] In practical applications, this method primarily addresses the issue that existing water management systems focus only on single indicators such as water level and volume, neglecting the real-time impact of hydrodynamic processes on aquatic organisms. This often results in water management sacrificing biodiversity and failing to provide precise and adaptive flow allocation tailored to the differentiated needs of various habitat units within a complex water network. To address this problem, this invention provides a collaborative scheduling method for complex water networks. This method can be implemented using automatic control equipment to achieve adaptive and refined collaborative control. Figure 1 This is a flowchart illustrating the collaborative scheduling method for a composite water network provided by the present invention, as shown below. Figure 1 As shown, the method includes: Step 110: Obtain real-time habitat status data for each grid unit in the composite water network.

[0023] Here, "complex water network" typically refers to a water system network with a complex topological structure, such as a river-lake-reservoir interconnected system, which can usually be divided into multiple grid units. A grid unit is a basic unit for regulating and responding to a complex complex water network, which is divided through digital topology modeling. Each grid unit has a specific ecological function, such as a spawning ground, a purification wetland, or a migration corridor.

[0024] In addition, the real-time habitat status data here refers to multi-dimensional physical and biochemical indicators that can reflect the current hydrodynamic and ecological environment of each grid unit.

[0025] Specifically, an integrated sensor array deployed in the water network can be used to acquire multi-dimensional habitat state vectors within each grid cell in real time. For example, this real-time habitat state data can include, but is not limited to, dynamic data such as flow velocity, water level, dissolved oxygen, and biomass within the current grid, thereby achieving real-time perception of all elements from hydrological data to ecological conditions.

[0026] Step 120: Based on the real-time habitat status data of each grid cell, calculate the habitat suitability index deviation of each grid cell.

[0027] Here, the Habitat Suitability Index Deviation is used to quantify the gap or degree of matching between the current actual hydrological environment and the ideal Habitat Suitability Index (HSI) for the target aquatic organisms.

[0028] Specifically, a real-time mapping logic between hydrodynamics and habitat indices can be pre-established to calculate the habitat suitability index deviation for each grid cell. For any grid cell, the actual habitat suitability index under the current flow field conditions can be calculated based on the acquired real-time habitat state data, such as flow velocity, water level, dissolved oxygen, and biomass parameters. Then, by comparing the actual habitat suitability index with the ideal habitat suitability index corresponding to the ecological function of the grid cell and calculating the difference, the current habitat suitability index deviation for that grid cell can be obtained.

[0029] Step 130: If the habitat suitability index deviation exceeds a first preset deviation threshold, identify abnormal grid cells, adjust the weight coefficient of the ecological gain objective term of the abnormal grid cells in the initial objective function, and obtain an updated objective function.

[0030] Here, the first preset deviation threshold can be understood as a preset ecological early warning threshold. Here, abnormal grid cells refer to grid cells whose habitat suitability deviates significantly from the ideal state and are identified as functionally impaired.

[0031] Furthermore, the initial objective function here refers to the fundamental mathematical model used for global optimization decision-making, which contains evaluation indicators across multiple dimensions. The ecological gain objective term refers to the portion of this function specifically used to measure the effectiveness of ecological restoration or improvement. Here, the weight coefficients corresponding to the ecological gain objective term represent the degree of preference for satisfying the ecological gain objective term of a specific region in the global scheduling decision. Therefore, the updated objective function here refers to the new decision function obtained by dynamically adjusting the parameters based on the real-time ecological damage situation.

[0032] Specifically, the system determines in real time whether the calculated habitat suitability index deviation of each grid cell exceeds a first preset deviation threshold, i.e., an ecological early warning threshold. If it does, an automatic response is triggered, identifying the grid cell as an abnormal grid cell, i.e., a grid cell with impaired function.

[0033] Furthermore, to prioritize mitigating local ecological crises during the redistribution of water flow across the entire network, the weighting coefficients of the ecological gain objective terms corresponding to the abnormal grid cell in the initial objective function can be dynamically adjusted. For example, the initial objective function may incorporate composite ecological gain terms such as water quality improvement and biodiversity index. By dynamically increasing the weighting coefficients corresponding to the region where the abnormal grid cell is located, it can be ensured that the optimization scheme prioritizes addressing the ecological needs of the abnormal grid cell, thereby constructing an updated objective function that considers multiple objectives.

[0034] It should be noted that by dynamically adjusting the weight coefficients corresponding to abnormal grid cells in the ecological gain objective, the damage to the ecological dimension can be more accurately quantified and mapped, ensuring that subsequent optimization schemes can prioritize and accurately address the ecological needs of damaged cells.

[0035] Step 140: Perform optimization calculations based on the updated objective function to generate a scheduling scheme for the composite water network, and control the composite water network based on the scheduling scheme.

[0036] Here, the scheduling scheme refers to the precise and adaptive water flow allocation execution instructions generated to meet the differentiated needs of different habitat units in the complex water network, such as the opening and closing combinations and opening status of each gate and pumping station.

[0037] Specifically, a digital twin engine can be used to simulate the redistribution of water flow across the entire network through different combinations of hydraulic structure control. Based on this, a multi-objective optimization algorithm, such as the Non-dominated Sorting Genetic Algorithm II (NSGA-II), is employed to perform global iterative optimization based on the update objective function. Under the premise of satisfying hard constraints such as flood control safety, the optimal gate-pump combination opening and closing scheme that can unleash the maximum ecological potential of the water network system is found and used as the final scheduling scheme.

[0038] Subsequently, the scheduling scheme is transformed into specific control instructions, such as being sent to a programmable logic controller (PLC), to adaptively complete the fine-grained water allocation and control the operation of the composite water network.

[0039] The method provided in this invention calculates the habitat suitability index deviation by acquiring the habitat status of composite water network grid units in real time. When abnormal grid units are identified due to excessive deviation, the weight coefficient of the ecological gain term of the abnormal grid units in the objective function is dynamically adjusted to obtain an updated objective function. Then, the optimal scheduling scheme is generated for closed-loop control. This effectively overcomes the disconnect between traditional water conservancy scheduling, which only focuses on water level and ignores aquatic biological habitats. It constructs a dynamic feedback mechanism for habitat suitability, ensuring that the water resources of the entire network can be adaptively and precisely allocated in response to local ecological crises. This greatly improves the collaborative protection capability and automated response level of ecological service functions in the operation of water conservancy projects.

[0040] Based on any of the above embodiments, the ecological gain target includes a water quality improvement sub-item and a biodiversity gain sub-item.

[0041] In step 130, the weight coefficients of the ecological gain objective term in the initial objective function of the abnormal grid cells are adjusted to obtain the updated objective function, including: The weight coefficients of the abnormal grid cells in the water quality improvement sub-item and the biodiversity gain sub-item are adjusted to obtain the updated objective function.

[0042] Here, the ecological gain target includes the water quality improvement sub-item and the biodiversity gain sub-item. These two items concretize the macro-level ecological gain target into evaluation sub-items of water quality purification improvement and biodiversity index.

[0043] Specifically, after identifying the anomalous grid cells, their corresponding weight coefficients in the water quality improvement and biodiversity gain sub-items can be dynamically increased. Through this multi-dimensional weight adjustment, it is ensured that the specific needs of the damaged area occupy a larger proportion in the global calculation, thereby constructing an update objective function that takes into account both local damage compensation and global balance.

[0044] In step 140, an optimization calculation is performed based on the updated objective function to generate a scheduling scheme for the composite water network, including: Multiple scheduling candidate schemes are obtained, and the simulated water quality improvement and simulated biodiversity gain of each grid unit under the scheduling candidate schemes are simulated. Based on the updated objective function, the simulated water quality improvement and simulated biodiversity gain of each grid cell are applied to calculate the target evaluation value of each scheduling candidate scheme. The scheduling scheme is obtained by performing global iterative optimization based on the target evaluation value.

[0045] Here, the scheduling candidate schemes refer to different pre-set combinations of control states such as gate opening degree and pump station power. Furthermore, the simulated water quality improvement and simulated biodiversity gain here are the future degrees of water quality improvement and biodiversity increase predicted by digital twin models under specific scheduling schemes.

[0046] Specifically, firstly, multiple scheduling candidate schemes under different combinations of gate and pump opening degrees in the complex water network can be extracted. Then, simulation methods such as digital twin engines are used to simulate the redistribution process of the entire network's water flow under different scheduling candidate schemes. For example, by combining aquatic coupling mechanisms, the simulated water quality improvement and simulated biodiversity gain of each grid cell under corresponding flow field and hydrodynamic conditions can be predicted and calculated.

[0047] Then, the simulated water quality improvement and simulated biodiversity gain of each grid cell are substituted into the updated objective function containing adjusted weight coefficients for mathematical calculation to obtain the target evaluation value corresponding to each scheduling candidate scheme. The target evaluation value here is a specific score measuring the comprehensive performance of each scheduling candidate scheme, reflecting the magnitude of the overall functional gain of the composite water network brought about by a specific scheduling action.

[0048] Furthermore, by applying global optimization algorithms such as multi-objective genetic algorithms, the optimal target evaluation value that maximizes the overall ecological function gain of the composite water network can be found through continuous iteration and screening based on the target evaluation values ​​of all candidate scheduling parameters. The candidate scheduling parameters corresponding to the optimal target evaluation value are then determined as the final scheduling scheme.

[0049] It should be noted that by conducting pre-simulation and global iterative optimization, the optimal solution for multiple objectives can be efficiently and accurately selected from a massive number of potential scheduling parameters, effectively avoiding the risks brought about by traditional blind scheduling.

[0050] The method provided in this invention refines the ecological gain objective into water quality improvement and biodiversity gain sub-items, simulates and calculates the simulated water quality improvement and simulated biodiversity gain under each candidate scheduling parameter, and then combines the updated objective function to calculate the target evaluation value for global iterative optimization. This effectively solves the problems of multiple ecological objective conflicts and coarse regulation granularity in complex water networks, enabling the final generated scheduling scheme to more finely evaluate the specific impact of different regulation actions on water quality and biodiversity. It realizes the transformation from static experience-based scheduling to adaptive and precise water flow allocation based on multi-objective optimization algorithms, maximizing the overall ecological potential of the water network system.

[0051] Based on any of the above embodiments, the initial objective function further includes a security constraint term; the security constraint term is used to output a preset penalty extreme value when the simulated water level value under the scheduling candidate scheme exceeds the preset warning water level.

[0052] Here, the initial objective function includes a safety constraint term in addition to the ecological gain dimension. This term is mainly used to ensure the basic flood control safety of the complex water network. Furthermore, the simulated water level value here refers to the expected water level of each node within the water network calculated through simulation under a specific scheduling candidate scheme. The preset warning water level here is the upper limit of water level safety set based on flood control requirements and can be preset based on actual conditions. The preset penalty extreme value here refers to a value tending towards infinity or extremely unfavorable in the mathematical model, used to eliminate unsafe scheduling candidate schemes during the optimization process.

[0053] Specifically, a digital model can be used to simulate the hydrodynamic evolution of the complex water network under the current scheduling candidate schemes, and the corresponding simulated water level values ​​can be extracted. It is then determined in real time whether the simulated water level value exceeds the preset warning water level stipulated by flood control requirements. If the preset warning water level is exceeded, a safety constraint mechanism is triggered, causing the safety constraint term to directly output a preset penalty extreme value, thereby eliminating the corresponding unsafe scheduling candidate scheme.

[0054] It should be noted that flood control safety is incorporated as a hard constraint into the optimization calculation. By assigning extreme penalty values ​​to force the optimization algorithm to eliminate scheduling schemes with potential flood risks, the bottom-line safety of ecological scheduling is ensured.

[0055] Based on any of the above embodiments, adjusting the weight coefficients of the abnormal grid cells in the water quality improvement sub-item and the biodiversity gain sub-item to obtain the updated objective function includes: Adjusting the weight coefficients of the abnormal grid cells corresponding to the water quality improvement sub-item and the biodiversity gain sub-item yields the ecological gain objective function. The update objective function is constructed based on the ecological gain objective function and the security constraint term.

[0056] Here, the ecological gain objective function refers to a composite mathematical expression that purely reflects the multidimensional ecological restoration effects, such as water quality and biodiversity.

[0057] Specifically, in the process of constructing and updating the objective function, for the identified abnormal grid cells, the weight coefficients of the abnormal grid cells in the water quality improvement sub-item and the biodiversity gain sub-item can be dynamically increased. The various ecological indicators after the weight adaptive adjustment are combined to construct an ecological gain objective function specifically for evaluating ecological benefits.

[0058] Then, the ecological gain objective function, which represents the priority of ecological restoration, is mathematically integrated with the flood control safety constraint, which serves as a veto condition, to form a complete updated objective function. During subsequent optimization calculations based on this updated objective function, if a preset penalty extreme value is triggered, this extreme value will dominate the evaluation result of the entire objective function, thus forcibly discarding the candidate solution.

[0059] Here, the updated objective function can be expressed by the following formula, as shown in the following equation: ; In the formula, This indicates that the objective function is being updated; Indicates the first The weighting coefficients corresponding to the water quality improvement sub-items in each grid cell; Indicates the first Water quality improvement per grid unit; Indicates the first The weighting coefficients corresponding to the biodiversity gain sub-item of each grid cell; Indicates the first Biodiversity gain per grid cell; This represents the weighting coefficient corresponding to the safety constraint term; Indicates the first The safety constraint term for the nth grid cell. As can be seen from the formula, if the nth... If a grid cell is deemed an abnormal grid cell, the weighting coefficients for the water quality improvement sub-item and the biodiversity gain sub-item corresponding to that grid cell can be increased. Additionally, if a grid cell's simulated water level exceeds a preset warning level under a certain scheduling candidate scheme, the safety constraint term for that grid cell will be output as a preset penalty extreme value.

[0060] The method provided in this invention introduces a safety constraint term into the objective function and outputs a preset penalty extreme value when the simulated water level exceeds the limit. Then, it combines the ecological gain objective function with dynamically adjusted weights to construct a complete update objective function. This effectively solves the problem of potential negative impacts of water conservancy project operation on biological systems and the conflict of multiple objectives. It enables the scheduling algorithm to strictly meet the hard premise of flood control safety while pursuing the maximum ecological potential and functional gain of the water network system, and truly achieves the multi-objective unity of flood control safety guarantee and ecological service function synergistic growth.

[0061] Based on any of the above embodiments, step 140, controlling the composite water network based on the scheduling scheme, includes: Obtain the feedback habitat suitability index of each grid unit in the composite water network after executing the current action parameters corresponding to the scheduling scheme; Based on the feedback habitat suitability index of each grid cell, the feedback index deviation of each grid cell is calculated. If the feedback index deviation of any grid cell exceeds a second preset deviation threshold, the feedback adjustment amount of the arbitrary grid cell is calculated based on the feedback index deviation of the arbitrary grid cell. Based on the feedback adjustment amount of the arbitrary grid cell, the current action parameters corresponding to the arbitrary grid cell are adjusted to obtain the updated action parameters; The updated action parameters are used as the current action parameters, and the process is repeated to obtain the feedback habitat suitability index of each grid cell after executing the current action parameters, until the deviation of the feedback index of each grid cell is calculated to be no greater than the second preset deviation threshold.

[0062] Here, the current action parameters refer to the specific control commands issued in the scheduling plan, such as the initially set specific gate opening or pump station power. The feedback habitat suitability index refers to the latest actual habitat suitability assessment index presented in the water network after the hydraulic structures have performed their control actions.

[0063] Specifically, the hydraulic structure actuators can be directly controlled via interfaces such as programmable logic controllers (PLCs), issuing current action parameters according to the current scheduling plan. Each time a control action is executed, feedback data on aquatic habitat indicators of each grid unit in the composite water network is immediately monitored through a sensor network, i.e., real-time habitat status data is acquired. Then, by calculating the acquired feedback data, the habitat suitability index of each grid unit after executing the current action parameters is obtained.

[0064] Then, for each grid cell, the feedback index deviation can be obtained by calculating the difference between the feedback habitat suitability index of that grid cell and the ideal habitat suitability index corresponding to that grid cell. It should be noted that the feedback index deviation of any grid cell is used to quantify the difference between the actual habitat effect of that grid cell after the implementation of the control action and the expected target.

[0065] Furthermore, it is determined in real time whether the calculated feedback index deviation of each grid cell exceeds a second preset deviation threshold. If the feedback index deviation of any grid cell exceeds the second preset deviation threshold, a closed-loop proportional-integral-derivative (PID) control strategy for the habitat suitability index deviation can be used to calculate and output the feedback adjustment amount for automatically fine-tuning that grid cell, based on the magnitude of the feedback index deviation and preset proportional, integral, and derivative control parameters. Here, the second preset deviation threshold can be understood as the boundary value of the target convergence interval for the allowable fluctuation of the habitat index; exceeding this threshold indicates that the ecological function improvement brought about by the current regulation has not met expectations. The feedback adjustment amount is an action correction value calculated based on the current deviation magnitude.

[0066] In one embodiment, the feedback adjustment amount of any grid cell can be calculated using the following formula, as shown below: ; In the formula, This represents the feedback adjustment amount for any grid cell; , , Indicates different types of current action parameters; This indicates the feedback index deviation at the current control time step.

[0067] Then, the calculated feedback adjustment of any grid cell can be directly applied to the current action parameters of that grid cell. By increasing or decreasing the corresponding opening or power command, the action parameters are corrected, thus obtaining the updated action parameters of that grid cell. The action parameters of other grid cells can remain the same as those in the scheduling scheme.

[0068] Next, the generated updated action parameters can be reissued and executed to replace the original action parameters. The habitat suitability index fed back after executing the updated action parameters is monitored again, and the feedback index deviation of each grid cell is recalculated. The above closed-loop process of error assessment and parameter fine-tuning is executed repeatedly until the feedback index deviation of each grid cell converges to the target range, that is, the feedback index deviation is reduced to no more than the second preset deviation threshold, and then the fine-tuning loop is stopped.

[0069] It should be noted that through continuous iterative cycles and real-time monitoring, the blindness of traditional one-time command issuance has been completely changed, realizing a complete closed loop from regulatory actions to ecological status response, and ensuring the ultimate achievement of regulatory precision.

[0070] The method provided in this invention obtains the feedback habitat suitability index of each grid unit after the execution of an action and calculates the feedback index deviation. When the deviation exceeds a second preset deviation threshold, the feedback adjustment amount is calculated and the action parameters are dynamically corrected. This process is repeated until the deviation converges. This effectively solves the problems of lack of closed-loop function improvement and blind and lagging water conservancy scheduling in the prior art. It establishes an intelligent execution loop that can perceive changes in ecological function in real time and finely adjust hydraulic structures in reverse. This enables every gate and pump opening and closing in a complex water network environment to accurately converge to the expected ecological protection target, greatly improving the accuracy and adaptability of water network coordinated regulation.

[0071] Based on any of the above embodiments, step 120 includes: Determine the ideal habitat suitability index for each grid cell; Based on the real-time habitat status data of each grid cell, the actual habitat suitability index of each grid cell is calculated. Based on the actual habitat suitability index and the ideal habitat suitability index of each grid cell, the habitat suitability index deviation of each grid cell is calculated.

[0072] Specifically, first, the ideal habitat suitability index for each grid cell is determined. Here, the ideal habitat suitability index refers to the benchmark value for evaluating the perfect habitat that a specific grid cell can provide for its target aquatic organisms or ecosystem under optimal ecological conditions.

[0073] Specifically, based on the core ecological functions carried by each grid unit of the pre-divided composite water network, such as serving as a spawning ground for certain fish or a purification wetland, as well as the specific habitat requirements of corresponding organisms at different growth stages, such as the optimal flow velocity range and the optimal inundation frequency, an ideal habitat suitability index is preset or calculated for each grid unit as a reference target.

[0074] Furthermore, based on the real-time habitat status data of each grid cell, a weighted calculation is performed to obtain the actual habitat suitability index for each grid cell. Specifically, multi-dimensional real-time habitat status data of the grid cell acquired by the integrated sensor array can be extracted, including parameters such as flow velocity, water level, dissolved oxygen, and biomass. Each parameter is assigned a corresponding weight based on its importance in influencing the specific ecological function of the grid cell. Subsequently, this real-time data is combined with these weights for weighted calculation or substituted into a preset mathematical model to comprehensively evaluate the current actual habitat suitability index of the grid cell.

[0075] Next, after obtaining the actual habitat suitability index of each grid cell under the current water flow field state, the difference between it and the ideal habitat suitability index corresponding to that grid cell is calculated to determine the degree of deviation between the two, thereby obtaining the specific habitat suitability index deviation value.

[0076] Understandably, by comparing the actual values ​​with the ideal benchmark values, the degree of matching or disconnect between the current water conservancy scheduling and ecological needs is accurately quantified, providing key feedback signals and constraints for subsequent alarm triggering and scheduling scheme optimization.

[0077] The method provided in this invention determines the ideal habitat suitability index for each grid unit and calculates the actual habitat suitability index from the real-time acquired multidimensional habitat state data. Then, it compares and calculates the habitat suitability index deviation between the two, effectively changing the shortcomings of the static index evaluation system in traditional scheduling. It establishes a real-time mapping logic and a dynamic perception evaluation system based on hydrodynamic-habitat index, which can objectively and accurately quantify the gap between the current state and the ideal state of different habitat units, providing a data foundation for the subsequent accurate and differentiated adaptive flow allocation and closed-loop control of ecological functions in complex water network systems.

[0078] Based on any of the above embodiments, step 120, determining the ideal habitat suitability index for each grid unit, includes: The ecological function corresponding to each grid unit is obtained; the ecological function includes at least one of spawning ground, wetland purification, and migration corridor. Based on the ecological function of each grid unit, the ideal habitat suitability index of each grid unit is determined.

[0079] Specifically, firstly, based on the constructed digital topology of the composite water network and the habitat unit division results, the ecological functions corresponding to each grid unit can be obtained. Here, ecological function refers to the specific ecological role or regional positioning of each grid unit in the entire composite water network ecosystem.

[0080] This ecological function includes at least one of the following: spawning ground, purification wetland, and migration corridor. For example, certain specific grid areas in a water network may be designated as spawning grounds for specific fish species, certain shallow-water vegetation areas may be positioned as purification wetlands to purify water, and narrow waterways connecting different water bodies may be designated as migration corridors for aquatic organisms.

[0081] Then, after clarifying the specific ecological functions of each grid unit, core habitat parameters are defined for each grid unit based on the specific needs of that ecological function. For example, for grid units serving as spawning grounds, the focus is on their optimal flow velocity range and water temperature conditions; for purification wetlands, the focus is on assessing their inundation duration and frequency. By combining the habitat requirements of aquatic organisms or vegetation at different growth stages, the optimal state of these core habitat parameters is converted into quantifiable values, thereby determining the ideal habitat suitability index specific to each grid unit.

[0082] In one embodiment, Figure 2 This is a schematic diagram of the grid unit division of the composite water network provided by the present invention, as shown below. Figure 2 As shown, the complex water network is meticulously divided into grid units with different ecological functions, mainly including spawning ground protection areas (Area A), purification wetlands (Area B), and main waterway / flood control areas (Area C). For each specific grid unit, core habitat constraints and hydraulic parameters are defined according to its ecological role. For example, for the spawning ground protection area, the focus is on pulse velocity and water level fluctuation rate to ensure the breeding habitat of aquatic organisms; for the purification wetland, the focus is on inundation duration and hydraulic residence time to maximize the self-purification and ecological restoration potential of the water body; and for the main waterway / flood control area, the main focus is on safe flow rates to strictly ensure the safety of the flood control baseline.

[0083] It should be noted that, among these differentiated grid units, based on a dynamic feedback mechanism of habitat suitability and a multi-objective optimization algorithm, gate pump regulation and synergistic enhancement are implemented, completely changing the previous extensive scheduling mode of unified command across the entire basin. This division and synergistic regulation method enables precise and adaptive flow allocation to meet the differentiated needs of different habitat units in the complex water network, thereby maximizing the overall ecological function gain of the water network while ensuring flood control safety.

[0084] The method provided in this invention obtains the specific ecological functions of each grid unit, such as spawning grounds, purification wetlands, or migration corridors, and determines the ideal habitat suitability index for each grid unit accordingly. This effectively solves the shortcomings of the existing technology, which uses a unified control command for the entire watershed and has overly coarse control granularity. It fully considers the complex and diverse ecological characteristics within the composite water network, enabling the scheduling benchmark to be adapted to the differentiated needs of different habitat units, thereby laying a refined evaluation foundation for achieving precise and adaptive water allocation.

[0085] Based on any of the above embodiments, real-time habitat status data includes flow velocity parameters, water level parameters, dissolved oxygen parameters, and biomass parameters.

[0086] Specifically, integrated sensor arrays deployed within each grid unit of the composite water network can be used to acquire multidimensional habitat state vectors for each unit in real time. These multidimensional habitat state vectors include flow velocity parameters, water level parameters, dissolved oxygen parameters, and biomass parameters. Flow velocity and water level parameters reflect current hydrodynamic processes and inundation characteristics, dissolved oxygen parameters characterize the current biochemical environment and self-purification capacity of the water body, and biomass parameters reflect the actual abundance and ecological base of aquatic plants or animals in the target habitat. Furthermore, in some practical applications, if biosensors for acquiring biomass parameters and other indicators are lacking, remote sensing combined with artificial intelligence (AI) recognition technology can be used to calculate water color indices and vegetation patch fragmentation, serving as alternative inputs for habitat state data in habitat assessment.

[0087] The method provided in this invention, by specifying real-time habitat status data including flow velocity parameters, water level parameters, dissolved oxygen parameters, and biomass parameters, effectively overcomes the technical shortcomings of existing regulation methods that only focus on water level and ignore the impact of hydrodynamic processes and actual aquatic biological habitats. By constructing a multi-dimensional, all-element dynamic sensing data matrix, the calculation of the habitat suitability index can be based on comprehensive and three-dimensional underlying data. This ensures that subsequent water conservancy regulation not only responds to hydrological changes but also accurately meets the actual needs of core ecological indicators such as biomass and dissolved oxygen, thereby significantly improving the scientific nature and scheduling precision of the deep integration of water conservancy projects and ecological environmental protection.

[0088] Based on any of the above embodiments Figure 3 This is a schematic diagram of the collaborative scheduling system architecture for the composite water network aquatic-biological system provided by the present invention, as shown below. Figure 3 As shown, the system is divided into three core layers from bottom to top: the perception layer, the digital mapping layer, and the decision and control layer, realizing a complete closed loop from data acquisition and digital twin analysis to intelligent regulation.

[0089] At the lowest level, the sensing layer, the system deploys a real-time data acquisition module for all aquatic and biological elements, specifically integrating an integrated sensor array including a water level gauge, a Doppler current meter, a multi-parameter water quality analyzer, and a bioacoustic monitor. This layer is responsible for acquiring real-time multi-dimensional habitat status data such as flow velocity, water level, dissolved oxygen, and biomass in each grid unit of the complex water network, enabling dynamic monitoring of all elements of physical hydrology and biochemical ecology, and providing underlying data support for upper-level analysis.

[0090] The central digital mapping layer is the core of the system's digital twin computing, integrating a three-dimensional hydrodynamic model and a habitat suitability model (HSI model), which are deeply fused through a water-life coupling engine. The three-dimensional hydrodynamic model primarily simulates hydrodynamic evolution processes such as flow velocity, flow direction, and inundation depth. The habitat suitability model focuses on the species' growth requirements, calculating the habitat suitability index deviation to achieve real-time, accurate mapping and quantitative evaluation of hydrophysical data to ecological and environmental conditions.

[0091] At the top-level decision-making and control layer, the system relies on built-in multi-objective optimization operators, such as the NSGA-II multi-objective genetic algorithm, to comprehensively calculate the simulated water quality improvement, simulated biodiversity gain, and flood control safety constraints of the complex water network. This allows the system to calculate the optimal balance between flood control and ecology and generate the optimal scheduling scheme. Subsequently, the system sends the generated scheduling instructions to the PLC controller, which directly drives the hydraulic structures such as sluice gates and pumping stations to perform adaptive water displacement and refined allocation, thereby achieving coordinated protection of the complex water network's flood control safety and ecological service functions.

[0092] In one embodiment, Figure 4 This is a flowchart illustrating the collaborative scheduling method for composite water networks based on habitat feedback provided by the present invention, as shown below. Figure 4 As shown, the method includes: First, real-time hydrodynamic and biological parameters of the composite water network unit are acquired, i.e., real-time habitat status data such as flow velocity, water level, dissolved oxygen, and biomass are collected using integrated sensor arrays and other means. Then, the deviation between the current habitat suitability index and the target value is calculated, quantifying the gap between the current actual habitat state and the ideal habitat suitability index, i.e., the habitat suitability index deviation for each grid unit is calculated.

[0093] Then, based on the calculated deviation, it is determined whether the habitat meets the optimal growth conditions. If the current deviation is within the allowable safety or target range, that is, if the optimal growth conditions are met, the current gate pump state will be maintained and a delayed monitoring cycle will be entered to continuously perform dynamic sensing. If the current deviation exceeds the preset ecological early warning threshold, that is, if the optimal growth conditions are not met, an automatic response mechanism will be triggered.

[0094] At this point, a digital twin engine can be invoked to simulate the flow field changes under different combinations of gate pump openings in parallel, simulating the redistribution effect of each control combination on the entire network's water flow. Then, through global optimization methods such as multi-objective optimization algorithms, the scheduling plan with the greatest functional gain is selected, thus determining the scheduling scheme. This ensures that the optimized scheme can prioritize addressing the ecological needs of damaged grid units while also considering the flood control safety of the entire network.

[0095] After determining the optimal scheduling scheme, PLC control commands are issued to execute refined water allocation, directly controlling the hydraulic structure actuators. Finally, during the execution of the control actions, the habitat feedback after the control is monitored in real time, and the control parameters are adjusted accordingly. That is, a closed-loop control strategy based on habitat suitability index deviation is used to automatically fine-tune the action parameters until the calculated feedback index deviation of each grid unit is no greater than a second preset deviation threshold, thus completing adaptive control. It can be understood that after completing this control, real-time hydrodynamic and biological parameters of the composite water network units continue to be acquired to continuously achieve precise adaptive control of the composite water network, shifting from simply avoiding risks to enhancing ecological functions.

[0096] In one embodiment, Figure 5 This is a comparative diagram showing the effects of the collaborative scheduling method for composite water networks provided by the present invention, as shown in the diagram. Figure 5 As shown, the horizontal axis represents time, and the vertical axis represents the comprehensive ecological function index. The figure includes two comparison curves: the dashed line represents the ecological performance under the conventional scheduling scheme, and the solid line represents the ecological performance under the synergistic enhanced regulation scheme provided in this embodiment of the invention. At the point where the regulation command is issued... Previously, the comprehensive ecological function index of the aquatic system fluctuated within a low range. This reflects that traditional static scheduling often only focuses on water level and ignores the real-time impact of hydrodynamic processes on habitats, resulting in the ecological function of the water network being in a state of natural fluctuation and limitation.

[0097] At the point where the control command is issued Subsequently, with the intervention of the collaborative scheduling scheme based on the updated objective function and the closed-loop adaptive control mechanism provided in this embodiment of the invention, the solid line showed a significant upward trend and stabilized at a high level of ecological function in the subsequent time series. In contrast, the dashed line representing the conventional scheduling scheme continued to hover at a low level. The region formed between the two curves represents the net ecological function gain brought about by the method provided in this embodiment of the invention. This gain region intuitively quantifies the actual ecological increment generated by the multi-objective optimization algorithm provided in this embodiment of the invention in terms of water quality purification improvement and biodiversity gain.

[0098] Understandably, this comparative result fully demonstrates that the collaborative scheduling method provided by the embodiments of the present invention achieves the technical advantage of regulation and enhancement, enabling complex composite water networks to achieve precise and adaptive water replacement and regulation in response to local ecological crises. It effectively solves the defects of traditional water conservancy projects that cause negative impacts on biological systems, and truly realizes the synergistic growth of water conservancy flood control safety and ecological service functions.

[0099] Based on any of the above embodiments Figure 6 This is a schematic diagram of the structure of the collaborative scheduling device for the composite water network provided by the present invention, as shown below. Figure 6 As shown, the device includes: Acquisition unit 610 acquires real-time habitat status data for each grid unit in the composite water network; The deviation calculation unit 620 calculates the habitat suitability index deviation of each grid cell based on the real-time habitat status data of each grid cell. The objective function update unit 630, when the habitat suitability index deviation exceeds a first preset deviation threshold, identifies abnormal grid cells, adjusts the weight coefficient of the ecological gain objective term of the abnormal grid cells in the initial objective function, and obtains an updated objective function; The collaborative scheduling unit 640 performs optimization calculations based on the updated objective function to generate a scheduling scheme for the composite water network, and controls the composite water network based on the scheduling scheme.

[0100] The device provided in this invention calculates the habitat suitability index deviation by acquiring the habitat status of composite water network grid units in real time. When abnormal grid units are identified due to excessive deviation, the weight coefficient of the ecological gain term of the abnormal grid units in the objective function is dynamically adjusted to obtain an updated objective function. Then, the optimal scheduling scheme is generated for closed-loop control. This effectively overcomes the disconnect between traditional water conservancy scheduling, which only focuses on water level and ignores aquatic biological habitats. It constructs a dynamic feedback mechanism for habitat suitability, ensuring that the water resources of the entire network can be adaptively and precisely allocated in response to local ecological crises. This greatly improves the collaborative protection capability and automated response level of ecological service functions in the operation of water conservancy projects.

[0101] Based on any of the above embodiments, the ecological gain target item includes a water quality improvement sub-item and a biodiversity gain sub-item; The objective function update unit is specifically used for: The weight coefficients of the abnormal grid cells in the water quality improvement sub-item and the biodiversity gain sub-item are adjusted to obtain the updated objective function; The coordinated scheduling unit is specifically used for: Multiple scheduling candidate schemes are obtained, and the simulated water quality improvement and simulated biodiversity gain of each grid unit under the scheduling candidate schemes are simulated. Based on the updated objective function, the simulated water quality improvement and simulated biodiversity gain of each grid cell are applied to calculate the target evaluation value of each scheduling candidate scheme. The scheduling scheme is obtained by performing global iterative optimization based on the target evaluation value.

[0102] Based on any of the above embodiments, the initial objective function further includes a safety constraint term; the safety constraint term is used to output a preset penalty extreme value when the simulated water level value under the scheduling candidate scheme exceeds the preset warning water level. The objective function update unit is specifically used for: Adjusting the weight coefficients of the abnormal grid cells corresponding to the water quality improvement sub-item and the biodiversity gain sub-item yields the ecological gain objective function. The update objective function is constructed based on the ecological gain objective function and the security constraint term.

[0103] Based on any of the above embodiments, the cooperative scheduling unit is specifically used for: Obtain the feedback habitat suitability index of each grid unit in the composite water network after executing the current action parameters corresponding to the scheduling scheme; Based on the feedback habitat suitability index of each grid cell, the feedback index deviation of each grid cell is calculated. If the feedback index deviation of any grid cell exceeds a second preset deviation threshold, the feedback adjustment amount of the arbitrary grid cell is calculated based on the feedback index deviation of the arbitrary grid cell. Based on the feedback adjustment amount of the arbitrary grid cell, the current action parameters corresponding to the arbitrary grid cell are adjusted to obtain the updated action parameters; The updated action parameters are used as the current action parameters, and the process is repeated to obtain the feedback habitat suitability index of each grid cell after executing the current action parameters, until the deviation of the feedback index of each grid cell is calculated to be no greater than the second preset deviation threshold.

[0104] Based on any of the above embodiments, the deviation calculation unit is specifically used for: Determine the ideal habitat suitability index for each grid cell; Based on the real-time habitat status data of each grid cell, the actual habitat suitability index of each grid cell is calculated. Based on the actual habitat suitability index and the ideal habitat suitability index of each grid cell, the habitat suitability index deviation of each grid cell is calculated.

[0105] Based on any of the above embodiments, the deviation calculation unit is further specifically used for: The ecological function corresponding to each grid unit is obtained; the ecological function includes at least one of spawning ground, wetland purification, and migration corridor. Based on the ecological function of each grid unit, the ideal habitat suitability index of each grid unit is determined.

[0106] Based on any of the above embodiments, the real-time habitat status data includes flow velocity parameters, water level parameters, dissolved oxygen parameters, and biomass parameters.

[0107] Figure 7 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 7 As shown, the electronic device may include a processor 710, a communication interface 720, a memory 730, and a communication bus 740, wherein the processor 710, the communication interface 720, and the memory 730 communicate with each other through the communication bus 740. The processor 710 can call logical instructions in the memory 730 to execute a collaborative scheduling method for a composite water network. The method includes: acquiring real-time habitat status data of each grid unit in the composite water network; calculating the habitat suitability index deviation of each grid unit based on the real-time habitat status data of each grid unit; identifying abnormal grid units when the habitat suitability index deviation exceeds a first preset deviation threshold, adjusting the weight coefficient of the ecological gain objective term of the abnormal grid unit in the initial objective function to obtain an updated objective function; performing optimization calculations based on the updated objective function to generate a scheduling scheme for the composite water network, and controlling the composite water network based on the scheduling scheme.

[0108] Furthermore, the logical instructions in the aforementioned memory 730 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0109] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the collaborative scheduling method for the composite water network provided by the above methods. The method includes: acquiring real-time habitat status data of each grid unit in the composite water network; calculating the habitat suitability index deviation of each grid unit based on the real-time habitat status data of each grid unit; identifying abnormal grid units when the habitat suitability index deviation exceeds a first preset deviation threshold, adjusting the weight coefficient of the ecological gain objective term of the abnormal grid unit in the initial objective function to obtain an updated objective function; performing optimization calculations based on the updated objective function to generate a scheduling scheme for the composite water network, so as to control the composite water network based on the scheduling scheme.

[0110] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program implements a collaborative scheduling method for a composite water network provided by the methods described above. The method includes: acquiring real-time habitat status data of each grid unit in the composite water network; calculating the habitat suitability index deviation of each grid unit based on the real-time habitat status data of each grid unit; identifying abnormal grid units when the habitat suitability index deviation exceeds a first preset deviation threshold; adjusting the weight coefficient of the ecological gain objective term of the abnormal grid unit in the initial objective function to obtain an updated objective function; performing optimization calculations based on the updated objective function to generate a scheduling scheme for the composite water network, and controlling the composite water network based on the scheduling scheme.

[0111] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0112] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0113] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for coordinated scheduling of a composite water network, characterized in that, include: Acquire real-time habitat status data for each grid unit in the composite water network; Based on the real-time habitat status data of each grid cell, the habitat suitability index deviation of each grid cell is calculated; If the habitat suitability index deviation exceeds a first preset deviation threshold, abnormal grid cells are identified, and the weight coefficients of the ecological gain objective term of the abnormal grid cells in the initial objective function are adjusted to obtain an updated objective function. Based on the updated objective function, an optimization calculation is performed to generate a scheduling scheme for the composite water network, so as to control the composite water network based on the scheduling scheme; The ecological gain objectives include water quality improvement sub-items and biodiversity gain sub-items; The step of adjusting the weight coefficients of the ecological gain objective term in the initial objective function for the abnormal grid cells to obtain the updated objective function includes: The weight coefficients of the abnormal grid cells in the water quality improvement sub-item and the biodiversity gain sub-item are adjusted to obtain the updated objective function.

2. The collaborative scheduling method for a composite water network according to claim 1, characterized in that, The step of performing optimization calculations based on the updated objective function to generate a scheduling scheme for the composite water network includes: Multiple scheduling candidate schemes are obtained, and the simulated water quality improvement and simulated biodiversity gain of each grid unit under the scheduling candidate schemes are simulated. Based on the updated objective function, the simulated water quality improvement and simulated biodiversity gain of each grid cell are applied to calculate the target evaluation value of each scheduling candidate scheme. The scheduling scheme is obtained by performing global iterative optimization based on the target evaluation value.

3. The method of claim 2, wherein, The initial objective function also includes a safety constraint term; the safety constraint term is used to output a preset penalty extreme value when the simulated water level value under the scheduling candidate scheme exceeds the preset warning water level. The step of adjusting the weight coefficients of the abnormal grid cells in the water quality improvement sub-item and the biodiversity gain sub-item to obtain the updated objective function includes: Adjusting the weight coefficients of the abnormal grid cells corresponding to the water quality improvement sub-item and the biodiversity gain sub-item yields the ecological gain objective function. The update objective function is constructed based on the ecological gain objective function and the security constraint term.

4. The method of claim 1 to 3, wherein, The control of the composite water network based on the scheduling scheme includes: Obtain the feedback habitat suitability index of each grid unit in the composite water network after executing the current action parameters corresponding to the scheduling scheme; Based on the feedback habitat suitability index of each grid cell, the feedback index deviation of each grid cell is calculated. If the feedback index deviation of any grid cell exceeds a second preset deviation threshold, the feedback adjustment amount of the arbitrary grid cell is calculated based on the feedback index deviation of the arbitrary grid cell. Based on the feedback adjustment amount of the arbitrary grid cell, the current action parameters corresponding to the arbitrary grid cell are adjusted to obtain the updated action parameters; The updated action parameters are used as the current action parameters, and the process is repeated to obtain the feedback habitat suitability index of each grid cell after executing the current action parameters, until the deviation of the feedback index of each grid cell is calculated to be no greater than the second preset deviation threshold.

5. The method of claim 1-3, wherein, The calculation of the habitat suitability index deviation for each grid cell based on the real-time habitat status data for each grid cell includes: Determine the ideal habitat suitability index for each grid cell; Based on the real-time habitat status data of each grid cell, the actual habitat suitability index of each grid cell is calculated. Based on the actual habitat suitability index and the ideal habitat suitability index of each grid cell, the habitat suitability index deviation of each grid cell is calculated.

6. The method of claim 5, wherein, Determining the ideal habitat suitability index for each grid cell includes: The ecological function corresponding to each grid unit is obtained; the ecological function includes at least one of spawning ground, wetland purification, and migration corridor. Based on the ecological function of each grid unit, the ideal habitat suitability index of each grid unit is determined.

7. The method of claim 5, wherein, The real-time habitat status data includes flow velocity parameters, water level parameters, dissolved oxygen parameters, and biomass parameters.

8. A collaborative scheduling device for a composite water network, characterized in that, include: The acquisition unit acquires real-time habitat status data for each grid unit in the composite water network; The deviation calculation unit calculates the habitat suitability index deviation for each grid cell based on the real-time habitat status data for each grid cell. The objective function update unit identifies abnormal grid cells when the habitat suitability index deviation exceeds a first preset deviation threshold, adjusts the weight coefficient of the ecological gain objective term of the abnormal grid cells in the initial objective function, and obtains the updated objective function. The collaborative scheduling unit performs optimization calculations based on the updated objective function to generate a scheduling scheme for the composite water network, and controls the composite water network based on the scheduling scheme. The ecological gain objectives include water quality improvement sub-items and biodiversity gain sub-items; The objective function update unit is specifically used for: The weight coefficients of the abnormal grid cells in the water quality improvement sub-item and the biodiversity gain sub-item are adjusted to obtain the updated objective function.

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 computer program, it implements the collaborative scheduling method for the composite water network as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the collaborative scheduling method for the composite water network as described in any one of claims 1 to 7.

Images