Water conservancy project cascade reservoir flood control cooperative scheduling intelligent decision-making method

Abstract

The invention discloses a water conservancy project cascade reservoir flood control cooperative scheduling intelligent decision-making method, and relates to the technical field of water conservancy project scheduling, and the method comprises the steps: carrying out the collection of multi-source data in advance, and carrying out the preprocessing of the collected multi-source data; establishing a cascade reservoir flood control cooperative scheduling prediction model, namely, constructing the cascade reservoir flood control cooperative scheduling prediction model by using a deep learning algorithm, training the model by taking historical data as a training sample, optimizing the model until the prediction precision meets the requirement, inputting real-time pre-processing data, and calculating the flood control cooperative scheduling prediction model; and outputting incoming water, rainfall and downstream water level prediction results in a future preset time period. Through a dynamic adjustment mechanism, the scheme can be corrected in time according to real-time hydrological changes in the scheduling implementation process, the ability of the cascade reservoir to deal with complex and changeable hydrological conditions is greatly improved, and especially in extreme weather such as sudden rainstorm, the scheduling strategy can be quickly responded and adjusted, and the overall flood control safety of a drainage basin is guaranteed.

Description

Technical Field

[0001] This invention relates to the field of water conservancy project scheduling technology, and more specifically, to an intelligent decision-making method for coordinated flood control scheduling of cascade reservoirs in water conservancy projects. Background Technology

[0002] In the water conservancy system, cascade reservoirs are an important vehicle for realizing comprehensive benefits such as flood control, power generation, and water supply. Among them, flood control scheduling is a key link in ensuring the safety of people's lives and property and social stability. With the intensification of climate change and the frequent occurrence of extreme rainstorm events, traditional cascade reservoir flood control scheduling methods have gradually revealed many shortcomings.

[0003] Traditional flood control methods rely heavily on human experience and fixed rules, lacking the ability to dynamically respond to real-time hydrological and meteorological data. For example, when faced with sudden rainstorms, due to the inability to predict the inflow of water in a timely and accurate manner, each reservoir often has to conduct flood control operations independently. This results in a lack of effective coordination between cascade reservoirs, leading to either excessive discharge from upstream reservoirs putting enormous flood control pressure on downstream reservoirs, or downstream reservoirs prematurely releasing storage capacity, resulting in water resource waste.

[0004] Meanwhile, traditional methods struggle to comprehensively consider the multi-objective needs of cascade reservoirs. During flood control scheduling, they often focus solely on flood safety while neglecting the balance of other benefits such as power generation and water supply, failing to maximize the overall benefits of the cascade reservoirs. Furthermore, traditional scheduling methods lack intelligent support in their decision-making process, resulting in low efficiency and difficulty in adapting to complex and ever-changing hydrological situations, thus failing to provide timely and scientific scheduling suggestions to dispatchers.

[0005] Therefore, there is an urgent need for a cascade reservoir flood control collaborative scheduling method that can integrate real-time data, achieve multi-reservoir coordination, take into account multiple objectives and benefits, and possess intelligent decision-making capabilities, so as to improve the flood control capacity and comprehensive benefits of cascade reservoirs. Summary of the Invention

[0006] To address the problems in related technologies, this invention proposes an intelligent decision-making method for coordinated flood control scheduling of cascade reservoirs in water conservancy projects, in order to overcome the aforementioned technical problems existing in existing related technologies.

[0007] The technical solution of this invention is implemented as follows:

[0008] A smart decision-making method for coordinated flood control scheduling of cascade reservoirs in water conservancy projects includes:

[0009] Step S1 involves pre-collecting multi-source data and pre-processing the collected multi-source data, including: real-time collection of multi-source data through hydrological stations, meteorological stations, water level stations and satellite remote sensing equipment, and cleaning, standardizing and fusion processing of the data;

[0010] Step S2: Establish a flood control coordinated scheduling prediction model for cascade reservoirs, which includes: constructing a flood control coordinated scheduling prediction model for cascade reservoirs using a deep learning algorithm, training the model using historical data as training samples and optimizing it until the prediction accuracy meets the requirements, inputting real-time preprocessed data, and outputting the prediction results of inflow, rainfall and downstream water level for the future preset time period;

[0011] Step S3: Construct a multi-objective optimization scheduling model, which includes calibrating an objective function with the objectives of minimizing flood risk, maximizing power generation, and maximizing water supply satisfaction rate, while setting reservoir operation constraints, water flow continuity constraints, and downstream safety constraints.

[0012] Step S4: The NSGA-Ⅲ algorithm is used to solve the multi-objective optimization model, generate the Pareto optimal solution set, and select the optimal scheduling scheme through the fuzzy comprehensive evaluation model, and present it to the scheduling personnel in a visual form.

[0013] Step S5 involves implementing the scheduling scheme and making dynamic adjustments based on the implementation. This includes: converting the optimal scheme into a scheduling instruction for execution, collecting operational data in real time, and if the prediction deviation exceeds a preset threshold, re-executing steps S2-S4 to generate a new scheme and make dynamic adjustments.

[0014] Furthermore, the data cleaning process employs outlier removal and missing value imputation; the fusion processing utilizes a weighted fusion algorithm.

[0015] Furthermore, the objective function for minimizing flood control risk includes: minimizing the total flood control risk of the cascade reservoir group, where flood control risk is measured by the probability that the water level of each reservoir exceeds the flood control high level and the probability that the water level of the downstream river exceeds the warning level, expressed as:

[0016] ;

[0017] Where R represents the total flood risk, Here, n represents the weighting coefficient, and n is the number of cascade reservoirs. Let the water level of the i-th reservoir at time t be... Exceeding its flood control high water level The probability is given by m, where m is the number of monitoring sections in the downstream river channel. Let the water level at the j-th monitoring section at time t be... Exceeding its warning level The probability of.

[0018] Furthermore, the objective function for maximizing power generation includes: maximizing the total power generation of the cascade reservoir group, expressed as:

[0019] ;

[0020] Where E represents the total electricity generation. Let be the power generation efficiency coefficient of the i-th reservoir. Let be the power generation flow of the i-th reservoir at time t. Let be the net head of the i-th reservoir at time t, which is the difference between the reservoir water level and the tailwater level of the power plant, and T be the total number of scheduling periods. The duration of each scheduling period.

[0021] Furthermore, the objective function for maximizing the water supply satisfaction rate includes: taking the satisfaction of downstream water users' water demand as the objective, and measuring it by the water supply satisfaction rate, expressed as:

[0022] ;

[0023] Where S represents the water supply satisfaction rate. The actual water supply at time t. Let be the downstream water demand at time t.

[0024] Furthermore, the reservoir operation constraints, water flow continuity constraints, and downstream safety constraints include:

[0025] Among them, reservoir operation constraints are used to indicate that the water level of each reservoir must be at the dead water level. and check flood level Between, that is: Outflow from each reservoir Minimum outbound flow is required and maximum outbound flow Between, that is: ;

[0026] Among them, the flow continuity constraint is used for the i-th reservoir in a cascade reservoir series, where the change in reservoir capacity at time t is equal to the inflow. Subtract outbound flow ,Right now:

[0027] ;in, , Let be the reservoir capacities of the i-th reservoir at times t and t-1, respectively;

[0028] Among them, the downstream safety constraint stipulates that the water level at each monitoring section of the downstream river channel must not exceed the warning water level, that is: ; downstream river flow The discharge capacity shall not exceed the safe discharge capacity of the river channel. ,Right now: .

[0029] Furthermore, step S4 also includes: evaluating the generated multiple scheduling schemes, including the following steps:

[0030] The evaluation indicators were determined, including the flood risk reduction rate, power generation increase rate, water supply satisfaction rate, and the operability of the dispatching plan.

[0031] The weights of each evaluation index are determined using the Analytic Hierarchy Process (AHP); the comprehensive evaluation score of each scheduling scheme is calculated using a fuzzy comprehensive evaluation model, and the scheduling scheme with the highest comprehensive evaluation score is taken as the optimal scheduling scheme.

[0032] The beneficial effects of this invention are:

[0033] This invention, through the construction of a multi-source data acquisition and preprocessing system, breaks through the limitations of data dispersion and delayed processing in traditional scheduling. It can integrate various key information such as hydrology, meteorology, and water level within the basin in real time, and ensures data consistency and reliability through standardization and fusion processing, providing comprehensive and accurate foundational support for subsequent scheduling decisions. Based on this, a cascade reservoir flood control collaborative scheduling prediction model built using deep learning algorithms can fully learn from the inflow patterns and scheduling experience contained in historical data, accurately predicting future hydrological conditions. This allows cascade reservoirs to move beyond independent scheduling of a single reservoir, enabling them to plan scheduling strategies in advance based on overall inflow trends, achieving coordinated action between upstream and downstream reservoirs. This collaborative scheduling mode effectively avoids the problems of excessive upstream discharge and passive downstream response caused by information asymmetry in traditional scheduling. Furthermore, through a dynamic adjustment mechanism, it can promptly correct plans based on real-time hydrological changes during scheduling implementation, significantly improving the ability of cascade reservoirs to cope with complex and variable hydrological conditions. Especially under extreme weather conditions such as sudden rainstorms, it can quickly respond and adjust scheduling strategies, ensuring the overall flood control safety of the basin.

[0034] Meanwhile, this invention, through the construction of a multi-objective optimization scheduling model, overcomes the limitations of traditional scheduling that focuses solely on flood control safety. It incorporates benefits such as power generation and water supply into the optimization system, and, combined with scientifically set constraints, achieves a comprehensive balance between flood control safety and other integrated benefits. In the optimization solution stage, the improved non-dominated sorting genetic algorithm efficiently generates multiple feasible scheduling schemes. Then, through a combination of a fuzzy comprehensive evaluation model and the analytic hierarchy process (AHP), the schemes are scientifically evaluated from multiple dimensions, ultimately selecting the optimal scheme. The entire process does not rely excessively on human experience, reducing the influence of subjective factors on decision-making and significantly improving the intelligence and scientific rigor of scheduling decisions. Furthermore, the visualized decision results display and human-computer interaction functions allow scheduling personnel to intuitively grasp the scheduling logic and expected effects of different schemes. This provides professional decision support while retaining the flexibility for manual adjustments, ensuring that the final implemented scheduling scheme not only conforms to the principle of technical optimization but also adapts to various complex situations in actual operation. Thus, under the core premise of ensuring flood control safety, it maximizes the comprehensive benefits of cascade reservoirs, providing strong support for the sustainable operation of water conservancy projects and the stable development of the basin's economy and society. Attached Figure Description

[0035] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0036] Figure 1 This is a flowchart illustrating an intelligent decision-making method for coordinated flood control scheduling of cascade reservoirs in a water conservancy project, according to an embodiment of the present invention. Detailed Implementation

[0037] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention are within the scope of protection of the present invention.

[0038] According to an embodiment of the present invention, an intelligent decision-making method for coordinated flood control scheduling of cascade reservoirs in water conservancy projects is provided.

[0039] like Figure 1 As shown, the intelligent decision-making method for coordinated flood control scheduling of cascade reservoirs in water conservancy projects according to an embodiment of the present invention includes the following steps:

[0040] Step S1: Perform multi-source data acquisition and preprocess the acquired multi-source data in advance;

[0041] Multi-source data are collected in real time through hydrological stations, meteorological stations, water level stations, rain gauge stations, and satellite remote sensing equipment deployed in the cascade reservoir basin. This includes, but is not limited to, rainfall at different times in the basin, inflow and outflow of each reservoir, water level, and reservoir capacity, as well as upstream inflow forecast data, downstream river water level-flow relationship data, and short-term and medium-term rainstorm warning data issued by the meteorological department.

[0042] The collected multi-source data undergoes preprocessing, including data cleaning, data standardization, and data fusion. Data cleaning ensures accuracy by removing outliers, filling in missing values, and using interpolation or prediction methods based on historical similar data. Data standardization converts data of different magnitudes and units into data under a unified standard, facilitating subsequent analysis and calculation. Data fusion employs a weighted fusion algorithm to merge data of the same type from different devices, improving data reliability.

[0043] Step S2 involves constructing a cascade reservoir flood control collaborative scheduling prediction model. This includes using a deep learning algorithm to construct the cascade reservoir flood control collaborative scheduling prediction model based on preprocessed multi-source data. The model inputs the real-time collected and preprocessed current data into the trained prediction model and outputs the predicted inflow of each reservoir in the cascade reservoirs, the predicted distribution of rainfall in the basin, and the predicted water level of the downstream river channel within a certain future time period.

[0044] In this technical solution, the model uses historical hydrological and meteorological data and historical data on cascade reservoir scheduling as training samples. Through training, it learns the mapping relationship between water inflow process, reservoir scheduling behavior and flood control effect.

[0045] Specifically, the collected historical data is divided into a training set and a test set in a 7:3 ratio. The training set is used to train the model, and the model parameters are continuously adjusted through the backpropagation algorithm. The test set is used to verify the prediction accuracy of the model. If the prediction error exceeds the preset threshold, an adaptive learning rate adjustment strategy and regularization method are used to optimize the model until the prediction accuracy of the model meets the requirements.

[0046] Step S3: Construct a multi-objective optimization scheduling model, including calibrating the objective function and constraints. The objective function includes flood control safety objective, power generation benefit objective, and water supply benefit objective. The constraints include reservoir operation constraints, water flow continuity constraints, and downstream safety constraints.

[0047] The flood control safety objective is to minimize the total flood control risk of the cascade reservoir group. Flood control risk is measured by the probability that the water level of each reservoir exceeds the flood control high level and the probability that the water level of the downstream river exceeds the warning level, expressed as:

[0048] ;

[0049] Where R represents the total flood risk, Here, n represents the weighting coefficient, and n is the number of cascade reservoirs. Let the water level of the i-th reservoir at time t be... Exceeding its flood control high water level The probability is given by m, where m is the number of monitoring sections in the downstream river channel. Let the water level at the j-th monitoring section at time t be... Exceeding its warning level The probability of.

[0050] The power generation efficiency target, which aims to maximize the total power generation of the cascade reservoir group, is expressed as follows:

[0051] ;

[0052] Where E represents the total electricity generation. Let be the power generation efficiency coefficient of the i-th reservoir. Let be the power generation flow of the i-th reservoir at time t. Let be the net head of the i-th reservoir at time t, which is the difference between the reservoir water level and the tailwater level of the power plant, and T be the total number of scheduling periods. The duration of each scheduling period.

[0053] The water supply efficiency target, which aims to meet the water demand of downstream users, is measured by the water supply satisfaction rate and is expressed as follows:

[0054] ;

[0055] Where S represents the water supply satisfaction rate. The actual water supply at time t. Let be the downstream water demand at time t.

[0056] Among them, reservoir operation constraints are used to indicate that the water level of each reservoir must be at the dead water level. and check flood level Between, that is: Outflow from each reservoir Minimum outbound flow is required and maximum outbound flow Between, that is: ;

[0057] Among them, the flow continuity constraint is used for the i-th reservoir in a cascade reservoir series, where the change in reservoir capacity at time t is equal to the inflow. Subtract outbound flow ,Right now:

[0058] ;in, , Let be the reservoir capacity of the i-th reservoir at times t and t-1, respectively.

[0059] Among them, the downstream safety constraint stipulates that the water level at each monitoring section of the downstream river channel must not exceed the warning water level, that is: ; downstream river flow The discharge capacity shall not exceed the safe discharge capacity of the river channel. ,Right now: .

[0060] Step S4: Perform multi-objective optimization and construct a fuzzy comprehensive evaluation model to evaluate the generated scheduling schemes;

[0061] This technical solution employs the Non-Dominated Sorting Genetic Algorithm (NSGA-III) to solve a multi-objective optimization scheduling model. It can find a uniformly distributed and well-converged Pareto optimal solution set in a multi-objective optimization problem. During the solution process, the predicted data output from the prediction model in step S2 is used as input parameters and substituted into the multi-objective optimization scheduling model. Through iterative calculation, multiple scheduling schemes satisfying the constraints are generated, i.e., solutions in the Pareto optimal solution set.

[0062] In addition, the generated scheduling schemes are evaluated, including the following steps:

[0063] First, evaluation indicators are determined, including flood risk reduction rate, power generation increase rate, water supply satisfaction rate, and the operability of the dispatching scheme. Then, the Analytic Hierarchy Process (AHP) is used to determine the weights of each evaluation indicator. Finally, a fuzzy comprehensive evaluation model is used to calculate the comprehensive evaluation score of each dispatching scheme, and the scheme with the highest comprehensive evaluation score is selected as the optimal dispatching scheme. Simultaneously, detailed information on the optimal dispatching scheme and other alternative schemes, including the outflow process of each reservoir, water level change process, corresponding flood risk, power generation, and water supply, is displayed to dispatchers in a visual format, providing intelligent decision support. If dispatchers need to adjust the optimal scheme based on actual conditions, they can modify relevant parameters through a human-computer interaction interface, and the system will recalculate and generate a new dispatching scheme.

[0064] Step S5: Implement the scheduling plan and make dynamic adjustments based on the implementation.

[0065] The generated optimal scheduling scheme is transformed into specific scheduling instructions and sent to the operation control centers of each reservoir in the cascade reservoirs. The operation control centers then control the operation of the reservoir's flood discharge facilities and power generation equipment according to the scheduling instructions, and perform operations such as adjusting the reservoir's outflow.

[0066] In addition, during the implementation of the scheduling scheme, real-time operational data of the cascade reservoirs and the latest hydrological and meteorological data are collected and input into the prediction model in step S2 to re-predict future water inflow. If the re-prediction results deviate significantly from the previous predictions, steps S3 and S4 are executed again to solve the multi-objective optimization scheduling model and evaluate the scheme, generating a new optimal scheduling scheme. The original scheduling scheme is then dynamically adjusted based on the new scheme to ensure that the cascade reservoirs are always in an optimal state of flood control and coordinated scheduling.

[0067] In summary, by employing the above-described technical solution of the present invention, the following effects can be achieved:

[0068] This invention, through the construction of a multi-source data acquisition and preprocessing system, breaks through the limitations of data dispersion and delayed processing in traditional scheduling. It can integrate various key information such as hydrology, meteorology, and water level within the basin in real time, and ensures data consistency and reliability through standardization and fusion processing, providing comprehensive and accurate foundational support for subsequent scheduling decisions. Based on this, a cascade reservoir flood control collaborative scheduling prediction model built using deep learning algorithms can fully learn from the inflow patterns and scheduling experience contained in historical data, accurately predicting future hydrological conditions. This allows cascade reservoirs to move beyond independent scheduling of a single reservoir, enabling them to plan scheduling strategies in advance based on overall inflow trends, achieving coordinated action between upstream and downstream reservoirs. This collaborative scheduling mode effectively avoids the problems of excessive upstream discharge and passive downstream response caused by information asymmetry in traditional scheduling. Furthermore, through a dynamic adjustment mechanism, it can promptly correct plans based on real-time hydrological changes during scheduling implementation, significantly improving the ability of cascade reservoirs to cope with complex and variable hydrological conditions. Especially under extreme weather conditions such as sudden rainstorms, it can quickly respond and adjust scheduling strategies, ensuring the overall flood control safety of the basin.

[0069] Meanwhile, this invention, through the construction of a multi-objective optimization scheduling model, overcomes the limitations of traditional scheduling that focuses solely on flood control safety. It incorporates benefits such as power generation and water supply into the optimization system, and, combined with scientifically set constraints, achieves a comprehensive balance between flood control safety and other integrated benefits. In the optimization solution stage, the improved non-dominated sorting genetic algorithm efficiently generates multiple feasible scheduling schemes. Then, through a combination of a fuzzy comprehensive evaluation model and the analytic hierarchy process (AHP), the schemes are scientifically evaluated from multiple dimensions, ultimately selecting the optimal scheme. The entire process does not rely excessively on human experience, reducing the influence of subjective factors on decision-making and significantly improving the intelligence and scientific rigor of scheduling decisions. Furthermore, the visualized decision results display and human-computer interaction functions allow scheduling personnel to intuitively grasp the scheduling logic and expected effects of different schemes. This provides professional decision support while retaining the flexibility for manual adjustments, ensuring that the final implemented scheduling scheme not only conforms to the principle of technical optimization but also adapts to various complex situations in actual operation. Thus, under the core premise of ensuring flood control safety, it maximizes the comprehensive benefits of cascade reservoirs, providing strong support for the sustainable operation of water conservancy projects and the stable development of the basin's economy and society.

[0070] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Those skilled in the art, upon considering the disclosure in the specification and embodiments, will readily conceive of other embodiments of this disclosure. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the claims.

[0071] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A smart decision-making method for coordinated flood control scheduling of cascade reservoirs in water conservancy projects, characterized in that, include: Step S1 involves pre-collecting multi-source data and pre-processing the collected multi-source data, including: real-time collection of multi-source data through hydrological stations, meteorological stations, water level stations and satellite remote sensing equipment, and cleaning, standardizing and fusion processing of the data; Step S2: Establish a flood control coordinated scheduling prediction model for cascade reservoirs, which includes: constructing a flood control coordinated scheduling prediction model for cascade reservoirs using a deep learning algorithm, training the model using historical data as training samples and optimizing it until the prediction accuracy meets the requirements, inputting real-time preprocessed data, and outputting the prediction results of inflow, rainfall and downstream water level for the future preset time period; Step S3: Construct a multi-objective optimization scheduling model, which includes calibrating an objective function with the objectives of minimizing flood risk, maximizing power generation, and maximizing water supply satisfaction rate, while setting reservoir operation constraints, water flow continuity constraints, and downstream safety constraints. Step S4: The NSGA-Ⅲ algorithm is used to solve the multi-objective optimization model, generate the Pareto optimal solution set, and select the optimal scheduling scheme through the fuzzy comprehensive evaluation model, and present it to the scheduling personnel in a visual form. Step S5 involves implementing the scheduling scheme and making dynamic adjustments based on the implementation. This includes: converting the optimal scheme into a scheduling instruction for execution, collecting operational data in real time, and if the prediction deviation exceeds a preset threshold, re-executing steps S2-S4 to generate a new scheme and make dynamic adjustments.

2. The intelligent decision-making method for coordinated flood control scheduling of cascade reservoirs in water conservancy projects according to claim 1, characterized in that, The data is cleaned by removing outliers and filling in missing values; the fusion process uses a weighted fusion algorithm.

3. The intelligent decision-making method for coordinated flood control scheduling of cascade reservoirs in water conservancy projects according to claim 1, characterized in that, The objective function for minimizing flood control risk includes: minimizing the total flood control risk of the cascade reservoir group, where flood control risk is measured by the probability that the water level of each reservoir exceeds the flood control high level and the probability that the water level of the downstream river exceeds the warning level, expressed as: ； Where R represents the total flood risk, Here, n represents the weighting coefficient, and n is the number of cascade reservoirs. Let the water level of the i-th reservoir at time t be... Exceeding its flood control high water level The probability is given by m, where m is the number of monitoring sections in the downstream river channel. Let the water level at the j-th monitoring section at time t be... Exceeding its warning level The probability of.

4. The intelligent decision-making method for coordinated flood control scheduling of cascade reservoirs in water conservancy projects according to claim 3, characterized in that, The objective function for maximizing power generation includes: maximizing the total power generation of the cascade reservoir group, expressed as: ； Where E represents the total power generation. Let be the power generation efficiency coefficient of the i-th reservoir. Let be the power generation flow of the i-th reservoir at time t. Let be the net head of the i-th reservoir at time t, which is the difference between the reservoir water level and the tailwater level of the power plant, and T be the total number of scheduling periods. The duration of each scheduling period.

5. The intelligent decision-making method for coordinated flood control scheduling of cascade reservoirs in water conservancy projects according to claim 4, characterized in that, The objective function for maximizing the water supply satisfaction rate includes: taking the satisfaction of downstream water users' water demand as the objective, and measuring it by the water supply satisfaction rate, expressed as: ； Where S represents the water supply satisfaction rate. The actual water supply at time t. Let be the downstream water demand at time t.

6. The intelligent decision-making method for coordinated flood control scheduling of cascade reservoirs in water conservancy projects according to claim 5, characterized in that, The aforementioned reservoir operation constraints, water flow continuity constraints, and downstream safety constraints include: Among them, reservoir operation constraints are used to indicate that the water level of each reservoir must be at the dead water level. and check flood level Between, that is: Outflow from each reservoir Minimum outbound flow is required and maximum outbound flow Between, that is: ; Among them, the flow continuity constraint is used for the i-th reservoir in a cascade reservoir series, where the change in reservoir capacity at time t is equal to the inflow. Subtract outbound flow ,Right now: ;in, , Let be the reservoir capacities of the i-th reservoir at times t and t-1, respectively; Among them, the downstream safety constraint stipulates that the water level at each monitoring section of the downstream river channel must not exceed the warning water level, that is: ; downstream river flow The discharge capacity shall not exceed the safe discharge capacity of the river channel. ,Right now: .

7. The intelligent decision-making method for coordinated flood control scheduling of cascade reservoirs in water conservancy projects according to claim 1, characterized in that, Step S4 further includes: evaluating the generated multiple scheduling schemes, including the following steps: The evaluation indicators were determined, including the flood risk reduction rate, power generation increase rate, water supply satisfaction rate, and the operability of the dispatching plan. The weights of each evaluation index are determined using the Analytic Hierarchy Process (AHP); the comprehensive evaluation score of each scheduling scheme is calculated using a fuzzy comprehensive evaluation model, and the scheduling scheme with the highest comprehensive evaluation score is taken as the optimal scheduling scheme.

Images