Dynamic configuration platform and method for regional drought-resistant water source

Abstract

The invention discloses a regional drought-resistant water source dynamic configuration platform and method, and relates to the technical field of water resource management, and the method comprises the steps: obtaining the spatial and temporal distribution characteristics of a target regional water resource, superposing the drought influence, and generating a planning grid; a gray correlation coefficient is introduced, the gray correlation coefficient is calculated and determined with the drought level as a reference sequence and the influence factors as a comparison sequence, and the number of the comparison sequence is at least one; a game decision module is constructed, according to the game decision principle, a first equilibrium game is carried out through inter-grid scheduling competition, and a second equilibrium game is carried out through inter-water structure competition; in combination with the planning grid and the grey correlation coefficient, a water resource dynamic configuration decision is made based on a game decision module, and a water resource configuration strategy is determined; and performing terminal visualization on the water resource allocation strategy, and guiding water resource allocation management of the target area. The technical problem that in the prior art, the configuration efficiency is low during water source dynamic configuration is solved, and the technical effect of improving the water resource configuration efficiency and accuracy is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of water resource management, and in particular to a regional drought-resistant water source dynamic configuration platform and method. Background Art

[0002] As global climate change and water shortage become increasingly serious, droughts occur frequently, causing significant impacts on agricultural production, ecological environment and residents' lives. Especially in arid and semi-arid areas, the limited water resources have intensified the urgent need for effective management and allocation. In this context, traditional water resource management methods face many challenges. Existing water resource allocation schemes often fail to consider the flow characteristics of water resources within the region and the competitive relationship between different water use structures, resulting in inefficient resource allocation and failure to meet the needs of modern agriculture and urban development. Summary of the invention

[0003] The present application provides a regional drought-resistant water source dynamic configuration platform and method, which are used to solve the technical problem of low configuration efficiency in the prior art when performing dynamic configuration of water sources.

[0004] In view of the above problems, the present application provides a regional drought-resistant water source dynamic configuration platform and method.

[0005] In a first aspect of the present application, a regional drought relief water source dynamic configuration platform is provided, the platform comprising:

[0006] A planning grid generation unit, wherein the planning grid generation unit obtains the spatiotemporal distribution characteristics of water resources in the target area, superimposes the impact of drought, and generates a planning grid, wherein each planning grid is marked with a drought level; a grey correlation coefficient determination unit, wherein the grey correlation coefficient is introduced, wherein the grey correlation coefficient is calculated and determined with the drought level as a reference sequence and the influencing factors as a comparison sequence, and the comparison sequence is at least one item; a game decision construction unit, wherein the game decision construction unit constructs a game decision module, wherein the game decision principle uses the scheduling competition between grids to conduct a first equilibrium game, and uses the competition between water use structures to conduct a second equilibrium game; a configuration decision unit, wherein the configuration decision unit combines the planning grid and the grey correlation coefficient, and makes a dynamic water resource configuration decision based on the game decision module to determine the water resource configuration strategy; and a configuration management unit, wherein the configuration management unit performs terminal visualization on the water resource configuration strategy to guide the water resource configuration management of the target area.

[0007] The second aspect of the present application provides a method for dynamically configuring regional drought-resistant water sources, the method comprising:

[0008] The spatiotemporal distribution characteristics of water resources in the target area are obtained, and the impact of drought is superimposed to generate a planning grid, wherein each planning grid is marked with a drought level; a grey correlation coefficient is introduced, and the grey correlation coefficient is calculated and determined with the drought level as a reference sequence and the influencing factors as a comparison sequence, and the comparison sequence is at least one item; a game decision module is constructed, wherein the game decision principle uses the scheduling competition between grids to conduct a first equilibrium game, and uses the competition between water use structures to conduct a second equilibrium game; combining the planning grid and the grey correlation coefficient, a dynamic water resource configuration decision is made based on the game decision module to determine the water resource configuration strategy; the water resource configuration strategy is terminal visualized to guide the water resource configuration management of the target area.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] The present application obtains the spatiotemporal distribution characteristics of water resources in the target area, superimposes the impact of drought, and generates a planning grid, wherein each planning grid is marked with a drought level; introduces a gray correlation coefficient, the gray correlation coefficient is calculated and determined with the drought level as a reference sequence and the influencing factors as a comparison sequence, and the comparison sequence is at least one; constructs a game decision module, wherein the game decision principle uses the scheduling competition between grids to conduct a first equilibrium game, and uses the competition between water use structures to conduct a second equilibrium game; combines the planning grid and the gray correlation coefficient, and makes a dynamic configuration decision of water resources based on the game decision module to determine the water resource configuration strategy; terminal visualization of the water resource configuration strategy guides the water resource configuration management of the target area. The present invention solves the technical problem of low configuration efficiency in the prior art when performing dynamic configuration of water sources, by obtaining the spatiotemporal distribution characteristics of water resources in the target area and superimposing the impact of drought, generating a planning grid marked with a drought level, combining the gray correlation coefficient, analyzing the relationship between the influencing factors and the drought level, constructing a game decision module, conducting scheduling competition between grids and water use structures, and finally realizing the dynamic configuration decision of water resources, achieving the technical effect of improving the efficiency and accuracy of water resource configuration. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0012] Figure 1 A schematic diagram of the structure of a regional drought relief water source dynamic configuration platform provided in an embodiment of the present application;

[0013] Figure 2 A schematic flow chart of a method for dynamically configuring regional drought-resistant water sources provided in an embodiment of the present application.

[0014] Explanation of the reference numerals: planning grid generating unit 11 , grey correlation coefficient determining unit 12 , game decision constructing unit 13 , configuration decision unit 14 , configuration management unit 15 . DETAILED DESCRIPTION

[0015] The present application provides a regional drought-resistant water source dynamic configuration platform and method to solve the technical problem of low configuration efficiency in the existing technology when performing dynamic configuration of water sources. By obtaining the spatiotemporal distribution characteristics of water resources in the target area and superimposing the impact of drought, a planning grid marked with drought level is generated. Combined with the grey correlation coefficient, the relationship between influencing factors and drought level is analyzed, a game decision-making module is constructed, and scheduling competition is carried out between grids and water use structures. Finally, dynamic configuration decisions of water resources are realized, achieving the technical effect of improving the efficiency and accuracy of water resource allocation.

[0016] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0017] It should be noted that any variations of the terms "include" and "have" are intended to cover non-exclusive inclusions. For example, a process, method, platform, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or inherent to these processes, methods, products or devices.

[0018] Embodiment 1, as Figure 1 As shown, the embodiment of the present application provides a regional drought relief water source dynamic configuration platform, which includes:

[0019] The planning grid generation unit 11 obtains the spatiotemporal distribution characteristics of water resources in the target area, superimposes the impact of drought, and generates planning grids, wherein each planning grid is marked with a drought level.

[0020] In an embodiment of the present application, firstly, the spatiotemporal distribution characteristics of water resources in the target area are obtained through a preset database. These characteristics include information such as precipitation, changes in surface water flow, and groundwater level fluctuations. Then, according to the differences in water resources in the region, the target area is divided into multiple initialization grids according to the preset difference degree. Next, each initialization grid is traversed to determine the water structure of each grid, that is, the type of water resources. Then, the initialization grid is mapped to the corresponding water structure, and the impact of drought is superimposed to generate the final planning grid. In the process of superimposing the impact of drought, the impact of drought on water structure is evaluated for each grid, so as to determine the water structure level. After setting the resource critical value, the drought level of each grid is further calculated, and the drought level is obtained by weighted superposition of the part of the water structure level that exceeds the critical value.

[0021] The final planning grid not only includes the water resource structure of each region, but also identifies the drought level of each grid.

[0022] Furthermore, in the platform provided in the embodiment of the application, the planning grid generation unit 11 is also used for:

[0023] The spatiotemporal distribution characteristics are traversed, and based on a preset difference, the target area is gridded to determine an initialization grid; the initialization grid is traversed to determine a grid water structure, wherein the measurement magnitude of each grid water structure is determined based on the same standard; the initialization grid and the grid water structure are mapped, and the impact of drought is superimposed to generate the planning grid.

[0024] In the embodiment of the present application, the spatiotemporal distribution characteristics of the target area are first traversed, that is, the distribution of water resources at different times and geographical locations is analyzed. These distribution characteristics include precipitation, river flow changes, groundwater level fluctuations, etc. Based on these data, the target area is gridded according to the preset difference standard to generate an initialization grid. When dividing, the difference is used as the main basis, and the regions with similar water resource characteristics or needs are grouped into the same grid by analyzing the topography, climate (such as precipitation and evaporation) and water demand of each region.

[0025] After the grid division is completed, each initialized grid is traversed to determine its water structure. Water structure refers to the use of water resources within the grid, including civil water, agricultural water, ecological water, etc. The water structure of each grid is divided according to a unified measurement standard, so that the data between all grids are consistent and comparable.

[0026] Next, the initialization grid is mapped to its water structure and drought impact is superimposed to generate a planning grid with drought levels. Here, drought impact refers to the degree to which drought conditions affect water supply and demand. The key to drought impact assessment lies in the monitoring and analysis of specific drought characteristics, such as persistent high temperatures and reduced rainfall, which can lead to varying degrees of water shortage.

[0027] Finally, after steps such as difference analysis, grid division, water structure determination and drought impact superposition, the planning grid is generated.

[0028] Furthermore, in the platform provided in the embodiment of the application, the planning grid generation unit 11 is also used for:

[0029] For the first grid, the grid water structure is traversed, the superposition calculation of the drought impact is performed, and the water structure level is determined; the resource critical value is set, and the drought level of the first grid is calculated based on the water structure level, wherein the drought level is the weighted superposition value of the over-limit part of the water structure level.

[0030] In the embodiment of the present application, for the first grid, the water structure within the grid is first traversed to identify different types of water demand, including civil water, agricultural water, and ecological water. Each water type has different demand characteristics, which is the basis for water resource allocation under the influence of drought. After traversing the water structure, the various water demands are classified, laying a clear foundation for the subsequent drought impact assessment.

[0031] Then, the specific impact of drought on each type of water demand is calculated by superimposing real-time meteorological data such as temperature, precipitation, and evaporation rate. The impact of drought varies depending on the sensitivity of each type of water demand. For example, high temperature and low rainfall will lead to a sharp increase in agricultural water demand, because the water demand of crops increases with the increase in evaporation rate; ecological water may require more replenishment under drought conditions to maintain the ecological balance of rivers and wetlands. Therefore, according to the sensitivity of different water use types to climate change, the meteorological impact is superimposed one by one and quantified as the urgency of each type of water use under the current drought. For example, under drought conditions, the specific increase in each type of water demand is calculated one by one by superimposing real-time meteorological data (such as temperature, precipitation, and evaporation rate). For agricultural water use, high temperature and low rainfall will lead to increased soil moisture loss and increased crop water demand. In this example, assuming that the agricultural water demand under normal weather is 100 cubic meters / day, affected by high temperature and increased evaporation rate, agricultural water use increases by 20% to 120 cubic meters / day. According to the preset standard, if the demand increase exceeds 15%, it is judged as "high demand", so agricultural water use is marked as "high demand", that is, the water structure level is high. For civil water use, civil water is less sensitive to temperature, but the demand for domestic water will increase under high temperature conditions, and it is expected to increase by 5%-10%. Assuming that the daily civil water demand is 50 cubic meters / day, the demand increases to 52.5 cubic meters / day under high temperature and drought conditions. According to the preset standard, it is marked as "medium demand", that is, the water structure level is medium. For ecological water use, in order to maintain the ecological balance of river wetlands, ecological water needs to be replenished under drought conditions. Assuming that the ecological water demand is 30 cubic meters / day under normal circumstances, due to the increase in evaporation rate, the ecological water demand rises to 35 cubic meters / day. According to the sensitivity of the ecosystem, ecological water use is marked as "medium-high demand", that is, the water structure level is medium-high. Through the above analysis, the water structure level is determined. Among them, the preset standard is set by technical experts. The preset standard is that if the increase in a certain type of water demand due to drought exceeds 15%, it is judged as "high demand", that is, the water structure level is high. If the demand increase is between 10% and 15%, it is considered "medium-high demand", that is, the water structure level is medium-high. If the demand increase is between 5% and 10%, it is considered "medium demand", that is, the water structure level is medium. If the demand increase is less than 5%, it is considered "low demand", that is, the water structure level is low.

[0032] In order to assess the drought level, a resource critical value is set for each type of water use, that is, the maximum sustainable water supply capacity of each water use structure within the grid. The resource critical value is set by technical experts based on historical data and current supply and demand conditions as a warning line for water resource allocation. For example, the agricultural water critical value is 110 cubic meters / day, the civil water critical value is 50 cubic meters / day, and the ecological water critical value is 32 cubic meters / day. By comparing each type of water demand with its resource critical value, the over-limit of each water structure is calculated, that is, the part that exceeds the critical value. The agricultural water demand is 120 cubic meters, which exceeds the critical value by 10 cubic meters. The civil water demand is 52.5 cubic meters, which exceeds the critical value by 2.5 cubic meters. The ecological water demand is 35 cubic meters, which exceeds the critical value by 3 cubic meters.

[0033] To reflect the overall drought situation of the grid, the over-limit parts of each water structure are weighted and superimposed according to their importance weights to obtain the final drought level. The weights are pre-set based on the importance of each water structure and the urgency of the drought. For example, the weight of agricultural water use is 0.5, the weight of civil water use is 0.2, and the weight of ecological water use is 0.3. These weights are pre-set by technical experts.

[0034] Then, according to the limit and weight, the weighted superposition value of the drought level is calculated as follows: drought level = (agricultural limit × agricultural weight) + (civilian limit × civil weight) + (ecological limit × ecological water use weight). The drought level is obtained by substituting the data into the calculation.

[0035] Through the above process, the drought level of the first grid is finally determined.

[0036] The grey correlation coefficient determination unit 12 introduces the grey correlation coefficient, and the grey correlation coefficient is calculated and determined with the drought level as a reference sequence and the influencing factors as a comparison sequence, and the comparison sequence is at least one item.

[0037] In the embodiment of the present application, in order to introduce the grey correlation coefficient, N influencing factors affecting the drought level, such as precipitation, temperature, evaporation rate, etc., are first determined, and a comparison sequence is established for each influencing factor, each sequence contains multiple phased nodes related to the change of drought conditions, forming N comparison sequences. Then the drought level is used as a reference sequence, and its grey correlation coefficient is calculated one by one with each comparison sequence. For each comparison sequence, its correlation coefficient at each node is calculated, and these correlation coefficients are averaged to obtain the overall grey correlation coefficient of the influencing factor. After completing the calculation of the grey correlation coefficients of all influencing factors, these correlation coefficients are sorted according to the degree of association.

[0038] Through the above process, the introduction of grey relational coefficient is completed.

[0039] Furthermore, in the platform provided by the application embodiment, the grey correlation coefficient determination unit 12 is also used for:

[0040] Determine N influencing factors that affect the drought level, determine N comparison sequences, each sequence contains multiple drought stage nodes; calculate the grey correlation coefficient for the reference sequence and the N comparison sequences; wherein the grey correlation coefficient calculation method includes: for the reference sequence and the first comparison sequence, calculate the node correlation coefficient and perform mean calculation as the grey correlation coefficient of the first influencing factor; complete the calculation of the grey correlation coefficient of the Nth influencing factor, and perform positive serialization sorting on the influencing factors.

[0041] In the embodiment of the present application, N key influencing factors affecting the drought level are first determined, including precipitation, temperature, evaporation rate, etc. Then, a comparison sequence is constructed for each influencing factor, and further refined into multiple drought stage nodes, i.e., numerical data points in different time periods. These nodes represent the performance of each influencing factor at each stage of drought change, ensuring that the dynamic change characteristics of these factors can be evaluated time by time, thereby forming a comparison sequence with a time dimension.

[0042] Subsequently, the drought levels were used as the reference series, i.e., the benchmark for all comparative analyses.

[0043] Then the grey correlation coefficient of the reference sequence and each comparison sequence is calculated. Specifically, the reference sequence (drought level) and each comparison sequence (influencing factor) are first standardized, and the data are normalized to the same range (between 0 and 1), thereby eliminating the magnitude difference between the data and making the comparison of all factors in the same dimension more accurate. After completing the data standardization, the absolute difference between the reference sequence and the comparison sequence is calculated at each time node to generate an absolute difference sequence. This absolute difference sequence reflects the degree of difference between the drought level and each influencing factor at each time node. The smaller the difference, the more consistent the changes between the two. Then, the maximum difference and the minimum difference are determined in the entire absolute difference sequence, and these two values ​​are used as the basis for calculating the correlation coefficient. At each time node, the correlation coefficient of the current node is calculated by the relationship between the absolute difference between the minimum difference and the current node and the maximum difference. Next, the correlation coefficients at all time nodes are averaged to obtain the overall grey correlation coefficient of the influencing factor.

[0044] After performing the above operations on all N comparison sequences in turn, the grey correlation coefficient calculation of each influencing factor is completed. Finally, the grey correlation coefficients of all factors are sorted from high to low according to the correlation degree.

[0045] The game decision building unit 13 builds a game decision module, wherein the game decision principle is to conduct a first equilibrium game through competition among grid scheduling and to conduct a second equilibrium game through competition among water use structures.

[0046] In the embodiment of the present application, in order to construct a game decision module, the game decision construction unit first retrieves and calls historical water resource scheduling records, integrates these records based on the game decision principle, and forms training samples. Then, these training samples are used to supervise the training of the first game decision branch (resource balance game between grids) and the second game decision branch (water use structure balance game within the grid). Through training, a game decision module is generated.

[0047] Furthermore, in the platform provided in the application embodiment, the game decision building unit 13 is also used for:

[0048] The game decision module includes a first game decision branch and a second game decision branch; retrieves and calls water resource scheduling records, integrates the records based on the game decision principle, and determines training samples; based on the training samples, performs supervised training of the first game decision branch and the second game decision branch to generate the game decision module.

[0049] In the embodiment of the present application, the game decision module includes a first game decision branch and a second game decision branch. The first branch processes the scheduling competition between grids, and the second branch processes the resource competition of the water use structure within the grid.

[0050] To build the game decision module, water resource scheduling records are first retrieved and called. By using database query technology, such as SQL statements to access relational databases, water resource scheduling records are obtained. These data include water resource usage of each grid at different times and under drought conditions, such as daily or monthly water consumption, available water resources, and historical scheduling decisions. Then the obtained scheduling records are integrated to determine the training samples. In this process, data cleaning and preprocessing techniques are applied, including removing redundant data, processing missing values, and unifying data formats. Specifically, each record is checked for completeness, and missing data is interpolated or deleted when necessary. At the same time, the timestamp format is unified to the ISO standard to facilitate time series analysis. After processing, all valid records are integrated into training samples, which contain water resource usage data in different seasons and different drought levels, forming a basic data set that can be used for model training.

[0051] Next, supervised training of the first game decision branch is performed. In this stage, supervised learning algorithms, such as random forests, are used to train based on input features in the scheduling records, such as the grid's historical water demand, available water resources, and the impact of neighboring grids. These features are used as input variables of the model, and the historical scheduling results are used as the target variable. Through training, the first game decision branch is obtained.

[0052] The supervised training of the second game decision branch is then performed, using the same supervised learning algorithm, such as random forest, to model the demand for each water use structure within the grid, and specifically analyze the priority and urgency of demand for agricultural water, civil water, and ecological water when resources are insufficient. This branch combines the Nash equilibrium principle in game theory during the training process to ensure that the optimal balance point of resource allocation is found between water use structures.

[0053] Finally, after completing the training of the two decision branches, the output results of the two branches are integrated to form a complete game decision module. This module is applied to water resource scheduling in real time, and realizes the reasonable allocation of resources between and within grids through the equilibrium strategy provided by game theory.

[0054] A configuration decision unit 14 is provided. The configuration decision unit 14 combines the planning grid with the grey correlation coefficient and makes a dynamic water resource configuration decision based on the game decision module to determine a water resource configuration strategy.

[0055] In the embodiment of the present application, the planning grid and the grey correlation coefficient are first combined to identify the water resource demand and urgency of each grid under the current drought conditions. Then, based on the first game decision branch, a first equilibrium game is performed to determine the configuration strategy of each grid and simulate the resource allocation under limited water resources. After that, for the determined grid configuration strategy, a second equilibrium game is performed based on the second game decision branch to further optimize the resource allocation of different water use structures in the same grid. Finally, a mapping between the grid configuration strategy and the water structure configuration strategy is established to generate the final water resource allocation strategy.

[0056] Furthermore, in the platform provided in the embodiment of the application, the configuration decision unit 14 is also used for:

[0057] In combination with the planning grid and the grey correlation coefficient, a first equilibrium game is performed based on the first game decision branch to determine a grid configuration strategy; with respect to the grid configuration strategy, a second equilibrium game is performed based on the second game decision branch to determine a water structure configuration strategy; a mapping between the grid configuration strategy and the water structure configuration strategy is established to generate the water resource configuration strategy.

[0058] In an embodiment of the present application, the first equilibrium game is first performed using the planning grid and the grey correlation coefficient in combination with the trained first game decision branch. At this stage, each grid is regarded as an independent participant, and their scheduling competition under limited water resources is simulated. By applying an optimization algorithm to analyze the water resource demand of each grid, the current available water volume, and the influence of adjacent grids, the priority under the current drought conditions is determined. Using the trained model in the first game decision branch, the optimization scheme for resource allocation is solved, and the optimal configuration strategy between the grids is found to ensure the reasonable and fair distribution of water resources among the grids.

[0059] Then, based on the determined grid configuration strategy, the second game decision branch is entered to conduct the second equilibrium game. This game focuses on the resource competition between different water use structures in the same grid, such as agricultural water use, civil water use and ecological water use. The multi-objective optimization method is used to analyze the urgency of various water demand to ensure that the main water demand is met in the water resource allocation process, while taking into account the reasonable allocation of other water use structures.

[0060] Finally, the mapping between the grid configuration strategy and the water structure configuration strategy is established, and the relationship between the two is clarified through data association analysis technology. This mapping ensures that each water structure can achieve accurate resource allocation within each grid. Finally, a water resource allocation strategy is generated, which specifies in detail the amount of water resources that each grid should obtain and its allocation principles under specific conditions.

[0061] Furthermore, in the platform provided in the embodiment of the application, the configuration decision unit 14 is also used for:

[0062] For the target area, the dynamic objective laws of water resources are determined; and dynamic allocation decisions of water resources are made based on the dynamic objective laws as constraints.

[0063] In the embodiment of the present application, firstly, data collection is performed to obtain historical and real-time data related to water resources for the target area. These data include precipitation, evaporation, flow changes of rivers in the basin, groundwater level fluctuations, etc. Then, data preprocessing is performed to improve the quality and reliability of the data. This process includes missing value filling and outlier detection to ensure the validity of the data in subsequent analysis.

[0064] Then, time series analysis is used to analyze the sorted data to identify the changing trends and periodic characteristics of water resources in different time periods. Specifically, the sliding average method is used to smooth data fluctuations and observe the long-term changing trends of water resources. After clarifying the dynamic objective law of water resources, this law is used as a constraint for subsequent water resource allocation. Through logical rules, constraints are set according to dynamic objective laws, such as flow direction, inflow and outflow relationship, etc., to ensure that the actual hydrological characteristics are followed during the resource allocation process.

[0065] Next, the dynamic allocation decision of water resources is made based on the dynamic objective law. Specifically, the water resource demand of each grid is analyzed by combining the acquired planning grid and the grey correlation coefficient, and the resource allocation is ensured to follow the dynamic law. In this process, the first equilibrium game is carried out to simulate the resource competition among the grids to determine a reasonable grid allocation strategy. Then, the second equilibrium game is carried out based on the grid configuration strategy to optimize the resource allocation between different water use structures (such as agricultural water, civil water and ecological water) in the same grid. Through this process, the dynamic allocation decision of water resources is completed.

[0066] A configuration management unit 15 is provided, wherein the configuration management unit 15 performs terminal visualization on the water resource allocation strategy to guide water resource allocation management in a target area.

[0067] In an embodiment of the present application, the configuration management unit extracts key data from the water resource allocation strategy, including the water resource allocation amount of each grid, the demand situation of the water use structure, and related dynamic objective laws. Next, the extracted data is converted into intuitive graphics and charts using visualization tools. For example, a heat map is used to display the water resource allocation situation of different grids, or a pie chart is used to display the proportion of each water use structure in the overall water resources. Through this terminal visualization, the water resource allocation management of the target area is guided.

[0068] In the embodiments of the present application, in summary, the embodiments of the present application have at least the following technical effects:

[0069] The present application obtains the spatiotemporal distribution characteristics of water resources in the target area, superimposes the impact of drought, and generates a planning grid, wherein each planning grid is marked with a drought level; introduces a gray correlation coefficient, the gray correlation coefficient is calculated and determined with the drought level as a reference sequence and the influencing factors as a comparison sequence, and the comparison sequence is at least one; constructs a game decision module, wherein the game decision principle uses the scheduling competition between grids to conduct a first equilibrium game, and uses the competition between water use structures to conduct a second equilibrium game; combines the planning grid and the gray correlation coefficient, and makes a dynamic configuration decision of water resources based on the game decision module to determine the water resource configuration strategy; terminal visualization of the water resource configuration strategy guides the water resource configuration management of the target area. The present invention solves the technical problem of low configuration efficiency in the prior art when performing dynamic configuration of water sources, by obtaining the spatiotemporal distribution characteristics of water resources in the target area and superimposing the impact of drought, generating a planning grid marked with a drought level, combining the gray correlation coefficient, analyzing the relationship between the influencing factors and the drought level, constructing a game decision module, conducting scheduling competition between grids and water use structures, and finally realizing the dynamic configuration decision of water resources, achieving the technical effect of improving the efficiency and accuracy of water resource configuration.

[0070] Embodiment 2, based on the same inventive concept as the regional drought relief water source dynamic configuration platform in the previous embodiment, Figure 2 As shown, the embodiment of the present application provides a method for dynamically configuring regional drought relief water sources, the method comprising:

[0071] The spatiotemporal distribution characteristics of water resources in the target area are obtained, and the impact of drought is superimposed to generate a planning grid, wherein each planning grid is marked with a drought level; a grey correlation coefficient is introduced, and the grey correlation coefficient is calculated and determined with the drought level as a reference sequence and the influencing factors as a comparison sequence, and the comparison sequence is at least one item; a game decision module is constructed, wherein the game decision principle uses the scheduling competition between grids to conduct a first equilibrium game, and uses the competition between water use structures to conduct a second equilibrium game; combining the planning grid and the grey correlation coefficient, a dynamic water resource configuration decision is made based on the game decision module to determine the water resource configuration strategy; the water resource configuration strategy is terminal visualized to guide the water resource configuration management of the target area.

[0072] Furthermore, the method for generating a planning grid further includes:

[0073] The spatiotemporal distribution characteristics are traversed, and based on a preset difference, the target area is gridded to determine an initialization grid; the initialization grid is traversed to determine a grid water structure, wherein the measurement magnitude of each grid water structure is determined based on the same standard; the initialization grid and the grid water structure are mapped, and the impact of drought is superimposed to generate the planning grid.

[0074] Furthermore, the method for generating the planning grid further includes:

[0075] For the first grid, the grid water structure is traversed, the superposition calculation of the drought impact is performed, and the water structure level is determined; the resource critical value is set, and the drought level of the first grid is calculated based on the water structure level, wherein the drought level is the weighted superposition value of the over-limit part of the water structure level.

[0076] Furthermore, the grey relational coefficient is introduced, and the method further comprises:

[0077] Determine N influencing factors that affect the drought level, determine N comparison sequences, each sequence contains multiple drought stage nodes; calculate the grey correlation coefficient for the reference sequence and the N comparison sequences; wherein the grey correlation coefficient calculation method includes: for the reference sequence and the first comparison sequence, calculate the node correlation coefficient and perform mean calculation as the grey correlation coefficient of the first influencing factor; complete the calculation of the grey correlation coefficient of the Nth influencing factor, and perform positive serialization sorting on the influencing factors.

[0078] Furthermore, the game decision module is constructed, and the method further includes:

[0079] The game decision module includes a first game decision branch and a second game decision branch; retrieves and calls water resource scheduling records, integrates the records based on the game decision principle, and determines training samples; based on the training samples, performs supervised training of the first game decision branch and the second game decision branch to generate the game decision module.

[0080] Furthermore, based on the game decision module, a water resource dynamic configuration decision is made, and the method further includes:

[0081] In combination with the planning grid and the grey correlation coefficient, a first equilibrium game is performed based on the first game decision branch to determine a grid configuration strategy; with respect to the grid configuration strategy, a second equilibrium game is performed based on the second game decision branch to determine a water structure configuration strategy; a mapping between the grid configuration strategy and the water structure configuration strategy is established to generate the water resource configuration strategy.

[0082] Furthermore, before making a decision on the dynamic allocation of water resources, the method further includes:

[0083] For the target area, the dynamic objective laws of water resources are determined; and dynamic allocation decisions of water resources are made based on the dynamic objective laws as constraints.

[0084] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0085] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0086] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. Regional drought relief water source dynamic configuration platform, characterized by: include: A planning grid generation unit, wherein the planning grid generation unit obtains the spatiotemporal distribution characteristics of water resources in the target area, superimposes the impact of drought, and generates planning grids, wherein each planning grid is marked with a drought level; A grey correlation coefficient determination unit, wherein the grey correlation coefficient is introduced, and the grey correlation coefficient is calculated and determined with the drought level as a reference sequence and the influencing factors as a comparison sequence, and the comparison sequence is at least one item; A game decision building unit, wherein the game decision building unit builds a game decision module, wherein the game decision principle performs a first equilibrium game based on the scheduling competition between grids and performs a second equilibrium game based on the competition between water use structures; A configuration decision unit, wherein the configuration decision unit combines the planning grid and the grey correlation coefficient, makes a dynamic water resource configuration decision based on the game decision module, and determines a water resource configuration strategy; A configuration management unit is used to perform terminal visualization on the water resource allocation strategy to guide water resource allocation management in a target area.

2. The regional drought relief water source dynamic configuration platform according to claim 1, characterized in that: The generating planning grid comprises: Traversing the spatiotemporal distribution characteristics, dividing the target area into grids based on a preset difference, and determining an initialization grid; Traversing the initialization grid to determine the grid water structure, wherein the measurement level of each grid water structure is determined based on the same standard; The initialization grid and the grid water structure are mapped, drought impact is superimposed, and the planning grid is generated.

3. The regional drought relief water source dynamic configuration platform according to claim 2, characterized in that: The generating the planning grid comprises: For the first grid, traverse the grid water structure, perform superposition calculation of drought impact, and determine the water structure level; A resource critical value is set, and based on the water structure level, a drought level of the first grid is calculated, wherein the drought level is a weighted superposition value of the over-limit portion of the water structure level.

4. The regional drought relief water source dynamic configuration platform according to claim 1, characterized in that: The introduction of grey correlation coefficient includes: Determine N influencing factors affecting the drought level, determine N comparison sequences, each sequence contains multiple drought stage nodes; Calculating the grey correlation coefficient for the reference sequence and the N comparison sequences; Among them, the calculation methods of grey correlation coefficient include: For the reference sequence and the first comparison sequence, the node correlation coefficient is calculated and the mean is calculated as the grey correlation coefficient of the first influencing factor; Complete the calculation of the grey correlation coefficient of the Nth influencing factor and sort the influencing factors in a positive order.

5. The regional drought relief water source dynamic configuration platform according to claim 1, characterized in that: Constructing the game decision module includes: The game decision module includes a first game decision branch and a second game decision branch; Retrieve and call water resource dispatch records, integrate the records based on the game decision principle, and determine training samples; Based on the training samples, supervised training of the first game decision branch and the second game decision branch is performed to generate the game decision module.

6. The regional drought relief water source dynamic configuration platform according to claim 5, characterized in that: The water resources dynamic configuration decision is made based on the game decision module, including: Combining the planning grid with the grey correlation coefficient, performing a first equilibrium game based on the first game decision branch, and determining a grid configuration strategy; For the grid configuration strategy, a second equilibrium game is performed based on the second game decision branch to determine a water structure configuration strategy; A mapping between the grid configuration strategy and the water structure configuration strategy is established to generate the water resource configuration strategy.

7. The regional drought relief water source dynamic configuration platform according to claim 6, characterized in that: Before making a decision on dynamic water resource allocation, the following should be considered: Determine the dynamic objective laws of water resources for the target area; Based on the dynamic objective laws mentioned above, dynamic water resource allocation decisions are made.

8. A method for dynamically configuring regional drought-resistant water sources, characterized in that: The method is performed by the regional drought-resistant water source dynamic configuration platform according to any one of claims 1 to 7, comprising: Obtain the spatiotemporal distribution characteristics of water resources in the target area, superimpose the impact of drought, and generate planning grids, where each planning grid is marked with a drought level; A grey correlation coefficient is introduced, wherein the grey correlation coefficient is calculated and determined with the drought level as a reference sequence and the influencing factors as a comparison sequence, and the comparison sequence is at least one item; Construct a game decision module, in which the game decision principle uses the scheduling competition between grids to conduct the first equilibrium game, and the competition between water use structures to conduct the second equilibrium game; Combining the planning grid with the grey correlation coefficient, making a dynamic water resource allocation decision based on the game decision module, and determining a water resource allocation strategy; The water resource allocation strategy is visualized at the terminal to guide the water resource allocation management in the target area.

Images