Multi-water-source forecast scheduling method, device and equipment for salt tide and storage medium

Abstract

The invention discloses a multi-water-source forecast scheduling method, device and equipment for salt tide and a storage medium, and belongs to the technical field of water source scheduling, and the method comprises the steps: obtaining a first time range of a first region, the first time range being a predicted time range of salt tide invasion in the first region; acquiring a first water demand of the first region within the first time range; establishing a multi-water-source scheduling model, wherein a plurality of objective functions and a plurality of constraint conditions of the multi-water-source scheduling model are determined based on the first time range and the first water demand; based on the multiple objective functions and the multiple constraint conditions, a multi-objective genetic algorithm is adopted to solve the multi-water-source scheduling model so as to determine a multi-water-source scheduling scheme, the multi-water-source scheduling scheme comprises the step that forecast scheduling is conducted on the first region within a second time range, and the second time range is used for indicating the time duration of forecast scheduling; the second time range precedes the first time range. The method can accurately realize the forecast scheduling of the salt tide.

Description

Technical Field

[0001] The present invention relates to the technical field of water source scheduling, and in particular to a multi-water source forecast scheduling method, device, equipment and storage medium for saltwater tides. Background Art

[0002] Water source forecast dispatch refers to the act of dispatching water from a water source in another area to a certain area in advance when a natural disaster (such as drought or saltwater tide) is predicted to occur in that area. Multi-water source forecast dispatch refers to dispatching water from multiple water sources to that area.

[0003] In the related art, water source scheduling for saltwater tide is usually saltwater suppression scheduling. Saltwater suppression scheduling mainly refers to releasing the water stored in the reservoir in a certain area when saltwater tide occurs in the area, thereby reducing the salinity of the water source in the area. However, when saltwater tide intrusion occurs, the pump station cannot draw water, and the city can only be supplied with water from the reservoir in the area. Saltwater suppression scheduling easily leads to insufficient water storage in the reservoir in the area, which in turn leads to insufficient water supply in the city. Summary of the invention

[0004] The present disclosure provides a method, device, equipment and storage medium for multi-water source forecasting and scheduling of saltwater tides, which can accurately realize the forecasting and scheduling of saltwater tides. The technical solution at least includes the following solutions: In a first aspect, a multi-water source forecasting and scheduling method for saltwater intrusion is provided, comprising: obtaining a first time range for a first area, the first time range being a predicted time range for saltwater intrusion in the first area; obtaining a first water demand for the first area within the first time range; establishing a multi-water source scheduling model, wherein a plurality of objective functions and a plurality of constraints of the multi-water source scheduling model are determined based on the first time range and the first water demand; based on the plurality of objective functions and the plurality of constraints, a multi-objective genetic algorithm is used to solve the multi-water source scheduling model to determine a multi-water source scheduling scheme, the multi-water source scheduling scheme comprising forecasting and scheduling the first area within a second time range, the second time range being used to indicate a time length of the forecast scheduling, the second time range being before the first time range.

[0005] Optionally, the multiple objective functions of the multi-water source scheduling model include: a water supply guarantee rate objective function, a reservoir water storage capacity objective function, a water supply disruption depth objective function, a green economic benefit objective function and a seawater desalination utilization objective function; wherein the water supply guarantee rate objective function is used to indicate that the total water supply guarantee rate of the area to be scheduled within the first time range and the second time range is the largest, and the area to be scheduled includes the first area and other areas that supply water to the first area; the reservoir water storage capacity objective function is used to indicate that the water storage capacity of the reservoirs in the area to be scheduled within the first time range and the second time range is the largest; the water supply disruption depth objective function is used to indicate that the total water supply disruption depth of the area to be scheduled within the first time range and the second time range is the smallest, and the water supply disruption depth is used to indicate the degree of water shortage in the area to be scheduled; the green economic benefit objective function is used to indicate that the pump station in the area to be scheduled consumes the least energy within the first time range and the second time range; and the seawater desalination utilization objective function is used to indicate that the seawater desalination utilization of the area to be scheduled within the first time range and the second time range is the smallest.

[0006] Optionally, the constraints of the multi-water source scheduling model include: water balance constraint, reservoir water storage constraint, supply flow constraint, first water demand constraint, pump station working water level constraint, pump station water intake capacity constraint, pump station operation time constraint, river water quality and reservoir water quality constraint, seawater desalination water supply capacity constraint; wherein, the water balance constraint is used to indicate that the water balance principle must be met during the multi-water source scheduling process; the reservoir water storage constraint is used to indicate that the water storage in the first reservoir must meet the first water storage range, the first water storage range is used to indicate the maximum water storage capacity and minimum water storage capacity of the first reservoir within a first time period, the first reservoir is any reservoir in the area to be scheduled, and the first time period is any time period within the first time range and the second time range; the supply flow constraint is used to indicate that the supply flow of the first reservoir in the first time period must be less than or equal to the maximum supply flow of the first reservoir in the first time period; the first water demand constraint is used to indicate that within the first time range, the sum of the first water storage capacities of the reservoirs in the area to be scheduled is greater than or equal to the first water demand, the first The water storage capacity is used to indicate the amount of water in the reservoir used for water supply; the pump station working water level constraint is used to indicate that when any pump station draws water from the water intake where it is located, the river water level of the water intake must be within the working water level range of the pump station; the pump station water intake capacity constraint is used to indicate that the water intake flow of any pump station in the first time period must be less than or equal to the first water intake flow and the second water intake flow, the first water intake flow is the maximum water intake flow of the pump station, and the second water intake flow is the maximum water intake flow of the river where the water intake of the pump station is located in the first time period; The station operation time constraint is used to indicate that any pump station must wait for at least a first period of time after being turned on before it can be turned off, and any pump station must wait for at least the first period of time after being turned off before it can be turned on, and the first period of time is the shortest operation time of the pump station; the river water quality and reservoir water quality constraints are used to indicate that the water quality of any river used for water intake and the water quality of the reservoir must meet the water quality requirements, and the water quality requirements include a chlorine content that is less than or equal to the maximum chlorine content; the seawater desalination water supply capacity constraint is used to indicate that the water supply of the seawater desalination plant is less than or equal to the maximum net water volume of the seawater desalination plant.

[0007] Optionally, obtaining the first time range of the first area includes: obtaining first hydrological data of the first area, the first hydrological data including the salinity of water in a river channel where each water intake of the first area is located; inputting the first hydrological data into a saltwater tide prediction model to obtain the first time range; wherein the saltwater tide prediction model is a multi-layer long short-term memory network model.

[0008] Optionally, obtaining the first water demand in the first area within the first time range includes: obtaining historical water supply data of multiple water plants in the first area; constructing an autoregressive moving average model for each water plant based on the historical water supply data of each water plant; determining the water demand of each water plant within the first time range based on the autoregressive moving average model of each water plant, and then determining the first water demand, the first water demand being the sum of the water demands of each water plant within the first time range.

[0009] Optionally, based on the multiple objective functions and the multiple constraints, a multi-objective genetic algorithm is used to solve the multi-water source scheduling model to determine the multi-water source scheduling plan for the first region, including: using a multi-objective genetic algorithm to solve the multi-water source scheduling model to obtain a non-inferior solution set, wherein the non-inferior solution set includes multiple non-inferior solutions; performing weighted summation on the multiple objective functions to obtain a total objective function; and using the optimal non-inferior solution corresponding to the total objective function as the multi-water source scheduling plan for the first region, wherein the optimal non-inferior solution corresponding to the total objective function is in the non-inferior solution set.

[0010] In the second aspect, a multi-water source forecasting and scheduling device for saltwater tides is also provided, including: a first acquisition module, used to obtain a first time range for a first area, the first time range is the predicted time range for saltwater tide invasion in the first area; a second acquisition module, used to obtain a first water demand for the first area within the first time range; a modeling module, used to establish a multi-water source scheduling model, and multiple objective functions and multiple constraints of the multi-water source scheduling model are determined based on the first time range and the first water demand; a solving module, used to solve the multi-water source scheduling model based on the multiple objective functions and the multiple constraints, using a multi-objective genetic algorithm to determine a multi-water source scheduling scheme, the multi-water source scheduling scheme includes forecasting and scheduling the first area within a second time range, the second time range is used to indicate the time length of the forecast scheduling, and the second time range is before the first time range.

[0011] Optionally, the first acquisition module is also used to acquire first hydrological data of the first area, the first hydrological data including the salinity of water in a river channel where each water intake in the first area is located; input the first hydrological data into a saltwater tide prediction model to obtain the first time range; wherein the saltwater tide prediction model is a multi-layer long short-term memory network model.

[0012] Optionally, the second acquisition module is also used to obtain historical water supply data of multiple water plants in the first area; based on the historical water supply data of each water plant, construct an autoregressive moving average model of each water plant; based on the autoregressive moving average model of each water plant, determine the water demand of each water plant within the first time range, and then determine the first water demand, which is the sum of the water demands of each water plant within the first time range.

[0013] Optionally, the solution module is also used to use a multi-objective genetic algorithm to solve the multi-water source scheduling model to obtain a non-inferior solution set, which includes multiple non-inferior solutions; perform weighted summation on the multiple objective functions to obtain a total objective function; and use the optimal non-inferior solution corresponding to the total objective function as the multi-water source scheduling plan for the first area, and the optimal non-inferior solution corresponding to the total objective function is in the non-inferior solution set.

[0014] In a third aspect, a computer device is also provided, including: a memory and a processor, wherein at least one computer program is stored in the memory, and the at least one computer program is loaded and executed by the processor, thereby executing the multi-water source forecasting and scheduling method for saltwater tides described in the above embodiment.

[0015] In a fourth aspect, a computer-readable storage medium is also provided, in which at least one computer program is stored. The at least one computer program is loaded and executed by a processor to execute the multi-water source forecasting and scheduling method for saltwater tides described in the above embodiment.

[0016] In a fifth aspect, a computer program product is provided, comprising a computer program / instruction, wherein when the computer program / instruction is executed by a processor, the method described in the first aspect is implemented.

[0017] The beneficial effects brought by the technical solution provided by the embodiments of the present disclosure include at least: The multi-water source forecast dispatch for saltwater tides first needs to accurately predict the time period of the saltwater tide in the first area, that is, the first time range, and then supply water to the first area before the first time range based on the multi-water source dispatching scheme. Carrying out multi-water source forecast dispatching before the saltwater tide occurs in the first area can ensure that the water storage in the reservoir of the first area is sufficient when the saltwater tide invades, so as to avoid water shortage in the city.

[0018] The use of multiple water sources for forecasting and dispatching can effectively reduce the unexpected situations that occur during forecasting and dispatching of a single water source (such as insufficient water available for dispatch from a single water source) and improve the reliability of forecasting and dispatching.

[0019] In the disclosed embodiment, by obtaining a first time range of a first area; obtaining a first water demand of the first area within the first time range; establishing a multi-water source scheduling model, multiple objective functions and multiple constraints of the multi-water source scheduling model are determined based on the first time range and the first water demand; using a multi-objective genetic algorithm to solve the multi-water source scheduling model and then determine the multi-water source scheduling plan, the accuracy and reliability of the generated multi-water source scheduling plan can be improved, and thus the multi-water source forecast scheduling can be effectively realized before the arrival of the salt tide. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, 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 disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 Schematic diagram of water supply relationship between various water sources Figure 2 A flowchart of a multi-water source forecasting and scheduling method for saltwater tide provided by an exemplary embodiment of the present disclosure is shown; Figure 3 A flowchart of a multi-water source forecasting and scheduling method for saltwater tide provided by another exemplary embodiment of the present disclosure is shown; Figure 4 Flowchart for training saltwater tide prediction model; Figure 5 Flow chart for obtaining the first water demand; Figure 6 This is a schematic diagram of the multi-water source joint complementary scheduling model; Figure 7 It is a flowchart of the NSGA-Ⅲ algorithm; Figure 8 A schematic structural diagram of a multi-water source forecasting and scheduling device for saltwater tides provided by an exemplary embodiment of the present disclosure is shown; Fig. 9 It is a schematic diagram of the structure of a computer device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0022] Unless otherwise defined, the technical or scientific terms used herein shall have the usual meanings understood by persons of ordinary skill in the field to which the present disclosure belongs. The words "first", "second", "third" and similar words used in the patent application specification and claims of the present disclosure do not indicate any order, quantity or importance, but are only used to distinguish different components. Similarly, words such as "one" or "one" do not indicate a quantitative limitation, but rather indicate the presence of at least one. Words such as "include" or "comprise" and similar words mean that the elements or objects appearing before "include" or "comprises" cover the elements or objects listed after "include" or "comprises" and their equivalents, and do not exclude other elements or objects.

[0023] In order to make the objectives, technical solutions and advantages of the present disclosure more clear, the embodiments of the present disclosure will be further described in detail below with reference to the accompanying drawings.

[0024] In order to facilitate understanding of the embodiments of the present disclosure, the types of saltwater intrusion and water sources are first described below.

[0025] Saltwater intrusion: During the dry season, seawater flows back into the river due to the tide, causing the salt content of the river water to rise sharply, exceeding the drinking water treatment standard, making it impossible to draw water from the water source for a period of time. This phenomenon is called saltwater intrusion.

[0026] Water sources: Water sources include pumping stations, water plants, reservoirs and desalination plants. Figure 1 This is a schematic diagram of the water supply relationship between various water sources. Figure 1 Explain the water supply relationship between various water sources.

[0027] The pump station 101 is used to draw water from the river 102 through the water intake. The water drawn from the river 102 by the pump station 101 can be provided to the water plant 104 and the reservoir 103. In addition, any pump station can also supply water to other pump stations with lower elevation information than the pump station. For example, if the terrain of pump station A is higher than that of pump station B, then pump station A can supply water to pump station B, but pump station B cannot supply water to pump station A.

[0028] The reservoir 103 is used to store water, and the water in the reservoir 103 can be provided to the water plant 104. In addition, any reservoir can also supply water to other reservoirs whose elevation information is lower than that of the reservoir. For example, if the terrain of reservoir A is higher than that of reservoir B, then reservoir A can supply water to reservoir B, but reservoir B cannot supply water to reservoir A.

[0029] The water plant 104 is used to supply water to the city 105 , and a certain amount of water may also be stored in the water plant 104 .

[0030] The seawater desalination plant 106 is used to take water from the seawater 107 and perform desalination treatment. The water desalinated in the seawater desalination plant 106 can be provided to the water plant 104 .

[0031] In the disclosed embodiment, the water sources include pumping stations, water plants, and reservoirs within the first region, as well as pumping stations and reservoirs in other areas outside the first region, while the seawater desalination plant is not limited to any region and only needs to supply water to the water plants within the first region.

[0032] Figure 2 A flowchart of a multi-water source forecasting and scheduling method for saltwater tide provided by an exemplary embodiment of the present disclosure is shown, and the method can be executed by a computer device. Figure 2 , the method comprising: In step 201, a first time range of a first region is obtained.

[0033] The first time range is the predicted time range for saltwater intrusion to occur in the first area. Here, the time range for saltwater intrusion is the time when the salinity of the water in the river channel where a water intake in the first area is located starts to exceed the standard and the time range when the salinity exceeds the standard. The salinity of the water in the river channel where the water intake is located exceeds the standard, which means that a saltwater intrusion has occurred (the salinity standard for salinity exceeding the standard is not limited in the disclosed embodiment). Exemplarily, it is predicted that the salinity of the water in the river channel where a water intake in the first area is located exceeds the standard at time A, and after a period of time, the salinity of the water stops exceeding the standard and returns to normal at time B, where A is before B, and the first time range of the river channel is [A, B].

[0034] Similarly, for each river channel where the water intake is located in the first area, a first time range can be predicted, and then multiple first time ranges can be determined. When a multi-water source scheduling model is subsequently established, planning is also carried out according to multiple first time ranges.

[0035] Optionally, the first region is an area where a river channel where saltwater intrusion may occur is located, for example, an area where a river channel with a history of saltwater intrusion is located.

[0036] In step 202, a first water demand of a first area within a first time range is obtained.

[0037] In step 203, a multi-water source scheduling model is established.

[0038] Multiple objective functions and multiple constraints of the multi-water source scheduling model are determined based on the first time range and the first water demand.

[0039] In the embodiment of the present disclosure, the multi-water source scheduling model is a mathematical model, which includes multiple objective functions and multiple constraints.

[0040] In step 204, based on multiple objective functions and multiple constraints, a multi-objective genetic algorithm is used to solve the multi-water source scheduling model to determine a multi-water source scheduling solution.

[0041] The multi-water source dispatching scheme includes forecast dispatching of multiple water sources for the first region within a second time range, the second time range is used to indicate the time length of the forecast dispatching, and the second time range is before the first time range. Here, the second time range is the time required for the forecast dispatching, and the length of the second time range is determined according to the multi-water source dispatching scheme.

[0042] Optionally, multiple water sources are forecasted and dispatched for the first region within the second time range, including: dispatching pump stations and reservoirs in multiple regions within the first time range. For example, water in pump stations and reservoirs in other regions except the first region can be dispatched to reservoirs in the first region within the second time range to achieve pre-water storage.

[0043] Optionally, the multi-water source scheduling scheme further includes performing multi-water source scheduling on the first region within a first time range. Performing multi-water source scheduling on the first region within the first time range includes the following two situations: The first situation: after the saltwater intrusion begins, some pumping stations in the first area can still draw water. For example, since the salinity of each pumping station starts to exceed the standard at different times, after the saltwater intrusion begins, some pumping stations in the first area may not exceed the standard in terms of salinity. Such pumping stations can still supply water to reservoirs and water plants in the first area.

[0044] Therefore, in this case, the multi-water source scheduling involved includes: the pumping station in the first area, the pumping station outside the first area and the reservoir outside the first area supply water to the reservoir in the first area; the pumping station in the first area, the pumping station outside the first area, the reservoir in the first area and the reservoir outside the first area supply water to the water plant in the first area.

[0045] The second situation: after the saltwater intrusion begins, all pumping stations in the first area are unable to draw water. In this case, the water source dispatch involved includes: pumping stations outside the first area and reservoirs outside the first area supply water to reservoirs in the first area; pumping stations outside the first area, reservoirs in the first area and reservoirs outside the first area supply water to water plants in the first area.

[0046] In the case of multiple objective functions and multiple constraints, a multi-objective genetic algorithm is used to solve the multi-water source scheduling model, which can obtain a non-inferior solution set, which includes multiple solutions. Then, an optimal solution can be selected from the multiple solutions in the non-inferior solution set, and the optimal solution is the multi-water source scheduling plan for the first region that is finally determined. The multi-water source forecast dispatch for saltwater tides first needs to accurately predict the time period of the saltwater tide in the first area, that is, the first time range, and then supply water to the first area before the first time range based on the multi-water source dispatching scheme. Carrying out multi-water source forecast dispatching before the saltwater tide occurs in the first area can ensure that the water storage in the reservoir of the first area is sufficient when the saltwater tide invades, so as to avoid water shortage in the city.

[0047] The use of multiple water sources for forecasting and dispatching can effectively reduce the unexpected situations that occur during forecasting and dispatching of a single water source (such as insufficient water available for dispatch from a single water source) and improve the reliability of forecasting and dispatching.

[0048] In the disclosed embodiment, by obtaining a first time range of a first area; obtaining a first water demand of the first area within the first time range; establishing a multi-water source scheduling model, multiple objective functions and multiple constraints of the multi-water source scheduling model are determined based on the first time range and the first water demand; using a multi-objective genetic algorithm to solve the multi-water source scheduling model and then determine the multi-water source scheduling plan, the accuracy and reliability of the generated multi-water source scheduling plan can be improved, and thus the multi-water source forecast scheduling can be effectively realized before the arrival of the salt tide.

[0049] Figure 3 A flowchart of a multi-water source forecasting and scheduling method for saltwater tide provided by another exemplary embodiment of the present disclosure is shown, and the method can be executed by a computer device. Figure 3 , the method comprising: In step 301, first hydrological data of a first region is obtained.

[0050] The first hydrological data includes the salinity of water in rivers where each water intake in the first region is located.

[0051] For the relevant contents of the first region, please refer to the aforementioned step 301, and the detailed description is omitted here.

[0052] Optionally, by testing the water quality of the water in the river where each water intake in the first area is located, it is possible to obtain the salinity of the water in the river where each water intake in the first area is located.

[0053] In step 302, first hydrological data is input into a saltwater tide prediction model to obtain a first time range.

[0054] Among them, the saltwater tide prediction model is a multi-layer long short-term memory network (LSTM) model.

[0055] Optionally, the saltwater tide prediction model is constructed using the following steps ac. Figure 4 This is the flowchart for training the saltwater tide prediction model. Figure 4Steps ac are described.

[0056] Step a, obtaining a first data set for training a saltwater tide prediction model.

[0057] The first data set includes historical hydrological data of multiple regions. For any of the multiple regions, the historical hydrological data includes basic basin geographic data, salt tide data, pump station operation status data, reservoir operation data, key section data of river sections, reservoir runoff water quality data, measured salinity data of river water intake points, and meteorological and hydrological data of the region.

[0058] Optionally, the historical hydrological data of a certain area can be obtained through field research, literature review, data collation, etc. In some embodiments, the work logs of the hydrological facilities in the area can also be obtained through discussions, etc., so as to obtain the historical hydrological data of the area. The hydrological facilities include river hydrological monitoring stations and river water quality monitoring stations.

[0059] Step b: preprocessing the data in the first data set.

[0060] Optionally, the preprocessing includes: outlier removal, interpolation, data smoothing, and data normalization.

[0061] Among them, the outlier removal process is used to remove obvious abnormal data in the first data set. The interpolation process is used to reasonably interpolate the missing time point data (such as using the mean of the previous and next time points) to improve the continuity and integrity of the data. The data smoothing process is used to reduce noise interference; for example, the sliding average filter algorithm can be used to smooth the time series data in the first data set to reduce noise interference. The data normalization process is used to convert data of different dimensions to the same scale, so that features of different dimensions can be compared and analyzed on the same scale.

[0062] Step c: Based on the preprocessed first data set, train the LSTM model to obtain a saltwater tide prediction model.

[0063] When training the LSTM model, instead of using all the data in the first data set for training, part of the data in the first data set is selectively used for training according to the training objective function.

[0064] In the disclosed embodiment, the objective function is the accuracy of salinity prediction, which is represented by minimizing the root mean square value between the salinity predicted by the LSTM model and the actual salinity. That is, the smaller the root mean square value, the more accurate the salinity prediction.

[0065] Part of the data selected from the first data set can be stored in a database to facilitate query and analysis.

[0066] Optionally, before training, a portion of the data selected from the first data set is divided into a training set and a test set, and then the training set is used to train the LSTM model, and the test set is used to verify the performance of the LSTM model. The division is performed, for example, in a ratio of 7:3. When dividing here, attention should be paid to sample balance, that is, the ratio of each type of data in the training set and the test set should be balanced.

[0067] Optionally, during the training process, hyperparameters can also be set, and the model will be continuously iterated according to the hyperparameters during the training process. The hyperparameters include: input feature dimension input_size, hidden layer state dimension hidden_size, LSTM stacking layer number num_layers, hidden layer bias state bias|, batch processing setting batch_first, dropout rate, and learning rate. Optionally, the Bayesian optimization algorithm is used to optimize the hyperparameters of the LSTM model, that is, the error of the LSTM model is calculated after each iteration until the error of the LSTM model is less than the error threshold, or the number of iterations reaches the maximum number.

[0068] Optionally, during the model iteration process, there are also learning parameters, and the learning parameters are continuously optimized and updated during the model iteration process, for example, the Adam optimization algorithm is used to optimize and update the learning parameters.

[0069] Optionally, using a test set to verify the performance of the LSTM model includes: inputting the salinity in the test set into the LSTM model, calculating the objective function value (that is, the root mean square between the predicted result and the actual salinity) according to the prediction result output by the LSTM model, and evaluating the performance of the LSTM model according to the objective function value. When evaluating the performance of the LSTM model, a prediction accuracy threshold can be preset. When the objective function value on the test set is greater than or equal to the prediction accuracy threshold, it means that the LSTM model meets the performance requirements and the LSTM model can be used as a saltwater tide prediction model; when the objective function value is less than the prediction accuracy threshold, it means that the LSTM model does not meet the performance requirements and needs to be retrained.

[0070] After the training of the salinity prediction model is completed, the first hydrological data of the first area can be input into the salinity prediction model to obtain the first time range.

[0071] In step 303, a first water demand of a first area within a first time range is obtained.

[0072] Optionally, step 303 includes the following steps df. Figure 5 To obtain the flow chart of the first water demand, the following is combined with Figure 5 Step df is described.

[0073] Step d: obtaining historical water supply data of multiple water plants in the first region.

[0074] When the first data set in step a of step 302 is obtained, the historical hydrological data of the first region can be obtained, and then in step d, the historical water supply data of multiple water plants in the first region are obtained based on the first data set.

[0075] Step e: construct an autoregressive moving average model for each water plant based on the historical water supply data of each water plant.

[0076] After obtaining the historical water supply data of multiple water plants in the first region, before constructing the Auto-Regression and Moving Average (ARMA) model, the historical water supply data of multiple water plants in the first region need to be preprocessed, including: removing and replacing outliers and removing noise.

[0077] The process of removing and replacing outliers is used to remove outliers in the historical water supply data of multiple water plants in the first region. After removing the outliers, it is necessary to fill in other data in the position where the outliers are located, such as adjacent data, so as to replace the outliers. For example, a group of data is 2, 2, 2, 7, 3... In this group of data, the outlier is 7. At this time, it is necessary to remove the outlier 7 and insert the data adjacent to the outlier 7. The data adjacent to the outlier 7 is the data adjacent to the outlier 7, such as 2 or 3, and the average value of the two, 2.5, can also be taken. After the group of data is removed and replaced with outliers, the group of data can be 2, 2, 2, 2, 3...

[0078] The noise removal process can be implemented by using the Kalman filter method to remove the noise in the data, and the retained data is the filtered data. There are many implementation methods of the Kalman filter method in the related art, and the detailed description is omitted here.

[0079] Optionally, the first region The ARMA model of a water plant is expressed using formula (1).

[0080] (1) In formula (1), Indicates the first region Water plants in The amount of water supplied during the period. To indicate the The number of autoregressive terms for each water plant represents the number of lags in the time series data itself. There are An autoregressive term. For the The number of moving average items for each water plant. For the The autoregressive coefficient of each water plant is For the The moving average coefficient of each water plant is Indicates the first region Water plants in The random error term for the time period.

[0081] In building When building an ARMA model for a water plant, we first set an initial and Then the least squares method is used to estimate the value of Other parameters in the ARMA model of each water plant (including autoregressive term coefficient, moving average term coefficient, random error term, etc.).

[0082] Initial setting and When the value of is different, the estimated other parameters are also different, and it is necessary to choose a suitable initial setting and In the embodiment of the present disclosure, the Akaike information criterion (AIC) is used to calculate each and The AIC score under the value combination scheme is the smallest AIC score. and The value of and The other parameters estimated by the value of are used as the values ​​of each parameter in the ARMA model.

[0083] By minimizing the AIC score and The values ​​of the parameters in the value combination scheme are used as the values ​​of each parameter in the ARMA model, which can optimize the performance of the ARMA model.

[0084] For other water plants in the first region except the i-th water plant, the ARMA model can also be constructed in the above manner, which is omitted here.

[0085] Step f, based on the autoregressive moving average model of each water plant, determining the water demand of each water plant within the first time range, and then determining the first water demand.

[0086] After determining the ARMA model of each water plant in the first region, the water demand of each water plant in the first region within the first time range can be predicted based on the ARMA model of each water plant in the first region. The first water demand is the sum of the water demands of each water plant within the first time range.

[0087] In step 304, a multi-water source scheduling model is established.

[0088] The multi-water source scheduling model includes multiple objective functions and multiple constraints, and the multiple objective functions and multiple constraints of the multi-water source scheduling model are determined based on the first time range and the first water demand.

[0089] Optionally, the objective functions of the multi-water source scheduling model include: a water supply guarantee rate objective function, a reservoir water storage capacity objective function, a water supply disruption depth objective function, a green economic benefit objective function and a seawater desalination utilization objective function. Figure 6 This is a schematic diagram of the multi-water source joint complementary scheduling model. Figure 6 These five objective functions are explained respectively.

[0090] Water supply guarantee rate objective function: The water supply guarantee rate objective function is used to indicate that the total water supply guarantee rate of the area to be scheduled within the first time range and the second time range is the maximum.

[0091] The water supply guarantee rate is used to indicate whether the water demand of the area to be dispatched is met within a certain period of time. A large water supply guarantee rate means that the water demand of the area to be dispatched is basically met, and a small water supply guarantee rate means that the water demand of the area to be dispatched cannot be met. Therefore, the larger the water supply guarantee rate, the better.

[0092] The first time range and the second time range are continuous, and the first time range and the second time range can be divided into multiple time periods, and planning can be performed according to the time periods. For example, the starting time of the second time range is time T1, and the ending time of the second time range is time T2, that is, saltwater intrusion will occur in the first area at time T2, and the saltwater intrusion in the first area will end at time T3. Then the first time range is also the time range from time T2 to time T3. When planning, the time period from time T1 to time T3 can be divided into multiple time periods, and the time length of each time period is equal, so there is a water demand in the area to be scheduled in each time period.

[0093] In this case, optionally, the water supply guarantee rate objective function is expressed using formula (2).

[0094] (2) In formula (2), is the objective function of water supply guarantee rate, is the total number of time periods, Indicated in Whether the water demand of the area to be dispatched is met within the time period. If the water demand of the area to be dispatched is met within a period of time, is 1, if in If the water demand of the area to be dispatched is not met within a period of time, is 0. is an integer, Greater than 0 and less than .

[0095] The objective function of water supply guarantee rate is to maximize the increase of water supply during the normal water supply period and the saltwater intrusion period to meet the water demand of the area to be dispatched within the second time range and the first time range.

[0096] Reservoir water storage objective function: The reservoir water storage objective function is used to indicate that the reservoirs in the area to be dispatched have the maximum water storage capacity within the first time range and the second time range.

[0097] The reservoirs in the area to be dispatched include reservoirs in the first area and reservoirs outside the first area.

[0098] Optionally, the reservoir water storage objective function is expressed using formula (3).

[0099] (3) In formula (3), is the reservoir water storage objective function, is the total number of reservoirs in the area to be dispatched, The first The reservoir is The water storage at the beginning of a time period, The first The weight of a reservoir. is an integer, Greater than 0 and less than The other parameters in formula (3) are the same as those in formula (2), and their detailed description is omitted here.

[0100] Among them, The weight of each reservoir can be set based on experience, and the embodiment of the present disclosure does not limit this.

[0101] The objective function of reservoir water storage is to make full use of the available regulation and storage capacity of each reservoir in the dispatching area, and to increase the water storage capacity of each reservoir as much as possible before the arrival of the salt tide, so as to meet the water demand of the first area when the river water intake pumping station in the first area cannot work normally during the salt tide intrusion.

[0102] Water supply disruption depth objective function: The water supply disruption depth objective function is used to indicate that the total water supply disruption depth in the area to be scheduled is the minimum within the first time range and the second time range. Among them, the water supply disruption depth is used to indicate the degree of water shortage in the area to be scheduled. The greater the water supply disruption depth, the greater the water shortage of users in the area to be scheduled. Here, the water shortage of users in the area to be scheduled means that the total water supply of various water sources in the area to be scheduled within a certain period of time is less than the total water demand of each water plant. Therefore, the smaller the water supply disruption depth in planning, the better.

[0103] Optionally, the water supply damage depth objective function is expressed using formula (4).

[0104] (4) In formula (4), is the water supply damage depth objective function, For the area to be dispatched The actual water supply in a period of time, For the area to be dispatched The other parameters in formula (4) are the same as those in formula (2), and their detailed description is omitted here.

[0105] The actual water supply is the sum of the first water storage of each water source in the area to be dispatched. The first water storage is used to indicate the amount of water in the reservoir for water supply. Assuming that the water storage in a reservoir is 10L, but in order to ensure the normal operation of the reservoir, a certain amount of water (for example, 1L) needs to be retained in the reservoir, then the first water storage of the reservoir is 9L. For any water source in the area to be dispatched, it can be determined that the first water storage is 9L. The first water storage capacity in a time period can be used to obtain the actual water supply.

[0106] The actual water demand is the sum of the water demand of each water plant in the dispatching area (including water plants in the first area and water plants outside the first area). The water demand in a time period can be determined by the method in step 303; and for water plants outside the first area, the water demand in the first area can be determined by the method in step 303. The water demand in a time period can also be predicted by using the ARMA model after establishing the ARMA model in a similar manner as in step 303. In this way, the sum of the water demand of each water plant in the area to be dispatched can be determined.

[0107] The water supply disruption depth objective function is used to ensure that the water demand of the dispatching area in any time period is met as much as possible.

[0108] Green economic benefit objective function: The green economic benefit objective function is used to indicate that the pumping stations in the area to be dispatched consume the least energy in the first time range and the second time range.

[0109] The pumping stations in the area to be dispatched include pumping stations within the first area and pumping stations outside the first area.

[0110] Here, the energy consumption of the pumping station is related to the pumping station head. The smaller the pumping station head, the less energy the pumping station consumes.

[0111] The pumping head refers to the height to which the pumping station can lift water. The head of a pump = net head + head loss. The head loss is a fixed value that cannot be changed. The net head refers to the height difference between the suction point of the pump and the high-level control point. For example, a pump draws water from a river and sends it to a high-level water tank. The net head refers to the height difference between the river level and the high-level water tank.

[0112] It can be seen that the higher the river level, the smaller the net lift of the pump station, the smaller the lift of the pump station, and the less energy consumption. Therefore, any pump station should try to draw water when the river water level at the water intake where the pump station is located is at a high water level, so as to reduce the energy consumption of the pump station.

[0113] Optionally, the green economic benefit objective function is expressed using formula (5).

[0114] (5) In formula (5), is the green economic benefit objective function; The average water level at the water intake of each pump station in the area to be dispatched during the startup period; is the total number of pumping stations in the area to be dispatched; For the The pump station The switch status within a time period, It can be 1 or 0. When it is 1, it means The pump station The device is powered on for a period of time. When it is 0, it means The pump station The device is powered off for a period of time. For the In the time period The river water level at the water intake of each pumping station; is an integer, Greater than 0 and less than The other parameters in formula (5) are the same as those in formula (2), and their detailed description is omitted here.

[0115] The green economic benefit objective function is used to ensure that the average water level at the water intake of each pump station in the dispatching area is the highest during the startup period, which is equivalent to making each pump station take water during the high water level period as much as possible, thereby reducing energy consumption and achieving the purpose of green economic benefits.

[0116] Seawater desalination utilization objective function: The seawater desalination utilization objective function is used to indicate that the seawater desalination utilization in the to-be-scheduled area within the first time range and the second time range is minimized.

[0117] Optionally, the seawater desalination objective function is expressed using formula (6).

[0118] (6) In formula (6), is the total number of desalination plants in the area to be dispatched, For the In the time period The water supply of a desalination plant, is an integer, Greater than 0 and less than The other parameters in formula (6) are the same as those in formula (2), and their detailed description is omitted here.

[0119] Seawater desalination is a relatively costly way to obtain fresh water. Under the premise of ensuring the highest possible water supply rate, the water supply capacity of existing water supply projects such as rivers and reservoirs should be fully utilized, and freshwater sources should be used first for direct water supply. Seawater desalination should only be used when freshwater sources cannot guarantee normal water supply. This can minimize the amount of seawater desalination water supply and reduce water supply costs.

[0120] Optionally, the constraints of the multi-water source scheduling model include: water balance constraint, reservoir water storage constraint, replenishment flow constraint, first water demand constraint, pump station working water level constraint, pump station water intake capacity constraint, pump station operation time constraint, river water quality and reservoir water quality constraint, and seawater desalination water supply capacity constraint. Figure 6 These nine constraints are explained separately.

[0121] Water balance constraint: Water balance constraint is used to indicate that the water balance principle must be met during the multi-water source scheduling process.

[0122] The water balance principle means that the total amount of water in the entire water supply system will not change.

[0123] In the process of multi-water source scheduling, the water balance principle must be met between each reservoir's own water storage capacity, the water replenishment flow from other water sources, and its own discharge flow.

[0124] For the entire multi-water source scheduling process, the water balance principle must also be met between incoming water, stored water and water consumption.

[0125] Optionally, the water balance constraint is expressed by formula (7) to formula (8). Formula (7) is used to express the water balance constraint for a single reservoir, and formula (8) is used to express the water balance constraint in the entire multi-water source dispatching process.

[0126] (7) In formula (7), For the At the beginning of the time period (that is, end of the time period) The water storage capacity of the reservoir, For the In the time period The inflow of a reservoir, For the In the time period The water supply flow of a reservoir. For the In the time period The downstream flow of a reservoir is used to indicate the water flow that meets other functional requirements besides water supply, such as downstream ecological flow. For the In the time period The sum of the recharge flows that a reservoir receives from other water sources. For the In the time period The reservoirs discharge water to The sum of the outflows from other reservoirs other than the reservoir. The other parameters in formula (7) have the same meanings as those in formula (2), formula (3) and formula (5), and their detailed description is omitted here.

[0127] (8) In formula (8), For the In the time period The other parameters in formula (8) have the same meanings as those in formula (7) and formula (4), and their detailed description is omitted here.

[0128] Reservoir water storage capacity constraint: The reservoir water storage capacity constraint is used to indicate that the water storage capacity in the first reservoir must meet the first water storage range. The first water storage range is used to indicate the maximum and minimum water storage capacity of the first reservoir in the first time period. The first reservoir is any reservoir in the area to be dispatched, and the first time period is any time period in the first time range and the second time range.

[0129] Here, the first water storage range is the boundary condition of each reservoir. Each reservoir has different boundary conditions at different time periods, and the water storage capacity of the first reservoir at any time period must meet the boundary conditions of that time period. For example, for a water supply reservoir that also has flood control functions, the maximum water storage capacity of the reservoir during the flood season cannot exceed the reservoir capacity corresponding to the flood limit water level, while in the non-flood season, it can be stored up to the beneficial storage capacity.

[0130] Optionally, the water balance constraint is expressed using formula (9).

[0131] (9) In formula (9), For the In the time period The minimum water storage capacity of a reservoir is also the lower limit of the first water storage range. For the In the time period The maximum water storage capacity of a reservoir is also the upper limit of the first water storage range. The meanings of other parameters in formula (9) are the same as those in formula (2) and formula (3), and detailed description is omitted here.

[0132] Recharge flow constraint: The recharge flow constraint is used to indicate that the recharge flow of the first reservoir in the first time period must be less than or equal to the maximum recharge flow of the first reservoir in the first time period.

[0133] The recharge flow between different reservoirs at different times is subject to the maximum flow capacity of the water diversion pipe or channel, as well as other constraints such as policies and laws. For example, two reservoirs belong to two administrative regions, and the policy between the two administrative regions sets an upper limit on the recharge flow between the two regions. Therefore, the recharge flow between different reservoirs at different times should be less than or equal to the maximum recharge flow allowed in that period.

[0134] Optionally, the recharge flow constraint is expressed using formula (10).

[0135] (10) In formula (10) Indicates In the time period The meanings of other parameters in formula (10) are the same as those in formula (7), and their detailed description is omitted here.

[0136] First water demand constraint: The first water demand constraint is used to indicate that within the first time range, the sum of the first water storage of each reservoir in the dispatch area is greater than or equal to the first water demand. The sum of the first water storage of each reservoir here is the actual water storage in the water supply damage depth objective function.

[0137] Within the first time range, if the pumping station in the first area is unable to draw water, the actual water storage capacity of each reservoir in the dispatching area should meet the first water demand so that the first area will not suffer from water shortage.

[0138] Optionally, the first water demand constraint is expressed using formula (11).

[0139] (11) In formula (11), is the start time of the first time range, is the length of the first time range, that is, Equal to the end time of the first time range. For the Reservoirs in The water storage capacity at the moment, For the The dead storage capacity of a reservoir, that is, the dead storage capacity of the reservoir The lowest water level allowed to drop under normal operation. is the safety factor, , For the area to be dispatched The meanings of other parameters in formula (11) are the same as those in formula (2), and their detailed description is omitted here.

[0140] Pump station working water level constraint: The pump station working water level constraint is used to indicate that when any pump station draws water from the water intake where it is located, the river water level at the water intake must be within the working water level range of the pump station.

[0141] The pump station can only operate normally when the river water level at the water intake is within the working water level range. Optionally, the pump station working water level constraint is expressed by formula (12).

[0142] (12) In formula (12), Indicated in In the time period The river water level at the water intake where the pump station is located, Indicates The lower limit of the working water level of each pump station, Indicates The meanings of other parameters in formula (12) are the same as those in formula (2) and formula (5), and their detailed description is omitted here.

[0143] Pumping station water intake capacity constraint: Pumping station water intake capacity constraint is used to indicate that the water intake flow of any pumping station in the first time period must be less than or equal to the first water intake flow and the second water intake flow. The first water intake flow is the maximum water intake flow of the pumping station, and the second water intake flow is the maximum water intake flow of the river where the water intake of the pumping station is located in the first time period.

[0144] Due to the actual engineering and boundary conditions such as the pump station output limitation, operation safety and the allowable water intake flow rate of the river, the pump station flow rate cannot be increased arbitrarily and there are constraints on the water intake capacity of the pump station.

[0145] Optionally, the pump station water intake capacity constraint is expressed using formula (13).

[0146] (13) In formula (13), For the The first water intake flow of each pumping station, For the The second water intake flow of the pump station indicates The river channel where the water intake of the pump station is located is The meanings of other parameters in formula (13) are the same as those in formula (8), and their detailed description is omitted here.

[0147] Pump station operation time constraint: Pump station operation time constraint is used to indicate that any pump station must wait for at least the first time period after it is turned on before it can be turned off, and any pump station must wait for at least the first time period after it is turned off before it can be turned on. The first time period is the shortest operation time of the pump station.

[0148] During the actual dispatching process, due to the difficulty of manual operation, workload and engineering characteristics of the pumping station, it is impossible for the pumping station to be opened and closed at any time according to the external water level. That is, after entering a certain state (such as opening or closing), the pumping station needs to maintain it for a period of time before it can switch to another state.

[0149] Optionally, the pump station operation time constraint is expressed using formula (14).

[0150] (14) In formula (14), For the first duration, for The time a pump station maintains a certain state (such as on or off) after entering that state.

[0151] River water quality and reservoir water quality constraints: River water quality and reservoir water quality constraints are used to indicate that the water quality of any river or reservoir used for water intake must meet water quality requirements. Water quality requirements include chlorine content being less than or equal to the maximum chlorine content.

[0152] The water quality of rivers and reservoirs must meet the water quality requirements. If the chlorine content of the water in the river or reservoir is high and exceeds the maximum chlorine content allowed for water plant water intake or industrial water use, water cannot be diverted or taken from the river or reservoir. In other special cases, such as sudden pollution accidents upstream of the river or reservoir, resulting in serious deterioration of the water quality, which exceeds the raw water quality requirements allowed for water plant water intake or industrial water use, water cannot be taken either. Therefore, during the dispatch period, the water quality at the river intake point and the reservoir should meet the water quality requirements.

[0153] Optionally, the water quality requirement also includes that the concentration of any water quality indicator in the water body must be less than or equal to the concentration threshold corresponding to the water quality indicator. Water quality indicators are, for example, COD (Chemical Oxygen Demand), NH3-N (an ammonia nitrogen content indicator), etc. The concentration threshold corresponding to any water quality indicator is an empirical value, and the embodiment of the present disclosure does not limit the value of the concentration threshold.

[0154] Optionally, the water quality of the river and the water quality constraints of the reservoir are expressed using formula (15) and formula (16).

[0155] (15) In formula (15), For the In the time period The chlorine content of the reservoir For the In the time period The chlorine content of the river water at the water intake of each pump station is The meanings of other parameters in formula (15) are the same as those in formula (2), formula (3) and formula (5), and their detailed description is omitted here.

[0156] (16) In formula (15), For the In the time period Any water quality index of a reservoir, For the In the time period Any water quality index of the river water body at the water intake where the pump station is located, is the concentration threshold corresponding to the water quality index. The meanings of other parameters in formula (16) are the same as those in formula (2), formula (3) and formula (5), and their detailed description is omitted here.

[0157] Desalination water supply capacity constraint: The desalination water supply capacity constraint is used to indicate that the water supply of the desalination plant is less than or equal to the maximum net water output of the desalination plant.

[0158] There is an upper limit to the working capacity of a seawater desalination plant (maximum net water volume), so the water supply of the seawater desalination plant should be less than or equal to this upper limit.

[0159] Optionally, the seawater desalination water supply capacity constraint is expressed using formula (17).

[0160] (17) In formula (17), For the In the time period The meanings of other parameters in formula (17) are the same as those in formula (6), and their detailed description is omitted here.

[0161] After determining the above-mentioned multiple objective functions and multiple constraints, a multi-water source scheduling model can be established based on the multiple objective functions and multiple constraints.

[0162] In step 305, based on multiple objective functions and multiple constraints, a multi-objective genetic algorithm is used to solve the multi-water source scheduling model to determine a multi-water source scheduling solution.

[0163] Optionally, the multi-objective genetic algorithm used in the embodiments of the present disclosure is a NSGA-III (Non-dominated Sorting Genetic Algorithm III) algorithm.

[0164] Optionally, step 305 includes the following step gi.

[0165] Step g: Use a multi-objective genetic algorithm to solve the multi-water source scheduling model and obtain a non-inferior solution set.

[0166] The non-inferior solution set includes multiple non-inferior solutions.

[0167] Optionally, when the multi-objective genetic algorithm is the NSGA-III algorithm, step g includes the following five steps. Figure 7 This is a flow chart of the NSGA-Ⅲ algorithm. Figure 7 Step g is described below. Figure 7 In the example, gen is used to count the number of iterative evolutions. When gen is equal to 1, it indicates that the first iterative evolution is being performed, and when gen is equal to 2, it indicates that the second iterative evolution is being performed.

[0168] The first step is to set the algorithm parameters of the NSGA-Ⅲ algorithm.

[0169] Optionally, the algorithm parameters of the NSGA-III algorithm include: population size, maximum number of iterations, probability of selection, crossover and mutation. There are many ways to set the algorithm parameters in the related art, and detailed description is omitted here.

[0170] In the second step, based on the multi-water source scheduling model, the initial parent population is randomly generated, the objective function values ​​of all individuals in the parent population are calculated according to the set algorithm parameters, and all individuals in the parent population are sorted according to non-dominated relationships according to different objective functions. During the sorting, all individuals in the parent population are selected, crossed, and mutated according to the set fitness value to obtain the first-generation subpopulation.

[0171] Here, the initial parent population includes multiple individuals, and the multi-water source scheduling model includes five objective functions, so each individual can also calculate five objective function values. The initial parent population and the first generation subpopulation constitute the first iterative evolution.

[0172] The third step is to combine the parent population with the child population, perform fast non-dominated sorting on the combined population, calculate the crowding degree, and select appropriate individuals to form a new parent population based on the crowding degree value.

[0173] The following is a brief description of the second iterative evolution process: First, the initial parent population and the first-generation subpopulation are combined, and the combined population is quickly non-dominated sorted, the crowding degree is calculated, and appropriate individuals are selected according to the crowding value to form a new parent population. Then, the fourth step is executed to obtain the subpopulation of the new parent population (that is, the second-generation subpopulation). The new parent population and the second-generation subpopulation here constitute the second iterative evolution.

[0174] Each subsequent iterative evolution adopts a similar method to the second iterative evolution, that is, the third and fourth steps are repeated, and detailed description is omitted here.

[0175] The fourth step is to generate sub-populations for the new parent population through selection, crossover, and mutation operators.

[0176] Step 5, step 3 and step 4, until the number of iterations reaches the maximum number of iterations, a non-inferior solution set is obtained.

[0177] There are many implementation methods for each step of the NSGA-Ⅲ algorithm in the related technologies, so the detailed description is omitted here.

[0178] Step h, performing weighted summation on multiple objective functions to obtain the total objective function.

[0179] When performing weighted summation on multiple objective functions, it is necessary to first determine the weight coefficient of each objective function.

[0180] For example, by investigating the water conservancy, water affairs, environment, municipal and other stakeholder departments in the area to be dispatched and consulting experts, the weight coefficient of each objective function can be determined.

[0181] Optionally, the overall objective function is expressed using formula (18).

[0182] (18) In formula (18), They are The weight coefficient of . This is the total objective function. The meanings of other parameters in formula (18) are the same as those in formulas (2) to (6), and their detailed description is omitted here.

[0183] Step i: taking the optimal non-inferior solution corresponding to the total objective function as the multi-water source scheduling plan for the first region.

[0184] The optimal non-inferior solution corresponding to the total objective function is in the non-inferior solution set.

[0185] The essence of step i is to find an optimal non-inferior solution from the non-inferior solution set through the total objective function. Here, after determining the total objective function, each non-inferior solution in the non-inferior solution set can find a total objective function value according to the total objective function, and the non-inferior solution with the largest total objective function value is the optimal non-inferior solution corresponding to the total objective function. The optimal non-inferior solution is the multi-water source scheduling plan for the first region.

[0186] The optimal non-inferior solution includes both forecasting and dispatching multiple water sources for the first region within the second time range and dispatching multiple water sources for the first region within the first time range.

[0187] The multi-water source forecast dispatch for saltwater tides first needs to accurately predict the time period of the saltwater tide in the first area, that is, the first time range, and then supply water to the first area before the first time range based on the multi-water source dispatching scheme. Carrying out multi-water source forecast dispatching before the saltwater tide occurs in the first area can ensure that the water storage in the reservoir of the first area is sufficient when the saltwater tide invades, so as to avoid water shortage in the city.

[0188] The use of multiple water sources for forecasting and dispatching can effectively reduce the unexpected situations that occur during forecasting and dispatching of a single water source (such as insufficient water available for dispatch from a single water source) and improve the reliability of forecasting and dispatching.

[0189] In the embodiment of the present disclosure, by obtaining a first time range of a first area; obtaining a first water demand of the first area within the first time range; establishing a multi-water source scheduling model, multiple objective functions and multiple constraints of the multi-water source scheduling model are determined based on the first time range and the first water demand; using a multi-objective genetic algorithm to solve the multi-water source scheduling model and then determine the multi-water source scheduling plan, the accuracy and reliability of the generated multi-water source scheduling plan can be improved, and thus the multi-water source forecast scheduling before the arrival of the salt tide and the multi-water source scheduling can be effectively realized before the salt tide arrives, and the multi-water source scheduling can be carried out during the salt tide invasion process.

[0190] The following are device embodiments of the present application. For details not described in detail in the device embodiments, reference may be made to the above method embodiments.

[0191] Figure 8 FIG. 1 shows a schematic diagram of a multi-water source forecasting and scheduling device for saltwater tides provided by an exemplary embodiment of the present disclosure. Figure 8 The multi-water source forecasting and scheduling device 800 for saltwater tides includes: a first acquisition module 801, a second acquisition module 802, a modeling module 803 and a solution module 804.

[0192] The first acquisition module 801 is used to acquire a first time range of a first area, where the first time range is a predicted time range for saltwater intrusion to occur in the first area.

[0193] The second acquisition module 802 is used to acquire a first water demand in a first area within a first time range.

[0194] The modeling module 803 is used to establish a multi-water source scheduling model, and multiple objective functions and multiple constraints of the multi-water source scheduling model are determined based on the first time range and the first water demand.

[0195] The solution module 804 is used to solve the multi-water source scheduling model based on multiple objective functions and multiple constraints using a multi-objective genetic algorithm to determine a multi-water source scheduling plan. The multi-water source scheduling plan includes forecast scheduling of the first area within a second time range. The second time range is used to indicate the time length of the forecast scheduling, and the second time range is before the first time range.

[0196] Optionally, the first acquisition module 801 is also used to obtain first hydrological data of the first area, the first hydrological data including the salinity of water in the river channel where each water intake in the first area is located; the first hydrological data is input into a saltwater tide prediction model to obtain a first time range; wherein the saltwater tide prediction model is a multi-layer long short-term memory network model.

[0197] Optionally, the second acquisition module 802 is also used to obtain historical water supply data of multiple water plants in the first area; based on the historical water supply data of each water plant, construct an autoregressive moving average model of each water plant; based on the autoregressive moving average model of each water plant, determine the water demand of each water plant within the first time range, and then determine the first water demand, which is the sum of the water demands of each water plant within the first time range.

[0198] Optionally, the solution module 804 is also used to use a multi-objective genetic algorithm to solve the multi-water source scheduling model to obtain a non-inferior solution set, which includes multiple non-inferior solutions; perform weighted summation on multiple objective functions to obtain a total objective function; and use the optimal non-inferior solution corresponding to the total objective function as the multi-water source scheduling plan for the first region, and the optimal non-inferior solution corresponding to the total objective function is in the non-inferior solution set.

[0199] It should be noted that: when the multi-water source forecasting and scheduling device for saltwater tide provided in the above embodiment performs multi-water source forecasting and scheduling, only the division of the above-mentioned functional modules is used as an example for illustration. In practical applications, the above-mentioned functional allocation can be completed by different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the multi-water source forecasting and scheduling device for saltwater tide provided in the above embodiment and the multi-water source forecasting and scheduling method embodiment for saltwater tide belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0200] The division of modules in the embodiments of the present disclosure is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional module in each embodiment of the present disclosure may be integrated into a processor, or may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated modules may be implemented in the form of hardware or in the form of software functional modules.

[0201] If the integrated module is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present disclosure is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a terminal device (which can be a personal computer, mobile phone, or communication device, etc.) or a processor (processor) to execute all or part of the steps of the method of each embodiment of the present disclosure. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0202] Fig. 9 Schematic diagram of the structure of the computer device provided by the embodiment of the present disclosure. Fig. 9 As shown, the computer device 900 includes: a processor 901 and a memory 902 .

[0203] The processor 901 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 901 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 901 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 901 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 901 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0204] The memory 902 may include one or more computer-readable storage media, which may be non-transitory. The memory 902 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 902 is used to store at least one instruction, which is used to be executed by the processor 901 to implement the multi-water source forecasting and scheduling method for saltwater tides provided in the embodiments of the present disclosure.

[0205] Those skilled in the art will understand that Fig. 9 The structure shown in the figure does not constitute a limitation on the computer device 900, and the computer device 900 may include more or less components than those shown in the figure, or combine some components, or adopt a different arrangement of components.

[0206] The embodiment of the present disclosure also provides a non-temporary computer-readable storage medium. When the instructions in the storage medium are executed by a processor of a computer device, the computer device is enabled to execute the multi-water source forecasting and scheduling method for saltwater tides provided in the embodiment of the present disclosure.

[0207] The embodiments of the present disclosure also provide a computer program product, including a computer program / instruction, which, when executed by a processor, implements the multi-water source forecasting and scheduling method for saltwater tides provided in the embodiments of the present disclosure.

[0208] The above description is only an optional embodiment of the present disclosure and is not intended to limit the present disclosure. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A multi-water source forecasting and dispatching method for saltwater tide, characterized in that: The method comprises: Acquire a first time range of a first region, where the first time range is a predicted time range for saltwater intrusion to occur in the first region; Obtaining a first water demand of the first area within the first time range; Establishing a multi-water source scheduling model, wherein multiple objective functions and multiple constraints of the multi-water source scheduling model are determined based on the first time range and the first water demand; Based on the multiple objective functions and the multiple constraints, a multi-objective genetic algorithm is used to solve the multi-water source scheduling model to determine a multi-water source scheduling plan. The multi-water source scheduling plan includes forecast scheduling of the first area within a second time range, and the second time range is used to indicate the time length of the forecast scheduling, and the second time range is before the first time range.

2. The method according to claim 1, characterized in that The multiple objective functions of the multi-water source scheduling model include: a water supply guarantee rate objective function, a reservoir water storage capacity objective function, a water supply damage depth objective function, a green economic benefit objective function and a seawater desalination utilization objective function; The water supply guarantee rate objective function is used to indicate that the total water supply guarantee rate of the area to be scheduled within the first time range and the second time range is the largest, and the area to be scheduled includes the first area and other areas that supply water to the first area; The reservoir water storage objective function is used to indicate that the water storage of the reservoir in the to-be-dispatched area is the maximum within the first time range and the second time range; The water supply disruption depth objective function is used to indicate that the total water supply disruption depth of the area to be scheduled within the first time range and the second time range is minimum, and the water supply disruption depth is used to indicate the degree of water shortage in the area to be scheduled; The green economic benefit objective function is used to indicate that the pump station in the to-be-dispatched area consumes the least energy within the first time range and the second time range; The seawater desalination utilization objective function is used to indicate that the seawater desalination utilization of the to-be-scheduled area within the first time range and the second time range is minimum.

3. The method according to claim 2, characterized in that The constraints of the multi-water source scheduling model include: water balance constraint, reservoir water storage constraint, replenishment flow constraint, first water demand constraint, pump station working water level constraint, pump station water intake capacity constraint, pump station operation time constraint, river water quality and reservoir water quality constraint, and seawater desalination water supply capacity constraint; The water balance constraint is used to indicate that the water balance principle must be met during the multi-water source scheduling process; The reservoir water storage constraint is used to indicate that the water storage in the first reservoir must satisfy the first water storage range, the first water storage range is used to indicate the maximum water storage and the minimum water storage of the first reservoir within a first time period, the first reservoir is any reservoir in the area to be dispatched, and the first time period is any time period within the first time range and the second time range; The recharge flow constraint is used to indicate that the recharge flow of the first reservoir in the first time period must be less than or equal to the maximum recharge flow of the first reservoir in the first time period; The first water demand constraint is used to indicate that within the first time range, the sum of the first water storage capacities of the reservoirs in the to-be-dispatched area is greater than or equal to the first water demand, and the first water storage capacities are used to indicate the amount of water in the reservoirs used for water supply; The pump station working water level constraint is used to indicate that when any pump station draws water from the water intake where it is located, the river water level at the water intake must be within the working water level range of the pump station; The pump station water intake capacity constraint is used to indicate that the water intake flow rate of any pump station in the first time period must be less than or equal to the first water intake flow rate and the second water intake flow rate, the first water intake flow rate is the maximum water intake flow rate of the pump station, and the second water intake flow rate is the maximum water intake flow rate of the river where the water intake of the pump station is located in the first time period; The pump station operation time constraint is used to indicate that any pump station must wait for at least a first time period after being turned on before it can be turned off, and any pump station must wait for at least the first time period after being turned off before it can be turned on, and the first time period is the shortest operation time of the pump station; The river water quality and reservoir water quality constraints are used to indicate that the water quality of any river used for water intake and the water quality of the reservoir must meet the water quality requirements, and the water quality requirements include that the chlorine content is less than or equal to the maximum chlorine content; The seawater desalination water supply capacity constraint is used to indicate that the water supply of the seawater desalination plant is less than or equal to the maximum net water capacity of the seawater desalination plant.

4. The method according to any one of claims 1 to 3, characterized in that: The obtaining of the first time range of the first region includes: Acquire first hydrological data of the first region, wherein the first hydrological data includes salinity of water in a river where each water intake of the first region is located; Inputting the first hydrological data into a saltwater tide prediction model to obtain the first time range; Wherein, the saltwater tide prediction model is a multi-layer long short-term memory network model.

5. The method according to any one of claims 1 to 3, characterized in that: The obtaining of the first water demand of the first area within the first time range includes: Obtaining historical water supply data of multiple water plants in the first region; Based on the historical water supply data of each water plant, an autoregressive moving average model is constructed for each water plant; Based on the autoregressive moving average model of each water plant, the water demand of each water plant within the first time range is determined, and then the first water demand is determined, and the first water demand is the sum of the water demands of each water plant within the first time range.

6. The method according to any one of claims 1 to 3, characterized in that: The method of solving the multi-water source scheduling model based on the multiple objective functions and the multiple constraints using a multi-objective genetic algorithm to determine the multi-water source scheduling scheme for the first region includes: A multi-objective genetic algorithm is used to solve the multi-water source scheduling model to obtain a non-inferior solution set, wherein the non-inferior solution set includes multiple non-inferior solutions; Performing weighted summation on the multiple objective functions to obtain an overall objective function; The optimal non-inferior solution corresponding to the total objective function is used as the multi-water source scheduling plan for the first region, and the optimal non-inferior solution corresponding to the total objective function is in the non-inferior solution set.

7. A multi-water source forecasting and dispatching device for saltwater tides, characterized in that: The device comprises: A first acquisition module is used to acquire a first time range of a first region, where the first time range is a predicted time range for saltwater intrusion to occur in the first region; A second acquisition module, used for acquiring a first water demand of the first area within the first time range; A modeling module, used for establishing a multi-water source scheduling model, wherein multiple objective functions and multiple constraints of the multi-water source scheduling model are determined based on the first time range and the first water demand; A solution module is used to solve the multi-water source scheduling model based on the multiple objective functions and the multiple constraints using a multi-objective genetic algorithm to determine a multi-water source scheduling plan, wherein the multi-water source scheduling plan includes forecast scheduling of the first area within a second time range, and the second time range is used to indicate the time length of the forecast scheduling, and the second time range is before the first time range.

8. A computer device, characterized in that: The computer device comprises: a memory and a processor, wherein at least one computer program is stored in the memory, and the at least one computer program is loaded and executed by the processor to implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one computer program, and the at least one computer program is loaded and executed by a processor to implement the method according to any one of claims 1 to 6.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images