Canal system water resource optimal configuration method and system

Abstract

The invention discloses a canal system water resource optimization configuration method and system, and the method comprises the steps: obtaining the audited water demand data of each water consumption unit in a region, and the region comprises one or more water consumption units; obtaining the regional available water supply amount; according to the audited water demand of each water consumption unit and the regional available water supply, determining whether the water resource supply-demand relationship in different time periods meets the supply-demand balance or not; if the supply and demand balance is met, performing water quantity configuration on each water consumption unit based on an on-demand configuration principle; and otherwise, performing water quantity configuration on each water consumption unit according to a pre-established canal system optimization water distribution model. By using the scheme of the invention, precise configuration and management of water resources in spatial and temporal distribution can be realized.

Description

Technical Field

[0001] The present invention relates to the technical field of water resource management, and in particular to a method and system for optimizing canal water resource allocation. Background Art

[0002] Water is an important resource for society. The rapid growth of water demand will put tremendous pressure on regional water systems, and the energy consumption and carbon emissions of water systems are also increasing. Under the constraints of the "dual carbon" goals, how to improve the efficiency of canal water resource utilization, promote the coordinated optimization of water and energy, and reduce carbon emissions while ensuring water security is a practical problem that needs to be solved urgently.

[0003] During the canal water diversion process, water loss, water distribution time, slope anti-seepage measures, etc. will have different degrees of impact on the water resource quality of agricultural irrigation and ecological water use, and the water resource quality determines the field irrigation guarantee rate, irrigation water utilization rate, and unit area yield of the irrigation area. Therefore, it is of practical significance to reasonably construct a canal system optimization water distribution model to ensure efficient scheduling of irrigation areas.

[0004] In recent years, the algorithms for optimizing the allocation of canal water resources have made continuous breakthroughs. The main intelligent algorithms used for optimizing the allocation of water resources include genetic algorithms, particle swarm algorithms, dynamic time warping algorithms, and time series prediction algorithms. The application of intelligent algorithms not only solves the problems of low computational efficiency and poor optimization quality of traditional algorithms, but also provides strong support for solving the multi-objective model of irrigation canals. In particular, to meet the water requirements of crops, the water resource allocation model established by taking the minimum value of parameters such as leakage loss or continuous water diversion differences in the canal water distribution channel as the objective function has become a frontier hotspot in the direction of optimizing water distribution, as it is related to the irrigation guarantee rate and yield benefits of the canal-configured fields, and the results in related fields are becoming increasingly fruitful.

[0005] For areas where water resources are unevenly distributed in geographical space and where supply and demand contradictions are prominent, existing technologies mostly formulate water supply allocation plans based on historical water supply experience, and fail to fully tap into and utilize data from different sources such as forecast information on incoming water, water demand, and geographical spatial information, resulting in inaccurate forecasts of regional water resources supply and demand and low dynamic storage capacity. Summary of the invention

[0006] The present invention provides a method and system for optimizing the allocation of canal water resources to achieve precise allocation and management of water resources in time and space.

[0007] To this end, the present invention provides the following technical solutions: In one aspect, the present invention provides a method for optimizing canal water resources allocation, the method comprising: Obtaining audited water demand data for each water use unit in a region, wherein the region includes one or more water use units; Obtain regional water availability; Determine whether the water supply and demand relationship at different times meets the supply and demand balance based on the reviewed water demand of each water user unit and the water supply in the area; If the supply and demand balance is met, water allocation is performed for each water-using unit based on the principle of allocation on demand; Otherwise, water allocation is performed for each water-using unit according to the pre-established canal optimal water distribution model.

[0008] Optionally, the method further comprises: Acquire data reported by each water-using unit; the data reported by each water-using unit includes: planting structure, planting area, planned water use period and planned water consumption data automatically calculated and generated in combination with irrigation quota; Review the data reported by each water-using unit.

[0009] Optionally, the method further comprises: The water demand prediction model is trained in advance using the historical water consumption data, planting structure, planting area and related influencing factors of each water-using unit; Predicting the water demand of each water-using unit according to the water demand prediction model to obtain a predicted value of the water demand of each water-using unit; The review of the data reported by each water use unit includes: The data reported by each water-using unit is reviewed based on the predicted water demand value of each water-using unit to determine the reviewed water demand data of each water-using unit.

[0010] Optionally, the water demand prediction model is any one of the following: a BP neural network model, an LSTM long short-term memory network model.

[0011] Optionally, the water demand data includes: ecological planned water use data and agricultural irrigation planned water use data; Determining whether the water supply and demand relationship of different time periods meets the supply and demand balance according to the water demand of each water-using unit after review and the water supply of the region includes: The ecological planned water consumption is evenly distributed to the ecological planned water consumption months, and the agricultural irrigation planned water consumption is evenly distributed to the agricultural irrigation planned water consumption months, and the total ecological and agricultural planned water consumption of each channel is calculated each month; According to the topological relationship between the canal systems, the total water demand of each water-using unit is calculated; According to the total water demand of each water-using unit and the available water supply in the area, it is determined whether the water supply and demand relationship in different time periods meets the supply and demand balance based on the comprehensive balance principle.

[0012] Optionally, the method further includes: constructing a canal system optimized water distribution model based on canal system association characteristics with the goal of short water distribution time and low water shortage rate in water-using units within the scheduling period.

[0013] Optionally, the channel system-related characteristics include any one or more of the following: channel system distribution, design flow of upper and lower level channels, and channel system water utilization coefficient.

[0014] Optionally, the constructing of a canal system optimized water distribution model includes: Establish a canal system optimal water distribution model based on rotation irrigation grouping; Taking the minimum total water shortage of each water-using unit as the goal, determine the objective function; Determine constraint conditions, wherein the constraint conditions include any one or more of the following: rotation irrigation cycle constraint, water diversion state constraint, flow capacity constraint of the water distribution channel, flow constraint of the upper channel, and water volume constraint of the water distribution channel; The parameters of the canal system optimal water distribution model are determined according to the constraint conditions and the objective function.

[0015] Optionally, the method further comprises: Plan the water transfer path for each water-using unit to obtain the water transfer path; A water distribution plan is generated according to the water allocation result and the water diversion path.

[0016] Optionally, planning the water diversion path for each water-using unit to obtain the water diversion path includes: using a graph depth-first search algorithm, combining the topological relationship between each sluice station in the canal system to plan the water diversion path for each water-using unit to obtain the water diversion path.

[0017] In another aspect, the present invention further provides a canal water resources optimization allocation system, the system comprising: A data acquisition module, used to acquire the audited water demand data of each water use unit in the area and acquire the water supply of the area, wherein the area includes one or more water use units; The supply and demand balance analysis module is used to determine whether the water supply and demand relationship in different periods meets the supply and demand balance based on the water demand data of each water-using unit after review and the water supply in the area; The water resource allocation module is used to allocate water to each water-using unit based on the principle of on-demand allocation when the supply and demand balance is met; when the supply and demand balance is not met, the water is allocated to each water-using unit according to the pre-established canal optimization water distribution model.

[0018] Optionally, the system further comprises: an audit module; The data acquisition module is also used to acquire data reported by each water use unit, and the data reported by each water use unit includes: planting structure, planting area, planned water use period and planned water use data automatically calculated and generated in combination with irrigation quota; The audit module is used to audit the data reported by each water-using unit and determine the audited water demand data of each water-using unit.

[0019] Optionally, the system further comprises: a prediction module; The prediction module is used to predict the water demand forecast value of each water-using unit according to the water demand prediction model; The audit module is specifically used to audit the data reported by each water use unit according to the water demand forecast value of each water use unit, and determine the water demand data of each water use unit after audit.

[0020] Optionally, the system also includes: a channel system optimized water distribution model construction module, which is used to construct a channel system optimized water distribution model based on channel system correlation characteristics, with the goal of short water distribution time in the scheduling period area and low water shortage rate of water use units.

[0021] Optionally, the system further comprises: The path planning module is used to plan the water diversion path for each water-using unit to obtain the water diversion path; The water distribution plan generation module is used to generate a water distribution plan according to the water volume configuration result and the water transfer path.

[0022] On the other hand, the present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the method for optimizing the allocation of canal water resources are executed.

[0023] The canal water resource optimization allocation method and system provided by the present invention determines whether the water resource supply and demand relationship in different time periods meets the supply and demand balance according to the audited water demand of each water-using unit and the regional water supply; if the supply and demand balance is met, the water volume of each water-using unit is allocated based on the principle of allocation on demand; otherwise, the water volume of each water-using unit is allocated according to the pre-established canal system optimization water distribution model. The scheme of the present invention allocates water to each water-using unit in the region based on the factors of time, space and use, which is helpful for the dynamic adjustment of water supply and demand balance, alleviates the shortage of water resources, and improves the comprehensive utilization efficiency of water resources.

[0024] Furthermore, the planting structure, planting area, planned water use period and planned water consumption data automatically calculated based on the irrigation quota reported by each water use unit are obtained; the data reported by each water use unit is reviewed based on the predicted data of the water demand prediction model to determine the reviewed water demand data of each water use unit, so that the reviewed water demand data is more accurate.

[0025] Furthermore, the graph depth-first search algorithm is used in combination with the topological relationship between the gate stations in the canal system to generate a water resource scheduling path, so that water resource scheduling can be controlled according to the water resource scheduling path in the intelligent configuration and scheduling management of water resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0027] Figure 1 It is a flow chart of a canal water resources optimization configuration method provided by an embodiment of the present invention; Figure 2 is a flow chart for constructing a water demand prediction model in an embodiment of the present invention; Figure 3 is a flow chart for constructing a canal system optimization water distribution model in an embodiment of the present invention; Figure 4 is another flow chart of the canal water resources optimization configuration method provided by an embodiment of the present invention; Figure 5 It is a flow chart of a water diversion path planning algorithm based on graph depth-first search in an embodiment of the present invention; Figure 6 It is a structural schematic diagram of a canal water resources optimization configuration system provided by an embodiment of the present invention; Figure 7 It is another structural schematic diagram of the canal water resources optimization configuration system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0028] The specific implementation of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the present invention, and is not used to limit the present invention.

[0029] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0030] In order to achieve optimal and accurate allocation and management of canal water resources in time and space, an embodiment of the present invention provides a canal water resources optimization allocation method and system, which determines whether the water resource supply and demand relationship in different time periods meets the supply and demand balance based on the audited water demand data of each water user unit and the regional water supply; and allocates water to each water user unit based on the determined water resource supply and demand relationship.

[0031] like Figure 1 FIG. 1 is a flow chart of a method for optimizing canal water resources allocation provided by an embodiment of the present invention, comprising the following steps: In step 101, the audited water demand data of each water use unit in a region is obtained, and the region includes one or more water use units.

[0032] The water use units can be divided into water use units, secondary water use units, main water use equipment (water use systems), etc. according to water use characteristics, rivers, and canal characteristics.

[0033] Specifically, the data reported by each water-using unit (such as planting structure, planting area, planned water use period, etc.) and the planned water consumption data automatically calculated and generated in combination with the irrigation quota can be reviewed, and the reviewed water demand data of each water-using unit can be determined through the review.

[0034] It should be noted that the water demand data includes: ecological planned water use data and agricultural irrigation planned water use data.

[0035] The reviewed ecological water use plan data may include: the name of the channel at this level, the name of the upper-level channel, the designed flow of the upper-level channel, the ecological planned water volume, the start month of the ecological planned water use, the end month of the ecological planned water use, etc.; The audited agricultural irrigation water use plan data may include the channel name at this level, the name of the superior channel, the design flow of the superior channel, the agricultural irrigation plan water volume, the starting month of the agricultural irrigation plan water use, the ending month of the agricultural irrigation plan water use, etc.

[0036] For example, the planned water consumption data reported by each water use unit include annual and monthly water use plans, including agricultural irrigation water use plans and ecological water use plans; water users under each water use unit fill in and calculate water demand by themselves, and the water use units collect and review the data according to the regional management departments at the village (community)-town (street)-district and county levels, and then integrate and compile water use plans for centralized reporting.

[0037] In some embodiments, the planned water demand data may be manually reviewed based on the historical water use records of each water use unit to determine the reviewed water demand data.

[0038] In some embodiments, the water demand prediction model can be trained in advance using the historical water use data of each water use unit, such as planting structure, planting area, historical water use period, historical water use amount, etc.; the water demand prediction value of each water use unit is predicted according to the water demand prediction model; the planned water consumption data is reviewed according to the water demand prediction value of each water use unit to determine the water demand data of each water use unit after review. Compared with the water demand data manually estimated or calculated based on the irrigation quota in the traditional quota method, the prediction based on the water demand prediction model can consider the water demand influencing factors from more dimensions of time and space, weaken the deviation caused by human subjective factors, and more accurately and reasonably determine the water demand data of each water use unit.

[0039] For example, water demand at different time and space scales, such as annual, monthly, agricultural irrigation, and ecological environment, is predicted in the region. Scientific calculations are performed based on historical water use data in the region, taking into account factors such as meteorology, crop type, growth cycle, regional area, and soil moisture content. Then, relevant responsible persons in local water administration departments preview, review, edit, and correct the water use plan of each water use unit based on the predicted water demand within the system. Finally, the verified water use plan information is pushed to relevant objects such as local water administration departments, emergency management departments, and important control water project management units.

[0040] In some embodiments, corresponding water demand prediction models may be trained for the planned ecological water consumption and the planned agricultural irrigation water consumption, respectively, using the same training method.

[0041] The water demand prediction model may adopt but is not limited to any one of the following: BP neural network model, LSTM long short-term memory network model.

[0042] Taking the BP neural network model as an example, the construction process of the water demand prediction model corresponding to the planned water consumption of agricultural irrigation is explained in detail below.

[0043] Reference Figure 2 , Figure 2 A flow chart of constructing a water demand prediction model in an embodiment of the present invention is shown, including the following steps: Step 201, obtaining sample data.

[0044] The sample data include: regional metering statistics of historical agricultural irrigation water volume at annual and monthly scales; and may also include: regional planting structure, planting area, historical water use periods, historical water use volume and other data.

[0045] Step 202: normalize the sample data.

[0046] Since the BP neural network is trained using normalized data, the trained network is also oriented towards normalized data. Therefore, when using the BP neural network, it is necessary to perform corresponding normalization and denormalization processing on the model input and output.

[0047] Among them, the agricultural irrigation water sample data at each time scale are normalized, and the normalization formula is as follows: (1) In the formula, is the original data, is the minimum value among them, is the maximum value among them, is the normalized data.

[0048] The denormalization of the output is the inverse operation of normalization. Therefore, the denormalization function of the output is as follows: (2) In the formula, is the denormalized data, is the minimum value among them, is the maximum value among them, is the normalized data.

[0049] Then, the data is randomly divided into three parts: training data, validation data, and test data in a ratio of 14:3:3. The training data set is used to train the BP neural network model, the validation data set is used to adjust the model parameters and evaluate the model performance during the training process, and the test data set is used to finally evaluate the generalization ability of the model.

[0050] Step 203: construct a water demand prediction model based on the BP neural network model according to the normalized sample data.

[0051] In order to improve the water demand prediction accuracy of regional agricultural irrigation water and ecological environment water, the traditional BP neural network model has the problem of local non-convergence. Here, the wavelet function can be introduced to improve the traditional BP neural network model.

[0052] First, the displacement variables are transformed by combining the wavelet function to obtain the wavelet transformation equation, as shown in the formula: (3) In the formula, and is the wavelet transformed dual variable, unit ; is the calculation period, unit ; Solve for displacement conversion, unit ; is the displacement variable, unit ; Evaluate functions for variables; is the function for transforming variables.

[0053] Then, the wavelet transformation equation is subjected to wavelet analysis, as shown in the following formula: (4) In the formula, Solve for a function of a variable for the transformation.

[0054] The improved BP neural network model performs correlation analysis on each water-using unit, performs set solution on the input and output sample data of the model, determines the number of each associated water-using unit, and determines the input and output water-using units of the improved model based on the number of each associated water-using unit. The improved BP neural network model solves the equation as follows: (5) In the formula, To improve the output variables of the BP neural network model under the control of the number of nodes, the unit ; To control the number of node units; To control the number of nodes; is the control node number; For the Control unit No. Control node weights; For the The displacement variable of the control node, unit ; is the wavelet transform function.

[0055] After determining the associated weights of each control node in the improved BP neural network model, the model output variables are calculated, as shown in the following formula: (6) In the formula, is the output variable; Associate values ​​for each control node; Enter the number of layers for the model; is the total number of control node units.

[0056] The improved BP neural network model uses the gradient method to calculate the error between the measured and output variables, and solves the model with the minimum error as the objective function, as shown in the formula: (7) In the formula, To calculate the relative error, the unit is ; Output variables for training sample units; is the measured sample data series value; is the total number of samples in the training set; is the number of training times.

[0057] The efficiency coefficient method is used to modify and calculate the variables of the improved BP neural network model, as shown in the following formula: (8) (9) (10) In the formula, , , Modify variables for the model; , , Before correction The control unit is The regressor variables of the layer; Correct the gradient for the variable.

[0058] Step 204: performing parameter training on the water demand prediction model.

[0059] Based on the determination of the model training samples, the improved BP neural network model is trained with parameters. The water demand prediction model can adopt a commonly used three-layer BP neural network structure, where the first layer is the input layer; the second layer is the hidden layer, and the transfer function of the hidden layer is set to the tansig function; the last layer is the output layer, and the activation function of the output layer is set to the purelin function.

[0060] Considering the limited training sample data, the number of training epochs can be set to 200, the learning rate lr can be set to 0.001, and the training error target can be set to 0.00001. The trainlm (Levenberg-Marqueardt) algorithm is used to train the improved BP neural network with the training data. After multiple rounds of iterations, the model is in a stable state.

[0061] In an embodiment of the present invention, actual data such as the planting structure, planting area, and planned water use period of an input region can be used to predict water demand prediction results in different time and space dimensions using a trained water demand prediction model based on an improved BP neural network.

[0062] According to the water demand forecast results, the planned water demand reported by the water user unit is reviewed. For example, if the difference between the planned water demand reported by the water user unit and the water demand forecast result determined based on the water demand forecast model is no more than 10%, the planned water demand is reviewed and approved; if the difference between the planned water demand reported by the water user unit and the forecast water demand is greater than 10%, the planned water demand is reviewed and revised, such as reducing the planned demand by a certain proportion.

[0063] Continue to refer to Figure 1 , in step 102, the available water volume in the area is obtained.

[0064] The regional water supply can be determined based on the upstream water supply. For example, the water supply of a certain water body, a certain area or a certain hydrological station in the upstream within a certain period of time in the future (short-term: a few hours to 3 days; medium-term: 3-15 days; long-term: more than 15 days) can be determined based on the previous or current hydrological and meteorological element data, combined with the water diversion plan and water resources allocation plan.

[0065] In step 103, based on the audited water demand data of each water user unit and the water supply in the area, determine whether the water supply and demand relationship in different time periods meets the supply and demand balance; if so, execute step 104; otherwise, execute step 105.

[0066] Specifically, the relationship between water supply and demand in different periods can be determined in the following ways: First, the ecological planned water consumption is evenly distributed to the ecological planned water use months, and the agricultural irrigation planned water consumption is evenly distributed to the agricultural irrigation planned water use months, and the total ecological and agricultural planned water consumption of each channel is calculated each month.

[0067] Then, according to the topological relationship between the canal systems, the total water demand of each water-using unit is finally calculated.

[0068] Then, according to the water demand and water supply of each water-using unit, the water supply and demand relationship analysis in different periods is carried out based on the comprehensive balance principle to determine whether the supply and demand balance is met.

[0069] In step 104, water volume is allocated to each water-using unit based on the principle of allocation on demand.

[0070] That is to say, when the water supply is sufficient, water can be allocated to each water-using unit based on the principle of on-demand configuration, thereby meeting the water needs of each water-using unit without causing waste of water resources.

[0071] In the case of sufficient water supply, continuous irrigation is usually adopted, and the water supply is equal to the water demand. Continuous irrigation means that the upper channel continuously irrigates different irrigation units in the lower channel at the same time, that is, the entire controlled area in the area is supplied with water at the same time, that is, the entire irrigation area is irrigated at the same time.

[0072] In step 105, water allocation is performed for each water-using unit according to the pre-established canal system optimization water distribution model.

[0073] That is to say, when water supply is insufficient, the canal optimization water distribution model is used to balance the water consumption of each water-using unit, maximize the utilization of limited water resources, and provide the best solution for each water-using unit.

[0074] In some embodiments, a canal system optimization water distribution model with multiple factors coordinated can be constructed based on the canal system association characteristics, with the goal of short water distribution time and low water shortage rate of water use units in the scheduling period, to achieve dynamic configuration of water volume for each water use unit in the region. The canal system association characteristics may include but are not limited to any one or more of the following: canal system distribution, design flow of upper and lower channels, canal system water utilization coefficient, etc. The canal system water utilization coefficient refers to the ratio of the net flow and gross flow of the irrigation canal system. According to previous survey results, the canal system water utilization coefficient of unlined channels in gravity irrigation areas with less than 300,000 mu is generally around 0.55, while the value of lined channels is greater than 0.55; for gravity irrigation areas with more than 300,000 mu, the canal system water utilization coefficient is generally above 0.65. The canal system water utilization coefficient of water-lifting irrigation areas is generally between 0.68 and 0.88.

[0075] The canal system optimization water allocation model is mainly based on the water resources scheduling needs of the basin's agricultural irrigation and ecological environment protection in the future, combined with the basic situation of the region and the total water use control target, water use quota and actual water use in recent years, and then determines the water use permit and water allocation results. Its general framework is to determine the objective function and constraints based on the analysis of water resources development and utilization, and then select the appropriate method to solve and find the best solution to balance these goals.

[0076] like Figure 3 FIG. 1 is a flow chart of constructing a canal system optimization water distribution model in an embodiment of the present invention, including the following steps: Step 301, based on the water intake from the upper channel, the channels to be distributed adopt the form of rotation irrigation to establish a channel system optimization water distribution model.

[0077] Irrigation canal systems are generally composed of four levels of canals: trunk, branch, bucket, and farm. In the case of insufficient water supply, the crop type, geographical location and other factors of each water-using unit can be considered, and water can be taken from the upper channel. The water resources are allocated in the form of rotation irrigation for the water-distributed channels. Rotational irrigation refers to the upper channel irrigating different irrigation units in the lower channel in turn. The advantages of rotational irrigation are concentrated channel flow, short working channel length, short water delivery time, and less water delivery loss, which is conducive to combining with agricultural measures and improving irrigation efficiency.

[0078] To this end, in an embodiment of the present invention, a canal system optimization water distribution model as shown below can be established: (11) In the formula, It is the flow of the upper channel; For the The water distribution flow of the water distribution channels; The number of rotation irrigation groups.

[0079] Step 302, determining the objective function with the goal of minimizing the total amount of water shortage in each water-using unit.

[0080] The objective function is as follows: (12) In the formula, The total amount of water shortage in each period of the water-using unit; is the total water demand of the channel being distributed; For the The water distribution flow of the water distribution channels; For the Water distribution time of the distributed channels.

[0081] Step 303, determining constraints.

[0082] The constraint conditions may include but are not limited to any one or more of the following: rotation irrigation cycle constraint, water diversion state constraint, flow capacity constraint of the water distribution channel, flow constraint of the upper channel, and water volume constraint of the water distribution channel. ① Irrigation cycle constraint: the water distribution time should be less than or equal to the irrigation cycle, as shown in the following formula: (13) In the formula, For the The water distribution time of the water distribution channels, It is the rotation irrigation cycle.

[0083] ② Water diversion state constraints: that is, the water diversion decision variables of each water distribution channel of each irrigation group. For the The first The decision variables for diverting water from the water distribution channels are: Indicates The first The water distribution channels are in the water diversion state; Indicates The first The water distribution channels are in a non-water-diverting state.

[0084] ③ Flow capacity constraint of the distributed channel: The distribution flow of the distributed channel should be less than or equal to the design flow of the channel at this level.

[0085] In view of the problem that when the flow is switched in the open channel water diversion project, improper regulation may cause the water level in front of the gate to exceed the upper and lower limits of the water level. It is necessary to sense the water conditions of each section and diversion outlet of the open channel water diversion project, and control the gate opening and safe water level when the flow is switched. Therefore, the water distribution flow of the water distribution channel should be less than or equal to the design flow of the channel at this level, as shown in the following formula: (14) In the formula, For the The water distribution flow of the water distribution channels; For the Design flow of the water distribution channel.

[0086] ④ Flow constraint of the upper channel: that is, the flow of the upper channel at any time is greater than or equal to the sum of the water distribution flow of the lower channel being diverted, as shown in the following formula: (15) In the formula, It is the flow of the upper channel; For the The water distribution flow of the distributed channel that is currently diverting water.

[0087] ⑤ Constraints on the water volume of the distributed channel: The product of the water distribution flow rate and the water distribution duration of the distributed channel is equal to the water distribution volume of the channel at this level, as shown in the following formula: (16) In the formula, For the Water distribution volume of the water distribution channels; For the The water distribution flow of the water distribution channels; For the Water distribution time of the distributed channels.

[0088] Step 304: Determine the parameters of the canal system optimal water distribution model according to the constraint conditions and the objective function.

[0089] For the problem that there are multiple conflicting objectives in the model that need to be optimized simultaneously, the non-dominated sorting genetic algorithm III (NSGA-III) can be used to solve it. By introducing the concept of hypercube partitioning, the target space can be better explored to generate higher quality non-dominated solutions.

[0090] By using the above canal system optimization water distribution model, it is possible to obtain the best water distribution plan for each water user in the case of insufficient water supply, so as to better meet the needs of the water users.

[0091] like Figure 4 FIG. 1 is another flow chart of a method for optimizing canal water resources allocation according to an embodiment of the present invention, comprising the following steps: In step 401, the audited water demand data of each water-using unit is obtained.

[0092] In step 402, the available water volume of a region is obtained, where the region includes one or more water-using units.

[0093] In step 403, the relationship between water supply and demand in different time periods is determined based on the audited water demand data of each water user unit and the water supply in the area.

[0094] In step 404, water allocation is performed on each water-using unit according to the determined water resource supply and demand relationship to obtain a water allocation result.

[0095] In step 405, water transfer paths are planned for each water-using unit to obtain a water transfer path.

[0096] For example, we can use the graph depth-first search algorithm and the topological relationship between the gate stations in the canal system to plan the water diversion path for each water-using unit and obtain the water diversion path. It mainly includes: (1) Each path point selected in the depth-first search is assigned a different weight according to the channel length. Then, the adjacency matrix, the objective function, and the set gate opening and closing conditions are used to determine whether it is passable from the previous path point to the next path point. After confirming that it is passable, the path nodes are saved in order. In order to ensure that the obtained paths are different, the adjacency matrix is ​​updated in real time in each loop iteration through the cost function. Finally, each selected path is stored in the form of a spanning tree subtree to form all paths that meet the constraints.

[0097] (2) Based on all the paths that meet the constraints, you can arbitrarily specify how many paths to combine, and finally keep the combination with the largest weight, that is, the highest search probability, according to the required number of combinations set by the user. The remaining path combination is the optimal path combination that meets the conditions.

[0098] In step 406, a water distribution plan is generated according to the water allocation result and the water transfer path.

[0099] like Figure 5 , which is a flow chart of a water diversion path planning algorithm based on depth-first search in an embodiment of the present invention, comprising the following steps: Step 501, initializing parameters.

[0100] First, determine the starting node and target node of water resource scheduling; then, create an empty set to store the visited nodes.

[0101] Step 502: Generate an adjacency matrix.

[0102] Step 503: depth-first search process.

[0103] Start the search at the start node and mark the start node as the current node.

[0104] Check whether the current node is the target node. If so, execute step 504. If the current node is not the target node, mark the current node as visited and add it to the visited node set.

[0105] During the search process, a data structure (such as a stack or a linked list) is used to record the path. Whenever a new node is visited, the node is added to the path record; when backtracking, the node is removed from the path record.

[0106] Traverse all adjacent nodes of the current node: For each adjacent node, if it has not been visited, set the current node as its parent node (for subsequent path backtracking), and then recursively continue the depth-first search with the adjacent node as the new current node.

[0107] When the depth-first search cannot proceed (that is, all reachable nodes have been visited or there are no unvisited adjacent nodes), backtracking is performed. When backtracking, according to the records of the parent node, it gradually returns to the previous level node until a new unvisited branch is found to continue the search, or returns to the starting node to end the search.

[0108] Step 504, result analysis.

[0109] After the search is completed, it is determined whether the nodes on the path meet the healthy status for the gate station to be opened and closed; if so, step 505 is executed; otherwise, the nodes with abnormal status are discarded and step 503 is continued.

[0110] Step 505: path generation.

[0111] The final water resource scheduling path that meets the instruction conditions is output, and may include path nodes, path length, water distribution channel flow, water distribution time and other related information.

[0112] In some implementations, remote sensing and geographic information technology can be further combined to simulate the water diversion path and water distribution process generated by the graph depth-first search algorithm, and generate water resource allocation and scheduling plans at different time scales such as years and months. This will help decision makers to more intuitively and accurately grasp the distribution, changes and scheduling of water resources, thereby better optimizing the water resource management system.

[0113] Furthermore, the water distribution plan can be designed according to the idea of ​​"annual allocation - dynamic adjustment - drought emergency response". For example, the water distribution plan can be divided into conventional water resource allocation and scheduling plan and emergency allocation and scheduling plan.

[0114] Accordingly, the embodiment of the present invention also provides a canal water resources optimization configuration system, such as Figure 6 The figure shows a structural diagram of the system.

[0115] The canal water resources optimization allocation system 600 of this embodiment includes the following modules: The data acquisition module 601 is used to acquire the audited water demand data of each water use unit in the region and acquire the water supply of the region, wherein the region includes one or more water use units; The supply and demand balance module 602 is used to determine whether the water supply and demand relationship in different time periods meets the supply and demand balance according to the water demand data of each water use unit after review and the water supply of the area; The water resource allocation module 603 is used to allocate water to each water-using unit based on the principle of on-demand allocation when the supply and demand balance is met; when the supply and demand balance is not met, the water is allocated to each water-using unit according to the pre-established canal optimization water distribution model.

[0116] In some embodiments, the canal water resource optimization configuration system 600 may further include: an audit module (not shown). Accordingly, in this embodiment, the data acquisition module 601 is also used to obtain the data reported by each water use unit, and the data reported by each water use unit includes: planting structure, planting area, planned water use period, and planned water consumption data automatically calculated and generated in combination with irrigation quota; the audit module audits the data reported by each water use unit in combination with the water demand prediction model, and determines the water demand data of each water use unit after audit.

[0117] In some embodiments, the canal water resources optimization allocation system 600 may further include: a prediction module (not shown in the figure), which is used to predict the water demand forecast value of each water use unit according to the water demand prediction model; accordingly, the review module can review the planned water consumption data according to the water demand forecast value of each water use unit to determine the water demand data of each water use unit after review.

[0118] The canal system optimization water distribution model can be constructed by the corresponding canal system optimization water distribution model construction module according to the canal system association characteristics, with the goal of short water distribution time in the scheduling period area and low water shortage rate of water use units. The specific construction method can refer to the description in the previous embodiment of the method of the present invention, which will not be repeated here.

[0119] It should be noted that the canal water resource optimization allocation model construction module can be a part of the canal water resource optimization allocation system 600 of the present invention, or it can be independent of the canal water resource optimization allocation system 600, which is not limited in this embodiment of the present invention.

[0120] like Figure 7 , which is another structural schematic diagram of the canal water resources optimization configuration system provided by an embodiment of the present invention.

[0121] and Figure 6The difference between the embodiment shown is that, in this embodiment, the canal water resources optimization allocation system 600 further includes: a path planning module 604 and a water distribution plan generation module 605. Among them: The path planning module 604 is used to plan the water transfer path for each water use unit to obtain the water transfer path; The water distribution plan generation module 605 is used to generate a water distribution plan according to the water volume configuration result and the water transfer path.

[0122] The specific implementation of each of the above modules can be found in the description of the above method embodiments of the present invention, which will not be repeated here.

[0123] The canal water resources optimization allocation method and system provided by the present invention allocates water to each water-using unit in the region by comprehensively considering factors such as time, space and purpose, which helps to dynamically adjust the balance between water supply and demand, alleviate water resource shortages, and improve the comprehensive utilization efficiency of water resources.

[0124] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0125] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0126] In several embodiments provided by the present invention, it should be understood that the disclosed device can be implemented in other ways.

[0127] The present invention also provides a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and the computer program can be executed when it is run. Figure 1 , Figure 2 , Figure 3 , Figure 4 and Figure 5 The storage medium may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc. The storage medium may also include a non-volatile memory (non-volatile) or a non-transitory memory, etc.

[0128] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website site, a computer, a server or a data provider to another website site, a computer, a server or a data provider by wired or wireless means.

[0129] The embodiments of the present invention are described in detail above. The present invention is described in detail using specific implementation methods herein. The description of the above embodiments is only used to help understand the method and system of the present invention. It is only a part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should belong to the scope of protection of the present invention, and the content of this specification should not be understood as limiting the present invention. Therefore, any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for optimizing canal water resources allocation, characterized in that: The method comprises: Obtaining audited water demand data for each water use unit in a region, wherein the region includes one or more water use units; Obtain regional water availability; Determine whether the water supply and demand relationship at different times meets the supply and demand balance based on the reviewed water demand of each water user unit and the water supply in the area; If the supply and demand balance is met, water allocation is performed for each water-using unit based on the principle of allocation on demand; Otherwise, water allocation is performed for each water-using unit according to the pre-established canal system optimal water allocation model; The water demand prediction model is trained in advance using the historical water consumption data, planting structure, planting area and related influencing factors of each water-using unit; Predicting the water demand of each water-using unit according to the water demand prediction model to obtain a predicted value of the water demand of each water-using unit; The review of the data reported by each water use unit includes: Review the data reported by each water user unit according to the predicted water demand value of each water user unit, and determine the reviewed water demand data of each water user unit; According to the canal system correlation characteristics, a canal system optimization water distribution model is constructed with the goal of short water distribution time in the dispatching period and low water shortage rate in water-using units. The channel system-related characteristics include any one or more of the following: channel system distribution, design flow of upper and lower level channels, and channel system water utilization coefficient.

2. The method for optimizing canal water resources allocation according to claim 1, characterized in that: The method further comprises: Acquire data reported by each water-using unit; the data reported by each water-using unit includes: planting structure, planting area, planned water use period and planned water consumption data automatically calculated and generated in combination with irrigation quota; Review the data reported by each water-using unit.

3. The method for optimizing canal water resources allocation according to claim 1, characterized in that: The water demand prediction model is any one of the following: BP neural network model, LSTM long short-term memory network model.

4. The method for optimizing canal water resources allocation according to claim 1, characterized in that: The water demand data include: ecological planned water use data and agricultural irrigation planned water use data; Determining whether the water supply and demand relationship of different time periods meets the supply and demand balance according to the water demand of each water-using unit after review and the water supply of the region includes: The ecological planned water consumption is evenly distributed to the ecological planned water consumption months, and the agricultural irrigation planned water consumption is evenly distributed to the agricultural irrigation planned water consumption months, and the total ecological and agricultural planned water consumption of each channel is calculated each month; According to the topological relationship between the canal systems, the total water demand of each water-using unit is calculated; According to the total water demand of each water-using unit and the available water supply in the area, it is determined whether the water supply and demand relationship in different time periods meets the supply and demand balance based on the comprehensive balance principle.

5. The method for optimizing canal water resources allocation according to claim 1, characterized in that: The construction of the canal system optimization water distribution model includes: Establish a canal system optimal water distribution model based on rotation irrigation grouping; Taking the minimum total water shortage of each water-using unit as the goal, determine the objective function; Determine constraint conditions, wherein the constraint conditions include any one or more of the following: rotation irrigation cycle constraint, water diversion state constraint, flow capacity constraint of the water distribution channel, flow constraint of the upper channel, and water volume constraint of the water distribution channel; The parameters of the canal system optimal water distribution model are determined according to the constraint conditions and the objective function.

6. The method for optimizing canal water resources allocation according to any one of claims 1 to 5, characterized in that: The method further comprises: Plan the water transfer path for each water-using unit to obtain the water transfer path; A water distribution plan is generated according to the water allocation result and the water diversion path.

7. The method for optimizing canal water resources allocation according to claim 6, characterized in that: The water transfer path planning for each water-using unit to obtain the water transfer path includes: The graph depth-first search algorithm is used to plan the water diversion path for each water-using unit in combination with the topological relationship between the sluice stations in the canal system to obtain the water diversion path.

8. A canal water resources optimization allocation system, characterized in that: The system comprises: A data acquisition module, used to acquire the audited water demand data of each water use unit in the area and acquire the water supply of the area, wherein the area includes one or more water use units; The supply and demand balance analysis module is used to determine whether the water supply and demand relationship in different periods meets the supply and demand balance based on the water demand data of each water-using unit after review and the water supply in the area; The water resource allocation module is used to allocate water to each water-using unit based on the principle of on-demand allocation when the supply and demand balance is met; when the supply and demand balance is not met, the water is allocated to each water-using unit according to the pre-established canal optimization water distribution model.

9. The canal water resources optimization allocation system according to claim 8, characterized in that: The system further comprises: an audit module; The data acquisition module is also used to acquire data reported by each water use unit, and the data reported by each water use unit includes: planting structure, planting area, planned water use period and planned water use data automatically calculated and generated in combination with irrigation quota; The audit module is used to audit the data reported by each water-using unit and determine the audited water demand data of each water-using unit.

10. The canal water resources optimization allocation system according to claim 9, characterized in that: The system further comprises: a prediction module; The prediction module is used to predict the water demand forecast value of each water-using unit according to the water demand prediction model; The audit module is specifically used to audit the data reported by each water use unit according to the water demand forecast value of each water use unit, and determine the water demand data of each water use unit after audit.

11. The canal water resources optimization allocation system according to claim 8, characterized in that: The system further comprises: The module for constructing a canal system optimized water distribution model is used to construct a canal system optimized water distribution model based on the canal system correlation characteristics, with the goal of short water distribution time and low water shortage rate in water-using units in the scheduling period.

12. The canal water resources optimization allocation system according to any one of claims 8 to 11, characterized in that: The system further comprises: The path planning module is used to plan the water diversion path for each water-using unit to obtain the water diversion path; The water distribution plan generation module is used to generate a water distribution plan according to the water volume configuration result and the water diversion path.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for optimizing canal water resources allocation according to any one of claims 1 to 7 are executed.

Images