Digital water affair control system and method for urban and rural water supply

Abstract

The invention relates to a digital water affair control system and method for urban and rural water supply, and relates to the related field of water affair management. The fuzzy coefficient calculation module predicts urban and rural population flow according to the time information and calculates a flow fuzzy coefficient; the water volume prediction module predicts the water volume of the country and the irrigation water volume; and the water affair control module comprehensively considers the prediction result and the fuzzy coefficient, optimizes total water supply amount distribution, obtains an optimal control parameter, and carries out water supply water affair control. The technical problems that dynamic changes of urban and rural population cannot be effectively treated by a traditional water affair control method, and water supply distribution is not matched with actual urban and rural demands can be solved; the method has the technical effects of monitoring the water supply condition in real time, comprehensively considering the factors such as the population flow condition, the own water volume and the irrigation water demand of the rural area and the urban area, accurately predicting the water supply amount, distributing and optimizing the water supply amount, ensuring the water supply stability and reliability and improving the water supply management efficiency.

Description

Technical Field

[0001] The present invention relates to the field of water management, and in particular to a digital water control system and method for urban and rural water supply. Background Art

[0002] With the continuous advancement of urbanization and sustained population growth, the demand for urban and rural water supply continues to increase, and the conventional water management model faces many challenges. On the one hand, urban and rural water supply systems are relatively independent and lack unified planning and coordinated management, resulting in inefficient resource utilization; on the other hand, the water supply network is aging and leaking seriously, and the frequent population mobility has brought tremendous pressure to water supply management.

[0003] In recent years, with the continuous maturity and application of technologies such as the Internet of Things and big data, water companies have also begun to actively explore the construction path of smart water services. However, the application of smart water services in the field of urban and rural water supply is still in its early stages, with problems such as insufficient intelligent management and insufficient depth of data mining, which restricts the further development of smart water services in the field of urban and rural water supply. Summary of the invention

[0004] The present invention aims to solve the technical problems that traditional water control methods cannot effectively handle the dynamic changes of urban and rural populations and water supply distribution does not match the actual needs of urban and rural areas, and provides a digital water control system and method for urban and rural water supply to solve the problems.

[0005] The technical solution of the present invention to solve the above technical problems is as follows: In a first aspect, the present invention provides a digital water control system for urban and rural water supply, including: an information acquisition module, used to obtain the total water supply currently supplied to urban and rural areas, and collect current time information; a fuzzy coefficient calculation module, used to predict the population flow in rural and urban areas according to the time information, obtain the predicted rural population and the predicted urban population, and calculate the rural flow fuzzy coefficient and the urban flow fuzzy coefficient; a water volume prediction module, used to predict the self-owned water volume and the irrigation water volume in the rural area according to the time information, and obtain the predicted self-owned water volume and the predicted irrigation water volume; a water control module, used to optimize the distribution of the total water supply according to the rural flow fuzzy coefficient and the urban flow fuzzy coefficient, in combination with the predicted rural population, the predicted urban population, the predicted self-owned water volume and the predicted irrigation water volume, obtain the optimal water control parameters, and perform water supply and water control.

[0006] Optionally, the digital water control system for urban and rural water supply also includes: obtaining the total water supply volume to urban areas and rural areas during the current water supply time period; and obtaining time information of the current water supply time period.

[0007] Optionally, the digital water control system for urban and rural water supply also includes: training a rural floating population prediction path array and an urban floating population prediction path array; inputting the time information into the rural floating population prediction path array and the urban floating population prediction path array respectively, and predicting and outputting a predicted rural floating population array and a predicted urban floating population array; obtaining the urban permanent population and the rural permanent population of the urban area and the rural area; calculating the mean of the predicted rural floating population array and the predicted urban floating population array to obtain the rural floating population and the urban floating population; calculating the predicted rural population and the predicted urban population based on the urban permanent population and the rural permanent population, combined with the rural floating population and the urban floating population; calculating the rural flow fuzzy coefficient and the urban flow fuzzy coefficient based on the predicted rural floating population array and the predicted urban floating population array.

[0008] Optionally, the digital water control system for urban and rural water supply also includes: collecting a sample time information set based on population monitoring data of urban areas and rural areas in historical time, and collecting urban floating population and rural floating population under different sample time information as a sample urban floating population set and a sample rural floating population set; using the sample time information set as input features, and using the sample urban floating population set and the sample rural floating population set as output features, respectively, to divide and obtain multiple urban floating population prediction training data and multiple rural floating population prediction training data; using the multiple urban floating population prediction training data and the multiple rural floating population prediction training data, respectively, based on machine learning, to train the urban floating population prediction path array and the rural floating population prediction path array.

[0009] Optionally, the digital water control system for urban and rural water supply also includes: calculating the maximum error ratio of rural floating population in the predicted rural floating population array as the rural floating population fuzzy coefficient; calculating the maximum error ratio of urban floating population in the predicted urban floating population array as the urban floating population fuzzy coefficient.

[0010] Optionally, the digital water control system for urban and rural water supply also includes: collecting sample time information sets, sample own water sets and sample irrigation water sets based on statistical data on rural area own water and irrigation water in historical time; using the sample time information sets, sample own water sets and sample irrigation water sets to train a rural water prediction path; inputting the time information into the rural water prediction path, and outputting predictions to obtain predicted own water and predicted irrigation water.

[0011] Optionally, the digital water control system for urban and rural water supply also includes: calculating the predicted water consumption of the rural population based on the predicted rural population, and calculating the predicted rural water demand in combination with the predicted self-owned water and the predicted irrigation water; calculating the predicted urban water demand based on the predicted urban population; constructing a water optimization function based on the predicted rural water demand, the predicted urban water demand, the rural flow fuzzy coefficient and the urban flow fuzzy coefficient; randomly allocating the total water supply to urban and rural areas to obtain a first urban water supply and a first rural water supply as first water control parameters, and calculating a first water fitness according to the water optimization function; continuing to randomly allocate the water supply and calculate the water fitness, performing iterative optimization until convergence, outputting the optimal water control parameters with the largest water fitness, and performing water supply control.

[0012] Optionally, the digital water control system for urban and rural water supply further includes: allocating and calculating rural weights and urban weights according to the rural flow fuzzy coefficient and the urban flow fuzzy coefficient; constructing a water optimization function according to the rural weight, the urban weight, the predicted rural water demand, and the predicted urban water demand, as shown in the following formula: ; in, For water service adaptability, is the city weight, For rural weight, Water supply to towns, To predict urban water demand, Water supply to villages, To predict rural water demand.

[0013] In a second aspect, the present invention provides a digital water control method for urban and rural water supply, including: obtaining the total water supply currently provided to urban and rural areas, and collecting current time information; predicting population flows in rural and urban areas based on the time information, obtaining predicted rural population and predicted urban population, and calculating rural flow fuzzy coefficients and urban flow fuzzy coefficients; predicting the amount of own water and irrigation water in the rural area based on the time information, obtaining predicted own water and predicted irrigation water; optimizing the distribution of the total water supply based on the rural flow fuzzy coefficient and the urban flow fuzzy coefficient, combining the predicted rural population, predicted urban population, predicted own water and predicted irrigation water, obtaining optimal water control parameters, and performing water supply control.

[0014] The beneficial effects of the present invention are as follows: an information collection module is used to obtain the total water supply for urban and rural areas, and to collect the current time information; a fuzzy coefficient calculation module is used to predict the population flow in rural and urban areas according to the time information, obtain the predicted rural population and the predicted urban population, and calculate the rural flow fuzzy coefficient and the urban flow fuzzy coefficient; a water volume prediction module is used to predict the self-owned water volume and the irrigation water volume in rural areas according to the time information, and obtain the predicted self-owned water volume and the predicted irrigation water volume; a water affairs control module is used to optimize the distribution of the total water supply according to the rural flow fuzzy coefficient and the urban flow fuzzy coefficient, combined with the predicted rural population, the predicted urban population, the predicted self-owned water volume and the predicted irrigation water volume, obtain the optimal water affairs control parameters, and perform water supply and water affairs control. The water supply situation is monitored in real time, and the factors such as the population flow situation, self-owned water volume and irrigation water demand in rural and urban areas are comprehensively considered to accurately predict and optimize the distribution of the water supply, ensure the stability and reliability of the water supply, and improve the efficiency of water supply management. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A schematic diagram of the structure of a digital water control system for urban and rural water supply provided by the present invention; Figure 2 A schematic flow chart of the digital water control method for urban and rural water supply provided by the present invention.

[0016] In the accompanying drawings, the components represented by the reference numerals are described as follows: Information collection module 10 , fuzzy coefficient calculation module 20 , water volume prediction module 30 , water affairs control module 40 . DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0018] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0019] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0020] Embodiment 1, as Figure 1 As shown, the embodiment of the present invention provides a digital water control system for urban and rural water supply, including: The information collection module 10 is used to obtain the total water supply currently provided to urban areas and rural areas, and to collect current time information.

[0021] Furthermore, the information collection module 10 of the present invention includes: Obtain the total water supply to urban and rural areas during the current water supply period; obtain the time information of the current water supply period.

[0022] Specifically, the current water supply and water affairs time cycle refers to a fixed time period in the operation of the water supply system, such as one day, one week or one month, which is the basic time unit of water supply management and is used to define the time range for data collection and analysis; the total water supply refers to the total amount of water supplied by the water supply system to urban and rural areas during the current water supply and water affairs time cycle, which is measured and counted by means of flow monitoring equipment and other means; time information refers to the specific time data of the current water supply and water affairs time cycle, such as start time and end time, which is collected using a time module or external time source to provide an accurate time reference for subsequent predictions and analysis.

[0023] Obtain the total water supply currently supplied to urban and rural areas, and collect the current time information. Specifically, obtain the total water supply data supplied to urban and rural areas in the current water supply cycle in real time through monitoring equipment such as flow sensors installed at key nodes of the water supply network; determine the current water supply time cycle, for example, one day as a cycle; monitor and accumulate the total water supply supplied to urban and rural areas in this cycle in real time through monitoring equipment such as flow sensors installed at key nodes of the water supply network. The flow sensors can measure the water flow velocity and flow rate, convert the water flow signal into an electrical signal, and upload it to the data acquisition system; the data acquisition system processes and calculates these signals to obtain the total water supply data. At the same time, the built-in time module or connects to the external time server to record time information such as the start and end time of the current water supply time cycle, obtain the total water supply and time information, and provide data support for subsequent analysis.

[0024] The fuzzy coefficient calculation module 20 is used to predict the population flow in rural areas and urban areas according to the time information, obtain the predicted rural population and the predicted urban population, and calculate the rural flow fuzzy coefficient and the urban flow fuzzy coefficient.

[0025] Further, the fuzzy coefficient calculation module 20 of the present invention includes: Training the predicted path array of rural floating population and the predicted path array of urban floating population; inputting the time information into the predicted path array of rural floating population and the predicted path array of urban floating population respectively, and predicting and outputting a predicted rural floating population array and a predicted urban floating population array; obtaining the urban permanent population and the rural permanent population of the urban area and the rural area; calculating the mean of the predicted rural floating population array and the predicted urban floating population array to obtain the rural floating population and the urban floating population; calculating the predicted rural population and the predicted urban population based on the urban permanent population and the rural permanent population, combined with the rural floating population and the urban floating population; calculating the rural flow fuzzy coefficient and the urban flow fuzzy coefficient based on the predicted rural floating population array and the predicted urban floating population array.

[0026] Specifically, population mobility forecasting refers to the process of estimating the changes in population size in rural and urban areas within a certain time period; predicted rural population and predicted urban population refer to the number of people expected to live or move in rural and urban areas within the target time period calculated by the forecasting model; urban permanent population and rural permanent population refer to the number of people who live in urban and rural areas for a long time, obtained through the population census or household registration management system; predicted rural population and predicted urban population refer to the total population expected to exist in rural and urban areas within the target time period by adding the permanent population to the floating population; rural mobility fuzzy coefficient and urban mobility fuzzy coefficient are indicators used to measure the uncertainty of population mobility forecasting, which are calculated by analyzing the data fluctuations and error range in the predicted floating population array, and are used to reflect the reliability of the forecast results.

[0027] According to the time information, population mobility predictions are performed in rural and urban areas to obtain predicted rural population and predicted urban population. Specifically, a rural floating population prediction path array and an urban floating population prediction path array are trained. Based on population monitoring data of urban and rural areas in historical time, a sample time information set, as well as urban floating population and rural floating population under different sample time information, are collected as a sample urban floating population set and a sample rural floating population set; these sample data are used as input and output features, and the urban floating population prediction path array and the rural floating population prediction path array are trained respectively through machine learning algorithms (such as neural networks, support vector machines, etc.), and the trained models can predict the corresponding trend of floating population quantity changes according to the input time information; the currently collected time information is input into the trained rural floating population prediction path array and the urban floating population prediction path array, and a predicted rural floating population array and a predicted urban floating population array are output, and the predicted rural floating population array and the predicted urban floating population array contain the estimated values ​​of the possible floating population quantity in rural and urban areas at different time points or time periods.

[0028] The number of urban permanent residents and rural permanent residents in urban areas and rural areas is obtained by connecting to a population database, a household registration management system or directly importing census data, reflecting a relatively stable population base in the region; the mean of the predicted rural floating population array and the predicted urban floating population array are calculated to obtain average estimated values ​​of the rural floating population and the urban floating population. Preferably, the predicted rural floating population array contains predicted values ​​of floating population at multiple time points, and the arithmetic mean of these values ​​is calculated as the estimated value of the rural floating population in the time period.

[0029] The urban permanent population is added to the urban floating population, and the rural permanent population is added to the rural floating population to obtain the predicted urban population and the predicted rural population. The fixed resident population and the temporary floating population in the region are comprehensively considered to obtain the total population expected to exist in each region within the target time period. According to the data fluctuations in the predicted rural floating population array and the predicted urban floating population array, the rural flow fuzzy coefficient and the urban flow fuzzy coefficient are calculated. Preferably, the degree of deviation of each predicted value from the mean in the array is analyzed to find the largest deviation ratio, which is used as the flow fuzzy coefficient corresponding to the urban area and the rural area. The rural flow fuzzy coefficient and the urban flow fuzzy coefficient reflect the uncertainty of the prediction results and the possible error margin. Generally speaking, when the population flow is abnormal due to holidays or special events, the fuzzy coefficient will be larger, suggesting that greater flexibility and buffer space should be considered in water supply allocation to cope with the difference between the actual population flow and the predicted value, so as to ensure the stability and reliability of water supply.

[0030] Furthermore, the fuzzy coefficient calculation module 20 of the present invention also includes: According to the population monitoring data of urban areas and rural areas in historical time, a sample time information set is collected, and the urban floating population and the rural floating population under different sample time information are collected as a sample urban floating population set and a sample rural floating population set; the sample time information set is used as an input feature, and the sample urban floating population set and the sample rural floating population set are used as output features respectively to perform division to obtain multiple sets of urban floating population prediction training data and multiple sets of rural floating population prediction training data; the multiple sets of urban floating population prediction training data and the multiple sets of rural floating population prediction training data are used respectively to train the urban floating population prediction path array and the rural floating population prediction path array based on machine learning.

[0031] Specifically, population monitoring data refers to a data set about the population size and its changes in urban and rural areas collected through population censuses and traffic flow monitoring, which contains population information at different time points and is the basis for training prediction models; the sample time information set is a set of representative data at specific time points or time periods selected from historical time, which is related to population mobility, such as holidays, working days, seasonal changes, etc.; urban floating population and rural floating population refer to the number of non-fixed and temporary populations in urban and rural areas under these sample time information, reflecting the dynamic changes in the population; the sample urban floating population set and the sample rural floating population set are sets formed by arranging and classifying the corresponding floating population data according to the sample time information, and are used for training machine learning models; partitioning refers to dividing the collected data into multiple independent data sets according to certain rules and proportions. Multiple sets of urban floating population prediction training data and multiple sets of rural floating population prediction training data are used to train and verify the performance of the model.

[0032] Train the predicted path arrays of rural floating population and urban floating population. Specifically, collect a set of sample time information from the population monitoring data of urban and rural areas in historical time. Preferably, determine the time periods with significant population mobility characteristics such as the Spring Festival holiday and summer vacation from the data of the past few years, and the corresponding dates as sample time information. Under these sample time information, collect the corresponding urban floating population and rural floating population data to form a sample urban floating population set and a sample rural floating population set.

[0033] The sample time information set is used as input features, and the sample urban floating population set and the sample rural floating population set are used as output features respectively, and the data is divided into a plurality of urban floating population prediction training data and a plurality of rural floating population prediction training data. Preferably, the data is divided into a training set and a validation set in a chronological order or by random sampling, wherein the training set is used for the preliminary training of the model, and the validation set is used for evaluating and adjusting the performance of the model; these training data are used to train the urban floating population prediction path array and the rural floating population prediction path array based on the machine learning algorithm respectively, and preferably, a neural network algorithm is used to take the sample time information as the input layer, and after the hidden layer processing and weight adjustment, the predicted floating population number is output; during the training process, the weights and parameters of the network are continuously adjusted to minimize the error between the prediction result and the actual sample floating population data; after multiple iterations and optimizations, the complex relationship between time information and the floating population number is gradually learned, and the corresponding urban and rural floating population numbers can be accurately predicted according to the input time information. The dynamic change trend of urban and rural populations is determined to provide support for the optimization of water supply allocation, thereby ensuring that water supply management can adapt to population fluctuations and improve the quality and efficiency of water supply services.

[0034] Furthermore, the fuzzy coefficient calculation module 20 of the present invention also includes: The maximum error ratio of rural floating population in the predicted rural floating population array is calculated as the rural floating population fuzzy coefficient; the maximum error ratio of urban floating population in the predicted urban floating population array is calculated as the urban floating population fuzzy coefficient.

[0035] Specifically, the predicted rural floating population array and the predicted urban floating population array refer to a series of predicted value sets about the number of rural and urban floating populations output according to the input time information through the previously trained data model, and store the expected number of floating populations at different time points or time periods in the form of arrays or lists; the rural floating population error ratio and the urban floating population error ratio, that is, the ratio of the difference a between the maximum and minimum values ​​and the mean b between the maximum and minimum values ​​to the mean b, as the error amplitude of the floating population, is usually expressed as a percentage. The larger the error, the larger the rural floating fuzzy coefficient / urban floating fuzzy coefficient. The rural floating fuzzy coefficient and the urban floating fuzzy coefficient are used to enhance the attention paid to water control in areas with large errors. Among them, the maximum value refers to the maximum value of all error ratios in the prediction array, representing the most serious deviation in the prediction results, and the minimum value refers to the minimum value of all error ratios in the prediction array.

[0036] According to the predicted rural floating population array and the predicted urban floating population array, the rural floating fuzzy coefficient and the urban floating fuzzy coefficient are calculated. Specifically, after completing the prediction of the rural and urban floating populations and obtaining the predicted rural floating population array and the predicted urban floating population array, the corresponding floating fuzzy coefficient is calculated; each predicted value in the prediction array is compared with the actual floating population data, and the error ratio of each predicted value is calculated. For example, the predicted value is 480 people, and the actual value is 450 people, then the error is 30 people, and the error ratio is (30 / 450)×100%; traverse the prediction array to find the maximum error ratio among all error ratios. The ratio of the difference a corresponding to the maximum and minimum values ​​and the mean b between the maximum and minimum values ​​is directly used as the rural flow fuzzy coefficient and the urban flow fuzzy coefficient, which indicates that this uncertainty needs to be considered when optimizing water supply allocation, and a certain buffer space should be reserved for possible errors to ensure the rationality and stability of water supply allocation. Generally speaking, during holidays or special events, there may be abnormal peaks in population mobility, and the prediction model cannot fully and accurately capture this change. At this time, a larger fuzzy coefficient will prompt the system to be more reasonable in allocating water supply and appropriately increase the redundancy of water supply to meet actual needs.

[0037] The water volume prediction module 30 is used to predict the self-owned water volume and irrigation water volume of the rural area according to the time information, and obtain the predicted self-owned water volume and the predicted irrigation water volume.

[0038] Further, the water volume prediction module 30 of the present invention includes: According to the statistical data of the amount of own water and irrigation water in rural areas in historical time, a sample time information set, a sample own water set and a sample irrigation water set are collected; the sample time information set, the sample own water set and the sample irrigation water set are used to train the rural water affairs prediction path; the time information is input into the rural water affairs prediction path, and the prediction output obtains the predicted own water amount and the predicted irrigation water amount.

[0039] Specifically, changes in water volume are closely related to factors such as seasons and precipitation. The time information is used to determine the differences in water volume in different time periods (such as the spring irrigation period); the amount of water in rural areas refers to the total amount of water resources that are naturally formed in rural areas or stored through water conservancy facilities and directly used for life, production, etc., including the amount of water from reservoirs, lakes, groundwater and other water sources; the amount of irrigation water in rural areas refers to the amount of water required for crop irrigation in agricultural production, which is an important part of water use in rural areas; the sample time information set is a set of representative data sets of specific time points or time periods selected from historical time, which is related to changes in water volume. related, such as different seasons, different years, etc.; the sample own water volume set and the sample irrigation water volume set are sets formed by arranging and classifying the corresponding historical own water volume and irrigation water volume data according to the sample time information, which are used for training the prediction model; the rural water affairs prediction path is obtained by training with algorithms such as machine learning, and is a model for predicting the own water volume and irrigation water volume in rural areas, which can output corresponding water volume prediction values ​​according to the input time information; inputting the time information into the rural water affairs prediction path means taking the currently collected time information as the input variable of the model, and obtaining the predicted own water volume and predicted irrigation water volume through the calculation and reasoning of the model.

[0040] According to the time information, the self-owned water volume and irrigation water volume of the rural area are predicted to obtain the predicted self-owned water volume and the predicted irrigation water volume. Specifically, a sample time information set, a sample self-owned water volume set and a sample irrigation water volume set are collected from the statistical data of the self-owned water volume and irrigation water volume in the rural area in the historical time. Preferably, from the data of the past few years, time periods with significant water volume change characteristics such as the spring irrigation period, rainy season, dry season, and the corresponding dates are selected as sample time information, and the self-owned water volume and irrigation water volume data in these time periods are recorded; these sample data are used to train the rural water affairs prediction path, based on machine learning algorithms such as linear regression, decision trees, neural networks, etc., with the sample time information set as input features, and the sample self-owned water volume set and the sample irrigation water volume set as output features, and the data are divided into a training set and a validation set; the training set is used to perform preliminary training on the model, and the parameters and structure of the model are adjusted to minimize the error between the prediction result and the actual sample water volume data; the validation set is used to evaluate the performance of the model, and the model is further optimized to avoid problems such as overfitting or underfitting.

[0041] When predicting water volume, the currently collected time information is input into the trained rural water forecast path. According to the learned rules and patterns, the predicted self-owned water volume and irrigation water volume are output. Before the dry season comes, the water supply is increased in advance according to the forecast results to ensure agricultural production and residents' living water; in the rainy season, the water supply strategy can be reasonably adjusted to make full use of natural precipitation to supplement the self-owned water volume. By understanding the self-owned water volume and irrigation water demand in rural areas in different time periods, water supply management can be carried out more scientifically and reasonably to ensure that the water demand in rural areas is met, while improving the utilization efficiency of water resources and avoiding water waste.

[0042] The water control module 40 is used to optimize the distribution of the total water supply according to the rural flow fuzzy coefficient and the urban flow fuzzy coefficient, combined with the predicted rural population, predicted urban population, predicted own water volume and predicted irrigation water volume, obtain the optimal water control parameters, and perform water supply and water control.

[0043] Furthermore, the water control module 40 of the present invention includes: According to the predicted rural population, the predicted water consumption of the rural population is calculated, and the predicted rural water demand is calculated by combining the predicted self-owned water and the predicted irrigation water; according to the predicted urban population, the predicted urban water demand is calculated; according to the predicted rural water demand, the predicted urban water demand, the rural flow fuzzy coefficient and the urban flow fuzzy coefficient, a water optimization function is constructed; the total water supply is randomly allocated to urban areas and rural areas to obtain a first urban water supply and a first rural water supply as the first water control parameters, and according to the water optimization function, a first water fitness is calculated; the random allocation of water supply is continued, and the water fitness is calculated, and iterative optimization is performed until convergence, and the optimal water control parameters with the largest water fitness are output to perform water supply and water control.

[0044] Specifically, predicting rural population water consumption refers to calculating the total amount of water that is expected to be needed in the rural area within the target time period based on the predicted rural population and a certain per capita water use standard or model; predicting rural water demand refers to considering factors such as rural population water use, self-owned water and irrigation water to obtain the total water demand of the rural area within the time period, reflecting the rural area's dependence on the water supply system and water supply pressure; predicting urban water demand refers to calculating the total amount of water expected to be used in the urban area based on the predicted urban population, combined with the per capita water use quota or water use model of the urban area, which is an important basis for urban water supply allocation; the first urban water supply and the first rural water supply refer to the water supply values ​​initially randomly assigned during the optimization process, and the first urban water supply and the first village water supply volume are used as the starting parameters of the optimization algorithm; the first water control parameter refers to the control parameter setting corresponding to the water supply volume based on the initial allocation, which is the initial state in the optimization process; the water fitness is an indicator calculated based on the water optimization function, which is used to evaluate the pros and cons of the current water supply allocation plan. The higher the fitness value, the more the corresponding water supply plan meets the optimization goal; iterative optimization refers to the process of adjusting the water supply allocation plan multiple times, constantly calculating and comparing the fitness value, and gradually improving the water supply plan until the preset optimization conditions (such as the maximum number of iterations or fitness convergence) are met; the optimal water control parameter refers to the parameter setting that can achieve the best water supply effect after iterative optimization, which will be directly used to guide the actual operation and control of the water supply system.

[0045] According to the rural flow fuzzy coefficient and the urban flow fuzzy coefficient, combined with the predicted rural population, predicted urban population, predicted self-owned water volume and predicted irrigation water volume, the distribution optimization of the total water supply is performed to obtain the optimal water control parameters. Specifically, according to the predicted rural population, the per capita water consumption of the rural population is calculated according to the per capita water consumption quota or water consumption model in the rural area. For example, if the per capita daily water consumption of the rural population is 0.1 cubic meters and the predicted rural population is 1,000 people, then the predicted rural population water consumption is 100 cubic meters / day; combined with the predicted self-owned water volume and the predicted irrigation water volume, the predicted rural water demand is calculated. For example, if the predicted self-owned water volume is 200 Cubic meters, the predicted irrigation water volume is 150 cubic meters, then the predicted rural water demand = predicted rural population water consumption (100) + predicted irrigation water (150) - predicted self-owned water (200) (self-owned water can partially offset the water supply demand) = 50 cubic meters (if the result is negative, it is taken as 0, indicating that the self-owned water is sufficient and no additional water supply is required); for urban areas, according to the predicted urban population, the per capita water quota or water use model of the urban area is used to calculate the predicted urban water demand and construct a water optimization function. The water optimization function comprehensively considers the predicted rural water demand, predicted urban water demand, rural flow fuzzy coefficient and urban flow fuzzy coefficient; for the total The water supply is randomly allocated to urban and rural areas. For example, the total water supply is 350 cubic meters per day, and the initial random allocation is 250 cubic meters for urban areas and 100 cubic meters for rural areas, which is used as the first water control parameter. The first water fitness of the allocation scheme is calculated according to the water optimization function. For example, the fitness calculated by substituting it into the water optimization function is 0.8. Multiple random allocations are continued, such as allocation scheme 2: 280 cubic meters for urban areas and 70 cubic meters for rural areas; scheme 3: 220 cubic meters for urban areas and 130 cubic meters for rural areas, etc., and the water fitness of each scheme is calculated respectively. Through iterative optimization algorithms, such as genetic algorithms and simulated annealing, the water fitness of each scheme is continuously increased. The allocation plan is adjusted continuously to gradually improve the water service fitness. Preferably, in the genetic algorithm, a plan with higher fitness is selected for crossover and mutation operations to generate a new allocation plan, and the fitness of the new plan is calculated; this process is repeated until the iteration reaches a preset number of times (such as 100 times) or the fitness converges (that is, the change in the fitness value is less than a certain threshold, such as 0.01), and the optimal water service control parameters with the largest water service fitness are output. The optimal water service control parameters will guide the actual operation of the water supply system, realize precise control and optimized management of water supply, and ensure that while meeting urban and rural water demand, the uncertainty of population mobility and the efficient use of water resources are taken into account.

[0046] Furthermore, the water control module 40 of the present invention further includes: According to the rural flow fuzzy coefficient and the urban flow fuzzy coefficient, the rural weight and the urban weight are obtained by allocation calculation; according to the rural weight, the urban weight, the predicted rural water demand, and the predicted urban water demand, a water affairs optimization function is constructed as follows: ; in, For water service adaptability, is the city weight, For rural weight, Water supply to towns, To predict urban water demand, Water supply to villages, To predict rural water demand.

[0047] Specifically, the rural flow fuzzy coefficient and the urban flow fuzzy coefficient are indicators to measure the uncertainty of population flow prediction, reflecting the degree of possible deviation between the predicted population and the actual population; the rural weight and urban weight are assigned according to the fuzzy coefficients, and are parameters used to balance the importance of rural and urban water supply allocation in the water affairs optimization function; the water affairs fitness is an indicator calculated according to the water affairs optimization function, which is used to evaluate the pros and cons of the current water supply allocation plan. The higher the fitness value, the more the corresponding water supply plan meets the optimization goal.

[0048] According to the predicted rural water demand, predicted urban water demand, rural flow fuzzy coefficient and urban flow fuzzy coefficient, a water affairs optimization function is constructed. Specifically, is the city weight, For rural weight, Water supply to towns, To predict urban water demand, Water supply to villages, Substituting water service adaptability into the prediction of rural water demand In the water supply optimization function, the water supply demand and uncertainty factors of rural and urban areas are comprehensively considered, and the weight distribution makes the optimization process able to reasonably balance the urban weight. , rural weight . Different water supply allocation schemes are evaluated and optimized according to the water optimization function to find the optimal water control parameters, thereby achieving efficient and reasonable water supply management.

[0049] The digital water control system for urban and rural water supply provided by the embodiment of the present invention has at least the following technical effects: an information collection module is used to obtain the total water supply for urban and rural areas and collect the current time information; a fuzzy coefficient calculation module is used to predict the population flow in rural and urban areas according to the time information, obtain the predicted rural population and the predicted urban population, and calculate the rural flow fuzzy coefficient and the urban flow fuzzy coefficient; a water volume prediction module is used to predict the self-owned water volume and the irrigation water volume in the rural area according to the time information, and obtain the predicted self-owned water volume and the predicted irrigation water volume; a water control module is used to optimize the distribution of the total water supply according to the rural flow fuzzy coefficient and the urban flow fuzzy coefficient, combined with the predicted rural population, the predicted urban population, the predicted self-owned water volume and the predicted irrigation water volume, obtain the optimal water control parameters, and perform water supply and water control. Real-time monitoring of water supply, comprehensive consideration of factors such as population flow, self-owned water volume and irrigation water demand in rural and urban areas, accurate prediction and distribution optimization of water supply, ensuring the stability and reliability of water supply, and improving the efficiency of water supply management.

[0050] Embodiment 2, as Figure 2 As shown, based on the same inventive concept of the digital water control system for urban and rural water supply provided in Example 1, an embodiment of the present invention also provides a digital water control method for urban and rural water supply, including: obtaining the total water supply currently supplied to urban and rural areas, and collecting the current time information; according to the time information, predicting the population flow in rural and urban areas, obtaining the predicted rural population and the predicted urban population, and calculating the rural flow fuzzy coefficient and the urban flow fuzzy coefficient; according to the time information, predicting the amount of own water in the rural area and the amount of irrigation water, obtaining the predicted amount of own water and the predicted amount of irrigation water; according to the rural flow fuzzy coefficient and the urban flow fuzzy coefficient, combining the predicted rural population, the predicted urban population, the predicted amount of own water and the predicted amount of irrigation water, optimizing the distribution of the total water supply, obtaining the optimal water control parameters, and performing water supply control.

[0051] Furthermore, the digital water control method for urban and rural water supply is also used to: obtain the total water supply to urban areas and rural areas during the current water supply time period; and obtain time information of the current water supply time period.

[0052] Furthermore, the digital water control method for urban and rural water supply is also used to: train a rural floating population prediction path array and an urban floating population prediction path array; input the time information into the rural floating population prediction path array and the urban floating population prediction path array respectively, and predict and output a predicted rural floating population array and a predicted urban floating population array; obtain the urban permanent population and the rural permanent population of the urban area and the rural area; calculate the mean of the predicted rural floating population array and the predicted urban floating population array to obtain the rural floating population and the urban floating population; calculate and obtain a predicted rural population and a predicted urban population based on the urban permanent population and the rural permanent population, combined with the rural floating population and the urban floating population; calculate and obtain a rural flow fuzzy coefficient and an urban flow fuzzy coefficient based on the predicted rural floating population array and the predicted urban floating population array.

[0053] Furthermore, the digital water control method for urban and rural water supply is also used to: collect a sample time information set based on population monitoring data of urban areas and rural areas in historical time, and collect urban migrant population and rural migrant population under different sample time information as a sample urban migrant population set and a sample rural migrant population set; use the sample time information set as input features, and use the sample urban migrant population set and the sample rural migrant population set as output features respectively, divide them, and obtain multiple urban migrant population prediction training data and multiple rural migrant population prediction training data; use the multiple urban migrant population prediction training data and the multiple rural migrant population prediction training data respectively, based on machine learning, to train the urban migrant population prediction path array and the rural migrant population prediction path array.

[0054] Furthermore, the digital water control method for urban and rural water supply is also used to: calculate the maximum error ratio of rural floating population in the predicted rural floating population array as the rural floating population fuzzy coefficient; calculate the maximum error ratio of urban floating population in the predicted urban floating population array as the urban floating population fuzzy coefficient.

[0055] Furthermore, the digital water control method for urban and rural water supply is also used to: collect sample time information sets, sample own water sets and sample irrigation water sets based on statistical data on own water and irrigation water in rural areas over historical time; use the sample time information sets, sample own water sets and sample irrigation water sets to train a rural water prediction path; input the time information into the rural water prediction path, and output the prediction to obtain predicted own water and predicted irrigation water.

[0056] Furthermore, the digital water control method for urban and rural water supply is also used to: calculate the predicted water consumption of the rural population based on the predicted rural population, and calculate the predicted rural water demand in combination with the predicted self-owned water and the predicted irrigation water; calculate the predicted urban water demand based on the predicted urban population; construct a water optimization function based on the predicted rural water demand, the predicted urban water demand, the rural flow fuzzy coefficient and the urban flow fuzzy coefficient; randomly distribute the total water supply to urban areas and rural areas, obtain the first urban water supply and the first rural water supply as the first water control parameters, and calculate the first water fitness according to the water optimization function; continue to randomly distribute the water supply, calculate the water fitness, perform iterative optimization until convergence, output the optimal water control parameters with the largest water fitness, and perform water supply water control.

[0057] Furthermore, the digital water control method for urban and rural water supply is also used to: allocate and calculate the rural weight and the urban weight according to the rural flow fuzzy coefficient and the urban flow fuzzy coefficient; and construct a water optimization function according to the rural weight, the urban weight, the predicted rural water demand, and the predicted urban water demand, as shown in the following formula: ; in, For water service adaptability, is the city weight, For rural weight, Water supply to towns, To predict urban water demand, Water supply to villages, To predict rural water demand.

[0058] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0059] Although preferred embodiments of the present invention have been described, additional changes and modifications may occur to these embodiments once those skilled in the art understand the basic inventive concepts.

[0060] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention belong to the scope of the present invention and its equivalent technologies, the present invention is also intended to include these changes and variations.

Claims

1. A digital water control system for urban and rural water supply, characterized in that: The system comprises: An information collection module is used to obtain the total water supply currently provided to urban and rural areas, and to collect current time information; A fuzzy coefficient calculation module is used to predict the population flow in rural areas and urban areas according to the time information, obtain the predicted rural population and the predicted urban population, and calculate the rural flow fuzzy coefficient and the urban flow fuzzy coefficient; A water volume prediction module, used to predict the self-owned water volume and irrigation water volume of the rural area according to the time information, and obtain the predicted self-owned water volume and the predicted irrigation water volume; The water control module is used to optimize the distribution of the total water supply according to the rural flow fuzzy coefficient and the urban flow fuzzy coefficient, combined with the predicted rural population, predicted urban population, predicted self-owned water volume and predicted irrigation water volume, obtain the optimal water control parameters, and perform water supply and water control.

2. The digital water control system for urban and rural water supply according to claim 1 is characterized in that: The total water supply currently provided to urban and rural areas is obtained, and the current time information is collected. The information collection module is used to perform the following method: Obtain the total water supply to urban and rural areas during the current water supply period; Get the time information of the current water supply time period.

3. The digital water control system for urban and rural water supply according to claim 1 is characterized in that: According to the time information, population flow prediction is performed in rural areas and urban areas to obtain predicted rural population and predicted urban population. The fuzzy coefficient calculation module is used to execute the following method: Training rural floating population prediction path array and urban floating population prediction path array; The time information is input into the rural floating population prediction path array and the urban floating population prediction path array respectively, and the prediction output is used to obtain the predicted rural floating population array and the predicted urban floating population array; Obtain the urban permanent population and rural permanent population of the urban area and rural area; Calculating the mean of the predicted rural floating population array and the predicted urban floating population array to obtain the rural floating population and the urban floating population; According to the urban permanent population and rural permanent population, combined with the rural floating population and urban floating population, the predicted rural population and the predicted urban population are calculated; According to the predicted rural floating population array and the predicted urban floating population array, the rural flow fuzzy coefficient and the urban flow fuzzy coefficient are calculated and obtained.

4. The digital water control system for urban and rural water supply according to claim 3 is characterized in that: The rural floating population prediction path array and the urban floating population prediction path array are trained, and the fuzzy coefficient calculation module is also used to execute the following method: Based on the population monitoring data of urban and rural areas in the historical period, a sample time information set is collected, and the urban floating population and rural floating population under different sample time information are collected as a sample urban floating population set and a sample rural floating population set; The sample time information set is used as an input feature, and the sample urban floating population set and the sample rural floating population set are used as output features respectively, and the division is performed to obtain a plurality of urban floating population prediction training data and a plurality of rural floating population prediction training data; The plurality of urban floating population prediction training data and the plurality of rural floating population prediction training data are respectively used to train the urban floating population prediction path array and the rural floating population prediction path array based on machine learning.

5. The digital water control system for urban and rural water supply according to claim 3 is characterized in that: According to the predicted rural floating population array and the predicted urban floating population array, the rural flow fuzzy coefficient and the urban flow fuzzy coefficient are calculated, and the fuzzy coefficient calculation module is also used to execute the following method: Calculating the maximum error ratio of rural floating population in the predicted rural floating population array as the rural floating fuzzy coefficient; The maximum urban floating population error ratio in the predicted urban floating population array is calculated as the urban floating fuzzy coefficient.

6. The digital water control system for urban and rural water supply according to claim 1 is characterized in that: According to the time information, the self-owned water volume and irrigation water volume of the rural area are predicted to obtain the predicted self-owned water volume and the predicted irrigation water volume, and the water volume prediction module is used to execute the following method: According to the statistical data of self-owned water and irrigation water in rural areas in historical time, the sample time information set, sample self-owned water set and sample irrigation water set are collected; The sample time information set, the sample own water volume set and the sample irrigation water volume set are used to train the rural water affairs prediction path; The time information is input into the rural water affairs prediction path, and the prediction output obtains the predicted self-owned water volume and the predicted irrigation water volume.

7. The digital water control system for urban and rural water supply according to claim 1 is characterized in that: According to the rural flow fuzzy coefficient and the urban flow fuzzy coefficient, combined with the predicted rural population, predicted urban population, predicted self-owned water volume and predicted irrigation water volume, the distribution optimization of the total water supply is performed to obtain the optimal water control parameters, and the water control module is used to execute the following method: Based on the predicted rural population, the predicted rural population water consumption is calculated, and the predicted rural water demand is calculated by combining the predicted self-owned water and the predicted irrigation water; Calculate and obtain predicted urban water demand based on the predicted urban population; Constructing a water affairs optimization function according to the predicted rural water demand, the predicted urban water demand, the rural flow fuzzy coefficient and the urban flow fuzzy coefficient; The total water supply is randomly distributed to urban areas and rural areas to obtain a first urban water supply and a first rural water supply as first water affairs control parameters, and a first water affairs fitness is calculated according to the water affairs optimization function; Continue to randomly distribute the water supply, calculate the water service fitness, perform iterative optimization until convergence, output the optimal water service control parameters with the largest water service fitness, and perform water supply and water service control.

8. The digital water control system for urban and rural water supply according to claim 7 is characterized in that: According to the predicted rural water demand, the predicted urban water demand, the rural flow fuzzy coefficient and the urban flow fuzzy coefficient, a water affairs optimization function is constructed, and the water affairs control module is also used to execute the following method: According to the rural flow fuzzy coefficient and the urban flow fuzzy coefficient, a rural weight and an urban weight are obtained by allocation and calculation; According to the rural weight, urban weight, predicted rural water demand, and predicted urban water demand, a water optimization function is constructed as follows: ； in, For water service adaptability, is the city weight, For rural weight, Water supply to towns, To predict urban water demand, Water supply to villages, To predict rural water demand.

9. A digital water control method for urban and rural water supply, characterized in that: A digital water control system for implementing urban and rural water supply according to any one of claims 1 to 8, comprising: Obtain the total water supply currently provided to urban and rural areas, and collect current time information; According to the time information, population flow prediction is performed in rural areas and urban areas to obtain predicted rural population and predicted urban population, and rural flow fuzzy coefficient and urban flow fuzzy coefficient are calculated; According to the time information, predict the self-owned water volume and the irrigation water volume of the rural area to obtain the predicted self-owned water volume and the predicted irrigation water volume; According to the rural flow fuzzy coefficient and the urban flow fuzzy coefficient, combined with the predicted rural population, predicted urban population, predicted self-owned water volume and predicted irrigation water volume, the distribution of the total water supply is optimized, the optimal water control parameters are obtained, and water supply control is performed.

Images