Water resource population bearing capacity threshold value measuring and calculating method based on hierarchical water consumption evaluation

Abstract

The invention relates to the technical field of water resource management, and particularly discloses a water resource population bearing capacity threshold value measuring and calculating method based on hierarchical water consumption evaluation, which comprises the following steps: step 1, deploying a sensor network in a target area, monitoring water resource conditions, climate changes, economic and social indexes and resident water consumption behaviors in real time through an edge computing unit, and calculating the water consumption of the target area; synchronizing the collected multi-dimensional data to a cloud end; 2, dividing domestic water consumption of residents into eight aspects according to water consumption behaviors of the residents by using a big data analysis technology and a probability density method, dividing water demand of the residents into three levels, and setting a water consumption interval; according to the method, the threshold value is dynamically adjusted, and an intelligent algorithm and reinforcement learning are introduced, so that water resource management flexibly responds to supply and demand changes, and water resource distribution and water saving policies are optimized; regional characteristics and social economic factors are comprehensively considered, support is provided for formulating personalized water-saving policies and long-term execution strategies for different regions, and policy execution is optimized in real time through an intelligent management platform.

Description

Technical Field

[0001] The present invention belongs to the technical field of water resource management, and particularly relates to a method for calculating the threshold of water resource population carrying capacity based on hierarchical water use evaluation. Background Art

[0002] The water resource population carrying capacity is a key indicator for measuring the sustainable utilization of water resources in a region. However, the traditional analysis methods of water resource population carrying capacity ignore the hierarchical characteristics of water resource demand, resulting in the inability to accurately predict and dynamically adjust the water resource population carrying capacity.

[0003] In the prior art, most calculations of water resource population carrying capacity are based on the traditional water resource supply-demand balance model. However, due to the lack of real-time data monitoring and dynamic adjustment mechanisms, there are often problems such as inaccurate prediction, inability to cope with complex climate changes and the diversity of residents' water use behaviors. In addition, traditional water-saving policies are usually static and single, and fail to be optimized and adjusted in real time according to the changes in water resource population carrying capacity. Moreover, the lack of comprehensive consideration of factors such as regional characteristics, residents' water use behaviors, and economic and social indicators leads to insufficient accuracy of calculation results and difficulty in meeting the actual application requirements. This poses great challenges to the prediction and management of water resources. Especially in a rapidly changing social environment, it is difficult to accurately evaluate future water resource demands and population carrying capacities, affecting the scientific scheduling and management of water resources.

[0004] Therefore, it is necessary to propose a method for calculating the threshold of water resource population carrying capacity based on hierarchical water use evaluation to solve the problem of inaccurate analysis and calculation of the traditional water resource population carrying capacity threshold in the prior art. Summary of the Invention

[0005] The purpose of the present invention is to provide a method for calculating the threshold of water resource population carrying capacity based on hierarchical water use evaluation to solve the problems mentioned in the above background art.

[0006] To achieve the above purpose, the present invention provides the following technical solutions:

[0007] A method for calculating the threshold of water resource population carrying capacity based on hierarchical water use evaluation includes the following steps:

[0008] Step 1: Deploy a sensor network in the target area, and use the edge computing unit to monitor the water resource status, climate change, economic and social indicators, and residents' water use behaviors in real time, and synchronize the collected multi-dimensional data to the cloud;

[0009] Step 2: Use big data analysis technology and probability density method to subdivide the domestic water use of residents into eight aspects according to residents' water use behaviors, and divide the water demand of residents into three levels and set water use intervals;

[0010] Step 3: Combine historical water usage data, real-time sensor information, and economic and social indicators, and use deep learning algorithms to predict water demand at each level, and calculate the threshold range of water resource population carrying capacity based on the available water resources;

[0011] Step 4: Use deep learning algorithms to monitor and predict the changing trend of water resource population carrying capacity in real time, and calculate the population carrying limit under different scenarios, and dynamically adjust the threshold range of water resource population carrying capacity;

[0012] Step 5: Based on the dynamically adjusted threshold range of water resource population carrying capacity, formulate personalized water-saving policies, and use the intelligent management platform to monitor the water resource usage efficiency in real time to optimize the implementation of water-saving policies;

[0013] Step 6: Introduce reinforcement learning algorithms to automatically adjust water resource allocation and usage strategies, and update the threshold range of water resource population carrying capacity in real time to optimize water resource management strategies.

[0014] Preferably, in Step 1, it includes:

[0015] Deploy multiple types of high-precision intelligent sensors within the target area to form a full-coverage Internet of Things system to monitor water resource conditions, climate change, economic and social indicators, and residents' water usage behaviors in real time;

[0016] The intelligent sensors transmit the collected real-time data to the edge computing unit within the target area through wireless communication technology;

[0017] The edge computing unit conducts preliminary analysis and processing on the real-time data, filters out noise data and performs time window weighted average processing to obtain multi-dimensional data;

[0018] Use a differential transmission algorithm to synchronously upload the multi-dimensional data to the cloud platform through a high-speed network channel, and realize data storage, analysis, and mining through the cloud platform.

[0019] Preferably, in Step 2, it includes:

[0020] Combine the clustering algorithm based on time series data, conduct big data analysis and clustering on residents' water usage behaviors, and subdivide them into eight aspects, including drinking water, toilet flushing water, personal hygiene water, cooking water, laundry water, household cleaning water, and breeding water, where personal hygiene water is further subdivided into washing and bathing water;

[0021] Based on the characteristics of the target area, calculate the water usage situation of each aspect through the new water usage calculation formula, and analyze the proportion of each aspect in the total water usage of residents;

[0022] New water usage calculation formula for different water usage behaviors:

[0023] (1) Calculation of drinking water consumption:

[0024]

[0025] Wherein, v drinking.r is the amount of water drunk per person per single time by a household resident, L / time, E r1 is the number of times of drinking water per person per day by a household resident, times / day, and m is the number of permanent residents in the household;

[0026] (2) Calculation of cooking water consumption:

[0027] W cook = v cook ·E2

[0028] Wherein, v cook is the amount of water used for single cooking by the household, and E2 is the number of cooking times per day by the household, times / day;

[0029] (3) Calculation of flushing water consumption:

[0030] W toilet = v toilet.j ·E3

[0031] Wherein, v toilet.j is the water consumption corresponding to the water efficiency grade of the toilet, L / (person·day), j corresponds to water efficiency grade 1 when j = 1, j corresponds to water efficiency grade 2 when j = 2, j corresponds to water efficiency grade 3 when j = 3, and E3 is the flushing frequency, times / day;

[0032] (4) Calculation of laundry water consumption:

[0033]

[0034] Wherein, v laundry is the single water consumption corresponding to the water efficiency grade of the washing machine, L / time, E 41 is the number of times the washing machine is used per week by the household, times / week, v hw is the water consumption for single hand washing, L / time, E 42 is the number of times of hand washing per week by the household, times / week, and m is the number of permanent residents in the household;

[0035] (5) Calculation of washing and grooming water consumption:

[0036]

[0037] Wherein, v wash is the single water consumption for washing and grooming, L / time, and E5 is the number of times of washing and grooming per day, times / day;

[0038] (6) Calculation of bathing water consumption:

[0039]

[0040] Wherein, W bath is the water consumption per single bath, in L / time, and E6 is the number of baths per week, in times / week;

[0041] (7) Calculation of household cleaning water consumption:

[0042]

[0043] Wherein, v e is the water consumption for mopping the floor per unit area, in L / m 2 , S is the housing area of residents, in m 2 / person, and E7 is the number of times of mopping the floor per week, in times / week;

[0044] (8) Calculation of breeding water consumption:

[0045]

[0046] Wherein, v breed.r is the breeding water consumption per single household resident, in L / time, and E r8 is the number of times of breeding water use per household resident per week, in times / week;

[0047] Frequency analysis is carried out on the water consumption of each water use category through the probability density method, and the water demand of residents is divided into three levels, namely rigid water demand, elastic water demand and luxury water demand;

[0048] Probability density function:

[0049]

[0050] Wherein, f(x) is the probability density of a certain water use behavior, K is the kernel function, h is the bandwidth parameter, and x i is the sample point;

[0051] The water use distribution of each level is calculated by using the probability density method to form a probability density distribution map;

[0052] Water use intervals are set for each level through the probability density distribution map and appropriately adjusted according to the characteristics of the target area.

[0053] Preferably, in step three, it includes:

[0054] Based on historical water use data, the LSTM network is used to preliminarily analyze the change of water use demand, and a spatio-temporal relationship model is constructed by combining real-time sensor information for real-time monitoring of water use demand fluctuations;

[0055] Integrate economic and social indicators, and fuse spatio-temporal information and non-linear change characteristics through deep learning algorithms to predict the water use demand of each level within a preset time period;

[0056] The non-linear change characteristics come from complex climate patterns, water resource supply-demand relationships, population changes, economic activities, and social behaviors and policy factors;

[0057] Based on the set water use intervals at each level, historical water use data is analyzed and calculated to obtain the per capita water use in each water use interval;

[0058] Introduce a water resource supply-demand balance model, compare the available water resources with the predicted water demands at each level, and calculate the water resource population carrying capacity interval;

[0059] Water resource supply-demand balance model:

[0060]

[0061] In the formula, R j is the available water volume of the j-th water source, W loss is the water resource loss, D l is the l-th type of water demand, and m and L are the numbers of water sources and water demand types respectively;

[0062] Use Monte Carlo simulation to sample different water resource supply-demand scenarios multiple times, predict the water resource population carrying capacity under multiple scenarios, and optimize the water resource supply-demand balance model;

[0063] Based on the water resource population carrying capacity interval and per capita water use, obtain the carrying limit value, warning line, moderate line, and surplus line, and provide decision-makers with water resource reasonable allocation, scheduling, and optimization plans.

[0064] Preferably, in step four, it includes:

[0065] Construct a water resource carrying capacity prediction model based on LSTM through multi-dimensional data, and improve the model prediction accuracy by using cross-validation and hyperparameter optimization methods;

[0066] Based on the characteristics of the target area, use the prediction model to conduct simulation analysis under different scenarios, calculate the corresponding water resource supply-demand balance, and further deduce the population carrying limit;

[0067] By calculating the predicted water resource population carrying capacity, combined with the change trends under each scenario, dynamically adjust the threshold interval of the water resource population carrying capacity.

[0068] Utilize multi-source data fusion technology to fuse data from different types of high-precision sensors, automatically generate customized water-saving suggestions by analyzing water use efficiency in real time and combining regional characteristics;

[0069] Introduce a variety of optimization algorithms, optimize the allocation of water resources and population carrying capacity according to the current scenario, and automatically adjust relevant optimization suggestions;

[0070] When it is predicted that the water resource population carrying capacity is about to reach the critical value, or the predicted scenario changes may lead to water resource shortage, the early warning mechanism is automatically triggered and the need for policy adjustment is prompted.

[0071] Preferably, in step five, it includes:

[0072] According to the water resource population carrying capacity of different regions and its dynamically adjusted thresholds, use nonlinear programming or genetic algorithms to formulate regional personalized water-saving policies;

[0073] Through the intelligent management platform, comprehensively monitor the water use efficiency of water resources. The platform integrates technologies such as Internet of Things sensors, data acquisition modules, and cloud computing analysis to collect the water use data of residents in each region in real time;

[0074] Adopt the LCA method to evaluate the long-term impacts of the implementation of water-saving policies on water resources, economy, and society, and balance the short-term benefits and long-term sustainability of water-saving policies;

[0075] Through the real-time feedback and decision support mechanism, automatically adjust the water-saving policy according to the feedback data, and monitor and adjust the policy implementation effect;

[0076] Introduce a social behavior model to evaluate the social acceptance and implementation effects of different water-saving policies, and optimize the implementation methods of water-saving policies.

[0077] Preferably, in step six, it includes:

[0078] Based on the reinforcement learning algorithm, construct a reward and punishment mechanism according to the current regional water-saving policy, and continuously optimize the water resource allocation and use strategy;

[0079] Reward mechanism: Design a reward function according to the effect of the water-saving policy to encourage the selection of reasonable and efficient water resource allocation strategies. For example:

[0080] Water resource conservation reward: When the water resource waste of a certain region or resident decreases, give a reward;

[0081] Balanced reward: If water resources can be fairly and reasonably allocated to each region and ensure the water use needs of all regions, give a reward;

[0082] Sustainability reward: When the water resource use strategy can last for a long time without water resource shortage or extreme waste, give a long-term reward.

[0083] Punishment mechanism: Punish strategies that are ineffective or consume water resources excessively. For example:

[0084] Water resource shortage punishment: When the water resources in a certain region are in shortage (i.e., the water volume is lower than a certain threshold), it will be punished;

[0085] Waste Penalty: If the water resource allocation is excessive or not in accordance with the priority needs, resulting in water resource waste in some areas, penalties will also be imposed.

[0086] Objective Optimization: Through rewards and penalties, continuously optimize the water resource allocation strategy and adjust it towards goals such as water conservation, high efficiency, and sustainability.

[0087] According to the changes in water resource availability and population data, use the DQN algorithm to perform dynamic state and action mapping, and optimize the water conservation policy in the current region;

[0088] Q-value Update Formula:

[0089]

[0090] In the formula, s t is the current state, a t is the current action, a′ is the action that can bring the maximum Q-value in the next state s t+1 r t+1 is the reward value, and γ is the discount factor;

[0091] And combine climate change, population growth, and regional water demand to dynamically update the water resource population carrying capacity threshold for each region;

[0092] Dynamic Threshold Adjustment: Dynamically update the water resource population carrying capacity threshold for each region according to factors such as climate change, population growth, and regional water demand. For example:

[0093] Population Growth: If the population growth in a certain region accelerates, adjust the carrying capacity threshold according to the water resource supply situation to ensure that the water resources are not overloaded;

[0094] Climate Change: In case of drought or reduced precipitation, adjust the carrying capacity threshold, give early warnings, and optimize the water resource allocation.

[0095] Change in Regional Water Demand: When the regional water demand changes, it will trigger real-time adjustment of the carrying capacity threshold to ensure reasonable water resource allocation for each resident in the region.

[0096] When there is a water resource shortage in a certain region, achieve dynamic optimal allocation of cross-regional water resources through a water resource scheduling strategy based on game theory, and mobilize the surplus water resources in neighboring regions for supplementation;

[0097] Combine with a water resource management expert system to evaluate the water resource scheduling effect in real time, and adjust the water resource management strategy within the preset time period through a feedback mechanism.

[0098] Preferably, the method also uses an adaptive neuro-fuzzy inference system to establish a dynamic adjustment model for the carrying capacity threshold, and automatically adjusts the water resources population carrying capacity threshold by inputting available water resources, climate change, population data, and historical water use data.

[0099] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0100] By dynamically adjusting the threshold, introducing intelligent algorithms and reinforcement learning, the present invention enables the water resources management to flexibly respond to the changes in supply and demand, optimizes the water resources allocation and water-saving policies, and ensures the optimal utilization of water resources in various scenarios; comprehensively considering regional characteristics and socioeconomic factors, it provides support for formulating personalized water-saving policies and long-term implementation strategies for different regions, and at the same time, through the intelligent management platform, it optimizes the policy implementation in real time, enhancing the personalization and implementation effect of the water-saving policies; based on cutting-edge technologies such as deep learning, it scientifically predicts potential water resources shortage problems, triggers early warnings in advance and proposes solutions, providing an effective guarantee for the long-term sustainable utilization of water resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0101] Figure 1 It is a flowchart of the method for calculating the water resources population carrying capacity threshold based on hierarchical water use evaluation of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0102] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0103] Embodiment 1:

[0104] Please refer to Figure 1 As shown, the method for calculating the water resources population carrying capacity threshold based on hierarchical water use evaluation includes the following steps:

[0105] Step 1: Deploy a sensor network in the target area, and through the edge computing unit, monitor the water resources status, climate change, economic and social indicators, and residents' water use behaviors in real time, and synchronize the collected multi-dimensional data to the cloud;

[0106] Step 2: Use big data analysis technology and probability density method to subdivide the domestic water use of residents into eight aspects according to residents' water use behaviors, and divide the water demand of residents into three levels and set water use intervals;

[0107] Step 3: Combine historical water usage data, real-time sensor information, and economic and social indicators, and use deep learning algorithms to predict water demand at various levels, and calculate the threshold range of water resource population carrying capacity based on the available water resources;

[0108] Step 4: Use deep learning algorithms to monitor and predict the changing trend of water resource population carrying capacity in real time, calculate the population carrying limit under different scenarios, and dynamically adjust the threshold range of water resource population carrying capacity;

[0109] Step 5: Based on the dynamically adjusted threshold range of water resource population carrying capacity, formulate personalized water-saving policies, and use an intelligent management platform to monitor the water resource usage efficiency in real time and optimize the implementation of water-saving policies;

[0110] Step 6: Introduce a reinforcement learning algorithm to automatically adjust water resource allocation and usage strategies, and update the threshold range of water resource population carrying capacity in real time to optimize water resource management strategies.

[0111] Deploy multiple types of high-precision intelligent sensors within the target area to form a full-coverage Internet of Things system, and monitor the water resource status, climate change, economic and social indicators, and residents' water usage behaviors in real time;

[0112] The intelligent sensors transmit the collected real-time data to the edge computing unit within the target area through wireless communication technology;

[0113] The edge computing unit conducts preliminary analysis and processing on the real-time data, filters out noise data and performs time window weighted average processing to obtain multi-dimensional data;

[0114] Use a differential transmission algorithm to synchronously upload the multi-dimensional data to the cloud platform through a high-speed network channel, and realize data storage, analysis, and mining through the cloud platform.

[0115] Furthermore, by deploying multiple types of high-precision intelligent sensors within the target area to form a full-coverage Internet of Things system, real-time monitoring of the water resource status, climate change, economic and social indicators, and residents' water usage behaviors is achieved. Through the differential transmission algorithm and high-speed network channel, efficient data transmission and synchronous upload to the cloud platform are ensured, and then the storage, analysis, and mining of a large amount of multi-dimensional data are realized.

[0116] Combined with a clustering algorithm based on time series data, through big data analysis and clustering of residents' water usage behaviors, it is subdivided into eight aspects, including drinking water, toilet flushing water, personal hygiene water, cooking water, laundry water, household cleaning water, and breeding water;

[0117] Based on the characteristics of the target area, calculate the water usage situation of each aspect through a newly added water consumption calculation formula, and analyze the proportion of each aspect in the total water consumption of residents;

[0118] Frequency analysis is carried out on the water consumption of each water use category by the probability density method, and the domestic water demand is divided into three levels, namely rigid water demand, elastic water demand and luxury water demand;

[0119] The water use distribution of each level is calculated by the probability density method to form a probability density distribution map;

[0120] Water use intervals are set for each level through the probability density distribution map and appropriately adjusted according to the characteristics of the target area.

[0121] Furthermore, through the clustering algorithm combined with time series data, big data analysis and clustering of domestic water use behaviors are carried out, and the complex water use patterns are subdivided into eight categories to provide more accurate water use demand analysis. The probability density method is used to conduct frequency analysis on each water use category, and by dividing into three levels of rigid water demand, elastic water demand and luxury water demand, the different water use demands of residents are more carefully identified, thereby providing a scientific basis for water resources management and optimization. By constructing a probability density distribution map and setting reasonable water use intervals, it can help adjust the water use strategy of the target area and achieve the efficient allocation and conservation of water resources.

[0122] Based on historical water use data, the LSTM network is used to conduct a preliminary analysis of the changes in water use demand, and a spatio-temporal relationship model is constructed by combining real-time sensor information for real-time monitoring of water use demand fluctuations;

[0123] Integrate economic and social indicators, and fuse spatio-temporal information and non-linear change characteristics through deep learning algorithms to predict the water use demand of each level within a preset time period;

[0124] Based on the set water use interval for each level, historical water use data is used for analysis and calculation to obtain the per capita water use of each water use interval;

[0125] Introduce a water resources supply-demand balance model, compare the available water resources with the predicted water use demand of each level, and calculate the water resources population carrying capacity interval;

[0126] Use Monte Carlo simulation to conduct multiple samplings on different water resources supply-demand scenarios, predict the water resources population carrying capacity under multiple scenarios, and optimize the water resources supply-demand balance model;

[0127] Based on the water resources population carrying capacity interval and per capita water use, obtain the carrying limit value, warning line, moderate line, and surplus line, and provide decision-makers with a reasonable water resources allocation, scheduling and optimization plan.

[0128] Furthermore, by combining the LSTM network to analyze historical water use data and using real-time sensor information to build a spatiotemporal relationship model, the fluctuation of water demand can be monitored in real time, providing accurate dynamic water demand forecasts. By integrating economic and social indicators with deep learning algorithms to fuse spatiotemporal information and nonlinear change characteristics, water demand at all levels can be effectively predicted. The water supply and demand balance model is introduced to compare the available water resources with the predicted demand, accurately calculate the water resource population carrying capacity range, and provide a scientific basis for decision makers.

[0129] A water resources carrying capacity prediction model based on LSTM is constructed through multi-dimensional data, and cross-validation and hyperparameter optimization are used to improve the prediction accuracy of the model;

[0130] Based on the characteristics of the target area, the prediction model is used to simulate and analyze different scenarios, calculate the corresponding water supply and demand balance, and further deduce the population carrying capacity;

[0131] By calculating the predicted water resources population carrying capacity and combining the changing trends under various scenarios, the threshold range of water resources population carrying capacity is dynamically adjusted.

[0132] Utilize multi-source data fusion technology to integrate data from different types of high-precision sensors, analyze water use efficiency in real time and combine regional characteristics to automatically generate customized water-saving suggestions

[0133] Introducing a variety of optimization algorithms to optimally allocate water resources and population carrying capacity according to the current situation, and automatically adjust relevant optimization suggestions;

[0134] When it is predicted that the population carrying capacity of water resources is about to reach a critical value, or when the predicted scenario changes may lead to water shortages, the early warning mechanism is automatically triggered and the need for policy adjustments is prompted.

[0135] Furthermore, the LSTM-based water resource carrying capacity prediction model is used to accurately simulate the water resource supply and demand balance under different scenarios and estimate the population carrying capacity. Multi-source data fusion technology is used to analyze water use efficiency in real time and combine regional characteristics to provide customized water-saving suggestions for different regions. At the same time, by dynamically adjusting the threshold range of water resource population carrying capacity and applying a variety of optimization algorithms, the optimal allocation of water resources and population carrying capacity is achieved, improving the flexibility of decision-making and the ability to respond to emergencies.

[0136] Based on the water resource population carrying capacity of different regions and its dynamically adjusted threshold, regional personalized water-saving policies can be formulated using nonlinear programming or genetic algorithms. For example, strict water quota management can be implemented in areas with relatively tight water resources, while incentive measures such as water fee discounts can be adopted in areas with relatively abundant water resources.

[0137] Adopt the LCA method to evaluate the long-term impacts of water-saving policy implementation on water resources, economy, and society, and balance the short-term benefits and long-term sustainability of water-saving policies;

[0138] Through a real-time feedback and decision support mechanism, automatically adjust water-saving policies according to the feedback data, and monitor and adjust the implementation effects of the policies;

[0139] Introduce a social behavior model to evaluate the social acceptance and implementation effects of different water-saving policies, and optimize the implementation methods of water-saving policies.

[0140] Furthermore, by using nonlinear programming or genetic algorithms to formulate personalized water-saving policies, it ensures that water-saving policies are more accurate and practical. Combining the life cycle analysis (LCA) method to evaluate the long-term impacts of water-saving policies on water resources, economy, and society helps to find a balance between short-term benefits and long-term sustainability, and avoid situations of excessive water conservation or resource waste. In addition, combining the social behavior model to evaluate the social acceptance of water-saving policies further optimizes the implementation methods of the policies, improves public participation and implementation effects, and thus promotes the long-term effective implementation of water-saving measures.

[0141] Based on the reinforcement learning algorithm, construct a reward and punishment mechanism according to the current regional water-saving policy, and continuously optimize the water resource allocation and usage strategies;

[0142] According to the changes in water resource availability and population data, use the DQN algorithm for dynamic state and action mapping to optimize the current regional water-saving policy;

[0143] And combine climate change, population growth, and regional water demand to dynamically update the water resource population carrying capacity threshold for each region;

[0144] When there is a water shortage in a certain region, achieve dynamic optimal allocation of cross-regional water resources through a game theory-based water resource scheduling strategy, and mobilize the surplus water resources of neighboring regions for supplementation;

[0145] Combine a water resource management expert system to evaluate the water resource scheduling effects in real time, and adjust the water resource management strategy within a preset time period through a feedback mechanism.

[0146] Furthermore, by using the DQN algorithm for dynamic state and action mapping, it can adjust policies in real time according to the changes in water resource availability and population data, and improve the water-saving effect. In addition, combining climate change, population growth, and regional water demand to dynamically update the water resource population carrying capacity threshold makes the policy more adaptable and forward-looking. When there is a water shortage in a certain region, the game theory-based water resource scheduling strategy can achieve cross-regional optimal allocation of water resources, mobilize the surplus resources of neighboring regions for supplementation, and avoid regional water resource crises.

[0147] This method also uses an adaptive neuro-fuzzy inference system to establish a dynamic adjustment model for the carrying capacity threshold. By inputting the available water resources, climate change, population data, and historical water usage data, it automatically adjusts the water resources population carrying capacity threshold.

[0148] Example 2:

[0149] Application example: Calculation of the water resources population carrying capacity threshold for domestic water use in an inland river basin in arid areas

[0150] I. Background introduction

[0151] In the inland river basin of arid areas, water resources are scarce and the contradiction between supply and demand is prominent. To reasonably evaluate the water resources population carrying capacity in this area, this paper is based on a hierarchical water use evaluation method to conduct refined classification and calculation of domestic water use, aiming to provide a scientific basis for water resources management and water-saving policy formulation.

[0152] II. Method overview

[0153] (1) Data collection and preprocessing

[0154] Deploy a sensor network: Deploy high-precision intelligent sensors in the urban areas of the inland river basin in arid areas, covering multiple aspects such as water resources, climate, economic and social indicators, and residents' water use behaviors. The sensors transmit data to the edge computing unit in real time through wireless communication technology for preliminary processing and noise filtering, and then synchronize to the cloud platform for storage and analysis through a high-speed network channel.

[0155] Data integration and processing: Use big data analysis technology to integrate and process the collected multi-dimensional data, including historical water use data, real-time sensor information, economic and social indicators, etc. Ensure the accuracy, integrity, and timeliness of the data.

[0156] (2) Hierarchical water use evaluation

[0157] Classification of water use behaviors: Divide domestic water use into eight aspects according to water use behaviors, namely drinking water, toilet flushing water, personal hygiene water (including washing and bathing), cooking water, laundry water, household cleaning water, and breeding water.

[0158] Classification of water demand levels:

[0159] Rigid water demand: Includes drinking water, cooking water, and the water consumption necessary for residents to maintain basic survival in other water use aspects. It is not affected by economic and social conditions and has irreplaceability and non-compressibility.

[0160] Flexible water demand: It includes (part of) the water used for flushing toilets, laundry water, personal hygiene water (the water for washing and bathing exceeding the basic needs), household cleaning water, etc. These water demands can change with external conditions and have medium substitutability.

[0161] Luxury water demand: It includes the water used for flushing toilets exceeding the specified standard, unreasonable personal hygiene water, and the additional water caused by excessive cleaning, etc. These water demands can be effectively compressed through technological improvements and enhanced water conservation awareness.

[0162] Setting of water usage intervals: Based on the probability density method, frequency analysis is carried out on the water consumption of each water usage behavior, and the intervals of rigid, flexible, and luxury water usage are set. Based on the set water usage intervals at each level, historical water usage data is used for analysis and calculation to obtain the per capita water consumption of each water usage interval at each level. For example, the water used for flushing toilets can be divided into rigid, flexible, and luxury water usage according to the water efficiency grade of the toilet; the water used for washing and bathing can be divided according to the daily usage times and temperature.

[0163] (3) Calculation of the threshold of water resources population carrying capacity

[0164] Water demand prediction: Combining historical water usage data, real-time sensor information, and economic and social indicators, deep learning algorithms are used to predict the water demands at each level. Consider the non-linear change characteristics such as complex climate patterns, water resources supply and demand relationships, population changes, economic activities, and social behaviors and policy factors.

[0165] Analysis of water resources supply and demand balance: Introduce a water resources supply and demand balance model to compare the available water resources with the predicted water demands at each level. Use Monte Carlo simulation to conduct multiple samplings on different water resources supply and demand scenarios to predict the water resources population carrying capacity under multiple scenarios.

[0166] Calculation of the threshold interval: Based on the water resources population carrying capacity interval and per capita water consumption, the carrying limit value, warning line, moderate line, and surplus line are obtained. These values reflect the range of the population that the region can carry under different water resources supply and demand conditions.

[0167] Dynamic adjustment and optimization:

[0168] Through deep learning algorithms, real-time monitoring and prediction of the changing trend of water resources population carrying capacity are carried out, and the population carrying limit is calculated according to different scenarios, and the threshold interval of water resources population carrying capacity is dynamically adjusted.

[0169] Introduce a reinforcement learning algorithm to automatically adjust the water resources allocation and usage strategy, and update the threshold interval of water resources population carrying capacity in real time to optimize the water resources management strategy.

[0170] (4) Formulation and implementation of water conservation policies

[0171] Personalized water-saving policies: Based on the dynamically adjusted threshold range of the water resources population carrying capacity, non-linear programming or genetic algorithms are used to formulate regional personalized water-saving policies.

[0172] Intelligent management platform monitoring: The intelligent management platform is used to monitor the water resource utilization efficiency in real time. By integrating technologies such as Internet of Things sensors, data acquisition modules, and cloud computing analysis, the water usage data of residents in each region is collected in real time.

[0173] Policy effect evaluation and optimization: The LCA method is adopted to evaluate the long-term impacts of the implementation of water-saving policies on water resources, economy, and society, and to balance the short-term benefits and long-term sustainability of water-saving policies. Through a real-time feedback and decision support mechanism, the water-saving policies are automatically adjusted, and the implementation effects of the policies are monitored and adjusted.

[0174] III. Specific calculation process

[0175] The definitions of the rigid, elastic, and luxurious intervals for the living water use behaviors of residents in the inland river basins of arid regions are shown in Table 1.

[0176] Table 1 Definitions of the rigid, elastic, and luxurious intervals for different water use behaviors

[0177]

[0178]

[0179] Drinking water: It is used to maintain human survival, so all of it is rigid demand, without elastic and luxurious demands;

[0180] Cooking water: Similar to drinking water, it is used for human survival to meet physiological needs, so there are no elastic and luxurious demands;

[0181] Toilet flushing water: According to the regulations in the water efficiency limit values and water efficiency grades for toilets in GB25502-2017, the first, second, and third grades are classified as rigid, elastic, and luxurious water use in sequence according to the water consumption;

[0182] Laundry water: The number of laundry times per week is selected;

[0183] Washing water: Selecting washing twice or less per day as rigid water use, and more than twice as elastic water use;

[0184] Bathing water: 25°C is the starting temperature of the thermal sensation, so 25°C is used as the dividing line;

[0185] Environmental cleaning water: The number of times of mopping the floor per week is selected as the basis for division;

[0186] Aquaculture water: The number of potted plants is selected as the basis for division.

[0187] Water consumption data collection: The water consumption data of various water - using behaviors of urban residents is collected in real - time through a sensor network.

[0188] Water demand prediction: Using deep - learning algorithms such as the LSTM network, combined with historical data and real - time sensor information, predict the water demand at different levels in the future for a period of time.

[0189] Calculation of the threshold of water resources population carrying capacity:

[0190] According to the rigid, elastic, and luxury water - using intervals of each water - using behavior set in Table 1, let [Q ai ,Q bi be the rigid water - using interval, (Q bi ,Q ci be the elastic water - using interval, (Q ci ,Q di be the luxury water - using interval, where i = 1, 2, …, 8, representing drinking water, toilet flushing water, personal hygiene water, cooking water, laundry water, household cleaning water, and aquaculture water respectively.

[0191] Based on the characteristics of the inland river basin in arid areas, calculate the water consumption and the rigid, elastic, and luxury water - using intervals of different water - using behaviors. Based on the set water - using intervals at each level, use historical water - using data for analysis and calculation to obtain the per capita water consumption in each water - using interval. Based on the available water volume of urban residents, divide it by the rigid, elastic, and luxury water - using intervals of each water - using behavior respectively to obtain the water resources population carrying capacity interval.

[0192] Based on the water resources population carrying capacity interval and per capita water consumption, determine the carrying limit value (obtained by dividing by the minimum value of the rigid interval), the warning line (obtained by dividing by the per capita water consumption value of the rigid interval), the moderate line (obtained by dividing by the sum of the boundary value between the rigid interval and the elastic interval and the per capita water consumption value of the elastic interval), and the surplus line (obtained by dividing by the boundary value between the elastic interval and the luxury interval).

[0193] IV. Application results

[0194] Through this method, we obtained the water resources population carrying capacity threshold interval of a certain town in the inland river basin of arid areas. According to the measurement results, there is an upper limit to the population that the town can carry under the current water resources conditions. When the population number approaches or exceeds the carrying limit value, the warning mechanism should be activated, and water - saving measures and optimized water resources allocation strategies should be taken.

[0195] At the same time, according to the rigid, elastic, and luxury water - using intervals of different water - using behaviors, we can formulate personalized water - saving policies. For example, for toilet flushing water, encourage residents to use water - saving toilets; for laundry water, advocate reasonable control of the number of laundry times and water consumption; for personal hygiene water, advocate water conservation and reduction of waste, etc.

[0196] Example 3:

[0197] The embodiment of the present invention further provides a computer-readable storage medium. A program of the method for calculating the threshold of water resources population carrying capacity based on hierarchical water use evaluation as described in any one of the above is stored on the computer-readable storage medium. When the program is executed by a processor, each process of the above-described embodiment of the calculation method is implemented, and the same technical effects can be achieved. To avoid repetition, it will not be described in detail here. Among them, the computer-readable storage medium is, for example, a read-only memory (ROM for short), a random access memory (RAM for short), a magnetic disk, or an optical disc, etc.

[0198] In the description of this specification, the description with reference to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0199] In the drawings of the disclosed embodiments of the present invention, only the structures related to the disclosed embodiments of the present invention are involved. Other structures can refer to the general design. Without conflict, the same embodiment and different embodiments of the present invention can be combined with each other.

[0200] The flowcharts shown in the drawings are only illustrative examples, and do not necessarily include all the contents and operations / steps, nor do they necessarily need to be executed in the described order. For example, some operations / steps can also be decomposed, combined, or partially merged. Therefore, the actual execution order may be changed according to the actual situation.

[0201] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for calculating the threshold value of water resources population carrying capacity based on hierarchical water use evaluation, characterized in that: The following steps are involved: Step 1: Deploy a sensor network in the target area, monitor water resources, climate change, economic and social indicators, and residents' water use behavior in real time through edge computing units, and synchronize the collected multi-dimensional data to the cloud; Step 2: Using big data analysis technology and probability density method, the domestic water use of residents is subdivided into eight aspects according to their water use behavior, and the water demand of residents is divided into three levels and the water use intervals are set; Step 3: Combine historical water use data, real-time sensor information, and economic and social indicators to use deep learning algorithms to predict water demand at all levels and calculate the threshold range of water resource population carrying capacity based on water resource availability; Step 4: Use deep learning algorithms to monitor and predict the changing trend of water resources population carrying capacity in real time, calculate the population carrying capacity limit under different scenarios, and dynamically adjust the threshold range of water resources population carrying capacity; Step 5: Develop personalized water-saving policies based on the dynamically adjusted water resource population carrying capacity threshold range, monitor water resource utilization efficiency in real time through the intelligent management platform, and optimize the implementation of water-saving policies; Step 6: Introduce reinforcement learning algorithm to automatically adjust water resource allocation and use strategies, and update the water resource population carrying capacity threshold range in real time to optimize water resource management strategies.

2. The method for calculating the threshold value of water resources population carrying capacity based on hierarchical water use evaluation according to claim 1 is characterized in that: In step one, include: Deploy multiple types of high-precision smart sensors in the target area to form a full-coverage IoT system to monitor water resources, climate change, economic and social indicators, and residents' water use behavior in real time; Smart sensors transmit the collected real-time data to the edge computing unit in the target area through wireless communication technology; The edge computing unit performs preliminary analysis and processing on real-time data, filters out noise data, and performs time window weighted average processing to obtain multi-dimensional data; A differentiated transmission algorithm is used to synchronously upload multidimensional data to the cloud platform through a high-speed network channel, and the cloud platform is used to store, analyze and mine data.

3. The method for calculating the threshold value of water resources population carrying capacity based on hierarchical water use evaluation according to claim 2 is characterized in that: In step 2, include: Combined with the clustering algorithm based on time series data, the water use behavior of residents is analyzed and clustered into eight aspects through big data analysis; Based on the characteristics of the target area, the water consumption of each aspect is calculated using the new water consumption calculation formula, and the proportion of each aspect in the total water consumption of residents is analyzed; The frequency analysis of water consumption of each water category was conducted by probability density method, and the water demand of residents was divided into three levels, namely rigid water demand, elastic water demand and luxury water demand. Probability density function: Where f(x) is the probability density of a water use behavior, K is the kernel function, h is the bandwidth parameter, and x i is the sample point; The probability density method is used to calculate the water use distribution at each level and form a probability density distribution map; The water use range is set for each level through the probability density distribution map, and appropriate adjustments are made according to the characteristics of the target area.

4. The method for calculating the threshold value of water resources population carrying capacity based on hierarchical water use evaluation according to claim 3 is characterized in that: In step three, include: Based on historical water use data, the LSTM network is used to conduct a preliminary analysis of changes in water demand, and a spatiotemporal relationship model is constructed in combination with real-time sensor information to monitor water demand fluctuations in real time; Integrate economic and social indicators, fuse spatiotemporal information and nonlinear change characteristics through deep learning algorithms, and predict water demand at all levels within a preset time period; Based on the set water consumption interval at each level, historical water consumption data is used for analysis and calculation to obtain the per capita water consumption at each level; A water resource supply and demand balance model is introduced to compare the available water resources with the predicted water demand at each level, and the water resource population carrying capacity range is calculated; Water supply and demand balance model: In the formula, R j is the available water volume of the jth water source, W loss is the loss of water resources, D l is the water demand of the lth type, m and L are the number of water sources and water demand types respectively; Use Monte Carlo simulation to conduct multiple sampling of different water resource supply and demand scenarios, predict the water resource population carrying capacity under various scenarios, and optimize the water resource supply and demand balance model; Based on the water resources population carrying capacity range and per capita water consumption, the carrying limit value, warning line, moderate line and surplus line are obtained, and reasonable water resources allocation, scheduling and optimization plans are provided to decision makers.

5. The method for calculating the threshold value of water resources population carrying capacity based on hierarchical water use evaluation according to claim 4 is characterized in that: In step 4, include: A water resources carrying capacity prediction model based on LSTM is constructed through multi-dimensional data, and cross-validation and hyperparameter optimization are used to improve the prediction accuracy of the model; Based on the characteristics of the target area, the prediction model is used to simulate and analyze different scenarios, calculate the corresponding water supply and demand balance, and further deduce the population carrying capacity; By calculating the predicted water resources population carrying capacity and combining the changing trends under various scenarios, the threshold range of water resources population carrying capacity is dynamically adjusted.

6. The method for calculating the threshold value of water resources population carrying capacity based on hierarchical water use evaluation according to claim 5 is characterized in that: In step 4, it also includes: Utilize multi-source data fusion technology to integrate data from different types of high-precision sensors, analyze water use efficiency in real time and combine regional characteristics to automatically generate customized water-saving suggestions; Introducing a variety of optimization algorithms to optimally allocate water resources and population carrying capacity according to the current situation, and automatically adjust relevant optimization suggestions; When it is predicted that the population carrying capacity of water resources is about to reach a critical value, or when the predicted scenario changes may lead to water shortages, the early warning mechanism is automatically triggered and the need for policy adjustments is prompted.

7. The method for calculating the threshold value of water resources population carrying capacity based on hierarchical water use evaluation according to claim 6 is characterized in that: In step five, include: According to the water resource population carrying capacity of different regions and its dynamically adjusted threshold, use nonlinear programming or genetic algorithms to formulate regional personalized water conservation policies; Use LCA methods to assess the long-term impact of water conservation policy implementation on water resources, economy and society, and balance the short-term benefits and long-term sustainability of water conservation policies; Through real-time feedback and decision-making support mechanisms, water-saving policies are automatically adjusted according to feedback data, and the effectiveness of policy implementation is monitored and adjusted; Introduce social behavioral models to evaluate the social acceptance and implementation effects of different water-saving policies and optimize the implementation methods of water-saving policies.

8. The method for calculating the threshold value of water resources population carrying capacity based on hierarchical water use evaluation according to claim 7 is characterized in that: In step six, include: Based on the reinforcement learning algorithm, a reward and punishment mechanism is established according to the current regional water conservation policy to continuously optimize the water resource allocation and use strategy; According to the changes in water resource availability and population data, the DQN algorithm is used to dynamically map states and actions to optimize the water-saving policy in the current area; Q value update formula: In the formula, s t is the current state, a t is the current action, a′ is in the next state s t+1 The action that can bring the maximum Q value, r t+1 is the reward value, γ is the discount factor; The water resource population carrying capacity threshold of each region is dynamically updated based on climate change, population growth, and regional water demand; When a region is short of water resources, a water resource scheduling strategy based on game theory can be used to dynamically optimize the allocation of water resources across regions and mobilize the remaining water resources in neighboring regions for replenishment. Combined with the water resources management expert system, the water resources scheduling effect is evaluated in real time, and the water resources management strategy within the preset time period is adjusted through the feedback mechanism.

9. The method for calculating the threshold value of water resources population carrying capacity based on hierarchical water use evaluation according to claim 8 is characterized in that: The method also uses an adaptive neuro-fuzzy inference system to establish a dynamic adjustment model for the carrying capacity threshold, and automatically adjusts the water resource population carrying capacity threshold by inputting water resource availability, climate change, population data, and historical water use data.

Images