Load dynamic scheduling method and system for watershed multi-tributary pollution and medium

Abstract

The invention discloses a load dynamic scheduling method and system for drainage basin multi-branch pollution and a medium, and relates to the technical field of water environment data management, and the method comprises the steps: deploying an online sensor network in a drainage basin, collecting pollutant data in real time, uploading the pollutant data to a control center, and building a pollution load database; performing time sequence traceability analysis by combining the ground pollutant list and the pollution load database, and establishing a traceability identifier; hydrology, water quality, rainfall and other dynamic indexes are collected, and a time-varying bearing threshold value of the zone pollutants is output; and executing load dynamic scheduling optimization and management by using the pollution load database, the traceability identifier and the bearing threshold. The technical problem that pollution load scheduling is inaccurate due to the fact that an existing drainage basin pollution control technology is single in monitoring index and lacks big data comprehensive evaluation and dynamic regulation and control capacity is solved, and the technical effect of improving the accuracy of pollution discharge load scheduling in a drainage basin through multi-dimensional water environment big data evaluation and dynamic regulation and control management is achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of water environment data management, and particularly relates to a load dynamic scheduling method and system for basin multi-tributary pollution and a medium. BACKGROUND

[0002] Traditional governance means are mostly single-point governance or passive monitoring, lacking analysis and management of overall water environment big data of a basin. Moreover, existing technologies mostly rely on local monitoring data, lacking real-time tracing and precise regulation and control of overall pollution situation and pollution sources of a basin, and failing to fully consider dynamic changes of multi-dimensional data such as hydrology, meteorology and ecology. SUMMARY

[0003] The present application provides a load dynamic scheduling method and system for basin multi-tributary pollution and a medium, for solving the technical problem that existing basin pollution control technologies have single monitoring indicators, lack comprehensive evaluation and dynamic regulation and control capabilities of big data, and result in inaccurate pollution load scheduling.

[0004] In a first aspect, the present application provides a load dynamic scheduling method for basin multi-tributary pollution, which comprises: deploying an online monitoring sensor network inside a basin, collecting pollution data in real time, uploading time-series pollution collection results to a control center, and establishing a pollution load database; obtaining a list of ground pollutants, performing time-series tracing analysis according to the list of ground pollutants and the pollution load database, and establishing a tracing identifier; collecting a dynamic index set, the dynamic index set including a basin hydrology, water quality, rainfall, water temperature, and biological index set, constructing an ecological capacity time-series evolution model of pollution background, self-cleaning capacity, and ecological response according to the dynamic index set, and outputting a partition pollutant time-varying carrying threshold; jointly constructing a pollution emission load-ecological capacity adaptation matrix using the pollution load database, the tracing identifier, and the partition pollutant time-varying carrying threshold, taking the pollution emission load-ecological capacity adaptation matrix as a constraint, performing load dynamic scheduling optimization, establishing a scheduling strategy, and performing load dynamic scheduling management according to the scheduling strategy.

[0005] In a second aspect of the present application, a load dynamic scheduling system for pollution of multiple tributaries in a river basin is provided, which comprises: a pollutant data acquisition module, configured to deploy an online monitoring sensor network inside the river basin, acquire pollutant data in real time, upload time-series pollutant acquisition results to a control center, and establish a pollution load database; a time-series traceability analysis module, configured to obtain a list of ground pollutants, perform time-series traceability analysis according to the list of ground pollutants and the pollution load database, and establish a traceability identifier; a time-varying carrying threshold generation module, configured to acquire a dynamic index set, the dynamic index set comprising a set of hydrological, water quality, rainfall, water temperature and biological indicators, construct a time-series evolution model of ecological capacity of pollution background, self-purification capacity and ecological response according to the dynamic index set, and output a time-varying carrying threshold of partition pollutants; a load dynamic scheduling optimization module, configured to jointly construct a pollution emission load-ecological capacity adaptation matrix by using the pollution load database, the traceability identifier and the time-varying carrying threshold of partition pollutants, execute load dynamic scheduling optimization by taking the pollution emission load-ecological capacity adaptation matrix as a constraint, and establish a scheduling strategy; and a load dynamic scheduling management module, configured to perform load dynamic scheduling management according to the scheduling strategy.

[0006] In a third aspect of the present application, a computer-readable storage medium is provided, which stores a computer program, and the computer program is executed by a processor to implement the method of the first aspect.

[0007] The one or more technical solutions provided in the present application have at least the following technical effects or advantages: The load dynamic scheduling method, system and medium for pollution of multiple tributaries in a river basin provided in the present application relate to the technical field of water environment data management, and have the technical effects of realizing scientific regulation and control of pollution emission load in a river basin, solving the technical problems of single monitoring index, lack of comprehensive evaluation and dynamic regulation and control capability of big data in existing river basin pollution treatment technology, and low precision of pollution load scheduling, and achieving multi-dimensional water environment big data evaluation and dynamic regulation and control management, and improving the precision of pollution emission load scheduling in a river basin. BRIEF DESCRIPTION OF DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0009] Figure 1 A flow chart of a method for dynamically dispatching pollution loads of multiple tributaries in a river basin provided in an embodiment of the present application; Figure 2 Schematic diagram of the structure of the load dynamic scheduling system for pollution of multiple tributaries in a river basin provided in an embodiment of the present application.

[0010] Explanation of the accompanying symbols: pollutant data collection module 11, time series tracing and analysis module 12, time-varying load threshold generation module 13, load dynamic scheduling optimization module 14, load dynamic scheduling management module 15. DETAILED DESCRIPTION

[0011] This application provides a method, system and medium for dynamic scheduling of pollution loads in multiple tributaries of a river basin, which is used to solve the technical problems of inaccurate pollution load scheduling caused by the single monitoring indicators of existing river basin pollution control technologies, the lack of big data comprehensive evaluation and dynamic regulation capabilities.

[0012] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only some of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0013] It should be noted that the terms "first", "second", etc. in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products or devices.

[0014] Example 1 like Figure 1 As shown, the present application provides a method for dynamic load scheduling of pollution in multiple tributaries of a river basin, the method comprising: P10: Deploy an online monitoring sensor network within the watershed to collect real-time pollution data and upload time-series pollution collection results to the control center to establish a pollution load database.

[0015] Specifically, the primary task of deploying an online monitoring sensor network within the watershed is to ensure the real-time collection of various types of pollution data and upload these data to the control center for subsequent analysis and scheduling. First, multiple sensors need to be deployed at the entrances of key tributaries and water sections within the watershed. These sensors should select appropriate detection methods based on the characteristics of the pollutants. For example, conventional pollutants such as ammonia nitrogen, total phosphorus, and chemical oxygen demand (COD) can be monitored by electrochemical sensors and photometric sensors. At the same time, appropriate sensors should also be configured for emerging pollutants such as antibiotic pollutants.

[0016] These sensors should upload real-time data such as pollution concentration and flow rate to the regional control center through wireless communication modules (such as LoRa, NB-IoT, etc.). The uploaded data includes the pollution concentration of each monitoring point, the corresponding water flow, and other hydrological and meteorological data (such as water temperature, precipitation, etc.). These data will be recorded and organized in chronological order to form time-series pollution data. Real-time collection of pollution data will provide accurate real-time data support for subsequent pollution source analysis, load prediction, and scheduling optimization.

[0017] After the pollution data is uploaded to the control center, the system will use these data to calculate the pollution load. The formula for calculating the pollution load is: pollution load = flow rate x pollution concentration. Through this calculation, the pollution load of each tributary, section, and other monitoring points can be obtained in real time. The control center will store these data in the pollution load database and establish a database based on time-series data to ensure that historical data can be traced back for subsequent analysis and decision-making. By dynamically updating the historical data in the database, the control center can always keep track of the pollution situation of each tributary and section within the watershed. Moreover, as the data volume accumulates, the system can generate the pollution load trend of each tributary, providing a scientific basis for subsequent scheduling decisions.

[0018] On this basis, the pollution load database provides accurate data support for subsequent steps such as pollution source tracing, pollution scheduling, and ecological capacity assessment. Through real-time monitoring and data aggregation, the control center can comprehensively grasp the water quality pollution situation within the watershed, providing strong data support for subsequent pollution source management, implementation of control measures, and ecological restoration assessment.

[0019] P20: Obtain a list of ground pollutants, conduct time-series tracing analysis based on the list of ground pollutants and the pollution load database, and establish a tracing identifier.

[0020] Optionally, the list of ground pollutants is obtained and analyzed, and combined with the pollution load database to conduct time series tracing analysis of the pollutants, thereby establishing the traceability identification. First of all, it is necessary to collect the list of possible ground pollutants in the basin. These pollutants usually come from multiple fields such as agriculture, industry, urban emissions, etc. Therefore, the list of ground pollutants contains all possible substances that can pollute water bodies, such as pesticides, fertilizers, industrial wastewater emissions, toxic heavy metals, plastic particles, antibiotics and other emerging pollutants. The list not only includes common pollutants (such as COD, ammonia nitrogen, total phosphorus), but also covers drug residues, heavy metals and other chemical pollutants.

[0021] Subsequently, based on the list of ground pollutants and real-time monitoring data in the pollution load database, time series tracing analysis is carried out. The pollution load database stores the pollution load data of each tributary and cross section in the basin at different time periods, including the concentration of pollutants at each monitoring point, flow data, etc. This analysis process can use data processing and analysis techniques, combined with the physical and chemical properties of pollutants and hydrological and hydrodynamic conditions, to deeply explore the spatial and temporal distribution characteristics of pollutants in the basin. Specifically, by comparing the pollutant concentration, flow and other data at different time points and different monitoring points, combined with the pollution source information recorded in the list of ground pollutants, the transmission path of the pollutants from the source to the monitoring point can be tracked, and the migration and transformation law of the pollutants in the basin can be analyzed. For example, if a certain monitoring point detects a significant increase in the concentration of a certain pollutant at a certain time period, combined with the hydrological conditions at that time period and the emission records of the corresponding pollution source in the list of ground pollutants, the possible source of the pollutant and its transmission path can be inferred, thereby achieving accurate tracing of the pollutant.

[0022] Finally, based on the results of time series tracing analysis, a traceability identification is established for each pollution source. The traceability identification, as a kind of mark, is used to identify the source of the pollutant, the category of the pollutant, the geographical location of the pollution source and the historical trajectory of the pollution. Through the traceability identification, the control center can track the changes of the pollutants in real time and accurately identify the hot spot areas of pollution in the basin. These traceability identifications not only provide a clear direction for the pollution control of the basin, but also serve as an important basis for decision-making in the subsequent dynamic scheduling of pollution load, helping to develop more scientific and reasonable control strategies. For example, after determining that the main pollutant of a high-pollution load tributary comes from a specific industrial emission source upstream, the traceability identification can be specially marked for the tributary, and the pollution control measures for the tributary, such as adjusting the emission time and optimizing the treatment process, can be prioritized in the subsequent scheduling strategy to reduce its contribution to the pollution of the main stream.

[0023] P30: Collect a dynamic indicator set, the dynamic indicator set including a watershed hydrology, water quality, rainfall, water temperature, a biological indicator set, constructing an ecological capacity time evolution model of pollution background, self-cleaning ability, ecological response according to the dynamic indicator set, and outputting a partition pollutant time-varying carrying threshold.

[0024] Further, the step P30 of the embodiments of the present application further includes: P31: After standardizing the dynamic indicator set, the pollution mutation in the standardization result is removed by using the pollution discharge record, and trend modeling and distribution modeling are performed on each pollution factor according to the pollution mutation removal result, and a pollution background fitting layer is established according to the time sequence modeling result; P32: Extracting a self-cleaning time sequence feature set from the standardization result, performing self-cleaning ability evaluation according to the self-cleaning time sequence feature set, establishing self-cleaning ability time sequence data of each pollutant, and establishing a self-cleaning ability layer based on the self-cleaning ability time sequence data; P33: Extracting biological indicator data and pollutant concentration indicator data in the standardization result, the biological indicator data including biological reaction indicators; P34: Performing critical reaction identification according to the biological indicator data and the pollutant concentration indicator data, and constructing an ecological response layer based on the critical reaction identification result; P35: Constructing an ecological capacity time evolution model according to the pollution background fitting layer, the self-cleaning ability layer, and the ecological response layer.

[0025] It should be understood that after completing the pollutant source tracing analysis in the watershed and establishing the source tracing identification, the next focus is on the dynamic evaluation of the ecological capacity of the watershed, and the dynamic indicator set of the watershed is collected and the ecological capacity time evolution model is constructed, and finally the partition pollutant time-varying carrying threshold is output.

[0026] Firstly, the dynamic indicator set of the watershed is collected, which covers multiple aspects such as watershed hydrology, water quality, rainfall, water temperature and biological indicators. The collection of these indicators aims to provide comprehensive and accurate data support for subsequent model construction. The collection of the dynamic indicator set includes watershed hydrology indicators (such as flow, flow rate, water level, etc.), water quality indicators (in addition to conventional pollutant concentration, detection data of emerging pollutants), rainfall indicators (recording rainfall, rainfall intensity and rainfall time distribution, etc.), water temperature indicators (monitoring the change of water temperature) and biological indicator set (covering biological reaction indicators such as biodiversity index, number of specific biological population, etc.). The collection of these indicators provides basic data for subsequent ecological capacity evaluation.

[0027] Next, the collected dynamic indicator set is standardized. The purpose of standardization is to eliminate the dimensional differences between different indicators, so that they can be compared and analyzed on the same scale. Specific methods can use Z-score standardization, Min-Max standardization and other common techniques. After standardization, the pollution mutation in the results is removed using the pollution record. Pollution mutation is usually caused by sudden pollution events, which have a significant impact on pollutant concentration in the short term, but do not reflect the normal pollution status of the basin. By removing these mutations, the pollution background of the basin can be more accurately assessed. After that, trend modeling and distribution modeling are performed for each pollution factor, and a pollution background fitting layer is established based on the time series modeling results. This fitting layer provides basic pollution background information for subsequent ecological capacity assessment.

[0028] Next, the self-purification time series feature set is extracted from the standardized data, which reflects the self-purification capacity of the water body. Self-purification capacity refers to the ability of a water body to eliminate pollutants through natural processes such as sedimentation and degradation without external intervention. Through analysis of the self-purification time series feature set, self-purification capacity assessment is performed, and self-purification capacity time series data for each pollutant is established. Based on these data, a self-purification capacity layer is further constructed, which can dynamically reflect changes in the self-purification capacity of the water body, providing support for subsequent pollution emission regulation.

[0029] Next, biological indicator data and pollutant concentration indicator data are extracted from the standardized results. Biological indicator data not only includes conventional indicators such as biodiversity index and specific biological population number, but also focuses on biological response indicators. Biological response indicators refer to the sensitive response of organisms to changes in pollutant concentration, such as physiological changes and behavioral changes. These indicators can more directly reflect the degree of influence of pollutants on the ecosystem. At the same time, corresponding pollutant concentration indicator data is extracted to provide a data basis for subsequent critical response identification. Based on the extracted biological indicator data and pollutant concentration indicator data, critical response identification is performed. Critical response refers to the response of biological indicators to significant changes when pollutant concentration reaches a certain threshold. This response usually marks the limit of the ecological system's tolerance to pollutants, and further pollution may cause irreversible damage to the ecological system. By identifying critical responses, the influence threshold of pollutants on the ecological system can be determined, and an ecological response layer can be constructed. The ecological response layer reflects the sensitivity and response degree of the basin's ecological system to changes in pollutant concentration, and is an indispensable part of ecological capacity assessment.

[0030] Finally, the pollution background fitting layer, self-purification capacity layer, and ecological response layer are combined to construct an ecological capacity time evolution model. This model takes into account the changes in pollutant concentration, the improvement of self-purification capacity, and the changes in ecological system response, and can accurately predict the pollutant carrying capacity and ecological capacity of each region in the basin. Through this model, the control center can monitor and adjust pollution emissions in real time, and output the time-varying carrying threshold of pollutants in each region. The time-varying carrying threshold of pollutants in each region refers to the maximum pollutant load that the river basin can bear under specific time and space conditions, and exceeding this threshold may cause irreversible damage to the ecological system. Through the ecological capacity time evolution model, the change of ecological capacity of the river basin can be monitored in real time, providing accurate threshold guidance for dynamic scheduling of pollution load.

[0031] P40: Construct a pollution emission load-ecological capacity adaptation matrix using the pollution load database, the traceability identifier, and the time-varying carrying threshold of pollutants in each region, and use the pollution emission load-ecological capacity adaptation matrix as a constraint to perform dynamic load scheduling optimization and establish a scheduling strategy.

[0032] Further, the step P40 of the embodiments of the present application further includes: P41: Read the basin branch data and flow rate data of the river basin; P42: Perform spatial dependence modeling of upstream and downstream based on the basin branch data and flow rate data to generate spatial dependence modeling results; P43: Configure an objective function based on the spatial dependence modeling results, and the evaluation features of the objective function include carrying adaptation items, pollution load control cost items, load time sequence peak shifting incentive items, and upstream and downstream coordination constraint items; P44: Perform dynamic load scheduling optimization under the constraint of the pollution emission load-ecological capacity adaptation matrix according to the objective function, and establish a scheduling strategy.

[0033] Optionally, by jointly using the pollution load database, the traceability identifier, and the time-varying carrying threshold of pollutants in each region, a pollution emission load-ecological capacity adaptation matrix is constructed, and dynamic load scheduling optimization is performed with this matrix as a constraint, and finally a scientific and reasonable scheduling strategy is established.

[0034] Before constructing the pollution emission load-ecological capacity adaptation matrix, the basin branch data and flow rate data of the river basin need to be read first. The basin branch data records the distribution of each tributary in the river basin, the location of the confluence point, and other information, while the flow rate data reflects the flow speed of the water body in each tributary. These data are crucial for understanding the transmission path and time delay of pollutants in the river basin. By analyzing the basin branch data and flow rate data, the upstream and downstream relationships between each tributary can be determined, providing a basis for subsequent spatial dependence modeling.

[0035] Based on the basin branch data and flow rate data, spatial dependence modeling of upstream and downstream is performed. The modeling process aims to quantify the mutual dependence between branches in terms of pollutant transmission and ecological impact. Specifically, by analyzing the transmission path, transmission time and transmission volume of pollutants between different branches, a spatial dependence model between upstream and downstream is established. This model can reflect the potential impact of pollutant discharge of a branch on downstream branches and the main stream, as well as the response law of downstream to the change of pollutant of upstream. The spatial dependence modeling results provide important spatial dimension information for subsequent scheduling strategy formulation.

[0036] Then, based on the results of spatial dependence modeling, the objective function is configured. The evaluation features of the objective function include the carrying capacity adaptation item, the pollution load regulation cost item, the load time sequence peak shifting incentive item and the upstream and downstream coordination constraint item. Among them, the carrying capacity adaptation item can ensure that the dynamic scheduling of pollutant discharge conforms to the ecological capacity of each region in the basin; the pollution load regulation cost item considers the cost brought by the regulation measures, such as the cost of flow regulation, facility activation, etc.; the load time sequence peak shifting incentive item is used to guide the time-sharing scheduling of pollution load, avoiding the concentrated discharge of pollutants in peak period; and the upstream and downstream coordination constraint item ensures the coordination of pollution discharge between upstream and downstream, avoiding the impact of excessive discharge of upstream on downstream water quality.

[0037] Finally, under the constraint of the pollution discharge load-ecological capacity adaptation matrix, the load dynamic scheduling optimization is performed according to the above objective function. Exemplarily, optimization algorithms such as linear programming, dynamic programming, etc. can be used to find the optimal pollution load scheduling scheme under the premise of meeting the ecological capacity constraint. In the optimization process, various factors such as carrying capacity adaptation, regulation cost, time sequence peak shifting and upstream and downstream coordination are comprehensively considered, so as to realize the effective regulation of pollution load and the rational use of resources while ensuring the ecological safety of the basin. Finally, based on the optimization results, the scheduling strategy is established, which clearly arranges the pollution load discharge of each branch under different time and space conditions, providing scientific decision support for basin pollution control.

[0038] This process not only considers the spatial dependence relationship between branches in the basin, but also balances various regulation requirements, providing strong technical support for the dynamic management of pollution load in the basin and the sustainable development of ecological system.

[0039] Further, the step P44 of the embodiment of the present application further includes: P44-1: randomly generate a population of scheduling schemes that satisfy the constraints, complete population initialization; P44-2: calculate the fitness value of each scheduling individual using the objective function, generate a calculation result; P44-3: perform population individual selection according to the calculation result, perform crossover and mutation operations using the population individual selection result to iteratively update the population; P44-4: when the iterative update result satisfies the termination condition, complete the dynamic load scheduling optimization.

[0040] In a possible embodiment of the present application, the dynamic load scheduling optimization can be further performed by introducing a genetic algorithm (or other optimization algorithm) to obtain the optimal pollution load scheduling strategy.

[0041] When performing dynamic load scheduling optimization, a population of scheduling schemes that satisfy the constraint conditions is first randomly generated, and population initialization is completed. These scheduling scheme populations are randomly generated based on the constraint conditions of the pollution emission load-ecological capacity adaptation matrix, and each scheduling scheme represents a possible pollution load allocation method. By randomly generating these schemes, multiple possibilities can be covered in the search space, ensuring that potential optimal solutions can be found in the subsequent optimization process.

[0042] Subsequently, the fitness value of each scheduling individual is calculated using the objective function, and a calculation result is generated. The objective function comprehensively considers multiple evaluation features such as load adaptation, regulation cost, timing peak shifting, and upstream and downstream collaboration, and the fitness value reflects the optimization degree of each scheduling scheme in satisfying the ecological capacity constraint. By calculating the fitness value of each individual, the advantages and disadvantages of each scheduling scheme can be evaluated.

[0043] Next, population individual selection is performed according to the calculation result, and the selection process can be based on the height of the fitness value to determine whether the individual is selected into the next generation population. Individuals with high fitness values have a higher probability of being selected, thereby preserving excellent scheduling schemes. After the selection operation, crossover and mutation operations are performed using the population individual selection result to iteratively update the population. The crossover operation generates new individuals by combining the features of two or more individuals, and the mutation operation introduces new genetic variations by randomly changing some features of the individual. These operations help to explore a wider solution space and avoid the algorithm from falling into local optimum.

[0044] When the iterative update result satisfies the termination condition, the dynamic load scheduling optimization is completed. The termination condition can be reaching a preset number of iterations, the fitness value changing to be stable, or satisfying a specific optimization precision requirement, etc. Once the termination condition is met, the algorithm stops iteration and outputs the current optimal scheduling scheme as the final dynamic load scheduling strategy.

[0045] The above method based on the population optimization algorithm can effectively find the optimal pollution load scheduling scheme under complex constraints. This process not only considers multiple evaluation characteristics, but also gradually improves the quality of the scheduling scheme through iterative optimization, providing scientific and reasonable decision support for dynamic management of watershed pollution load and sustainable development of the ecological system.

[0046] Further, the population individual selection according to the calculation result comprises the following steps: P44-31: proportionally dividing the population according to the calculation result to establish a first divided population and a second divided population; P44-32: setting an enhanced random factor in the first divided population and a weakened random factor in the second divided population; P44-33: performing random selection of population individuals according to the enhanced random factor and the calculation result of the first divided population to establish a first selection result; P44-34: performing random selection of population individuals according to the weakened random factor and the calculation result of the second divided population to establish a second selection result; and P44-35: fusing the first selection result and the second selection result to complete the population individual selection.

[0047] Optionally, the process of population individual selection can be further refined by proportionally dividing the population and introducing enhanced and weakened random factors to improve the flexibility and diversity of the selection process, thereby improving the global search ability and convergence speed of the optimization algorithm.

[0048] When performing population individual selection, the population is first proportionally divided according to the calculation result. Specifically, the current population is divided into two parts, i.e., a first divided population and a second divided population, according to the fitness value or other evaluation criteria. This division aims to differentially process individuals with different fitness levels to better balance the global search and local search capabilities. For example, individuals with higher fitness values can be classified into the first divided population, while individuals with lower fitness values can be classified into the second divided population, or division can be made according to other specific evaluation criteria.

[0049] An enhanced random factor is set in the first divided population. The role of the enhanced random factor is to increase the randomness of this part of individuals in the selection process, thereby improving the global search ability of the algorithm. The enhanced random factor can be realized by adjusting the selection probability distribution, introducing random disturbance, etc., so that the individuals in the first divided population have higher randomness in the selection process, avoiding the algorithm from falling into local optimum too early.

[0050] In the second split population, a weakening random factor is set. The weakening random factor reduces the randomness of individuals in this part of the population in the selection process, thereby improving the local search ability of the algorithm. The weakening random factor can be realized by reducing the range of selection probability distribution, reducing random disturbance, etc., so that the individuals in the second split population are more inclined to deterministic selection based on fitness value in the selection process, thereby accelerating the convergence of the algorithm.

[0051] According to the calculation results of the first split population and the enhanced random factor, the population individuals are randomly selected to establish the first selection result. In this process, the enhanced random factor makes the individuals in the first split population have higher randomness in selection, which helps to explore a wider solution space and find potential high-quality solutions.

[0052] According to the calculation results of the second split population and the weakening random factor, the population individuals are randomly selected to establish the second selection result. In this process, the weakening random factor makes the individuals in the second split population more inclined to deterministic selection based on fitness value in the selection process, which helps to further optimize the existing high-quality solutions and accelerate the convergence of the algorithm.

[0053] Finally, the first selection result and the second selection result are fused to complete the selection of population individuals. By fusing the selection results of two different randomness levels, a balance between global search and local search can be achieved, avoiding premature convergence into local optimum and quickly converging after finding high-quality solutions. This fusion method can be simple merging or weighted merging based on specific weights, depending on the design and optimization goals of the algorithm.

[0054] This process provides a more effective population individual selection mechanism for load dynamic scheduling optimization, which helps to find the optimal pollution load scheduling scheme under complex constraints.

[0055] Further, the population individual selection result is used to perform crossover and mutation operations. The step P44-3 of the embodiment of the application further includes: P44-36: After the crossover and mutation operations, a gene correction strategy is configured; P44-37: individual correction discrimination is performed according to the gene correction strategy, and the individual is updated using the individual correction discrimination result.

[0056] Specifically, the processing process after the crossover and mutation operations using the population individual selection result can be further refined to ensure that the generated individuals have better adaptability and meet the actual constraint conditions.

[0057] First, configure the genetic correction strategy. The crossover and mutation operations usually generate new individuals, and the genes (i.e., scheduling schemes) of these new individuals may contain parts that do not meet the problem constraints or actual requirements, resulting in a decrease in the fitness of the individuals. The configuration of the genetic correction strategy aims to correct the individuals after crossover and mutation, ensuring that the generated individuals still improve in fitness while meeting the constraint conditions. These correction strategies may include adjusting parts that do not meet scheduling rules, optimizing unreasonable time sequences, or ensuring that the adjustments still comply with ecological capacity constraints, etc.

[0058] Next, according to the configured genetic correction strategy, the individuals generated after the crossover and mutation operations are corrected and distinguished. Specifically, first, each newly generated individual is checked for constraint conditions to verify whether it meets the constraints of the pollution emission load-ecological capacity adaptation matrix, such as whether it exceeds the ecological capacity threshold, whether the pollution load allocation is reasonable, etc. If the individual meets the constraint conditions, it is retained; if it does not meet the constraint conditions, it is adjusted according to the pre-set correction rules. The correction rules may include adjusting certain gene values of the individual to make it meet the constraint conditions again, or optimizing the individual through a specific repair algorithm.

[0059] After completing the constraint condition check and correction, the individuals in the population are updated according to the correction results. The corrected individuals will replace the original individuals that do not meet the constraint conditions, ensuring that each individual in the population meets the requirements of the optimization algorithm. At the same time, during the correction process, specific information about the correction is recorded, including the state of the individual before and after the correction, the application of the correction rules, etc. This information can be used for subsequent analysis and optimization, helping to further improve the genetic correction strategy.

[0060] By configuring the genetic correction strategy and correcting and updating the individuals, the stability and effectiveness of the optimization algorithm can be effectively ensured. This process not only avoids the entry of individuals that do not meet the constraint conditions due to crossover and mutation operations into subsequent iterations, but also improves the convergence speed of the algorithm and the quality of the solution, providing a more reliable mechanism for load dynamic scheduling optimization, which helps to find the optimal pollution load scheduling scheme under complex constraint conditions.

[0061] P50: performing load dynamic scheduling management according to the scheduling strategy.

[0062] Further, the step P50 of the embodiments of the present application further includes: P51: calling the deployed online monitoring sensor network to perform basin pollution monitoring and establish a feedback time series dataset; P52: performing response consistency verification of the scheduling strategy according to the feedback time series dataset to generate a verification result; P53: updating the scheduling strategy according to the verification result.

[0063] It should be understood that the load dynamic scheduling management is performed according to the previously determined scheduling strategy. The core goal of this process is to ensure that through the optimized scheduling strategy, the pollution load can be efficiently managed in actual operation, and it is ensured that the water quality of the river basin is always within a safe range.

[0064] Firstly, the deployed online monitoring sensor network is called to perform real-time monitoring of pollutants in the river basin. Through the sensor network, the pollutant concentration, flow and other data of each monitoring point in the river basin are obtained and uploaded to the control center in real time. These data will form a feedback time series dataset, representing the changing trend of pollutants and the real-time dynamics of pollution load in the river basin. Through these feedback data, the system can monitor the effect of the scheduling strategy after execution in real time, ensuring that the pollutant discharge is within the predetermined range.

[0065] Then, according to the obtained feedback time series dataset, the executed scheduling strategy is verified for response consistency. The purpose of response consistency verification is to check whether the scheduling strategy meets the expected goal in actual operation and can effectively respond to changes in pollutant concentration. For example, the system will compare the actual pollution load in the feedback dataset with the target value set in the scheduling strategy to analyze the execution effect of the scheduling strategy at different times and regions. If there is a deviation between the actual response and the expected target, further analysis is needed to find out the reason for the deviation, such as whether it is caused by errors in monitoring data, unreasonable model assumptions or external environmental changes.

[0066] Finally, according to the verification result, the scheduling strategy is updated. If the verification result shows that the response consistency of the scheduling strategy is good, it means that the current strategy can effectively achieve dynamic scheduling of pollution load and can continue to be executed. However, if the verification result shows that there is a significant deviation, the scheduling strategy needs to be adjusted according to the information in the feedback time series dataset. The adjustment may include reconfiguring pollution load allocation, optimizing scheduling time window, adjusting branch discharge sequence, etc., to ensure that the scheduling strategy can better adapt to the actual situation of the river basin and achieve effective control of pollution load and rational use of ecological capacity.

[0067] This process not only can monitor the pollution status of the river basin in real time, but also can dynamically adjust the scheduling strategy according to the actual situation, to ensure that it always meets the goals and requirements of river basin pollution control, so as to achieve precise control of pollutants, improve management effect, and ultimately protect the stability of water quality and ecological safety of the river basin.

[0068] Further, the step P51 of the embodiment of the present application further includes: P51-1: performing ecological species distribution analysis of the river basin, configuring key monitoring points; P51-2: setting ecological monitoring points at the key monitoring points, establishing ecological change indicators; P51-3: adding the ecological change indicators to the feedback time series dataset.

[0069] Specifically, in addition to performing real-time monitoring of pollutants in the watershed, further ecological species distribution analysis and configuration of key monitoring points are included, aiming to ensure that the pollutant scheduling strategy not only effectively manages water quality, but also monitors the health status of the watershed ecosystem in real time, to achieve comprehensive environmental protection.

[0070] First, before performing watershed pollution monitoring, an ecological species distribution analysis of the watershed is conducted. This analysis aims to comprehensively understand the distribution of different ecological species within the watershed, including fish, benthic animals, plankton, etc. Through ecological species distribution analysis, key areas and species sensitive to changes in pollutants can be identified, and the health status of these areas and species can reflect the overall health status of the watershed ecosystem. Based on the results of ecological species distribution analysis, key monitoring points are configured, which should cover ecologically sensitive areas and major tributary confluence points in the watershed, etc., to ensure that monitoring data can comprehensively reflect the response of the watershed ecosystem.

[0071] Next, ecological monitoring points are set up in the key ecological areas or habitats identified in the above analysis. These monitoring points will be used to collect ecological change indicators of ecological species in real time, which can include biodiversity index, population number change of specific species, biological health indicators (such as growth rate of fish, reproduction rate, etc.), and other indicators reflecting the health status of the ecosystem. Through these monitoring points, the system can detect changes in ecological species in a timely manner, especially the response to changes in pollutant concentration. For example, when the concentration of pollutants exceeds the safety threshold, sensitive ecological species may show signs of population reduction, population diversity decline, etc. Through monitoring of these changes, timely feedback can be provided for adjustment of pollution control measures.

[0072] Finally, the collected ecological change indicators will be added to the feedback time series data set. These ecological change indicators are long-term feedback data, reflecting the gradual changes of the ecosystem during the pollution load scheduling process. This data set, together with the time series data set of pollutants, forms a comprehensive environmental change database. Through this database, the system can not only monitor changes in pollutants, but also track the response and recovery of the ecosystem. Over time, the system can observe the gradual recovery or degradation of the ecosystem, thereby continuously optimizing the scheduling strategy to ensure that the discharge of pollutants in the watershed does not cause irreversible damage to the ecosystem.

[0073] This process not only enables real-time monitoring of the pollution status of the watershed, but also assesses the long-term health status of the ecosystem, ensuring that the regulation of pollutants not only focuses on water quality itself, but also considers the health of the ecosystem, ultimately achieving the dual goals of water quality protection and ecological restoration.

[0074] To sum up, the embodiments of the present application have at least the following technical effects: The present application collects pollutant data in real time through an online sensor network and establishes a pollution load database, realizes dynamic monitoring of pollutants in the basin and real-time evaluation of pollution load, combines the ground pollutant list and the pollution load database for time series tracing analysis, accurately identifies the pollution sources and their spatio-temporal distribution, provides a scientific basis for pollution scheduling, optimizes the pollution load scheduling strategy by constructing a pollution emission load-ecological capacity adaptation matrix, ensures effective matching of pollution emission and ecological capacity, and protects water quality within the ecological safety range, uses multi-dimensional data to perform real-time feedback and optimization of the scheduling strategy, and improves pollution control efficiency, and promotes the intelligent and scientific development of basin pollution control in combination with hydrological, water quality, ecological and other dynamic indicators.

[0075] The technical effect of improving the accuracy of pollution emission load scheduling in the basin through multi-dimensional water environment big data evaluation and dynamic control management is achieved.

[0076] Embodiment 2

[0077] Based on the same inventive concept as the pollution load dynamic scheduling method of the multi-tributary basin in the foregoing embodiments, as shown in Figure 2 The present application provides a pollution load dynamic scheduling system for a multi-tributary basin, and the system and method embodiments in the present application are based on the same inventive concept. The system comprises: A pollutant data acquisition module 11 is configured to deploy an online monitoring sensor network within the basin, acquire pollutant data in real time, and upload time series pollutant acquisition results to a control center to establish a pollution load database.

[0078] A time series tracing analysis module 12 is configured to obtain a ground pollutant list, perform time series tracing analysis according to the ground pollutant list and the pollution load database, and establish a tracing identifier.

[0079] A time-varying carrying threshold generation module 13 is configured to acquire a dynamic index set, the dynamic index set comprising basin hydrology, water quality, rainfall, water temperature, and a biological index set, construct an ecological capacity time series evolution model of pollution background, self-purification capacity, and ecological response according to the dynamic index set, and output a partition pollutant time-varying carrying threshold.

[0080] A load dynamic scheduling optimization module 14 is configured to jointly construct a pollution emission load-ecological capacity adaptation matrix using the pollution load database, the tracing identifier, and the partition pollutant time-varying carrying threshold, use the pollution emission load-ecological capacity adaptation matrix as a constraint, perform load dynamic scheduling optimization, and establish a scheduling strategy.

[0081] a load dynamic scheduling management module 15, configured to perform load dynamic scheduling management according to the scheduling strategy.

[0082] Further, the time-varying carrying threshold generation module 13 is further configured to perform the following steps: After standardizing the dynamic index set, the pollution mutation in the standardization result is removed by using the pollution emission record, trend modeling and distribution modeling are performed on each pollution factor according to the pollution mutation removal result, and a pollution background fitting layer is established according to the time sequence modeling result; self-purification time sequence feature sets are extracted from the standardization result, self-purification capacity evaluation is performed according to the self-purification time sequence feature sets, self-purification capacity time sequence data of each pollutant is established, and a self-purification capacity layer is established based on the self-purification capacity time sequence data; biological index data and pollutant concentration index data in the standardization result are extracted, the biological index data including biological reaction indicators; critical reaction identification is performed according to the biological index data and the pollutant concentration index data, and an ecological response layer is constructed based on the critical reaction identification result; and an ecological capacity time sequence evolution model is constructed according to the pollution background fitting layer, the self-purification capacity layer and the ecological response layer.

[0083] Further, the load dynamic scheduling optimization module 14 is further configured to perform the following steps: The basin branch data and the flow rate data of the basin are read, spatial dependence modeling of upstream and downstream is performed according to the basin branch data and the flow rate data, and a spatial dependence modeling result is generated; a target function is configured based on the spatial dependence modeling result, evaluation features of the target function including carrying adaptation items, pollution load regulation cost items, load time sequence peak shifting incentive items and upstream and downstream collaborative constraint items; load dynamic scheduling optimization is performed according to the target function under the constraint of the pollution emission load-ecological capacity adaptation matrix, and a scheduling strategy is established.

[0084] Further, the load dynamic scheduling optimization module 14 is further configured to perform the following steps: A scheduling scheme population meeting the constraint is randomly generated, and population initialization is completed; the fitness value of each scheduling individual is calculated by using the target function, and a calculation result is generated; population individual selection is performed according to the calculation result, and crossover and mutation operations are performed by using the population individual selection result to iteratively update the population; when the iterative update result meets the termination condition, the load dynamic scheduling optimization is completed.

[0085] Further, the load dynamic scheduling optimization module 14 is further configured to perform the following steps: According to the calculation result, proportionally divide the population to establish a first divided population and a second divided population; set an enhanced random factor in the first divided population and a weakened random factor in the second divided population; according to the enhanced random factor and the calculation result of the first divided population, randomly select population individuals to establish a first selection result; according to the weakened random factor and the calculation result of the second divided population, randomly select population individuals to establish a second selection result; and fuse the first selection result and the second selection result to complete the selection of population individuals.

[0086] Further, the load dynamic scheduling optimization module 14 is further used to execute the following steps: After the crossover and mutation operations, a gene correction strategy is configured; individual correction discrimination is performed according to the gene correction strategy, and the individual is updated by using the individual correction discrimination result.

[0087] Further, the load dynamic scheduling management module 15 is further used to execute the following steps: The deployed online monitoring sensor network is called to perform the drainage basin pollution monitoring, and a feedback time series data set is established; the response consistency of the scheduling strategy is verified according to the feedback time series data set, and a verification result is generated; and the scheduling strategy is updated according to the verification result.

[0088] Further, the load dynamic scheduling management module 15 is further used to execute the following steps: The ecological species distribution analysis of the drainage basin is performed, and a key monitoring point is configured; an ecological monitoring point is set at the key monitoring point, and an ecological change index is established; and the ecological change index is added to the feedback time series data set.

[0089] Embodiment 3

[0090] Based on the same inventive concept as the load dynamic scheduling method for drainage basin multi-tributary pollution in the foregoing embodiments, the present application also provides a computer readable storage medium, and the storage medium stores a computer program, and the computer program is executed by a processor to realize the method in Embodiment 1.

[0091] Through the foregoing detailed description of the load dynamic scheduling method for drainage basin multi-tributary pollution, those skilled in the art can clearly understand the load dynamic scheduling method for drainage basin multi-tributary pollution, the system and the medium in the embodiment. Therefore, in order to make the specification simple, it will not be described in detail here. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the related parts are described in the method part.

[0092] The above description of disclosed embodiments enables one of ordinary skill in the art to make and use the application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein can be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0093] It should be noted that the above-mentioned order of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. And the above describes the specific embodiments of the present application. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are possible or can be advantageous.

[0094] The above description is only the preferred embodiments of the present application, and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0095] The specification and drawings are merely exemplary of the present application, and any and all modifications, variations, combinations or equivalents that are within the scope of the present application should be considered covered by the present application. Obviously, those skilled in the art can make various modifications and changes to the present application without departing from the scope of the present application. Thus, if these modifications and changes of the present application belong to the scope of the present application and its equivalent technology, the present application is intended to include these modifications and changes.

Claims

1. A method for dynamic load scheduling of pollution in multiple tributaries of a river basin, characterized by: The method comprises: Deploy an online monitoring sensor network in the watershed to collect pollutant data in real time, upload the time series pollutant collection results to the control center, and establish a pollution load database; Obtaining a list of ground pollutants, performing a time series source tracing analysis based on the list of ground pollutants and the pollution load database, and establishing a source tracing identification; Collect dynamic indicator sets, including basin hydrology, water quality, rainfall, water temperature, and biological indicators, and construct an ecological capacity time-series evolution model based on the pollution background, self-purification capacity, and ecological response, and output the time-varying pollutant carrying threshold of the sub-region; The pollution load database, the source identification, and the time-varying pollutant carrying threshold of the partition are used to jointly construct a pollution emission load-ecological capacity adaptation matrix, and the pollution emission load-ecological capacity adaptation matrix is ​​used as a constraint to perform load dynamic scheduling optimization and establish a scheduling strategy; Dynamic load dispatch management is performed according to the dispatch strategy.

2. The method for dynamic load scheduling of pollution in multiple tributaries of a river basin as claimed in claim 1, characterized in that: The method of constructing an ecological capacity time series evolution model of pollution background, self-purification capacity, and ecological response based on the dynamic indicator set and outputting a time-varying carrying threshold of pollutants in different regions includes: After standardizing the dynamic indicator set, pollution mutations in the standardization results are eliminated using pollution discharge records, trend modeling and distribution modeling are performed on each pollution factor based on the pollution mutation elimination results, and a pollution background fitting layer is established based on the time series modeling results; Extracting a self-purification time series feature set from the standardized processing result, performing a self-purification capacity assessment based on the self-purification time series feature set, establishing self-purification capacity time series data for each pollutant, and establishing a self-purification capacity layer based on the self-purification capacity time series data; Extracting biological indicator data and pollutant concentration indicator data from the standardized processing results, wherein the biological indicator data includes biological response indicators; Identify critical reactions based on the biological indicator data and pollutant concentration indicator data, and construct an ecological response layer based on the critical reaction identification results; An ecological capacity time series evolution model is constructed based on the pollution background fitting layer, the self-purification capacity layer, and the ecological response layer.

3. The method for dynamic load scheduling of pollution loads of multiple tributaries in a river basin as claimed in claim 1, characterized in that: The method uses the pollution emission load-ecological capacity adaptation matrix as a constraint, performs load dynamic scheduling optimization, and establishes a scheduling strategy, including: Read the watershed branch data and flow rate data of the watershed; Performing upstream and downstream spatial dependency modeling based on the watershed branch data and flow velocity data to generate a spatial dependency modeling result; Configuring an objective function based on the spatial dependency modeling result, wherein the evaluation characteristics of the objective function include a load adaptation item, a pollution load control cost item, a load time sequence peak shifting incentive item, and an upstream and downstream coordination constraint item; According to the objective function and under the constraints of the pollution emission load-ecological capacity adaptation matrix, load dynamic scheduling optimization is performed to establish a scheduling strategy.

4. The method for dynamic load scheduling of pollution in multiple tributaries of a river basin as claimed in claim 3, characterized in that: The performing load dynamic scheduling optimization according to the objective function under the constraint of the pollution emission load-ecological capacity adaptation matrix includes: Randomly generate a population of scheduling solutions that meet the constraints and complete population initialization; Calculating the fitness value of each scheduling individual using the objective function to generate a calculation result; Performing population individual selection according to the calculation results, and performing crossover and mutation operations using the population individual selection results to iteratively update the population; When the iterative update result meets the termination condition, the load dynamic scheduling optimization is completed.

5. The method for dynamic load scheduling of pollution of multiple tributaries in a river basin as claimed in claim 4, characterized in that: The performing of population individual selection according to the calculation result includes: Performing proportional division of the population according to the calculation results to establish a first divided population and a second divided population; Set the enhancement random factor in the first split population and the reduction random factor in the second split population; Performing random selection of population individuals according to the enhanced random factor and the calculation result of the first split population to establish a first selection result; Perform random selection of individuals in the population according to the attenuated random factor and the calculation result of the second split population to establish a second selection result; The first selection result and the second selection result are integrated to complete the population individual selection.

6. The method for dynamic load scheduling of pollution in multiple tributaries of a river basin as claimed in claim 4, characterized in that: The crossover and mutation operations are performed using the population individual selection results, including: After crossover and mutation operations, configure the gene correction strategy; Individual correction discrimination is performed according to the gene correction strategy, and the individual is updated using the individual correction discrimination result.

7. The method for dynamic load scheduling of pollution in multiple tributaries of a river basin as claimed in claim 1, characterized in that: The dynamic load dispatch management according to the dispatch strategy includes: Call the deployed online monitoring sensor network to perform watershed pollution monitoring and establish a feedback time series dataset; Performing response consistency verification of the scheduling strategy according to the feedback time series data set to generate a verification result; The scheduling strategy is updated according to the verification result.

8. The method for dynamic load scheduling of pollution loads of multiple tributaries in a river basin as claimed in claim 7, characterized in that: The calling of the deployed online monitoring sensor network to perform watershed pollution monitoring and establish a feedback time series data set includes: Perform ecological species distribution analysis of the watershed and configure key monitoring points; Set up ecological monitoring points at the key monitoring points and establish ecological change indicators; The ecological change indicator is added to the feedback time series dataset.

9. Dynamic load dispatching system for pollution of multiple tributaries in a river basin, characterized by: The system comprises: A pollutant data collection module is used to deploy an online monitoring sensor network in the watershed to collect pollutant data in real time, upload the time series pollutant collection results to the control center, and establish a pollution load database; A time series source tracing analysis module is used to obtain a list of ground pollutants, perform time series source tracing analysis based on the list of ground pollutants and the pollution load database, and establish a source tracing identification; A time-varying carrying capacity threshold generation module is used to collect a dynamic indicator set, including a watershed hydrology, water quality, rainfall, water temperature, and biological indicator set. Based on the dynamic indicator set, a time-series evolution model of ecological capacity for pollution background, self-purification capacity, and ecological response is constructed to output a time-varying pollutant carrying capacity threshold for each zone. A load dynamic scheduling optimization module is used to jointly construct a pollution emission load-ecological capacity adaptation matrix using the pollution emission load database, the traceability identifier, and the time-varying carrying threshold of the zoned pollutants, and to perform load dynamic scheduling optimization and establish a scheduling strategy using the pollution emission load-ecological capacity adaptation matrix as a constraint; A load dynamic scheduling management module is used to perform load dynamic scheduling management according to the scheduling strategy.

10. A computer-readable storage medium, characterized in that The storage medium stores a computer program, which implements the method steps according to any one of claims 1 to 8 when executed by a processor.

Images