Green infrastructure spatial layout optimization system and method based on improved multi-objective optimization algorithm

Abstract

The invention discloses a green infrastructure spatial layout optimization system and method based on an improved multi-objective optimization algorithm, and the method comprises the steps: obtaining rainfall, soil humidity, drainage network pressure and other environmental data through a real-time data collection module, and carrying out the data preprocessing and fusion through a Kalman filter and a weighted average method. And then, based on a multi-objective optimization model of the full life cycle cost and the runoff control efficiency, performing optimization calculation through an improved NSGA-III algorithm, and generating an optimal green infrastructure layout scheme. The system can dynamically adjust constraint conditions according to real-time monitoring data, and the feasibility and high efficiency of an optimization scheme in practical application are ensured. And finally, implementing an optimization scheme through an execution mechanism module, including adjusting a drainage path and optimizing green infrastructure layout. According to the method, the hydrological regulation and control capability of the city can be remarkably improved while the construction and operation and maintenance cost is reduced, and effective technical support is provided for sustainable development of the city.

Description

Technical Field

[0001] The present invention relates to the technical field of green facility planning and optimization, and particularly relates to a method and system for optimizing the spatial layout of green infrastructure based on an improved multi-objective optimization algorithm. Background Art

[0002] With the acceleration of the global urbanization process, urbanization has brought serious environmental and hydrological challenges, especially the problem of stormwater management. Traditional urban stormwater management usually relies on "hard" infrastructure (such as pipe systems, drainage systems, etc.) to control rainwater runoff. However, with the improvement of the urbanization level, traditional "hard" infrastructure can no longer effectively cope with the rapidly growing urban rainwater discharge and complex hydrological problems, especially in the case of frequent extreme weather events.

[0003] Green Infrastructure (GI) is a kind of facility that uses natural or mimics natural processes to improve stormwater management, water quality and provide ecological services. Compared with traditional "hard" infrastructure, green infrastructure has good environmental adaptability and sustainability, such as permeable pavements, green roofs, rain gardens, etc., which can effectively reduce urban flood disasters, reduce runoff pollution, increase urban green spaces, etc. Green infrastructure not only helps to manage rainwater runoff, but also can improve air quality, enhance biodiversity, etc.

[0004] However, although green infrastructure plays an increasingly important role in urban stormwater management, in the actual application process, how to reasonably layout these green infrastructures to achieve the optimal hydrological control effect and the lowest life cycle cost is still a key problem that has not been solved.

[0005] In the prior art, although there are various optimization algorithms applied to the layout of green infrastructure, most of them rely on static data and models, lack the ability of dynamic adjustment and real-time feedback, and cannot balance the life cycle cost and benefits, resulting in unsatisfactory effects in actual applications. Summary of the Invention

[0006] Technical Objectives: Aiming at the deficiencies of the existing optimization of the spatial layout of green infrastructure, the present invention discloses a method and system for optimizing the spatial layout of green infrastructure based on an improved multi-objective optimization algorithm. This method can reduce the life cycle cost, improve the runoff control efficiency and water quality treatment effect by real-time monitoring and dynamic adjustment of the optimization scheme.

[0007] Technical Solutions: To achieve the above technical objectives, the present invention adopts the following technical solutions:

[0008] A method for optimizing the spatial layout of green infrastructure based on an improved multi-objective optimization algorithm, comprising the following steps:

[0009] By deploying multiple sensors, including drainage network pressure sensors, soil moisture sensors, and rainfall monitoring sensors, rainfall intensity, soil moisture, and pipe network pressure data in the green infrastructure area are collected in real time;

[0010] Preprocess the collected data, use a Kalman filter to denoise the multi-source data, and fuse the data by the weighted average method to form unified format data that can be used for subsequent optimization calculations;

[0011] Based on the preprocessed data, construct an optimization model for the spatial layout of green infrastructure. The optimization objectives include the life cycle cost, runoff control efficiency, and water quality control efficiency. The objective function is:

[0012] f cost-eff =α·f cost +β·f efficiency

[0013] where f cost represents the life cycle cost, and the life cycle is the construction and operation of green infrastructure. f efficiency represents the runoff control efficiency. α and β are the weight coefficients of the optimization objectives, and α + β = 1;

[0014] Use the improved NSGA-III algorithm for multi-objective optimization. Introduce the priority matching rule during the optimization process to reasonably balance different optimization objectives and avoid falling into local optimal solutions;

[0015] During the optimization process, ensure that the optimization plan is adjusted according to real-time data by dynamically adjusting the constraint conditions;

[0016] Compare the simulation results with the real-time monitoring data, calculate the deviation, and use the feedback mechanism to adjust the optimization results to ensure the practical feasibility of the optimization plan.

[0017] Preferably, the calculation formula for the life cycle cost f cost is:

[0018]

[0019] where C i represents the unit construction cost of the i-th type of green infrastructure, A i is the area of the i-th type of green infrastructure, represents the unit maintenance cost of the j-th type of green infrastructure, is the maintenance area of the j-th type of green infrastructure, and r and m respectively represent the number of green infrastructure categories and the number of maintenance categories.

[0020] Preferably, the runoff control efficiency fefficiency The calculation formula is as follows:

[0021]

[0022] Among them, Q k is the flow of the k-th green infrastructure, C k is the water quality control efficiency of the k-th green infrastructure, and n represents the number of green infrastructures in the optimization area.

[0023] Preferably, the improved NSGA-III algorithm adopts a two-layer reference point division strategy, and introduces a priority matching rule in the crossover operation. After the parent individuals are sorted according to the cost-efficiency ratio, a directed crossover operation is performed.

[0024] Preferably, the feedback mechanism includes comparing the simulation results of the optimization scheme with real-time monitoring data, calculating the error and optimizing the results by dynamically adjusting the optimization parameters.

[0025] The present invention also provides a green infrastructure spatial layout optimization system based on an improved multi-objective optimization algorithm, which is characterized in that it is used to implement a green infrastructure spatial layout optimization method based on an improved multi-objective optimization algorithm as described above, including:

[0026] A data acquisition module, which arranges drain pipe network pressure sensors, soil humidity sensors, and rainfall monitoring sensors to collect relevant environmental data of the green infrastructure area in real time;

[0027] A data preprocessing module, which receives the data transmitted by the data acquisition module, denoises the data using a Kalman filter, and performs data fusion using a weighted average method to generate unified format data required for optimization;

[0028] An optimization calculation module, which based on the fused data, uses the improved NSGA-III algorithm to calculate the optimal layout scheme of the green infrastructure, and the optimization objectives include the life cycle cost, runoff control efficiency, and water quality control efficiency;

[0029] A dynamic constraint adjustment module, which dynamically adjusts the constraint conditions of the optimization model according to real-time monitoring data to achieve real-time optimization;

[0030] A feedback control module, which compares the optimization results with real-time monitoring data, calculates the deviation and adjusts the optimization scheme to ensure its actual effectiveness;

[0031] An actuator module, which executes the adjustment of the green infrastructure layout according to the optimization scheme.

[0032] Preferably, the optimization calculation module includes:

[0033] An objective function calculation unit for calculating and weighing the life-cycle cost and runoff control efficiency of green infrastructure;

[0034] A multi-objective optimization unit for executing an improved NSGA-III algorithm to generate an optimized solution set and perform objective balancing.

[0035] Preferably, the dynamic constraint adjustment module dynamically adjusts constraints according to the pressure of the drainage pipe network and soil moisture, specifically including: when the pressure of the drainage pipe network exceeds the standard, automatically adjusting the upper limit range of the cost constraint to 10% to 30%; when the soil moisture exceeds the set value, automatically adjusting the weight coefficient of the aquifer green infrastructure, with a range of 0.3 to 0.5 times.

[0036] Preferably, the actuator module includes an array of electric control valves, which can adjust the drainage path according to the optimization result and ensure the flexibility and stability of the system.

[0037] Preferably, it further includes a redundant communication module, which automatically switches to a standby communication network when the main communication link is interrupted to ensure the stable operation of the system.

[0038] Beneficial effects: A method and system for optimizing the spatial layout of green infrastructure based on an improved multi-objective optimization algorithm provided by the present invention have the following beneficial effects:

[0039] 1. By combining real-time data collection and a dynamic constraint adjustment mechanism, the present invention realizes the dynamic optimization of the layout of green infrastructure. When the pressure of the drainage pipe network exceeds the preset threshold or the soil moisture exceeds the set value, the optimization model can automatically adjust the constraint conditions, such as increasing the upper limit of the cost constraint or increasing the weight coefficient of the water storage facility, to ensure that in extreme weather or sudden hydrological changes, the system can quickly respond and optimize the layout of green infrastructure, avoiding problems such as urban waterlogging. This dynamic optimization ability makes the present invention highly adaptable and operable in practical applications.

[0040] 2. The present invention adopts an improved NSGA-III algorithm and achieves a balance between the life-cycle cost and runoff control efficiency through dynamic weight coefficients α and β. Through multi-objective optimization, the optimization scheme not only considers the construction and operation and maintenance costs of green infrastructure, but also comprehensively considers benefits such as water quality control and runoff management, ensuring that the final scheme can achieve the best balance between economy and environmental benefits and avoiding resource waste and insufficient efficiency caused by a single optimization objective in traditional methods.

[0041] 3. Through the feedback mechanism and dynamic adjustment, the present invention ensures the feasibility of the optimization scheme in practical applications. When there is a deviation between the simulation results of the optimization scheme and the real-time monitoring data, the system can automatically adjust the optimization parameters to ensure that the scheme continuously adapts to the changes in the actual environment. For example, when the soil humidity is too high, the system can adjust the weight of the water storage facilities of the green infrastructure to optimize its hydrological control effect. This mechanism enhances the sustainability of the green infrastructure in dealing with urban rainwater management and improving the efficiency of water quality treatment, and promotes the long-term operation of the urban hydrological ecosystem. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art.

[0043] Figure 1 It is the overall flowchart of the method for optimizing the spatial layout of the green infrastructure of the present invention;

[0044] Figure 2 It is the overall block diagram of the system for optimizing the spatial layout of the green infrastructure of the present invention;

[0045] Figure 3 It is the schematic diagram of the working process of the data preprocessing module of the present invention;

[0046] Figure 4 It is the schematic diagram of the application of the improved NSGA-III algorithm of the present invention in the multi-objective optimization process. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0047] The following will more clearly and completely illustrate the present invention by way of a preferred embodiment in conjunction with the drawings, but the present invention is not limited to the scope of the described embodiments.

[0048] As Figure 1 shown, a method for optimizing the spatial layout of green infrastructure based on an improved multi-objective optimization algorithm includes the following steps:

[0049] S1. By deploying a plurality of sensors, including drainage network pressure sensors, soil humidity sensors, and rainfall monitoring sensors, the rainfall intensity, soil humidity, and network pressure data in the green infrastructure area are collected in real time;

[0050] In order to realize the real-time monitoring of the urban hydrological conditions, a sensor network is first deployed in key areas. The functions of each type of sensor are as follows:

[0051] Drainage network pressure sensor: Installed at the intersection nodes of the urban drainage network, it is used to monitor the pressure in the drainage network in real time. Through the change of the network pressure, it can be inferred whether the drainage capacity has reached saturation, and timely feedback whether the drainage system can handle the new precipitation.

[0052] Soil moisture sensor: Buried under green infrastructure (such as rain gardens, permeable pavements, etc.), it monitors the soil moisture changes in real time. This data helps to evaluate the soil permeability and rainwater retention capacity.

[0053] Rainfall monitoring sensor: By deploying multiple rainfall monitoring points, it collects data such as rainfall intensity and cumulative rainfall in real time. These data directly affect the calculation of runoff and the configuration of green infrastructure.

[0054] S2. Preprocess the collected data. Use the Kalman filter to denoise the multi-source data, and fuse the data by the weighted average method to form a unified format data for subsequent optimization calculations.

[0055] The original data collected by the sensor usually contains noise and inconsistencies, which will affect the accuracy of the optimization model. Therefore, the Kalman filter is used for data denoising. The Kalman filter can extract useful signals from multi-dimensional data and remove the noise caused by the external environment.

[0056] Then, use the weighted average method to fuse the data from different sensors. For example, the pipe network pressure, soil moisture and rainfall data come from different sensors. Use the weighted average to integrate them into a unified data set to ensure that the subsequent optimization calculations can be based on consistent and accurate data.

[0057] S3. Based on the preprocessed data, construct an optimization model for the spatial layout of green infrastructure. The optimization objectives include the life-cycle cost, runoff control efficiency and water quality control efficiency. The objective function is:

[0058] f cost-eff =α·f cost +β·f efficiency

[0059] Among them, f cost represents the life-cycle cost. The life cycle is the construction and operation of green infrastructure. The life-cycle cost covers the construction cost, operation and maintenance cost of green infrastructure, etc. f efficiency represents the runoff control efficiency, which reflects the higher the control ability of green infrastructure for precipitation runoff, the more effective the rainwater retention and infiltration. α and β are the weight coefficients of the optimization objectives, and α + β = 1;

[0060] By adjusting the weight coefficients α and β, the cost or efficiency can be prioritized according to different needs. This process uses multiple data sources (such as soil moisture, rainfall, etc.) to construct an optimal layout model and ensures that the scheme can find the best balance between economic benefits and environmental benefits.

[0061] In one embodiment, the full - life - cycle cost f cost is calculated by the formula:

[0062]

[0063] where C i represents the unit construction cost of the i - th type of green infrastructure, A i is the area of the i - th type of green infrastructure, represents the unit maintenance cost of the j - th type of green infrastructure, is the maintenance area of the j - th type of green infrastructure, and r and m respectively represent the number of green infrastructure categories and the number of maintenance categories;

[0064] By calculating the construction and maintenance costs of various types of green infrastructure, a comprehensive full - life - cycle cost is obtained. This formula helps to consider the construction cost and long - term operation and maintenance cost of the infrastructure during the optimization process, ensuring that when optimizing the layout of green infrastructure, the hydrological control effect can be maximized within a reasonable budget.

[0065] In one embodiment, the runoff control efficiency f efficiency is calculated by the formula:

[0066]

[0067] where Q k is the flow of the k - th green infrastructure, such as the rainwater collection volume of facilities like green roofs and rain gardens, C k is the water quality control efficiency of the k - th green infrastructure, i.e., the ability of this infrastructure to improve water quality, and n represents the number of green infrastructures in the optimized area.

[0068] The significance of this formula is to obtain the overall runoff control efficiency by calculating the hydrological control benefits of each green infrastructure. During the optimization process, this value is used to measure the effect of green infrastructure in controlling rainwater runoff, so that the optimization scheme can reduce the facility construction cost while meeting the requirements of water quality and water volume control.

[0069] S4. Use the improved NSGA - III algorithm for multi - objective optimization. During the optimization process, introduce the priority matching rule to reasonably balance different optimization objectives to avoid falling into local optimal solutions;

[0070] The present invention uses the improved NSGA - III algorithm, such as Figure 4As shown, this algorithm can find the Pareto optimal solution among multiple optimization objectives. NSGA-III is an algorithm for multi-objective optimization problems, especially suitable for dealing with the trade-off problems among multiple objectives. By introducing the priority matching rule, the present invention can ensure that during the optimization process, a reasonable balance is achieved among different objectives (such as cost, efficiency, etc.), avoiding over-optimization under a single objective and thus falling into a local optimal solution. This algorithm generates the optimal solution set through the population evolution and selection process, ensuring the global optimality of the green infrastructure layout.

[0071] In one embodiment, the improved NSGA-III algorithm adopts a two-layer reference point division strategy and introduces a priority matching rule in the crossover operation. The parent individuals are sorted according to the cost-efficiency ratio and then perform the directional crossover operation, specifically as follows:

[0072] Two-layer reference point division strategy: The NSGA-III algorithm usually uses reference points to allocate the objective space. The improved version further refines the weights and priorities of the objectives by dividing the objective space into multiple levels, improving the search efficiency.

[0073] Priority matching rule: To better balance multiple objectives such as cost and efficiency, the parent individuals in the optimization process are sorted according to the cost-efficiency ratio. Individuals with higher priorities will perform the crossover operation first, which ensures that the balance between cost and efficiency is reasonably handled during the optimization process.

[0074] This improvement enhances the ability of the NSGA-III algorithm to handle complex multi-objective optimization problems, can effectively avoid local optimal solutions, and improves the generation efficiency of global optimal solutions.

[0075] S5. During the optimization process, by dynamically adjusting the constraint conditions, ensure that the optimization scheme is adjusted according to real-time data;

[0076] To ensure that the optimization scheme can flexibly respond to actual environmental changes, the present invention introduces a dynamic constraint adjustment mechanism during the optimization process.

[0077] When it is monitored that the pressure of the drainage pipe network exceeds the standard, the system will automatically increase the upper limit of the cost constraint, so that more funds can be invested in the construction of the improved drainage system, thereby improving the drainage capacity.

[0078] When the soil humidity exceeds the preset threshold, the optimization system will increase the weight coefficient of green infrastructure (such as water storage tanks, rain gardens), thereby enhancing the water retention and management capabilities and ensuring that the regulation ability of the hydrological environment is not restricted.

[0079] S6. Compare the simulation results with the real-time monitoring data, calculate the deviation, and use the feedback mechanism to adjust the optimization results to ensure the practical feasibility of the optimization scheme.

[0080] The present invention introduces a feedback mechanism for verifying the effectiveness of the solution in real time during the optimization process. The specific operation is as follows: First, the system compares the simulation results of the optimization solution with the real-time monitoring data and calculates the deviation (i.e., the difference between the simulation and the actual data). Then, based on these deviations, the system corrects the solution by adjusting the optimization parameters to ensure that the optimization results can accurately reflect the real-time environment. The feedback mechanism ensures that the optimization solution has high adaptability and accuracy in practical applications.

[0081] In one embodiment, the feedback mechanism includes comparing the simulation results of the optimization solution with the real-time monitoring data, calculating the error, and optimizing the results by dynamically adjusting the optimization parameters.

[0082] The feedback mechanism is a key component in the present invention, ensuring that the optimization solution can be effectively adjusted according to real-time data in practical applications. The specific implementation is as follows:

[0083] The optimization process first generates an optimization solution based on historical data and simulation results;

[0084] Then, the effect of the optimization solution is compared with real-time monitoring data such as rainfall, soil moisture, and drainage network pressure, and the error between the two is calculated.

[0085] If the error is large, the system corrects the optimization results by dynamically adjusting the optimization parameters such as adjusting the weight coefficients of the objective function and the operating parameters of the optimization algorithm to ensure that the solution can adapt to changes in the actual environment.

[0086] This feedback mechanism can continuously adjust and optimize the layout of green infrastructure, ensuring that the solution can still achieve the best effect in the face of different environmental changes, with high flexibility and adaptability.

[0087] As Figure 2 shown, the present invention also provides a green infrastructure spatial layout optimization system based on an improved multi-objective optimization algorithm, which is characterized in that it is used to implement a green infrastructure spatial layout optimization method based on an improved multi-objective optimization algorithm as described above, including:

[0088] A data acquisition module, which arranges drainage network pressure sensors, soil moisture sensors, and rainfall monitoring sensors to collect relevant environmental data in the green infrastructure area in real time. These sensors monitor the state of the drainage system, soil moisture, and rainfall in real time and transmit the collected signals to other modules of the system. This module ensures that the system can obtain accurate environmental data as the basis for subsequent optimization.

[0089] As Figure 3As shown in the figure, there is a data preprocessing module which is responsible for receiving the raw data transmitted by the data acquisition module and denoising the data through a Kalman filter to reduce the noise caused by external interference or equipment errors. At the same time, the weighted average method integrates the data from different types of sensors and outputs data with a unified format and higher accuracy, providing accurate data input for subsequent optimization calculations.

[0090] The optimization calculation module is the core module of this system and is responsible for performing the improved NSGA-III algorithm for multi-objective optimization. By performing optimization calculations on real-time data, it generates the optimal layout plan for green infrastructure. This module considers multiple objective functions during the optimization process, including the life-cycle cost and the hydrological control efficiency, etc., to ensure that the optimization plan finds the optimal solution among multiple objectives.

[0091] In one embodiment, the optimization calculation module includes:

[0092] The objective function calculation unit is used to calculate the optimal layout plan for green infrastructure. This unit calculates two major optimization objectives:

[0093] Life-cycle cost: Considering the construction cost, operation and maintenance cost, and long-term maintenance cost of green infrastructure.

[0094] Runoff control efficiency: Reflecting the hydrological management effect of green infrastructure, calculating the ability of the infrastructure in terms of rainwater retention and runoff reduction.

[0095] The multi-objective optimization unit is used to execute the improved NSGA-III algorithm, generate an optimization solution set and perform objective balancing.

[0096] The objective function calculation unit weighs these two objectives according to the set weights (determined by α and β) to ensure that the optimization plan can balance economy and efficiency.

[0097] The dynamic constraint adjustment module, based on real-time monitoring data, dynamically adjusts the constraint conditions in the optimization process according to the feedback of the system. For example, when the pressure of the drainage pipe network exceeds the standard, the system will automatically increase the allowable cost constraint, allowing the optimization plan to make appropriate adjustments, thereby enhancing the carrying capacity of the drainage system.

[0098] In one embodiment, the dynamic constraint adjustment module dynamically adjusts the constraints according to the pressure of the drainage pipe network and the soil moisture. The specific adjustment rules are as follows:

[0099] When the pressure of the drainage pipe network exceeds the standard, the system increases the upper limit of the cost constraint, enabling more resources to be invested in the plan to optimize the drainage pipe network capacity, thereby avoiding the overflow of the drainage pipe network and reducing the risk of waterlogging. The adjustment range is 10%-30%, which can be flexibly adjusted according to the actual situation.

[0100] When the soil humidity is too high, in order to strengthen the retention and infiltration of rainwater, the system will increase the weighting coefficient of the water storage layer of green infrastructure (such as rain gardens or cisterns). The adjustment range is 0.3 to 0.5 times to ensure that the system can improve the rainwater management ability according to the change of soil humidity.

[0101] The feedback control module compares the simulation results of the optimization scheme with real-time data, calculates the error and dynamically adjusts the optimization scheme. It ensures that in practical applications, the optimization scheme can flexibly respond to environmental changes and adjust parameters to maintain optimal performance.

[0102] The actuator module is responsible for actual operations according to the optimization results, such as adjusting the drainage path, regulating the layout of green infrastructure, etc., to ensure that the optimization scheme can be implemented and play a role in practice.

[0103] In one embodiment, the actuator module includes an array of electric control valves. The actuator module adjusts the drainage path through the array of electric control valves. This module can adjust the drainage direction and regulate the opening and closing state of the drainage pipe network in real time according to the optimization calculation results to ensure the efficient implementation of the optimization scheme. The flexibility and stability of the array of electric control valves ensure that the system can react and adjust in a timely manner under different environmental conditions, avoid excessive or uneven pressure in the drainage pipe network, and improve the drainage efficiency.

[0104] In one embodiment, the system further includes a redundant communication module, which automatically switches to a backup communication network when the main communication link is interrupted to ensure the stable operation of the system.

[0105] To ensure the stable operation of the system in any situation, the present invention adds a redundant communication module to the system. This module can monitor the status of the main communication link in real time. If a fault or interruption occurs, it will automatically switch to the backup communication network. In this way, even if there is a problem with the main communication link, the system can still continue to operate, ensuring that data transmission is not affected and improving the reliability of the system.

[0106] The above are only the preferred embodiments of the present invention. It should be pointed out that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A method for optimizing the spatial layout of green infrastructure based on an improved multi-objective optimization algorithm, characterized in that, It includes the following steps: By deploying multiple sensors, including drainage network pressure sensors, soil moisture sensors, and rainfall monitoring sensors, the rainfall intensity, soil moisture, and network pressure data in the green infrastructure area are collected in real time; Preprocess the collected data. Use a Kalman filter to denoise the multi-source data, and fuse the data through a weighted average method to form unified format data that can be used for subsequent optimization calculations; Based on the preprocessed data, construct an optimization model for the spatial layout of green infrastructure. The optimization objectives include the life-cycle cost, runoff control efficiency, and water quality control efficiency. The objective function is: f cost-eff = α·f cost + β·f efficiency Among them, f cost represents the life cycle cost, and the life cycle refers to the construction and operation of green infrastructure. f efficiency represents the runoff control efficiency. α and β are the weight coefficients of the optimization objectives, and α + β = 1; Use the improved NSGA-III algorithm for multi-objective optimization. Introduce a priority matching rule during the optimization process to enable reasonable balance of different optimization objectives to avoid falling into local optimal solutions; During the optimization process, dynamically adjust the constraint conditions to ensure that the optimization plan is adjusted according to real-time data; Compare the simulation results with the real-time monitoring data, calculate the deviation, and use the feedback mechanism to adjust the optimization results to ensure the practical feasibility of the optimization plan.

2. The green infrastructure space layout optimization method based on an improved multi-objective optimization algorithm according to claim 1, wherein, The full life cycle cost f cost The calculation formula is as follows: Among them, C i represents the unit construction cost of the i-th type of green infrastructure, A i is the area of the i-th type of green infrastructure, represents the unit maintenance cost of the j-th type of green infrastructure, is the maintenance area of the j-th type of green infrastructure, and r and m represent the number of green infrastructure categories and the number of maintenance categories respectively.

3. The green infrastructure spatial layout optimization method based on an improved multi-objective optimization algorithm according to claim 1, characterized in that The runoff control efficiency f efficiency The calculation formula is as follows: Among them, Q k is the flow of the k-th green infrastructure, and C k is the water quality control efficiency of the k-th green infrastructure. n represents the number of green infrastructures in the optimization area.

4. An optimization method for the spatial layout of green infrastructure based on an improved multi-objective optimization algorithm according to claim 1, characterized in that The improved NSGA-III algorithm adopts a two-layer reference point division strategy and introduces a priority matching rule in the crossover operation. The parent individuals perform a directional crossover operation after being sorted according to the cost-efficiency ratio.

5. The green infrastructure spatial layout optimization method based on an improved multi-objective optimization algorithm according to claim 1, characterized in that, The feedback mechanism includes comparing the simulation results of the optimization plan with the real-time monitoring data, calculating the error, and optimizing the results by dynamically adjusting the optimization parameters.

6. A green infrastructure spatial layout optimization system based on an improved multi-objective optimization algorithm, characterized in that, It is used to implement a method for optimizing the spatial layout of green infrastructure based on an improved multi-objective optimization algorithm as described in any one of claims 1-5, including: A data acquisition module that deploys drainage network pressure sensors, soil moisture sensors, and rainfall monitoring sensors to collect relevant environmental data in the green infrastructure area in real time; A data preprocessing module that receives the data transmitted by the data acquisition module, uses a Kalman filter to denoise the data, and performs data fusion using a weighted average method to generate unified format data required for optimization; An optimization calculation module that, based on the fused data, uses the improved NSGA-III algorithm to calculate the optimal layout plan of the green infrastructure. The optimization objectives include the life-cycle cost, runoff control efficiency, and water quality control efficiency; A dynamic constraint adjustment module that dynamically adjusts the constraint conditions of the optimization model according to real-time monitoring data to achieve real-time optimization; A feedback control module that compares the optimization results with the real-time monitoring data, calculates the deviation, and adjusts the optimization plan to ensure its practical effectiveness; An actuator module that, according to the optimization plan, executes the adjustment of the green infrastructure layout.

7. The green infrastructure spatial layout optimization system based on an improved multi-objective optimization algorithm according to claim 6, characterized in that The optimization calculation module includes: An objective function calculation unit for calculating and weighing the life-cycle cost and runoff control efficiency of the green infrastructure; A multi-objective optimization unit for executing the improved NSGA-III algorithm, generating an optimization solution set, and performing objective balance.

8. The green infrastructure space layout optimization system based on an improved multi-objective optimization algorithm according to claim 6, characterized in that, The dynamic constraint adjustment module dynamically adjusts the constraints according to the drainage network pressure and soil humidity, specifically including: when the drainage network pressure exceeds the standard, the upper limit range of the cost constraint is automatically adjusted to 10% to 30%; when the soil humidity exceeds the set value, the weight coefficient of the aquifer green infrastructure is automatically adjusted, and the range is 0.3 to 0.5 times.

9. The green infrastructure spatial layout optimization system based on an improved multi-objective optimization algorithm according to claim 6, characterized in that, The actuator module includes an electric control valve array, which can adjust the drainage path according to the optimization result and ensure the flexibility and stability of the system.

10. The green infrastructure spatial layout optimization system based on an improved multi-objective optimization algorithm according to claim 6, wherein It further includes a redundant communication module, which automatically switches to the standby communication network when the main communication link is interrupted to ensure the stable operation of the system.

Images