Urban water environment pollution load distribution optimization method, device, equipment and medium

Abstract

The invention relates to the technical field of pollution load distribution, and discloses an urban water environment pollution load distribution optimization method, device, equipment and medium, the urban water environment pollution load distribution optimization method comprises the following steps: dividing a target research area according to spatial geographic data to obtain target subareas; based on preset composite chaotic mapping, performing population initialization on particles corresponding to pollution source emission of each target subarea; taking minimization of treatment cost, maximization of a water quality standard-reaching rate and minimization of a preset Gini coefficient as targets, updating the initial population, according to a target inertia weight parameter and a target learning factor, updating and repeatedly iterating particle speed and position until a preset convergence condition is reached, and obtaining an optimal emission strategy of a pollution source; according to the method, the minimum treatment cost, the maximum water quality standard-reaching rate and the minimum preset Gini coefficient are taken as targets, and a more accurate and reliable pollution source optimal emission strategy is obtained through particle swarm optimization.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of pollution load allocation, and particularly relates to a city water environment pollution load allocation optimization method, device, equipment and medium. BACKGROUND

[0002] City water pollution load allocation is to scientifically and reasonably allocate the total amount of pollutants allowed (i.e. water environmental capacity) of a specific water area (such as urban rivers, lakes, nearshore sea areas, etc.) to different pollution sources (or regions, industries), and to clarify the pollutant emission control quota of each responsible subject, so as to ensure that the water quality of the water body meets the standard and to provide an operable implementation basis for emission reduction measures. City water pollution load allocation is a core means to coordinate urban economic development and water environment ecological protection, and therefore it is necessary to analyze city water pollution load allocation strategies.

[0003] In related technologies, there are two methods for determining city water pollution load allocation strategies. The first method is equal proportion allocation method, which determines the total load reduction amount or the allowed emission amount that a pollution source should bear in the future according to the proportion of the actual emission amount or emission intensity of each pollution source in the total emission amount of the region in the base year. However, this method only considers historical (current) emission amount and does not consider the actual treatment capacity, technical level, emission reduction cost and difference in treatment level of the pollution source. The second method is preset Gini coefficient allocation method, which applies a preset Gini coefficient to evaluate and optimize the pollution emission efficiency (or load allocation fairness) of different pollution units. However, this method has strong subjectivity in index selection and target preset Gini coefficient setting, and may deviate from the core target of environmental quality.

[0004] Therefore, the city water pollution load allocation strategy obtained by the method for determining city water pollution load allocation strategy in related technologies is not reasonable and accurate, and does not conform to the actual situation. SUMMARY

[0005] Therefore, the present application provides a city water environment pollution load allocation optimization method, device, equipment and medium to solve the problem of unreasonable and inaccurate city water pollution load allocation strategy caused by the method for determining city water pollution load allocation strategy in related technologies.

[0006] In a first aspect, the present application provides a method for optimizing allocation of urban water environment pollution load, comprising: dividing a target research area of a target city according to spatial geographic data of the target research area to obtain a plurality of target partition regions; constructing a plurality of objective functions of each target partition region with the aim of minimizing treatment cost, maximizing water quality compliance rate, and minimizing a preset Gini coefficient; initializing a population of particles corresponding to pollution source emissions of each target partition region based on a preset composite chaotic mapping to obtain an initial population; updating the initial population according to the plurality of objective functions, updating particle velocity and position according to a target inertia weight parameter and a target learning factor, and iteratively repeating until a preset convergence condition is reached to obtain an optimal pollution source emission strategy for each target partition region; the target inertia weight parameter is a parameter obtained by adjusting an inertia weight parameter according to a change rate of the plurality of objective functions; the target learning factor is a factor obtained by adjusting a learning factor according to a preset sine parameter; and allocating the urban water environment pollution load according to the optimal pollution source emission strategy.

[0007] The present application divides the target research area according to the spatial geographic data of the target city, obtains a plurality of target partition regions, and the geographic conditions of different partition regions in the target research area will affect pollution diffusion, bearing, etc., so that the target research area is divided to obtain a plurality of target partition regions, and each target partition region is independently studied, thereby improving the accuracy of subsequent urban water environmental pollution load allocation. The present application minimizes the treatment cost, maximizes the water quality standard rate, and minimizes the preset Gini coefficient, constructs a plurality of objective functions for each target partition region, optimizes the treatment cost, water quality standard rate and environmental preset Gini coefficient to achieve the balance of economic target, environmental target and social fairness target, so that the subsequent urban water environmental pollution load allocation can effectively control the urban water environmental governance investment, ensure the improvement of water environmental quality, avoid the pollution load allocation gap between target partition regions being too large, and improve the stability of the overall governance effect. The present application initializes the population of particles corresponding to the pollution source discharge of each target partition region based on the preset composite chaotic mapping, obtains the initial population, so that the generated initial population has high diversity and uniform distribution, covers a wider solution space, avoids the local aggregation problem that may be caused by traditional random initialization, and ensures that various possible pollution source discharge strategies can be explored. The target inertia weight parameter of the present application is a parameter obtained by adjusting the inertia weight parameter according to the change rate of the plurality of objective functions, which can enhance the global optimization ability and improve the local convergence precision. The target learning factor is a factor obtained by adjusting the learning factor according to the preset sine parameter, which uses the periodic change of the preset sine function to dynamically adjust the learning factor, optimizes the parameter adaptability, dynamically balances the global exploration and dynamic development ability, and improves the multi-objective coordination ability. The present application updates the initial population according to the plurality of objective functions, updates the particle velocity and position according to the target inertia weight parameter and the target learning factor, and iterates repeatedly until the preset convergence condition is reached, to obtain the optimal pollution source discharge strategy of each target partition region, thereby improving the rationality and scientificity of the optimal pollution source discharge strategy, and making the allocation of urban water environmental pollution load according to the optimal pollution source discharge strategy more accurate and more in line with the actual situation.

[0008] In an optional implementation, the target study area is divided according to spatial geographic data of the target study area of the target city, to obtain a plurality of target sub-area regions, including: obtaining geographic feature data, a plurality of drainage outlet coordinates, a region boundary of the target study area, and digital elevation model data according to the spatial geographic data of the target study area of the target city; taking the region boundary of the target study area as a constraint, and taking each drainage outlet coordinate as a center, a perpendicular bisector between adjacent drainage outlets is determined; the target study area is divided according to the perpendicular bisector between adjacent drainage outlets, to obtain a plurality of sub-area regions; the plurality of sub-area regions are adjusted by using the geographic feature data and the digital elevation model data, to obtain a plurality of target sub-area regions.

[0009] In an optional implementation, the plurality of target functions include an economic target function, an environmental target function, and a social target function; the plurality of target functions of each target sub-area region are constructed with the goals of minimizing governance cost, maximizing water quality compliance rate, and minimizing a preset Gini coefficient, including: the economic target function of each target sub-area region is constructed according to the sum of the fixed pollution control cost and the treatment cost of the pollutant reduction amount of a plurality of pollution sources in each target sub-area region, with the goal of minimizing governance cost; the environmental target function of each target sub-area region is constructed according to a preset water quality compliance indication function, with the goal of maximizing water quality compliance rate; and the social target function of each target sub-area region is constructed according to the pollutant types and the reduction rates of different pollutants, with the goal of minimizing the preset Gini coefficient.

[0010] In an optional implementation, the particles corresponding to the pollution sources of each target sub-area region are initialized based on a preset composite chaotic mapping, to obtain an initial population, including: generating a nonlinear pseudo-random sequence according to a preset nonlinear chaotic term of the preset composite chaotic mapping and the particles corresponding to the pollution sources of each target sub-area region; and performing uniformity correction on the nonlinear pseudo-random sequence according to a piecewise linear term of the preset composite chaotic mapping, to obtain the initial population.

[0011] In an optional implementation, the initial population is updated according to the plurality of target functions, including: determining the target function value of each particle in the initial population according to the plurality of target functions, and updating the fitness of each particle in the initial population according to the target function value; updating the historical optimal position of each particle in the initial population by comparing the current position and the historical optimal position of each particle in the initial population; and updating the global optimal position of the initial population by screening the current global optimal position from the historical optimal positions of all particles in the initial population.

[0012] In an optional implementation, the particle velocity and position are updated according to the target inertia weight parameter and the target learning factor, including: adjusting the inertia weight parameter according to the change rate of the plurality of target functions to obtain the target inertia weight parameter; adjusting the learning factor according to the preset sine parameter to obtain the target learning factor; updating the particle velocity according to the target inertia weight parameter, the current iteration velocity of the particle, the target learning factor, the historical optimal position of each particle, and the global optimal position to obtain a target particle velocity; and updating the particle position according to the current position of each particle and the target particle velocity.

[0013] In a second aspect, the present application provides a city water environment pollution load allocation optimization device, comprising: a region division module, configured to divide a target research region of a target city according to spatial geographic data of the target research region to obtain a plurality of target sub-regions; a target determination module, configured to construct a plurality of target functions of each target sub-region with the minimum treatment cost, the maximum water quality compliance rate, and the minimum preset Gini coefficient as targets; a population initialization module, configured to initialize a particle corresponding to a pollution source discharge of each target sub-region based on a preset composite chaotic mapping to obtain an initial population; an update iteration module, configured to update the initial population according to the plurality of target functions, update the particle velocity and position according to a target inertia weight parameter and a target learning factor, and repeatedly iterate until a preset convergence condition is reached to obtain an optimal pollution source discharge strategy of each target sub-region; the target inertia weight parameter is a parameter obtained by adjusting the inertia weight parameter according to the change rate of the plurality of target functions; the target learning factor is a factor obtained by adjusting the learning factor according to a preset sine parameter; and a pollution load allocation module, configured to allocate the city water environment pollution load according to the optimal pollution source discharge strategy.

[0014] In a third aspect, the present application provides a computer device, comprising: a memory and a processor, which are communicatively connected with each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the city water environment pollution load allocation optimization method of the first aspect or any of the corresponding embodiments thereof.

[0015] In a fourth aspect, the present application provides a computer readable storage medium, which stores computer instructions, and the computer instructions are used to make a computer execute the city water environment pollution load allocation optimization method of the first aspect or any of the corresponding embodiments thereof.

[0016] In a fifth aspect, the present application provides a computer program product, which comprises computer instructions, and the computer instructions are used to make a computer execute the city water environment pollution load allocation optimization method of the first aspect or any of the corresponding embodiments thereof. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the specific embodiments or the related art, the drawings needed to be used in the specific embodiments or the related art description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0018] Figure 1 is a flowchart of a city water environment pollution load allocation optimization method according to an embodiment of the present application.

[0019] Figure 2 is an optimization target diagram of a pollution load allocation multi-objective optimization model according to an embodiment of the present application.

[0020] Figure 3 is a flowchart of another city water environment pollution load allocation optimization method according to an embodiment of the present application.

[0021] Figure 4 is a flowchart of a preset improved particle swarm algorithm according to an embodiment of the present application.

[0022] Figure 5 is a structural block diagram of a city water environment pollution load allocation optimization device according to an embodiment of the present application.

[0023] Figure 6 is a hardware structure diagram of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the present application.

[0025] City water pollution load allocation is a core means to coordinate city economic development and water environment ecological protection, through scientific quantification of environmental capacity, fair sharing of governance responsibility, and optimization of resource allocation. The traditional allocation mode is difficult to balance economic, environmental and social benefits. Commonly used proportional allocation method and preset Gini coefficient allocation method are limited to the control of social fairness as a single target, ignoring the difference of governance cost and the feasibility of governance technology, and cannot meet the accurate and refined governance needs of city water system.

[0026] The embodiment of the present application provides a kind of urban water environmental pollution load distribution optimization method, by with minimum treatment cost minimization, water quality standard rate maximization and preset Gini coefficient minimization as goal, particle swarm optimization is carried out, to achieve the effect of more accurate and reliable pollution source optimal emission strategy.

[0027] According to the embodiment of the present application, a kind of urban water environmental pollution load distribution optimization method embodiment is provided, it needs to be explained, the steps shown in the flowchart of the drawing can be executed in computer system, such as a group of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in different order from here.

[0028] A kind of urban water environmental pollution load distribution optimization method is provided in the present embodiment, it can be used in computer equipment, Figure 1 It is the flow chart of the urban water environmental pollution load distribution optimization method according to the embodiment of the present application, as Figure 1 Shown, the flow includes the following steps:

[0029] Step S101, according to the spatial geographic data of target research area of target city, the target research area is divided, and a plurality of target partition regions are obtained.

[0030] Wherein, target research area is the area that needs to carry out urban water environmental pollution load distribution is preset;Spatial geographic data is the data indicating geographic entity, geographic phenomenon, geographic environment and their mutual relationship, for example, spatial geographic data includes geographic feature data, a plurality of drainage outlet coordinates, the area boundary of target research area and digital elevation model data;Geographic feature data covers multiple geographic features, such as topography (mountain peak, valley, etc.), ground object (building, road, river, etc.), and the size, position relationship and other data of various geographic features are labeled;Drainage outlet coordinates are the position coordinates of drainage outlet in specific geographic coordinate system or plane coordinate system;Digital elevation model data is the data that simulates and expresses the surface topography fluctuation of target research area in digital form.

[0031] In some optional embodiments, based on the drainage outlet coordinates, the Thiessen polygon is generated, so that the target research area is divided;Specifically, according to the spatial geographic data of target research area of target city, the geographic feature data, a plurality of drainage outlet coordinates, the area boundary of target research area and digital elevation model data are obtained;With the area boundary of target research area as constraint, with each drainage outlet coordinates as center, the perpendicular bisector between adjacent drainage outlets is determined;According to the perpendicular bisector between adjacent drainage outlets, the target research area is divided, and a plurality of partition regions are obtained;The plurality of partition regions are adjusted by using geographic feature data and digital elevation model data, and a plurality of target partition regions are obtained.

[0032] The basic principle of the Thiessen polygon is to generate mutually non-overlapping polygonal regions based on discrete points, and to satisfy that any point within each polygon is closest to its corresponding discrete point. The mathematical expression of the Thiessen polygon is:

[0033]

[0034] wherein V(P i ) is the nearest neighbor region of the i-th inspection port P i controlled, s is an arbitrary inspection port, is the set of inspection ports, d(s, P i ) is the distance from an arbitrary inspection port s to the i-th inspection port P i , and d(s, P j ) is the distance from an arbitrary inspection port s to the j-th inspection port P j .

[0035] In some optional embodiments, the Thiessen polygon is generated by using a Geographic Information System (GIS) software tool.

[0036] In some optional embodiments, the flow direction, flow accumulation, and other flow data are calculated by using geographic feature data and digital elevation model data, and the flow data are used to correct the multiple partition regions. For example, a flow is directed to partition region A, but actually flows into a river channel of partition region B, so the flow direction needs to be modified to be directed to partition region B.

[0037] In step S102, multiple objective functions of each target partition region are constructed with the objectives of minimizing the treatment cost, maximizing the water quality compliance rate, and minimizing a preset Gini coefficient.

[0038] As shown in Figure 2 , an optimization objective diagram of the multi-objective optimization model for pollution load allocation is exemplarily shown. For optimization of pollution load allocation of a city control unit, efficiency optimality and social fairness optimality are to be ensured. The efficiency includes treatment cost and environmental benefit. To ensure efficiency optimality, the treatment cost is to be minimized and the water quality compliance rate is to be maximized. The social fairness includes a comprehensive preset Gini coefficient. To ensure social fairness optimality, the preset Gini coefficient is to be minimized. The preset Gini coefficient is an index for measuring the balance degree of distribution of different pollution reduction rates.

[0039] In some optional embodiments, the plurality of objective functions comprises an economic objective function, an environmental objective function and a social objective function; the plurality of objective functions of each target partition region is constructed with the minimum governance cost, the maximum water quality compliance rate and the minimum preset Gini coefficient as the target, comprising: the economic objective function of each target partition region is constructed with the sum of the fixed pollution control cost of the plurality of pollution sources of each target partition region and the treatment cost of the pollutant reduction amount as the target of minimizing the governance cost; the environmental objective function of each target partition region is constructed with the preset water quality compliance indication function as the target of maximizing the water quality compliance rate; and the social objective function of each target partition region is constructed with the pollutant types and the reduction rates of different pollutants as the target of minimizing the preset Gini coefficient.

[0040] Exemplarily, the expression of the economic objective function is:

[0041]

[0042] wherein min is the minimum value, f1 is the economic objective function, a is the pollution source number, A is the total number of pollution sources, is the fixed pollution control cost of the a-th pollution source, including sewage treatment facility construction cost, equipment purchase cost, etc., which needs to be calculated by annual depreciation according to the service life, is the treatment cost of the unit pollutant reduction amount of the a-th pollution source, z a is the pollutant reduction amount of the a-th pollution source, is the treatment cost of the pollutant reduction amount.

[0043] Exemplarily, the expression of the environmental objective function is:

[0044]

[0045]

[0046] wherein max is the maximum value, f2 is the environmental objective function, B is the total number of water quality monitoring sections, b is the water quality monitoring section number, δ b is the preset water quality compliance indication function of the b-th water quality monitoring section, and the preset water quality compliance indication function value is 1 if the b-th water quality monitoring section is compliant, and the preset water quality compliance indication function value is 0 if the b-th water quality monitoring section is not compliant.

[0047] Exemplarily, the expression of the social objective function is:

[0048]

[0049] wherein min is the minimum value, f3 is the social objective function, a is the pollution source number, A is the total number of pollution sources, c is the pollution source number, ya the reduction rate of the pollutant of the a th pollution source, y c the reduction rate of the pollutant of the c th pollution source, the average reduction rate of all pollutants, that is, the absolute difference synthesis of the reduction rates of all pollutants as the numerator and the standardization factor as the denominator.

[0050] In some optional embodiments, after constructing the plurality of objective functions, constraint conditions can be constructed according to actual conditions, such as the constraint that the pollution load allocation model should satisfy that the total amount of allocation does not exceed the total amount of allowed river entry, the reduction rate does not exceed the effective range, and the environmental Gini coefficient is not higher than the current value.

[0051] In step S103, the particles corresponding to the pollutant sources of each target partition region are initialized based on the preset composite chaotic mapping to obtain an initial population.

[0052] In some optional embodiments, the particles corresponding to the pollutant sources of each target partition region are initialized based on the preset composite chaotic mapping to obtain an initial population, including: generating a nonlinear pseudo-random sequence according to the preset nonlinear chaotic term of the preset composite chaotic mapping and the particles corresponding to the pollutant sources of each target partition region; and performing uniformity correction on the nonlinear pseudo-random sequence according to the piecewise linear term of the preset composite chaotic mapping to obtain the initial population.

[0053] The preset composite chaotic mapping can be a Logistic-Tent composite chaotic mapping, including a preset nonlinear chaotic term and a piecewise linear term. The preset nonlinear chaotic term can be a Logistic chaotic mapping, and the piecewise linear term can be a Tent chaotic mapping. The Logistic chaotic mapping dominates nonlinear chaos and is used to generate a nonlinear pseudo-random sequence. The Tent chaotic mapping dynamically adjusts the weight to balance the uniformity of the distribution of high and low values.

[0054] For example, the formula for population initialization is:

[0055]

[0056] wherein x e+1 is the current state of the particle e+1, represents the normalized position of the particle e+1, reflects the distribution of the current solution in the search space, r is a chaotic control parameter for adjusting the chaos intensity, x e is the current state of the particle e, rx e (1-x e ) is the preset nonlinear chaotic term, and are the piecewise linear terms.

[0057] In the embodiments of the present application, the improved Logistic-Tent composite chaotic mapping is used to ensure the diversity and uniformity of solutions, i.e., the initial population is widely and uniformly distributed in the solution space, so as to ensure that various possible allocation schemes can be explored. The preset composite chaotic mapping combines the advantages of two classical chaotic mappings by segmentation, significantly improves the population diversity while ensuring the calculation efficiency, and lays a foundation for efficient search of the subsequent optimization algorithm.

[0058] In step S104, the initial population is updated according to the plurality of objective functions, and the particle velocity and position are updated according to the target inertia weight parameter and the target learning factor. The iteration is repeated until a preset convergence condition is reached, and the optimal emission strategy of the pollution source of each target partition region is obtained. The target inertia weight parameter is a parameter obtained by adjusting the inertia weight parameter according to the change rate of the plurality of objective functions. The target learning factor is a factor obtained by adjusting the learning factor according to the preset sine parameter.

[0059] The preset convergence condition can be set according to actual needs. For example, the preset convergence condition can be that when the particle swarm speed decays to 1% of the initial generation, the convergence threshold is reached, and it is determined to be converged.

[0060] In step S105, the urban water environmental pollution load is allocated according to the optimal emission strategy of the pollution source.

[0061] The optimal emission strategy of the pollution source includes the optimal emission information of each pollution source, such as the optimal chemical oxygen demand (COD) of the pollution source and the optimal ammonia nitrogen allowable emission amount. According to the optimal emission strategy of the pollution source, the total allowable emission amount (or emission reduction amount) of the target research area is reasonably allocated to each pollution source (such as a sewage treatment plant and an administrative district) in the target research area.

[0062] The urban water environment pollution load distribution optimization method provided by the embodiment is used for dividing the target research region according to the spatial geographic data of the target research region of the target city, obtaining a plurality of target partition regions, and the geographic conditions of different partition regions in the target research region will affect pollution diffusion, bearing and the like, therefore, the target research region is divided to obtain a plurality of target partition regions, each target partition region is independently researched, and the accuracy of subsequent urban water environment pollution load distribution is improved. The embodiment minimizes the treatment cost, maximizes the water quality compliance rate and minimizes the preset Gini coefficient, constructs a plurality of objective functions of each target partition region, optimizes the treatment cost, the water quality compliance rate and the environmental preset Gini coefficient to balance the economic target, the environmental target and the social fairness target, so that the subsequent urban water environment pollution load distribution can effectively control the urban water environment treatment input, ensure the water environment quality improvement, avoid the pollution load distribution gap between the target partition regions being too large, and improve the stability of the overall treatment effect. The embodiment initializes the particles corresponding to the pollution source discharge of each target partition region based on the preset composite chaotic mapping, obtains the initial population, so that the generated initial population has high diversity and uniform distribution, covers a wider solution space, avoids the local aggregation problem caused by the traditional random initialization, and ensures that various possible pollution source discharge strategies can be explored. The target inertia weight parameter is a parameter obtained by adjusting the inertia weight parameter according to the change rate of the plurality of objective functions, the target inertia weight parameter can enhance the global optimization ability and improve the local convergence precision, the target learning factor is a factor obtained by adjusting the learning factor according to the preset sine parameter, the learning factor is dynamically adjusted by using the periodic change of the preset sine function, the parameter adaptability is optimized, the global exploration and dynamic development ability are dynamically balanced, and the multi-target collaborative ability is improved. The embodiment updates the initial population according to the plurality of objective functions, updates the particle speed and position according to the target inertia weight parameter and the target learning factor, iterates repeatedly until the preset convergence condition is reached, obtains the optimal pollution source discharge strategy of each target partition region, improves the rationality and scientificity of the optimal pollution source discharge strategy, and makes the urban water environment pollution load distribution more accurate and more in line with the actual situation.

[0063] An urban water environment pollution load distribution optimization method is provided in the embodiment, which can be used for a computer device, Figure 3 is a flow chart of another urban water environment pollution load distribution optimization method according to the embodiment of the present application, as Figure 3 shown, the flow includes the following steps:

[0064] In step S301, the target research region is divided according to the spatial geographic data of the target research region of the target city, and a plurality of target partition regions are obtained. For details, please refer toFigure 1 Step S101 of the illustrated embodiment will not be described here again.

[0065] Step S302, a plurality of objective functions of each target partition region are constructed with the minimum treatment cost, the maximum water quality compliance rate and the minimum preset Gini coefficient as the target. For details, please refer to Figure 1 Step S102 of the illustrated embodiment will not be described here again.

[0066] Step S303, based on the preset composite chaotic mapping, the population of the particles corresponding to the pollution source emissions of each target partition region is initialized to obtain the initial population. For details, please refer to Figure 1 Step S103 of the illustrated embodiment will not be described here again.

[0067] Step S304, the initial population is updated according to the plurality of objective functions, and the particle velocity and position are updated according to the target inertia weight parameter and the target learning factor. The iteration is repeated until the preset convergence condition is reached, and the optimal emission strategy of the pollution source of each target partition region is obtained; the target inertia weight parameter is a parameter obtained by adjusting the inertia weight parameter according to the change rate of the plurality of objective functions; and the target learning factor is a factor obtained by adjusting the learning factor according to the preset sine parameter.

[0068] Specifically, the above step S304 includes:

[0069] Step S3041, the objective function value of each particle in the initial population is determined according to the plurality of objective functions, and the fitness of each particle in the initial population is updated according to the objective function value.

[0070] Among them, the objective function value corresponding to the current position of each particle is calculated, and the objective function value is used to evaluate the pros and cons of the solution, which provides a basis for the update of the optimal position in the subsequent.

[0071] Step S3042, the historical optimal position of each particle in the initial population is updated by comparing the current position and the historical optimal position of each particle in the initial population.

[0072] Among them, the current position and the historical optimal position of the particle are compared, and the better solution of the individual is retained to update the historical optimal position of each particle in the initial population according to the better solution.

[0073] Step S3043, the current global optimal position is selected from the historical optimal positions of all particles in the initial population, and the global optimal position of the initial population is updated.

[0074] Step S3044, the inertia weight parameter is adjusted according to the change rate of the plurality of objective functions to obtain the target inertia weight parameter.

[0075] Exemplarily, in the related art, the formula for updating the particle velocity and position is:

[0076]

[0077] wherein, is the velocity of the particle e at the t+1th iteration, is the velocity of the particle e at the tth iteration, w is an inertia weight parameter, c1 is an individual learning factor, c2 is a social learning factor, r1 is a first random number, which can be a random number between 0 and 1, r2 is a second random number, which can be a random number between 0 and 1, p best,e is the historical optimal position of the particle e, g best is a global optimal position, is the position of the particle e at the tth iteration, is the position of the particle e at the t+1th iteration.

[0078] In some optional embodiments, when updating the particle velocity and position, the inertia weight parameter, the individual learning factor and the social learning factor are core parameters affecting the performance of the algorithm.

[0079] The inertia weight parameter of the formula for updating the particle velocity and position in the related art has certain limitations. Under a high inertia weight (a fixed value that is too large), the particle flight speed is fast, the global exploration ability is strong, but it oscillates near the optimal solution in the later stage. Under a low inertia weight (a fixed value that is too small), the local development is fine, but it is easy to fall into a local optimum. Therefore, in the early stage (exploration period), the value of the target inertia weight parameter is increased to enhance the global optimization ability, and in the later stage (development period), the value of the target inertia weight parameter is reduced to improve the local convergence precision. The specific dynamic switching basis is the change rate of the objective function.

[0080] wherein, the inertia weight parameter is adaptively adjusted according to the change rate of the objective function, and the formula for determining the change rate of the objective function is:

[0081]

[0082] wherein, Δf is the change rate of the objective function, f best (t) is the optimal objective function value of the tth generation, f best (t-1) is the optimal objective function value of the t-1th generation.

[0083] In some optional embodiments, the inertia weight parameter is adjusted according to a change rate of the plurality of objective functions to obtain a target inertia weight parameter, including: setting a preset change rate threshold, when the change rate of the objective function is greater than or equal to the preset change rate threshold, the inertia weight parameter is reduced to obtain the target inertia weight parameter, so as to enhance the local development capability; when the change rate of the objective function is less than the preset change rate threshold, the inertia weight parameter is increased to obtain the target inertia weight parameter, so as to enhance the global search capability.

[0084] In step S3045, the learning factor is adjusted according to a preset sine-cosine parameter to obtain a target learning factor.

[0085] The learning factor includes an individual learning factor and a social learning factor, and the individual learning factor and the social learning factor are key parameters for controlling the movement of the particles to the individual historical optimal position and the group historical optimal position. In the related art, the use of a fixed learning factor parameter can cause the particles to be unable to effectively explore new regions when the particles are far away from the historical optimal position and the global optimal position, thereby affecting the exploration capability, and also causing the particles to be unable to jump out of the local optimum in a flat region of the solution space. Therefore, the embodiment of the present application introduces a dynamic balance mechanism, and adjusts the learning factor by using a sine-cosine optimization algorithm (SCA). In the early stage, the learning factor is increased to strengthen the individual cognition (explore new schemes), and in the later stage, the learning factor is increased to enhance the ability to quickly converge to the optimum.

[0086] Specifically, the learning factor is adjusted according to a preset sine-cosine parameter to obtain a target learning factor, including: replacing the learning factors c1 and c2 with r1 sinr2 and r1 cosr2 to optimize the speed update equation of the particles in the population, and the specific formula is as follows:

[0087]

[0088]

[0089] wherein, is the speed of the particle e in the t+1th iteration, is the speed of the particle e in the tth iteration, ω1 is a target inertia weight parameter, r1 is a first random number, which can be a random number between 0 and 1, r2 is a second random number, which can be a random number between 0 and 2π, and p best,e is the historical optimal position of the particle e, g best is a global optimal position, t is the number of iterations, and p is a random number, which can be a random number between 0 and 1, and the value of p affects the update mode of the particle, T max is the maximum number of iterations, is the position of the particle e in the tth iteration.

[0090] In step S3046, the particle velocity is updated according to the target inertia weight parameter, the current iteration speed of the particle, the target learning factor, the historical optimal position of each particle, and the global optimal position, to obtain a target particle velocity.

[0091] In step S3047, the particle position is updated according to the current position of each particle and the target particle velocity.

[0092] In step S3048, iteration is repeated until a preset convergence condition is reached, to obtain the optimal emission strategy of the pollution source of each target subarea.

[0093] As shown in the flowchart of the preset improved particle swarm optimization algorithm, Figure 4 the population is initialized by using the Logistic-Tent composite chaotic mapping; the fitness of each particle is updated; the historical optimal position of each particle is updated; the global optimal position is updated; the inertia weight is adaptively optimized, the learning factor is improved by using the SCA positive sine parameter, and the speed and position of each particle are updated based on the improved target inertia weight and target learning factor; it is determined whether the population converges, if the population converges, the iteration is ended, if the population does not converge, the step of updating the fitness of each particle is returned, and iteration is repeated until the population converges.

[0094] In step S305, the urban water environmental pollution load is distributed according to the optimal emission strategy of the pollution source. For details, refer to step S105 of the embodiment shown in Figure 1 , which will not be repeated here.

[0095] In this embodiment, an urban water environmental pollution load distribution optimization device is also provided, which is used to implement the above-mentioned embodiments and preferred embodiments, and will not be repeated here. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware, or a combination of software and hardware is also possible and is contemplated.

[0096] The present embodiment provides an urban water environmental pollution load distribution optimization device, as shown in Figure 5 , comprising:

[0097] The area division module 501 is configured to divide the target research area according to the spatial geographic data of the target research area of the target city, to obtain a plurality of target subareas.

[0098] The target determination module 502 is configured to construct a plurality of target functions of each target subarea, with the goals of minimizing the treatment cost, maximizing the water quality compliance rate, and minimizing the preset Gini coefficient.

[0099] The population initialization module 503 is configured to initialize populations of the particles corresponding to the pollution source emissions of each target partition region based on a preset composite chaotic mapping, to obtain initial populations.

[0100] The update iteration module 504 is configured to update the initial populations according to the multiple target functions, to update the particle velocities and positions according to a target inertia weight parameter and a target learning factor, and to iteratively update until a preset convergence condition is reached, to obtain the optimal pollution source emission strategy of each target partition region. The target inertia weight parameter is a parameter obtained by adjusting an inertia weight parameter according to variation rates of the multiple target functions. The target learning factor is a factor obtained by adjusting a learning factor according to a preset sine parameter.

[0101] The pollution load allocation module 505 is configured to allocate the urban water environmental pollution load according to the optimal pollution source emission strategy.

[0102] In some optional embodiments, the region division module 501 includes:

[0103] The data acquisition unit is configured to acquire geographic element data, multiple outfall coordinates, a region boundary of the target research region, and digital elevation model data according to spatial geographic data of the target research region of the target city.

[0104] The division line determination unit is configured to determine perpendicular bisectors between adjacent outfalls as a constraint with the region boundary of the target research region as a center.

[0105] The region division unit is configured to divide the target research region according to the perpendicular bisectors between the adjacent outfalls, to obtain multiple partition regions.

[0106] The region adjustment unit is configured to adjust the multiple partition regions by using the geographic element data and the digital elevation model data, to obtain multiple target partition regions.

[0107] In some optional embodiments, the target determination module 502 includes:

[0108] The economic target determination unit is configured to construct an economic target function of each target partition region according to a sum of fixed pollution treatment costs of multiple pollution sources of each target partition region and treatment costs of pollutant reduction amounts, with the minimum treatment cost as a target.

[0109] The environmental target determination unit is configured to construct an environmental target function of each target partition region according to a preset water quality compliance indication function, with the maximum water quality compliance rate as a target.

[0110] The social target determination unit is configured to construct a social target function of each target partitioned region according to the pollutant types and the reduction rates of different pollutants, with the preset Gini coefficient minimization as the target.

[0111] In some optional embodiments, the population initialization module 503 comprises:

[0112] The random sequence generation unit is configured to generate a nonlinear pseudo-random sequence according to the preset nonlinear chaotic term of the preset composite chaotic mapping and the particles corresponding to the pollutant source emissions of each target partitioned region.

[0113] The uniformity correction unit is configured to perform uniformity correction on the nonlinear pseudo-random sequence according to the piecewise linear term of the preset composite chaotic mapping to obtain the initial population.

[0114] In some optional embodiments, the update iteration module 504 comprises:

[0115] The fitness update unit is configured to determine the target function value of each particle in the initial population according to the plurality of target functions, and update the fitness of each particle in the initial population according to the target function value.

[0116] The historical position update unit is configured to compare the current position of each particle in the initial population with the historical optimal position, and update the historical optimal position of each particle in the initial population.

[0117] The global optimal update unit is configured to screen the current global optimal position from the historical optimal positions of all particles in the initial population, and update the global optimal position of the initial population.

[0118] The weight parameter adjustment unit is configured to adjust the inertia weight parameter according to the change rates of the plurality of target functions to obtain a target inertia weight parameter.

[0119] The learning factor adjustment unit is configured to adjust the learning factor according to the preset positive sine parameter to obtain a target learning factor.

[0120] The particle velocity update unit is configured to update the particle velocity according to the target inertia weight parameter, the current iteration velocity of the particle, the target learning factor, the historical optimal position of each particle, and the global optimal position to obtain a target particle velocity.

[0121] The particle position update unit is configured to update the particle position according to the current position of each particle and the target particle velocity.

[0122] The further function descriptions of the above-mentioned various modules and units are the same as those of the above-mentioned corresponding embodiments, and will not be repeated here.

[0123] In this embodiment, the urban water environment pollution load allocation optimization device is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0124] This invention also provides a computer device having the above-described features. Figure 5 The device shown is an optimization device for the allocation of urban water pollution load.

[0125] Please see Figure 6 , Figure 6 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 6 As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 6 Take a processor 10 as an example.

[0126] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0127] The memory 20 stores instructions executable by at least one processor 10 to cause the at least one processor 10 to perform the method shown in the above embodiments.

[0128] The memory 20 can include a program storage area and a data storage area. The program storage area can store an operating system, application programs required for at least one function, etc. The data storage area can store data created by the computer device, etc. In addition, the memory 20 can include a high-speed random access memory, and can also include a non-transitory memory such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid state memory device. In some alternative embodiments, the memory 20 can optionally include memory that is remotely located with respect to the processor 10, and which can be connected to the computer device through a network. Examples of such networks include, but are not limited to, the Internet, an enterprise intranet, a local area network, a mobile communications network, and combinations thereof.

[0129] The memory 20 can include a volatile memory, such as a random access memory, and / or can include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid state memory device. The memory 20 can also include an array of multi-state flash memory cells, which can be used to store data and / or instructions in multiple states.

[0130] The computer device also includes a communications interface 30 for communicating with other devices or communication networks.

[0131] The embodiments of the present application also provide a computer readable storage medium, and the method according to the embodiments of the present application can be implemented in hardware, firmware, or recorded in a storage medium, or implemented as computer code to be originally stored in a remote storage medium or a non-transitory machine readable storage medium downloaded through a network and stored in a local storage medium, so that the method described herein can be processed by such software on a storage medium using a general purpose computer, a special purpose processor, or programmable or special purpose hardware. The storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, or a solid state disk, etc. Further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that the computer, processor, microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the method shown in the above embodiments.

[0132] Part of the present application can be applied as a computer program product, for example, computer program instructions, when executed by a computer, through the operation of the computer, can invoke or provide the method and / or technical solutions according to the present application. Those skilled in the art should understand that the form of computer program instructions in computer readable medium includes but is not limited to source files, executable files, installation package files and the like, and accordingly, the way of computer program instructions executed by computer includes but is not limited to: the computer directly executes the instructions, or the computer compiles the instructions and then executes the corresponding compiled program, or the computer reads and executes the instructions, or the computer reads and installs the instructions and then executes the corresponding installed program. Here, the computer readable medium can be any available computer readable storage medium or communication medium accessible to the computer.

[0133] Although the embodiments of the present application are described in conjunction with the drawings, various modifications and changes can be made by those skilled in the art without departing from the spirit and scope of the present application, and such modifications and changes fall within the scope defined by the appended claims.

Claims

1. A method for optimizing allocation of pollution load in an urban water environment, characterized by, The method comprises: According to the spatial geographic data of the target research area of the target city, the target research area is divided to obtain a plurality of target partition areas; With the minimum governance cost, the maximum water quality standard rate and the minimum preset Gini coefficient as the target, a plurality of target functions of each target partition area are constructed; Based on the preset composite chaotic mapping, the particles corresponding to the pollution source emissions of each target partition area are initialized to obtain an initial population; According to a plurality of target functions, the initial population is updated, and the particle velocity and position are updated according to a target inertia weight parameter and a target learning factor, and repeated iteration is performed until a preset convergence condition is reached to obtain an optimal pollution source emission strategy for each target partition area; The target inertia weight parameter is a parameter obtained by adjusting the inertia weight parameter according to the change rate of a plurality of target functions; The target learning factor is a factor obtained by adjusting the learning factor according to a preset sine parameter. According to the optimal pollution source emission strategy, the urban water environmental pollution load is allocated.

2. The method of claim 1, wherein, According to the spatial geographic data of the target research area of the target city, the target research area is divided to obtain a plurality of target partition areas, comprising: According to the spatial geographic data of the target research area of the target city, the geographic element data, a plurality of drainage outlet coordinates, the area boundary of the target research area and the digital elevation model data are obtained; With the area boundary of the target research area as a constraint, the vertical bisector between adjacent drainage outlets is determined with each drainage outlet coordinate as the center; According to the vertical bisector between adjacent drainage outlets, the target research area is divided to obtain a plurality of partition areas; The plurality of partition areas are adjusted using the geographic element data and the digital elevation model data to obtain a plurality of target partition areas.

3. The method according to claim 1 or 2, characterized in that, The plurality of target functions include economic target functions, environmental target functions and social target functions; the plurality of target functions of each target partition area are constructed with the minimum governance cost, the maximum water quality standard rate and the minimum preset Gini coefficient as the target, comprising: With the minimum governance cost as the target, the economic target function of each target partition area is constructed according to the sum of the fixed pollution control cost and the treatment cost of the pollutant reduction amount of a plurality of pollution sources in each target partition area; With the maximum water quality standard rate as the target, the environmental target function of each target partition area is constructed according to a preset water quality standard indication function; With the minimum preset Gini coefficient as the target, the social target function of each target partition area is constructed according to the pollutant type and the reduction rate of different pollutants.

4. The method according to claim 1 or 2, characterized in that, The initial population is obtained by initializing the particles corresponding to the pollution source emissions of each target partition area based on the preset composite chaotic mapping, comprising: According to the preset nonlinear chaotic term of the preset composite chaotic mapping and the particles corresponding to the pollution source emissions of each target partition area, a nonlinear pseudo-random sequence is generated; According to the piecewise linear term of the preset composite chaotic mapping, the non-linear pseudo-random sequence is uniformly corrected to obtain the initial population.

5. The method according to claim 1 or 2, characterized in that, The updating of the initial population according to the plurality of target functions comprises: According to the plurality of target functions, the target function value of each particle in the initial population is determined, and the fitness of each particle in the initial population is updated according to the target function value; The historical optimal position of each particle in the initial population is updated by comparing the current position of each particle in the initial population with the historical optimal position of each particle in the initial population; The global optimal position of the initial population is updated by screening the current global optimal position from the historical optimal positions of all particles in the initial population.

6. The method of claim 1 or 2, wherein, The updating of the particle velocity and position according to the target inertia weight parameter and the target learning factor comprises: The target inertia weight parameter is adjusted according to the change rate of the plurality of target functions; The target learning factor is adjusted according to the preset sine parameter; The target particle velocity is obtained by updating the particle velocity according to the target inertia weight parameter, the current iteration speed of the particle, the target learning factor, the historical optimal position of each particle, and the global optimal position; The particle position is updated according to the current position of each particle and the target particle velocity.

7. An urban water environment pollution load distribution optimization device characterized by comprising: The device comprises: The region division module is configured to divide the target research region of the target city according to the spatial geographic data of the target research region to obtain a plurality of target sub-regions; The target determination module is configured to construct a plurality of target functions for each target sub-region with the objective of minimizing the governance cost, maximizing the water quality compliance rate, and minimizing the preset Gini coefficient; The population initialization module is configured to initialize the population of particles corresponding to the pollution source discharge of each target sub-region based on a preset composite chaotic mapping to obtain an initial population; The update iteration module is configured to update the initial population according to the plurality of target functions, update the particle velocity and position according to the target inertia weight parameter and the target learning factor, and iteratively update until a preset convergence condition is reached to obtain an optimal pollution source discharge strategy for each target sub-region; the target inertia weight parameter is a parameter obtained by adjusting the inertia weight parameter according to the change rate of the plurality of target functions; and the target learning factor is a factor obtained by adjusting the learning factor according to a preset sine parameter; The pollution load allocation module is configured to allocate the urban water environmental pollution load according to the optimal pollution source discharge strategy.

8. A computer device, comprising: It comprises: The memory and the processor are communicatively connected, the memory stores computer instructions, and the processor executes the computer instructions to perform the urban water environmental pollution load allocation optimization method of any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions for causing a computer to perform the urban water environmental pollution load allocation optimization method of any one of claims 1-6.

10. A computer program product, characterised in that, Computer program product including computer instructions for causing a computer to perform the urban water environmental pollution load distribution optimization method of any one of claims 1 to 6.

Images