A garbage collection point flexibility collaborative site selection method, device, equipment and medium

Abstract

The application discloses a garbage collection point toughness cooperative site selection method, comprising the following steps: generating a hierarchical topological road network of a region to be planned, constructing a residential area life garbage source point set and a constraint region set according to the hierarchical topological road network; based on the life garbage source point set and the constraint region set, generating a preset number of initial site selection schemes of garbage collection points of each plot by using a genetic algorithm; wherein the initial site selection scheme is a combination vector composed of effective coordinate points of garbage collection points of all plots in the region to be planned; based on a pre-constructed multi-plot cooperative cost function, the initial site selection scheme is iteratively optimized to obtain an optimal site selection scheme. The application can significantly improve the scientificity and normativity of multi-plot life garbage collection facility layout and reduce the life garbage collection and transportation cost.

Description

Technical Field

[0001] This invention relates to the field of urban waste collection and treatment technology, and in particular to a method, apparatus, equipment and storage medium for collaborative site selection of residential waste collection points for resilient cities. Background Technology

[0002] With rapid economic development and urbanization, the amount of urban domestic waste generated is increasing rapidly, and the scale and operating costs of sanitation collection and transportation facilities are constantly rising. Existing technologies often design the site selection of collection facilities and collection routes independently, and the site selection focuses more on larger sanitation facilities such as garbage transfer stations, while lacking a systematic and coordinated design for the site selection of temporary storage facilities such as the front-end domestic waste collection points or collection rooms.

[0003] As essential supporting facilities for 5-10 minute community living circles, temporary storage facilities such as household waste collection points are characterized by their large number and scattered layout. They are often independently laid out according to the service radius based on the building plan of the community plot during the planning stage. Usually, they are placed in corners or hidden places of the community to consider the NIMBY effect. The adjacency relationship and spacing between collection points in different plots are not designed in a coordinated manner. After the project is completed, the sanitation department can only passively design the collection and transportation routes based on the fixed and scattered collection points. This results in the system lacking resilient redundancy and coordination mechanisms, making it difficult to support the construction requirements of resilient cities.

[0004] This one-way process of "site selection first, route later" has led to a serious disconnect between planning, construction and operation: existing collection points often only consider the service radius and NIMBY needs within a single plot, and are manually set up based on experience, lacking coordination with adjacent plots. The layout of collection points is not systematic, and it is common for collection points in two adjacent communities to have different opening directions on municipal roads and be far apart, which requires sanitation collection vehicles to repeatedly start, stop, turn around and go back, significantly increasing fuel consumption and operation time.

[0005] Therefore, there is an urgent need in this field for a new method that can synergistically optimize the selection of waste collection points and the planning of collection and transportation routes in order to optimize the layout of sanitation facilities and reduce waste collection and transportation costs. Summary of the Invention

[0006] This invention provides a resilient collaborative site selection method for waste collection points, which can significantly improve the scientificity and standardization of the layout of waste collection facilities in multiple locations and reduce waste collection and transportation costs.

[0007] In a first aspect, embodiments of the present invention provide a resilient collaborative site selection method for waste collection points, comprising: Generate a hierarchical topology road network for the area to be planned, and construct a set of municipal solid waste generation source points and a set of constraint regions based on the hierarchical topology road network; Based on the set of sources of domestic waste and the set of constrained areas, a genetic algorithm is used to generate a preset number of initial site selection schemes for waste collection points in each plot; wherein, the initial site selection scheme is a combination vector composed of the effective coordinates of waste collection points of all plots in the area to be planned; Based on the pre-constructed multi-plot collaborative cost function, the initial site selection scheme is iteratively optimized to obtain the optimal site selection scheme.

[0008] Furthermore, the generation of the hierarchical topology road network for the area to be planned includes: Obtain the planning vector map and planning-related indicators of each plot within the area to be planned; wherein, the planning vector map includes, but is not limited to, land use planning map, building master plan, municipal road network, and the location of planned NIMBY buildings within the plot and adjacent NIMBY buildings outside the plot; the planning-related indicators include, but are not limited to, land area, plot ratio, building area, planned total population, planned total number of households, and planned number of households in each building; Based on the acquired data, the land boundary line and building boundary of each plot are extracted, and each building within the plot is assigned a unique ID and layer attribute information. Based on the extracted data, the endpoints of feasible roads are used as nodes, feasible roads are used as edges, and each edge is assigned a toll cost weight coefficient according to the traffic capacity of the feasible roads to generate a hierarchical topology network for the area to be planned.

[0009] Furthermore, the step of constructing the set of municipal solid waste generation sources and the set of constraint regions based on the hierarchical topology road network includes: Extract the geometric center of the outline of each building within each plot in the area to be planned, and use it as the source point of domestic waste generation to construct a set of domestic waste generation source points; wherein, the attributes of each domestic waste generation source point include, but are not limited to, the plot number, the building number, the average daily amount of waste, and the building type. Extract the prohibited site selection areas for collection points within the area to be planned, and construct a set of hard constraints; wherein, the prohibited site selection areas for collection points include, but are not limited to, substation areas, gas pressure regulating station areas, fire lane areas, main entrance and exit areas of residential communities, and the surrounding preset distance range of each area; Extract the collection point location buffer zone within the area to be planned and construct a soft constraint set; wherein, the collection point location buffer zone includes, but is not limited to, school teaching buildings, hospital inpatient departments, office building lobbies, and ground floor residential windows.

[0010] Furthermore, the method of generating a preset number of initial site selection schemes for garbage collection points in various plots using a genetic algorithm includes: Traverse and extract the land boundary line of each plot within the area to be planned, and remove the constraint area that is the concentration of the constraint area from the range of the land boundary line to obtain the effective site selection area of ​​each plot. Calculate the bounding rectangle of the effective addressing region, and randomly generate coordinate points within the bounding rectangle as the effective coordinate points of the effective addressing region; Concatenate all valid coordinates of the plots in order of plot ID to generate a site selection combination vector, which serves as an initial site selection scheme for garbage collection points. Generate a preset number of initial site selection schemes, and combine them to obtain an initial site selection scheme set.

[0011] Furthermore, the process of constructing the multi-plot collaborative cost function includes: Construct an internal transfer cost function, an external collection and transportation cost function, and a constraint penalty term; wherein, the internal transfer cost is the passage cost for sanitation workers to transfer garbage from buildings to garbage collection points, the external collection and transportation cost is the operation cost for municipal sanitation vehicles to stop at garbage collection points and load and unload garbage, and the constraint penalty term is determined based on the constraint region set; The first weight coefficient of the internal transfer cost function and the second weight coefficient of the external collection and transportation cost function are preset. The weight sum of the internal transfer cost function and the external collection and transportation cost function is calculated, and the multi-plot collaborative cost function is obtained by combining the constraint penalty term.

[0012] Furthermore, the construction of the external collection cost function includes: Each valid coordinate point in the combined vector is projected onto the nearest feasible road to obtain a set of projection points; The projection point set is sorted according to the road direction, and the distance between adjacent projection points is calculated. The distance is used to determine whether adjacent projection points are shared stops. The shared stops mean that the municipal sanitation vehicle stops only once when loading and unloading garbage at the two garbage collection points corresponding to the adjacent projection points. The road direction is from the garbage collection point to the garbage transfer station. Based on the number of shared parking spots, the number of times municipal sanitation vehicles start and stop is determined, and the start-stop efficiency cost is calculated based on the number of start-stops and the fuel consumption coefficient per start-stop. Perform linear regression analysis on the projection point set to calculate the vertical distance from the effective coordinate point to the projection point, and calculate the route straightness cost based on the vertical distance; An external collection and transportation cost function is constructed by combining the start-stop efficiency cost and the route straightness cost.

[0013] Furthermore, the iterative optimization of the initial site selection scheme based on the pre-constructed multi-plot collaborative cost function to obtain the optimal site selection scheme includes: Step 1: Take the preset number of initial site selection schemes as parent site selection schemes, substitute them into the multi-plot collaborative cost function, calculate the comprehensive cost value, and mark the scheme with the lowest comprehensive cost value as the Pareto optimal solution. Step 2: Use the binary tournament selection method to select the best site selection scheme from all parent site selection schemes; Step 3: Based on the excellent site selection scheme, use crossover operation and Gaussian mutation to generate offspring site selection schemes; Step 4: Merge the offspring location scheme into the parent location scheme, select a preset number of schemes based on the comprehensive cost value, and iterate. Repeat steps 1 to 3 above until the preset number of iterations is reached. Step 5: Output the Pareto optimal solution as the final optimal addressing scheme.

[0014] Secondly, embodiments of the present invention provide a resilient collaborative site selection device for waste collection points, comprising: The topology network construction module is used to generate a hierarchical topology network of the area to be planned, and to construct a set of municipal solid waste generation source points and a set of constraint regions based on the hierarchical topology network. The site selection scheme generation module is used to generate a preset number of initial site selection schemes for garbage collection points in various plots based on the set of domestic waste generation sources and the set of constraint areas, using a genetic algorithm; wherein, the initial site selection scheme is a combination vector composed of the effective coordinate points of garbage collection points of all plots in the area to be planned; The site selection optimization module is used to iteratively optimize the initial site selection scheme based on a pre-constructed multi-plot collaborative cost function, and solve for the optimal site selection scheme.

[0015] Thirdly, embodiments of the present invention provide an electronic device, comprising: Memory, used to store computer programs; A processor for executing the computer program; Wherein, when the processor executes the computer program, it implements the waste collection point resilient collaborative location method described in any of the first aspects above.

[0016] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program that, when executed, implements the resilient collaborative site selection method for waste collection points as described in any of the first aspects above.

[0017] Compared with existing technologies, the resilient collaborative site selection method for waste collection points provided in this invention has the following advantages: It generates a hierarchical topological road network for the area to be planned; constructs a set of waste generation sources and a set of constraint regions based on the hierarchical topological road network; generates a preset number of initial site selection schemes for waste collection points in various plots using a genetic algorithm based on the set of waste generation sources and the set of constraint regions; wherein the initial site selection scheme is a combination vector composed of the effective coordinates of waste collection points in all plots within the area to be planned; and iteratively optimizes the initial site selection scheme based on a pre-constructed multi-plot collaborative cost function to obtain the optimal site selection scheme. This invention can significantly improve the scientific and standardized layout of multi-plot waste collection facilities and reduce waste collection and transportation costs. Attached Figure Description

[0018] To more clearly illustrate the technical features of the embodiments of the present invention, the drawings used in the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart illustrating a resilient collaborative site selection method for waste collection points provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of a resilient collaborative site selection device for waste collection points provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] It should be noted that although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, and the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein is for the purpose of describing embodiments of the invention only and is not intended to limit the invention.

[0023] In a first aspect, embodiments of the present invention provide a resilient collaborative site selection method for waste collection points, see [link to previous document]. Figure 1 This is a flowchart illustrating an embodiment of a resilient collaborative site selection method for waste collection points provided by the present invention.

[0024] like Figure 1 As shown, the method includes the following steps: S1: Generate a hierarchical topological road network for the area to be planned, and construct a set of domestic waste generation source points and a set of constraint regions based on the hierarchical topological road network; Specifically, the spatial base and constraint system of the area to be planned are first constructed, a hierarchical topology road network that fits the real traffic scenario is generated, and based on the road network, the set of domestic waste generation sources and multi-source constraint area set of the whole area are accurately constructed, so as to provide a refined spatial data source and compliance constraint boundary for subsequent site selection modeling.

[0025] S2: Based on the set of sources of domestic waste and the set of constrained areas, a genetic algorithm is used to generate a preset number of initial site selection schemes for waste collection points in each plot; wherein, the initial site selection scheme is a combination vector composed of the effective coordinates of waste collection points of all plots in the area to be planned; Specifically, based on the aforementioned waste source distribution characteristics and restricted area range, invalid site selection spaces for each plot are screened out, compliant and valid coordinate points are generated in batches within the valid site selection range of the plot, and all valid coordinate points of the plot are sequentially spliced ​​to form a combined vector. This combined vector is used as a single initial site selection scheme to generate a preset number of initial site selection populations in batches, thus completing the population initialization work for solving the genetic algorithm.

[0026] S3: Based on the pre-constructed multi-plot collaborative cost function, the initial site selection scheme is iteratively optimized to obtain the optimal site selection scheme.

[0027] Specifically, a multi-plot collaborative cost function is pre-constructed to drive the site selection scheme to evolve in a directional manner under the rules of the multi-plot collaborative cost function, and finally search for the regional site selection scheme with the best overall benefits.

[0028] In summary, the hierarchical topological road network, the set of domestic waste generation sources, and the set of multi-source constrained regions constructed by this invention accurately reproduce the real road traffic costs, the distribution of construction waste, and the soft and hard constraints of site selection. This provides a high-precision and highly compatible spatial basis and constraint benchmark for subsequent site selection optimization. By constructing a multi-plot collaborative cost function and combining iterative optimization with a genetic algorithm, the layout of waste collection points achieves multi-dimensional collaborative optimality in terms of waste generation matching degree, transportation economy, intensive and straight collection and transportation, environmental friendliness, and compliance and safety. This effectively solves the industry pain points of traditional waste collection point site selection, such as experience-based layout, single constraints, cost imbalance, easy generation of NIMBY conflicts, and poor overall layout coordination. It significantly improves the scientific nature, standardization, and overall operation and maintenance efficiency of multi-plot waste collection facility layout.

[0029] In one optional implementation, generating the hierarchical topology network of the area to be planned includes: Obtain the planning vector map and planning-related indicators of each plot within the area to be planned; wherein, the planning vector map includes, but is not limited to, land use planning map, building master plan, municipal road network, and the location of planned NIMBY buildings within the plot and adjacent NIMBY buildings outside the plot; the planning-related indicators include, but are not limited to, land area, plot ratio, building area, planned total population, planned total number of households, and planned number of households in each building; Based on the acquired data, the land boundary line and building boundary of each plot are extracted, and each building within the plot is assigned a unique ID and layer attribute information. Based on the extracted data, the endpoints of feasible roads are used as nodes, feasible roads are used as edges, and each edge is assigned a toll cost weight coefficient according to the traffic capacity of the feasible roads to generate a hierarchical topology network for the area to be planned.

[0030] Specifically, obtain basic data for the area to be planned, including vector maps and related indicators of the control detailed plans and construction detailed plans for single or multiple plots, such as land use planning maps (land use scope, land use nature), building site plans (building distribution, building type, access roads within the community, main and secondary entrances and exits), municipal road network (road red lines, road grades, road widths, road centerlines), and the location of planned NIMBY (Not In My Backyard) buildings within the target plot area and adjacent NIMBY buildings outside the area (such as shopping malls, schools, administrative office buildings, historical buildings, etc.). Related indicators include land area, plot ratio, building area, total planned population, total planned number of households, and number of planned households in each building, in dwg and shp formats.

[0031] Python is used to extract the closed polygons of the land parcel boundary and building boundaries for each plot, and each building within the plot is assigned a unique ID and layer attribute information. The attribute information includes the planned total population (N), the planned total number of households (At), the total number of households in the i-th building (Ai), the land use code (residential, commercial, educational, administrative office, etc.), and the building type (residential building, commercial building, school, property office). If the population information of a building is missing, the planned total population of the building can be estimated by the average household population of 3.0 and the total number of households in the building.

[0032] Based on the extracted data, ArcGIS Network Analyst or Python NetworkX was first used to extract the red lines of municipal roads, road center lines, and the center lines of roads within residential areas. Topology cleaning was then performed to address topology defects in the original road network, such as broken points, missing intersection nodes, and redundant line segments. Specifically, this included: first, broken point fusion optimization, which sets a spatial tolerance threshold of 0.5 meters to automatically merge road endpoints with a spacing of less than 0.5 meters to address scattered broken points and micro-distance disconnections in the road network; and second, intersection node generation, which breaks line segments at all road intersections to generate independent topology nodes at each intersection and junction.

[0033] Based on the standardized road data after topology cleaning, a vector road network dataset G(V, E) is constructed for the area to be planned. The vertex set V corresponds to the endpoints and intersection topology nodes of all feasible roads, and the edge set E corresponds to all cleaned feasible road segments. Simultaneously, complete attribute information, including basic attributes such as road grade, road width, and road name, is bound to the edge elements of each road segment in the network dataset. Then, based on differences in road capacity, differentiated toll cost weight coefficients ω are assigned to the edges of each road segment to construct a hierarchical topological road network system. The reassignment rules are as follows: the toll cost weight of municipal arterial roads and secondary arterial roads is set to 1, the toll cost weight of municipal branch roads is set to 1.5, the toll cost weight of regular roads within residential areas is set to 2, the toll cost weight of pedestrian paths is set to 3, and the toll cost weight of stepped road sections is set to 5; for all impassable areas and blocked road sections, their toll cost weight is set to infinity and marked as prohibited road sections. Through differentiated weight assignment, a hierarchical topological road network for the planned area is finally formed, which combines topological integrity, hierarchical differentiation, and accurate traffic attributes.

[0034] This embodiment constructs a hierarchical topological road network for the area to be planned, providing a high-precision hierarchical basic road network model for the subsequent selection of waste collection points, effectively improving the scientific nature and relevance of the planning analysis results.

[0035] In one optional implementation, the step of constructing a set of municipal solid waste generation sources and a set of constraint regions based on the hierarchical topology network includes: Extract the geometric center of the outline of each building within each plot in the area to be planned, and use it as the source point of domestic waste generation to construct a set of domestic waste generation source points; wherein, the attributes of each domestic waste generation source point include, but are not limited to, the plot number, the building number, the average daily amount of waste, and the building type. Extract the prohibited site selection areas for collection points within the area to be planned, and construct a set of hard constraints; wherein, the prohibited site selection areas for collection points include, but are not limited to, substation areas, gas pressure regulating station areas, fire lane areas, main entrance and exit areas of residential communities, and the surrounding preset distance range of each area; Extract the collection point location buffer zone within the area to be planned and construct a soft constraint set; wherein, the collection point location buffer zone includes, but is not limited to, school teaching buildings, hospital inpatient departments, office building lobbies, and ground floor residential windows.

[0036] Specifically, the process iterates through all plots of land and the building outline vector data within each plot within the planning area. Using the outline polygon of a single building as the basic unit, geometric operations are performed to extract the geometric center corresponding to each building outline. This center is defined as the source point of domestic waste generation for that single building. The domestic waste generation source points corresponding to all buildings together constitute the domestic waste generation source point set P for the planning area. The source point set can be represented as P = {p A1 …p An p B1 …p Bn ,…, p K1 …p Kn In this context, subscripts A, B, ..., K represent different plots of land within the planning area, and subscripts 1, 2, ..., n within the same plot represent the serial numbers of each building within that plot. At the same time, source matching attribute information is generated for each piece of domestic waste, and the attribute dimensions cover core indicators such as the plot number, building number, average daily waste volume of the building, and building type.

[0037] Further integrating municipal safety regulations and living environment requirements, a multi-source constraint dataset C covering the entire region is constructed, specifically divided into a hard constraint set C0. hard With soft constraint set C soft Two types of constraint regions.

[0038] Among them, the hard constraint set is the area where the collection point is absolutely prohibited from being located. Priority is given to extracting key safety and access-sensitive areas such as substation areas, gas pressure regulating station areas, fire lane areas, and main entrances and exits of residential communities within the area to be planned. A preset buffer distance is extended outward from each core area, and the core area and the surrounding buffer range are defined as a hard constraint no-go zone. From a spatial perspective, the interference of garbage collection point location selection on the safety of municipal facilities, fire access, and access to community entrances and exits is completely avoided.

[0039] The soft constraint set is a flexible restriction area for collection points. It extracts densely populated and environmentally sensitive areas such as school teaching buildings, hospital inpatient departments, office building lobbies, and windows of ground-floor residential buildings within the planning area as the core base of soft constraints. A multi-level buffer constraint system is constructed based on the degree of NIMBY (Not In My Backyard) impact. For example, the area within 0 to 10 meters of ground-floor residential windows is designated as the first-level prohibited site selection area, where garbage collection points are strictly prohibited. The area within 10 to 30 meters of ground-floor residential windows is designated as the second-level high-cost area, where site selection is restricted, but a higher site selection cost weight must be included. The hierarchical constraint method takes into account both the comfort of living and the flexibility of site selection space.

[0040] The set of sources of domestic waste generated in this embodiment can accurately locate the waste production location and characteristics of a single building. At the same time, it innovatively constructs a hierarchical multi-source constraint system, providing high-precision and realistic basic data support for subsequent intelligent site selection of waste collection points and optimization of collection and transportation routes.

[0041] In one optional implementation, the step of generating a preset number of initial site selection schemes for garbage collection points in various plots using a genetic algorithm includes: Traverse and extract the land boundary line of each plot within the area to be planned, and remove the constraint area that is the concentration of the constraint area from the range of the land boundary line to obtain the effective site selection area of ​​each plot. Calculate the bounding rectangle of the effective addressing region, and randomly generate coordinate points within the bounding rectangle as the effective coordinate points of the effective addressing region; Concatenate all valid coordinates of the plots in order of plot ID to generate a site selection combination vector, which serves as an initial site selection scheme for garbage collection points. Generate a preset number of initial site selection schemes, and combine them to obtain an initial site selection scheme set.

[0042] Specifically, based on the constructed set of constraint areas, the land boundary lines corresponding to each plot within the area to be planned are extracted one by one. Within the space of the land boundary lines, the spatial ranges corresponding to the hard constraint areas and the hierarchical soft constraint areas are eliminated as a whole, and prohibited spaces that do not meet the site selection specifications are screened out. The remaining space is the effective site selection area where garbage collection points can be deployed for the corresponding plot.

[0043] After determining the effective site selection area for a single plot, geometric operations are performed on this effective site selection area to solve for its minimum bounding rectangle. This bounding rectangle is used as the spatial boundary for randomly distributed points, and spatial coordinate points are randomly generated within the rectangular space. x rand , y rand The ray casting method is used to determine whether the coordinate points are located within the effective site selection area, and coordinate points that fall within the effective site selection area are selected as candidate effective coordinate points for the land parcel. S k （x k , y k ） .

[0044] Subsequently, following the order of the land parcel IDs, the valid coordinate points corresponding to each land parcel are sequentially concatenated to form a one-dimensional site selection combination vector. S vec , S vec = [S A (x,y), S B (x,y), ... S K (x,y)] In this context, A, B, ..., K are independent plots of land. A single site selection combination vector corresponds to a complete initial site selection scheme for a garbage collection point. By repeating the above steps of random point generation and vector splicing, multiple sets of site selection combination vectors that meet the preset quantity requirements are generated in a loop. All initial site selection schemes are summarized to form the initial scheme set required for the genetic algorithm to solve the problem, thus completing the data preparation work for population initialization.

[0045] This embodiment can quickly generate compliant initial site selection schemes in batches, improving the convergence speed of subsequent genetic algorithms and the reliability of site selection optimization results.

[0046] In one optional implementation, the process of constructing the multi-plot collaborative cost function includes: Construct an internal transfer cost function, an external collection and transportation cost function, and a constraint penalty term; wherein, the internal transfer cost is the passage cost for sanitation workers to transfer garbage from buildings to garbage collection points, the external collection and transportation cost is the operation cost for municipal sanitation vehicles to stop at garbage collection points and load and unload garbage, and the constraint penalty term is determined based on the constraint region set; The first weight coefficient of the internal transfer cost function and the second weight coefficient of the external collection and transportation cost function are preset. The weight sum of the internal transfer cost function and the external collection and transportation cost function is calculated, and the multi-plot collaborative cost function is obtained by combining the constraint penalty term.

[0047] Specifically, the multi-plot collaborative cost function consists of three core modules: internal transfer cost function, external collection and transportation cost function, and constraint penalty term, which correspond to different operational scenarios and constraint rules in the entire waste collection and transportation process.

[0048] The internal transfer cost function is used to characterize the travel cost for sanitation workers to transfer garbage from buildings to garbage collection points. It iterates through each plot and, based on the constructed hierarchical topology network, calculates the shortest distance cost for all buildings to transfer garbage from their respective waste-generating points to the corresponding garbage collection points using Dijkstra's algorithm. The calculation formula is as follows: ); in, For the cost of internal transfer, The daily waste output of building i in plot k is expressed in kg / d. This parameter can give high-waste-generating buildings a stronger location attraction, causing waste collection points to automatically approach high-density waste-generating buildings, thus conforming to the actual waste distribution characteristics. This represents the cost of topological travel distance.

[0049] It should be noted that the formula for calculating the daily output of household waste is as follows: ; ; in, The total daily output of domestic waste for the entire site is expressed in kg / d. The total planned population for the target plot. The per capita daily household waste generation indicator, according to the "Urban Environmental Sanitation Facilities Planning Standard", can be taken as 0.8-1.4 kg / (person·d). The coefficient for uneven distribution of household waste generation ranges from 1 to 1.5.

[0050] The daily output of domestic waste from the waste source corresponding to building i is expressed in kg / d. Let be the planned number of households in the i-th residential building. The total number of planned households in all buildings of the target plot is used to allocate the total waste production of the plot based on the proportion of households in a single building to the total number of households in the plot.

[0051] The external collection and transportation cost function is used to characterize the operating cost of municipal sanitation vehicles, mainly quantifying the comprehensive operating cost generated by municipal sanitation vehicles stopping at various garbage collection points, loading and unloading garbage, and patrolling between points.

[0052] The constraint penalty term uses the aforementioned hard constraint set and soft constraint set as the criterion. It sets gradient penalty values ​​for unreasonable site selection behaviors such as site selection points encroaching on prohibited hard constraint regions or falling into high-cost soft constraint regions. The general calculation formula for the penalty term in this embodiment is as follows: ; ; in, This is a hard constraint region status indicator, a Boolean variable with a value of 0 or 1. It takes the value of 1 when the block selection point falls into the hard constraint forbidden selection region, and 0 otherwise. The lethal penalty factor has a fixed value of 10. 9 Once the selected site intrudes into the hard constraint area, it will add an extremely high cost of billions to the overall solution, causing the cost of the candidate solution to exceed the standard significantly. It will be directly eliminated in the genetic algorithm population screening to ensure that the optimal solution set completely avoids the safe construction restriction area. This is a Boolean variable that serves as a soft-constraint region status indicator, taking the value of 0 or 1. It takes the value of 1 when the selected block location falls into the soft-constraint region, and 0 otherwise. The NIMBY (Not In My Backyard) sensitivity coefficient has a value of 10. 6 This is used to quantify the negative impact weight of sensitive buildings on surrounding site selection; As a buffer distance decay function, the closer the location points are, the more drastic the increase of the squared term and the greater the nonlinear penalty, forcing the location points to quickly escape the sensitive core region. In the formula, The preset buffer radius is uniformly set to 30m. The actual spatial distance from the selected location to the nearest sensitive target, when d act When ≥30, f(d) It is 0.

[0053] After constructing the internal transfer cost, external collection and transportation cost, and tiered penalty items, a first weighting coefficient for the internal transfer cost and a second weighting coefficient for the external collection and transportation cost are configured according to the importance of the land transfer operation and the municipal collection and transportation operation. The basic comprehensive collection and transportation cost is obtained by weighted summation. Then, the basic collection and transportation cost is superimposed with the aforementioned tiered penalty items to form a complete multi-land parcel collaborative cost function that takes into account operational economy, traffic rationality, and site selection compliance. The formula is as follows: ; in, As the first weighting coefficient, For the cost of external collection and transportation, This is the second weighting coefficient.

[0054] For example, the first weighting coefficient can be 10. -4This coefficient is used to normalize the internal transportation cost in kg·m to the range of [0, 100], representing the economic value of a unit of labor intensity. It is assumed that the labor cost for a cleaner to move 1 kg of garbage 1 meter is approximately 0.0001 yuan. If the value is 300,000 (kg / d)·m, then the normalized internal transportation cost is 30 yuan.

[0055] The second weighting coefficient can be set to 50. This coefficient adopts an asymmetric weighting strategy and is significantly higher than the actual fuel consumption cost. The basis for setting it is the comprehensive benefit of reducing the start-stop of a municipal sanitation vehicle (about 0.15L of fuel consumption), which is equivalent to shortening the internal cleaning path by more than 500m. A larger β value can give priority to the convenience of municipal collection vehicles, sacrificing a small amount of internal convenience in exchange for smooth overall collection. Assuming that the actual mechanical loss and fuel consumption cost of a sanitation vehicle starting and stopping once is about 2 yuan, the normalized external cost is 100 yuan.

[0056] The multi-plot collaborative cost function constructed in this embodiment breaks through the limitations of traditional single cost evaluation, and provides a reliable quantitative evaluation standard for the genetic algorithm to accurately select the optimal site selection scheme and realize the collaborative optimization layout of multi-plot garbage collection points. It effectively avoids problems such as site selection violations, cost imbalance, and local optima in the optimization results.

[0057] In one optional implementation, constructing the external collection cost function includes: Each valid coordinate point in the combined vector is projected onto the nearest feasible road to obtain a set of projection points; The projection point set is sorted according to the road direction, and the distance between adjacent projection points is calculated. The distance is used to determine whether adjacent projection points are shared stops. The shared stops mean that the municipal sanitation vehicle stops only once when loading and unloading garbage at the two garbage collection points corresponding to the adjacent projection points. The road direction is from the garbage collection point to the garbage transfer station. Based on the number of shared parking spots, the number of times municipal sanitation vehicles start and stop is determined, and the start-stop efficiency cost is calculated based on the number of start-stops and the fuel consumption coefficient per start-stop. Perform linear regression analysis on the projection point set to calculate the vertical distance from the effective coordinate point to the projection point, and calculate the route straightness cost based on the vertical distance; An external collection and transportation cost function is constructed by combining the start-stop efficiency cost and the route straightness cost.

[0058] Specifically, for the combination vector of site selection schemes, the effective coordinates of each candidate waste collection point in the vector are projected onto the nearest feasible road to obtain the projection point set. T ={t A , t B , … tK}

[0059] Based on the direction of municipal roads and the collection direction from candidate points to the regional waste transfer station, the projection point set T is ordered, and the distance between adjacent projection points is calculated sequentially using the following formula: ; Next, a judgment is made. A threshold of 50 meters is set for merging parking points. If the distance between two adjacent points is less than this threshold, it is determined that the two collection points are too close and can be merged into the same group of shared parking points, which is counted as only 1 vehicle start-stop operation. If the distance between two adjacent points is greater than or equal to the threshold, it is determined as an independent parking point, which is counted as 2 vehicle start-stop operations.

[0060] By calculating the total number of start-stop cycles for all locations and combining this with the fuel consumption coefficient per start-stop cycle, a start-stop efficiency cost formula is constructed: ; in, The cost of starting and stopping the intensive process is measured in liters. This represents the total number of times sanitation vehicles start and stop. The single start-stop fuel consumption coefficient represents the extra fuel consumption of a sanitation vehicle to complete a full cycle of deceleration, stopping, garbage loading, and acceleration. In this embodiment, the industry experience value of 0.15L / cycle is adopted. By quantifying the start-stop fuel consumption loss, the energy waste of sanitation operations caused by overly dense deployment of points can be effectively constrained.

[0061] Simultaneously, a route straightness cost is constructed to constrain issues such as collection points deviating from the main line of municipal roads and the collection route being tortuous and circuitous. Linear regression analysis is performed on the projection point set T to fit the optimal collection baseline straight line, and the effective coordinate points of each plot are calculated one by one. S k to projection point t k vertical distance H k The overall route tortuosity is quantified by the sum of squared residuals, and the calculation formula is as follows: ; This penalty item, by amplifying the punishment for road deviation errors, can effectively force garbage collection facilities to be arranged neatly close to the center line of municipal roads, avoiding sanitation vehicles from frequently turning into community side roads, narrow roads or dead ends due to location deviation, and significantly improving the smoothness of the collection and transportation routes.

[0062] Finally, the weighted fusion yields the complete external collection cost function: ; in, The route straightness penalty factor is preferably set to 100 in this embodiment. This is used to balance the difference in magnitude between the start-stop fuel consumption cost and the sum of squares of the linear residuals, and to solve the problem of the linear residuals being too small and the weight ratio being too low. This ensures that the route straightness constraint and the start-stop intensity constraint have equal regulatory power in the target optimization process, and guarantees the balanced optimization of the two types of operation losses.

[0063] The external collection and transportation cost function constructed in this embodiment achieves the optimal synergy between start-stop efficiency and route straightness, ensuring the economy and efficiency of municipal collection and transportation operations.

[0064] In one optional implementation, the step of iteratively optimizing the initial site selection scheme based on a pre-constructed multi-plot collaborative cost function to obtain the optimal site selection scheme includes: Step 1: Take the preset number of initial site selection schemes as parent site selection schemes, substitute them into the multi-plot collaborative cost function, calculate the comprehensive cost value, and mark the scheme with the lowest comprehensive cost value as the Pareto optimal solution. Step 2: Use the binary tournament selection method to select the best site selection scheme from all parent site selection schemes; Step 3: Based on the aforementioned optimal location scheme, a crossover operation and Gaussian mutation are used to generate a progeny location scheme; Step 4: Merge the offspring location scheme into the parent location scheme, select a preset number of schemes based on the comprehensive cost value, and iterate. Repeat steps 1 to 3 above until the preset number of iterations is reached. Step 5: Output the Pareto optimal solution as the final optimal addressing scheme.

[0065] Specifically, based on the constructed multi-plot collaborative cost function, the batch-generated initial site selection schemes are iteratively optimized in multiple rounds. The population quality is continuously optimized through the selection, crossover, and mutation iteration mechanism of the genetic algorithm, and finally the globally optimal site selection scheme is converged and output, realizing the collaborative optimization layout of multi-plot garbage collection points.

[0066] The specific iterative optimization process is as follows: Step 1: Initialize the population and select the first-generation optimal solution. The entire set of a predetermined number of initial site selection schemes is used as the parent site selection population for the genetic algorithm. Each parent site selection scheme is then fed into a pre-constructed multi-plot collaborative cost function to accurately calculate the comprehensive cost value corresponding to each scheme. After completing the cost calculation for all parent schemes, the site selection scheme with the lowest comprehensive cost value in the population is selected and marked as the first-level (Rank 1) Pareto optimal solution, serving as the benchmark optimal solution in the iteration process.

[0067] Step two involves selecting superior individuals using a binary tournament selection method. The algorithm randomly selects two schemes for comparison, prioritizing the scheme with the higher rank. When two schemes are at the same rank, their crowding distance is calculated. Crowding distance measures the difference between a scheme and its neighboring schemes in the target space, prioritizing individuals with larger crowding distances. This aims to maintain population diversity and prevent all site selection points from prematurely clustering on a single street, thus thoroughly exploring the site selection potential of different road segments. Through multiple cyclical sampling comparisons, a sufficient number of high-quality parent individuals are selected in batches, while inferior schemes with high costs, unreasonable layouts, or illegal site selection defects are eliminated, providing a high-quality population base for subsequent offspring generation.

[0068] Step 3: Generate offspring location schemes through crossover and Gaussian mutation operations.

[0069] In the crossover operation phase, preset crossover probability parameters are used. P c The value is set to 0.85. Based on this high crossover probability, multi-point slicing crossover is performed on the excellent site selection schemes selected through screening. The site selection gene fragments of different excellent schemes are randomly sliced ​​and interchanged and fused to achieve precise stitching of the local advantageous layouts of different schemes. For example, the high-quality parallel layout genes of plots 1 and 2 in scheme A can be recombined with the high straightness site selection genes of plot 3 in scheme B, which can greatly improve the fusion efficiency of high-quality features of the population and accelerate the global optimization convergence speed of the algorithm.

[0070] In the mutation operation phase, a preset mutation probability parameter is used. P m The value is 0.15, using the step size standard deviation. The Gaussian perturbation mutation mechanism of the meter performs local fine-tuning optimization on the individuals after crossover. During the algorithm evolution process, if some candidate points happen to be located in the high penalty edge zone of the 30-meter NIMBY buffer zone in sensitive areas such as schools and hospitals, it is easy to cause the solution cost to be too high and difficult to optimize autonomously. By using Gaussian random fine-tuning with a step size of 10 meters, it can drive the illegal or high penalty points to flexibly explore and move in all directions, effectively jump out of the high value area of ​​NIMBY penalty, and search for better coordinate positions in the compliant low cost range. It effectively solves the defects of traditional algorithms that are prone to getting into local optima and cannot finely optimize edge points, and improves the precision and compliance of the offspring location scheme.

[0071] Step 4, Population Merging and Iterative Update. All offspring site selection schemes generated in the iteration are merged with the original parent site selection schemes to form a mixed population containing both new and old individuals. The comprehensive cost value of all mixed individuals is then calculated again using a multi-plot collaborative cost function. Sorting and filtering are performed based on cost advantages, retaining a predetermined number of high-quality schemes as the parent population for the next iteration. This iterative process of optimal solution marking, excellent individual selection, crossover mutation to generate offspring, and population filtering and updating is repeated continuously to iterate and optimize the layout structure and comprehensive cost of the site selection schemes until the algorithm reaches a predetermined maximum iteration threshold, at which point the iteration loop terminates.

[0072] Step 5: Output the globally optimal location scheme. Once the iteration process meets the preset termination condition, extract the final Pareto optimal solution and determine it as the optimal location scheme for the layout of waste collection points across multiple plots, thus completing the intelligent and collaborative optimization layout of waste collection points throughout the entire area.

[0073] It should be noted that this embodiment also constructs a standardized energy consumption calculation model for sanitation operations, which quantifies the energy-saving and emission-reduction benefits of the optimization scheme from two dimensions: energy consumption for start-stop operations and energy consumption for driving mileage. It automatically calculates the reduction in start-stop operations and fuel savings of the optimal site selection scheme of this invention compared to the traditional independent site selection mode, and finally outputs a structured and quantifiable site selection optimization effect evaluation report.

[0074] In this embodiment, the traditional independent site selection mode is selected as the comparison benchmark group. The traditional site selection mode only considers the optimal transfer distance within the plot or the location of the geometric center of the plot to place the collection point, without considering the coordination of points between plots, the straightness of the collection route and the efficiency of operation.

[0075] First, a quantitative calculation model for reducing the number of start-stop operations is constructed to calculate the benefits of optimized parking operations brought about by intensive site deployment. The formula for calculating the reduction in the number of start-stop operations is as follows: N stop ( S vec )- N stop ( S best ); in, This is to reduce the number of times sanitation vehicles start and stop. N stop ( S best ) represents the total number of times a sanitation vehicle needs to stop under the traditional independent site selection mode (usually equal to the total number of plots K), while ) represents the actual effective number of starts and stops after the optimal site selection scheme of this invention is determined by the 50-meter spacing threshold and the point merging correction.

[0076] Furthermore, a dual-dimensional fuel saving calculation model that considers both start-stop fuel saving and route fuel saving is constructed to comprehensively quantify the overall operational energy consumption optimization effect. The formula for calculating the total fuel saving is as follows: ; in, Total fuel savings for sanitation operations; The additional fuel consumption coefficient for a single start-stop cycle of a sanitation vehicle is 0.15L / cycle, which is taken from industry experience in this embodiment. It is used to characterize the additional fuel consumption during the entire process of vehicle deceleration, stopping, loading, and starting acceleration. This refers to the total sanitation collection and transportation mileage corresponding to the traditional site selection scheme, which is the actual driving trajectory length of vehicles traversing all collection points under the traditional independent site layout mode. The total collection and transportation mileage corresponding to the optimal location scheme of the present invention is the actual operating trajectory length after point merging and path straightening optimization. The constant-speed fuel consumption coefficient for heavy-duty sanitation vehicles is set at 0.35L / km, corresponding to the standard fuel consumption of 35L / 100km under the cruising speed of 30-40km / h in urban roads. It is used to accurately calculate the fuel-saving benefits caused by straighter routes and shorter mileage.

[0077] The model covers two core energy-saving scenarios: “reducing start-stop losses by merging points” and “reducing mileage losses by straightening routes”. It can comprehensively and realistically reflect the energy-saving benefits of sanitation operation and maintenance brought about by the collaborative site selection optimization of multiple plots.

[0078] This embodiment uses a genetic algorithm to iteratively optimize the site selection scheme. The final Pareto optimal solution can achieve global collaborative optimization of the layout of garbage collection points in multiple plots, which greatly improves the overall operating efficiency and planning rationality of the garbage collection and transportation system.

[0079] Secondly, embodiments of the present invention provide a resilient collaborative site selection device for waste collection points, see [link to relevant documentation]. Figure 2 This is a schematic diagram of an embodiment of a resilient collaborative site selection device for waste collection points provided by the present invention.

[0080] like Figure 2 As shown, the device includes: Topology network construction module 21 is used to generate a hierarchical topology network of the area to be planned, and to construct a set of domestic waste generation source points and a set of constraint areas based on the hierarchical topology network; The site selection scheme generation module 22 is used to generate a preset number of initial site selection schemes for garbage collection points in various plots based on the set of domestic waste generation sources and the set of constraint areas, using a genetic algorithm; wherein, the initial site selection scheme is a combination vector composed of the effective coordinate points of garbage collection points of all plots in the area to be planned; The site selection optimization module 23 is used to iteratively optimize the initial site selection scheme based on a pre-constructed multi-plot collaborative cost function to obtain the optimal site selection scheme.

[0081] In one optional implementation, generating the hierarchical topology network of the area to be planned includes: Obtain the planning vector map and planning-related indicators of each plot within the area to be planned; wherein, the planning vector map includes, but is not limited to, land use planning map, building master plan, municipal road network, and the location of planned NIMBY buildings within the plot and adjacent NIMBY buildings outside the plot; the planning-related indicators include, but are not limited to, land area, plot ratio, building area, planned total population, planned total number of households, and planned number of households in each building; Based on the acquired data, the land boundary line and building boundary of each plot are extracted, and each building within the plot is assigned a unique ID and layer attribute information. Based on the extracted data, the endpoints of feasible roads are used as nodes, feasible roads are used as edges, and each edge is assigned a toll cost weight coefficient according to the traffic capacity of the feasible roads to generate a hierarchical topology network for the area to be planned.

[0082] In one optional implementation, the step of constructing a set of municipal solid waste generation sources and a set of constraint regions based on the hierarchical topology network includes: Extract the geometric center of the outline of each building within each plot in the area to be planned, and use it as the source point of domestic waste generation to construct a set of domestic waste generation source points; wherein, the attributes of each domestic waste generation source point include, but are not limited to, the plot number, the building number, the average daily amount of waste, and the building type. Extract the prohibited site selection areas for collection points within the area to be planned, and construct a set of hard constraints; wherein, the prohibited site selection areas for collection points include, but are not limited to, substation areas, gas pressure regulating station areas, fire lane areas, main entrance and exit areas of residential communities, and the surrounding preset distance range of each area; Extract the collection point location buffer zone within the area to be planned and construct a soft constraint set; wherein, the collection point location buffer zone includes, but is not limited to, school teaching buildings, hospital inpatient departments, office building lobbies, and ground floor residential windows.

[0083] In one optional implementation, the step of generating a preset number of initial site selection schemes for garbage collection points in various plots using a genetic algorithm includes: Traverse and extract the land boundary line of each plot within the area to be planned, and remove the constraint area that is the concentration of the constraint area from the range of the land boundary line to obtain the effective site selection area of ​​each plot. Calculate the bounding rectangle of the effective addressing region, and randomly generate coordinate points within the bounding rectangle as the effective coordinate points of the effective addressing region; Concatenate all valid coordinates of the plots in order of plot ID to generate a site selection combination vector, which serves as an initial site selection scheme for garbage collection points. Generate a preset number of initial site selection schemes, and combine them to obtain an initial site selection scheme set.

[0084] In one optional implementation, the process of constructing the multi-plot collaborative cost function includes: Construct an internal transfer cost function, an external collection and transportation cost function, and a constraint penalty term; wherein, the internal transfer cost is the passage cost for sanitation workers to transfer garbage from buildings to garbage collection points, the external collection and transportation cost is the operation cost for municipal sanitation vehicles to stop at garbage collection points and load and unload garbage, and the constraint penalty term is determined based on the constraint region set; The first weight coefficient of the internal transfer cost function and the second weight coefficient of the external collection and transportation cost function are preset. The weight sum of the internal transfer cost function and the external collection and transportation cost function is calculated, and the multi-plot collaborative cost function is obtained by combining the constraint penalty term.

[0085] In one optional implementation, constructing the external collection cost function includes: Each valid coordinate point in the combined vector is projected onto the nearest feasible road to obtain a set of projection points; The projection point set is sorted according to the road direction, and the distance between adjacent projection points is calculated. The distance is used to determine whether adjacent projection points are shared stops. The shared stops mean that the municipal sanitation vehicle stops only once when loading and unloading garbage at the two garbage collection points corresponding to the adjacent projection points. The road direction is from the garbage collection point to the garbage transfer station. Based on the number of shared parking spots, the number of times municipal sanitation vehicles start and stop is determined, and the start-stop efficiency cost is calculated based on the number of start-stops and the fuel consumption coefficient per start-stop. Perform linear regression analysis on the projection point set to calculate the vertical distance from the effective coordinate point to the projection point, and calculate the route straightness cost based on the vertical distance; An external collection and transportation cost function is constructed by combining the start-stop efficiency cost and the route straightness cost.

[0086] In one optional implementation, the step of iteratively optimizing the initial site selection scheme based on a pre-constructed multi-plot collaborative cost function to obtain the optimal site selection scheme includes: Step 1: Take the preset number of initial site selection schemes as parent site selection schemes, substitute them into the multi-plot collaborative cost function, calculate the comprehensive cost value, and mark the scheme with the lowest comprehensive cost value as the Pareto optimal solution. Step 2: Use the binary tournament selection method to select the best site selection scheme from all parent site selection schemes; Step 3: Based on the excellent site selection scheme, use crossover operation and Gaussian mutation to generate offspring site selection schemes; Step 4: Merge the offspring location scheme into the parent location scheme, select a preset number of schemes based on the comprehensive cost value, and iterate. Repeat steps 1 to 3 above until the preset number of iterations is reached. Step 5: Output the Pareto optimal solution as the final optimal addressing scheme.

[0087] It should be noted that the waste collection point resilience collaborative site selection device provided in this embodiment of the invention is used to execute all the process steps of the waste collection point resilience collaborative site selection method in the above embodiment. The working principle and beneficial effects of the two are one-to-one, so they will not be described again.

[0088] Thirdly, embodiments of the present invention provide an electronic device, see [link to previous document]. Figure 3 The diagram shown is a structural schematic of an electronic device provided in an embodiment of the present invention.

[0089] like Figure 3 As shown, the device includes: Memory 31 is used to store computer programs; Processor 32 is used to execute the computer program; When the processor 32 executes the computer program, it implements the resilient collaborative site selection method for waste collection points as described in any of the above embodiments.

[0090] For example, the computer program may be divided into one or more modules / units, which are stored in the memory 31 and executed by the processor 32 to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the electronic device.

[0091] The processor 32 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0092] The memory 31 can be used to store the computer programs and / or modules. The processor 32 implements various functions of the electronic device by running or executing the computer programs and / or modules stored in the memory 31 and calling the data stored in the memory 31. The memory 31 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory 31 may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital card (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0093] It should be noted that the aforementioned electronic devices include, but are not limited to, processors and memory, as will be understood by those skilled in the art. Figure 3 The structural diagram is merely an example of the electronic device described above and does not constitute a limitation on the electronic device. It may include more components than shown in the diagram, or combine certain components, or use different components.

[0094] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing a computer program that, when executed, implements the resilient collaborative site selection method for waste collection points described in any of the above embodiments.

[0095] It should be understood that the present invention can implement all or part of the processes in the above-described resilient collaborative site selection method for waste collection points, or it can be accomplished by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the above-described resilient collaborative site selection method for waste collection points. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0096] The above description is merely a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. It should be noted that, for those skilled in the art, several equivalent obvious modifications and / or equivalent substitutions can be made without departing from the technical principles of the present invention, and these obvious modifications and / or equivalent substitutions should also be considered within the scope of protection of the present invention.

Claims

1. A resilient collaborative site selection method for waste collection points, characterized in that, include: Generate a hierarchical topology road network for the area to be planned, and construct a set of municipal solid waste generation source points and a set of constraint regions based on the hierarchical topology road network; Based on the set of sources of domestic waste and the set of constrained areas, a genetic algorithm is used to generate a preset number of initial site selection schemes for waste collection points in each plot; wherein, the initial site selection scheme is a combination vector composed of the effective coordinates of waste collection points of all plots in the area to be planned; Based on the pre-constructed multi-plot collaborative cost function, the initial site selection scheme is iteratively optimized to obtain the optimal site selection scheme.

2. The resilient collaborative site selection method for waste collection points as described in claim 1, characterized in that, The generation of the hierarchical topology road network for the area to be planned includes: Obtain the planning vector map and planning-related indicators of each plot within the area to be planned; wherein, the planning vector map includes, but is not limited to, land use planning map, building master plan, municipal road network, and the location of planned NIMBY buildings within the plot and adjacent NIMBY buildings outside the plot; the planning-related indicators include, but are not limited to, land area, plot ratio, building area, planned total population, planned total number of households, and planned number of households in each building; Based on the acquired data, the land boundary line and building boundary of each plot are extracted, and each building within the plot is assigned a unique ID and layer attribute information. Based on the extracted data, the endpoints of feasible roads are used as nodes, feasible roads are used as edges, and each edge is assigned a toll cost weight coefficient according to the traffic capacity of the feasible roads to generate a hierarchical topology network for the area to be planned.

3. The resilient collaborative site selection method for waste collection points as described in claim 1, characterized in that, The construction of the set of municipal solid waste generation sources and the set of constraint regions based on the hierarchical topology road network includes: Extract the geometric center of the outline of each building within each plot in the area to be planned, and use it as the source point of domestic waste generation to construct a set of domestic waste generation source points; wherein, the attributes of each domestic waste generation source point include, but are not limited to, the plot number, the building number, the average daily amount of waste, and the building type. Extract the prohibited site selection areas for collection points within the area to be planned, and construct a set of hard constraints; wherein, the prohibited site selection areas for collection points include, but are not limited to, substation areas, gas pressure regulating station areas, fire lane areas, main entrance and exit areas of residential communities, and the surrounding preset distance range of each area; Extract the collection point location buffer zone within the area to be planned and construct a soft constraint set; wherein, the collection point location buffer zone includes, but is not limited to, school teaching buildings, hospital inpatient departments, office building lobbies, and ground floor residential windows.

4. The resilient collaborative site selection method for waste collection points as described in claim 1, characterized in that, The method of generating a preset number of initial site selection schemes for garbage collection points in various plots using a genetic algorithm includes: Traverse and extract the land boundary line of each plot within the area to be planned, and remove the constraint area that is the concentration of the constraint area from the range of the land boundary line to obtain the effective site selection area of ​​each plot. Calculate the bounding rectangle of the effective addressing region, and randomly generate coordinate points within the bounding rectangle as the effective coordinate points of the effective addressing region; Concatenate all valid coordinates of the plots in order of plot ID to generate a site selection combination vector, which serves as an initial site selection scheme for garbage collection points. Generate a preset number of initial site selection schemes, and combine them to obtain an initial site selection scheme set.

5. The resilient collaborative site selection method for waste collection points as described in claim 1, characterized in that, The process of constructing the multi-plot collaborative cost function includes: Construct an internal transfer cost function, an external collection and transportation cost function, and a constraint penalty term; wherein, the internal transfer cost is the passage cost for sanitation workers to transfer garbage from buildings to garbage collection points, the external collection and transportation cost is the operation cost for municipal sanitation vehicles to stop at garbage collection points and load and unload garbage, and the constraint penalty term is determined based on the constraint region set; The first weight coefficient of the internal transfer cost function and the second weight coefficient of the external collection and transportation cost function are preset. The weight sum of the internal transfer cost function and the external collection and transportation cost function is calculated, and the multi-plot collaborative cost function is obtained by combining the constraint penalty term.

6. The resilient collaborative site selection method for waste collection points as described in claim 5, characterized in that, The construction of the external collection cost function includes: Each valid coordinate point in the combined vector is projected onto the nearest feasible road to obtain a set of projection points; The projection point set is sorted according to the road direction, and the distance between adjacent projection points is calculated. The distance is used to determine whether adjacent projection points are shared stops. The shared stops mean that the municipal sanitation vehicle stops only once when loading and unloading garbage at the two garbage collection points corresponding to the adjacent projection points. The road direction is from the garbage collection point to the garbage transfer station. Based on the number of shared parking spots, the number of times municipal sanitation vehicles start and stop is determined, and the start-stop efficiency cost is calculated based on the number of start-stops and the fuel consumption coefficient per start-stop. Perform linear regression analysis on the projection point set to calculate the vertical distance from the effective coordinate point to the projection point, and calculate the route straightness cost based on the vertical distance; An external collection and transportation cost function is constructed by combining the start-stop efficiency cost and the route straightness cost.

7. The resilient collaborative site selection method for waste collection points as described in claim 1, characterized in that, The method of iteratively optimizing the initial site selection scheme based on a pre-constructed multi-plot collaborative cost function to obtain the optimal site selection scheme includes: Step 1: Take the preset number of initial site selection schemes as parent site selection schemes, substitute them into the multi-plot collaborative cost function, calculate the comprehensive cost value, and mark the scheme with the lowest comprehensive cost value as the Pareto optimal solution. Step 2: Use the binary tournament selection method to select the best site selection scheme from all parent site selection schemes; Step 3: Based on the excellent site selection scheme, use crossover operation and Gaussian mutation to generate offspring site selection schemes; Step 4: Merge the offspring location scheme into the parent location scheme, select a preset number of schemes based on the comprehensive cost value, and iterate. Repeat steps 1 to 3 above until the preset number of iterations is reached. Step 5: Output the Pareto optimal solution as the final optimal addressing scheme.

8. A resilient collaborative site selection device for waste collection points, characterized in that, include: The topology network construction module is used to generate a hierarchical topology network of the area to be planned, and to construct a set of municipal solid waste generation source points and a set of constraint regions based on the hierarchical topology network. The site selection scheme generation module is used to generate a preset number of initial site selection schemes for garbage collection points in various plots based on the set of domestic waste generation sources and the set of constraint areas, using a genetic algorithm; wherein, the initial site selection scheme is a combination vector composed of the effective coordinate points of garbage collection points of all plots in the area to be planned; The site selection optimization module is used to iteratively optimize the initial site selection scheme based on a pre-constructed multi-plot collaborative cost function, and solve for the optimal site selection scheme.

9. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program; Wherein, when the processor executes the computer program, it implements the resilient collaborative site selection method for waste collection points as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed, implements the resilient collaborative site selection method for waste collection points as described in any one of claims 1 to 7.

Images