Method, device and equipment for planning domestic waste removal routes based on timeliness

Abstract

The present invention discloses a method, device, and equipment for planning household garbage collection routes based on timeliness. The method comprises: obtaining the garbage type and amount generated at each garbage generation point in a city within a garbage generation cycle; setting timeliness constraints for each garbage generation point based on the garbage type and amount generated, and establishing an objective function that minimizes collection costs and the negative impact of transfer stations; solving the objective function using an improved multi-objective genetic algorithm, and combining the location distribution and collection costs of each garbage point, as well as the negative impact of garbage transfer stations on residential areas, to determine the optimal location and number of garbage transfer stations; and formulating collection routes for various types of garbage at garbage transfer stations within different cycles based on the solution results. The present invention can effectively optimize the location and collection routes of garbage transfer stations, reduce collection costs, improve collection efficiency, and reduce the impact of garbage transfer stations on residential areas while meeting garbage collection needs.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method, device and equipment for planning a domestic waste removal route based on timeliness. Background Art

[0002] In the context of waste sorting, different types of waste have different daily production volumes and therefore require different collection frequencies. Furthermore, different types of waste have different physical and chemical properties, resulting in different timelines for collection. For example, kitchen waste contains large amounts of organic matter and water, emitting a pungent odor that attracts mosquitoes and flies, significantly impacting residents' health and well-being. Therefore, it cannot be stored for long periods and must be collected daily. Other types of waste are produced in larger quantities and are prone to odor, requiring daily collection. Recyclable waste has a lower environmental impact and can be stored longer, requiring collection once or twice a week. Hazardous waste is collected and temporarily stored at designated storage locations, typically once or twice every two weeks.

[0003] As an important link in garbage disposal, the location of the garbage transfer station not only has a vital impact on the cost of garbage collection, but also affects the planning of collection routes and the arrangement of different types of garbage collection vehicles. It also has an impact on the surrounding residents and the environment. That is, the site selection of garbage collection facilities is an unpopular site selection problem. If the transfer station is too close to the residential area, it will cause dissatisfaction among residents and may endanger the health of nearby residents; if the transfer station is too far from the residential area, it may lead to increased transportation costs. Summary of the Invention

[0004] The embodiments of the present invention provide a method, device and equipment for planning the route of domestic waste collection based on timeliness, which can effectively optimize the site selection and collection route of garbage transfer stations, reduce collection costs, improve collection efficiency and reduce the impact of garbage transfer stations on residential areas while meeting garbage collection needs.

[0005] An embodiment of the present invention provides a method for planning a domestic waste removal route based on timeliness, comprising:

[0006] Obtain the type and amount of garbage generated at each garbage generating point in the city during the garbage generation cycle;

[0007] Set time constraints for each garbage generation point based on garbage type and generation volume, and establish an objective function that minimizes the cost of removal and the negative impact of transfer stations;

[0008] An improved multi-objective genetic algorithm is used to solve the objective function. The optimal location and number of garbage transfer stations are determined by combining the location distribution and transportation costs of each garbage point, as well as the negative impact of garbage transfer stations on residential areas.

[0009] According to the solution results, the transportation routes of garbage transfer stations for various types of garbage in different cycles are formulated.

[0010] As an improvement to the above solution, the timeliness constraints for each garbage generation point are set according to the garbage type and amount, and an objective function is established to minimize the removal costs and the negative impact of the transfer station, including:

[0011] Classify and identify the garbage generated at each garbage generating point in the city and clarify the type of garbage it belongs to;

[0012] For different types of garbage, corresponding timeliness constraints are set based on their characteristics and impact on the environment and residents' health. For example, kitchen waste is set to be collected daily, recyclable waste is set to be collected 1-2 times a week, and hazardous waste is set to be collected 1-2 times every two weeks.

[0013] Establish an objective function to minimize the negative impact of transportation costs and transfer stations:

[0014]

[0015] Among them, d ij Represents the distance between node i and node j;

[0016] t ij represents the travel time of the cleaning truck from node i to node j;

[0017] t kvi represents the time required for vehicle kv to reach node i;

[0018] C k represents the fixed cost of the kth type of special removal vehicle;

[0019] C′ k represents the transportation cost per unit distance of the kth type of special transportation vehicle;

[0020] cap ew represents the maximum capacity of waste generation point e for w types of waste;

[0021] δ w represents the timeliness constraint of the wth type of garbage;

[0022] π d represents the fixed cost of building a transfer station at potential location D;

[0023] represents the amount of waste type w generated at the waste generation point e in the sth cycle;

[0024] It represents the number of waste collection vehicles kv used to collect waste type w at waste point e in cycle s;

[0025] Q kvw It represents the cabin capacity of vehicle kv loaded with type w garbage;

[0026] a i represents the earliest time that node i is allowed to be cleared, where i∈A, A is the set of all i and j points;

[0027] b i represents the latest time allowed for clearing at node i, where i∈A;

[0028] T i s It represents the time it takes for the cleaning vehicle to reach node i in the sth cycle, where i∈A;

[0029] α represents the waiting cost incurred if the vehicle arrives early;

[0030] β represents the penalty cost incurred by the vehicle if it arrives late;

[0031] The decision variables are as follows:

[0032]

[0033]

[0034] As an improvement to the above solution, the improved multi-objective genetic algorithm is used to solve the objective function. Taking into account the location distribution and transportation costs of each garbage point, as well as the negative impact of garbage transfer stations on residential areas, the optimal location and number of garbage transfer stations are solved, including:

[0035] Initialize the population: Generate the initial population using the population initialization method based on the good point set strategy to ensure the diversity and coverage of the population;

[0036] Fast non-dominated sorting: Perform non-dominated sorting on the current population, divide individuals into different non-dominated levels, and determine the ranking of each individual;

[0037] Calculate the crowding degree: Calculate the crowding degree of individuals in each non-dominated level to evaluate the distribution density of individuals in the objective function space;

[0038] Elite retention strategy: merge the parent and child populations, and select excellent individuals to form a new parent population through non-dominated sorting and crowding comparison;

[0039] Selection operation: According to the non-dominated sorting and crowding degree, individuals with good performance are selected to enter the next generation population;

[0040] Crossover operation: Perform a crossover operation on selected individuals to produce new offspring individuals by exchanging genetic information;

[0041] Mutation operation: perform mutation operations on offspring individuals to introduce new genetic diversity and prevent the algorithm from falling into local optimality;

[0042] Dynamic crowding distance strategy: During population evolution, the crowding calculation method is dynamically adjusted to maintain population diversity and uniform distribution;

[0043] Adaptive crossover and mutation operators: Adaptively adjust crossover and mutation probabilities based on the fitness distribution of the population to accelerate algorithm convergence and maintain population diversity;

[0044] Iterative evolution: Repeated selection, crossover, and mutation operations, and apply dynamic crowding distance strategy until the iteration termination condition is met;

[0045] Output Pareto optimal solution set: After the number of iterations or convergence criteria are met, the Pareto optimal solution set is output, which includes the location and number of garbage transfer stations for different schemes.

[0046] As an improvement to the above solution, the removal routes of various types of garbage at the garbage transfer station in different cycles are formulated based on the solution results, including:

[0047] Based on the solution to the optimal location and number of garbage transfer stations, for each decision cycle, according to the type and amount of garbage at the garbage generation point and the set timeliness constraints, a collection route that meets the timeliness and capacity constraints is planned.

[0048] Another embodiment of the present invention provides a device for planning a domestic waste removal route based on timeliness, including:

[0049] An acquisition module is used to obtain the type and amount of garbage generated at each garbage generating point in the city during the garbage generation cycle;

[0050] The setting module is used to set the timeliness constraints of each garbage generation point according to the garbage type and generation volume, and establish an objective function to minimize the removal cost and the negative impact of the transfer station;

[0051] The solution module is used to solve the objective function using an improved multi-objective genetic algorithm. It combines the location distribution and transportation costs of each garbage point, as well as the negative impact of garbage transfer stations on residential areas, to determine the optimal location and number of garbage transfer stations.

[0052] The formulation module is used to formulate the removal routes of various types of garbage at the garbage transfer station in different cycles based on the solution results.

[0053] As an improvement to the above solution, the setting module is specifically used to:

[0054] Classify and identify the garbage generated at each garbage generating point in the city and clarify the type of garbage it belongs to;

[0055] For different types of garbage, corresponding timeliness constraints are set based on their characteristics and impact on the environment and residents' health. For example, kitchen waste is set to be collected daily, recyclable waste is set to be collected 1-2 times a week, and hazardous waste is set to be collected 1-2 times every two weeks.

[0056] Establish an objective function to minimize the negative impact of transportation costs and transfer stations:

[0057]

[0058] Among them, d ij Represents the distance between node i and node j;

[0059] t ij represents the travel time of the cleaning truck from node i to node j;

[0060] t kvi represents the time required for vehicle kv to reach node i;

[0061] C k represents the fixed cost of the kth type of special removal vehicle;

[0062] C′ k represents the transportation cost per unit distance of the kth type of special transportation vehicle;

[0063] cap ew represents the maximum capacity of waste generation point e for w types of waste;

[0064] δ w represents the timeliness constraint of the wth type of garbage;

[0065] π d represents the fixed cost of building a transfer station at potential location D;

[0066] represents the amount of waste type w generated at the waste generation point e in the sth cycle;

[0067] It represents the number of waste collection vehicles kv used to collect waste type w at waste point e in cycle s;

[0068] Q kvw It represents the cabin capacity of vehicle kv loaded with type w garbage;

[0069] ai represents the earliest time that node i is allowed to be cleared, where i∈A, A is the set of all i and j points;

[0070] b i represents the latest time allowed for clearing at node i, where i∈A;

[0071] T i s It represents the time it takes for the cleaning vehicle to reach node i in the sth cycle, where i∈A;

[0072] α represents the waiting cost incurred if the vehicle arrives early;

[0073] β represents the penalty cost incurred by the vehicle if it arrives late;

[0074] The decision variables are as follows:

[0075]

[0076] As an improvement to the above solution, the solution module is specifically used to:

[0077] Initialize the population: Generate the initial population using the population initialization method based on the good point set strategy to ensure the diversity and coverage of the population;

[0078] Fast non-dominated sorting: Perform non-dominated sorting on the current population, divide individuals into different non-dominated levels, and determine the ranking of each individual;

[0079] Calculate the crowding degree: Calculate the crowding degree of individuals in each non-dominated level to evaluate the distribution density of individuals in the objective function space;

[0080] Elite retention strategy: merge the parent and child populations, and select excellent individuals to form a new parent population through non-dominated sorting and crowding comparison;

[0081] Selection operation: According to the non-dominated sorting and crowding degree, individuals with good performance are selected to enter the next generation population;

[0082] Crossover operation: Perform a crossover operation on selected individuals to produce new offspring individuals by exchanging genetic information;

[0083] Mutation operation: perform mutation operations on offspring individuals to introduce new genetic diversity and prevent the algorithm from falling into local optimality;

[0084] Dynamic crowding distance strategy: During population evolution, the crowding calculation method is dynamically adjusted to maintain population diversity and uniform distribution;

[0085] Adaptive crossover and mutation operators: Adaptively adjust crossover and mutation probabilities based on the fitness distribution of the population to accelerate algorithm convergence and maintain population diversity;

[0086] Iterative evolution: Repeated selection, crossover, and mutation operations, and apply dynamic crowding distance strategy until the iteration termination condition is met;

[0087] Output Pareto optimal solution set: After the number of iterations or convergence criteria are met, the Pareto optimal solution set is output, which includes the location and number of garbage transfer stations for different schemes.

[0088] As an improvement to the above solution, the formulation module is specifically used to:

[0089] Based on the solution to the optimal location and number of garbage transfer stations, for each decision cycle, according to the type and amount of garbage at the garbage generation point and the set timeliness constraints, a collection route that meets the timeliness and capacity constraints is planned.

[0090] Another embodiment of the present invention provides a domestic waste collection route planning device based on timeliness, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the domestic waste collection route planning method based on timeliness described in the above-mentioned embodiment of the invention.

[0091] Another embodiment of the present invention provides a storage medium, wherein the computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the timeliness-based domestic waste collection path planning method described in the above-mentioned embodiment of the invention.

[0092] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0093] The embodiment of the present invention first collects and analyzes the geographical coordinates, garbage types, and generation volume of each garbage generation point in the city; on this basis, corresponding timeliness constraints are set for different types of garbage to ensure that the garbage can be processed in a timely manner according to its characteristics; then, an improved multi-objective genetic algorithm is used to comprehensively evaluate the location distribution of garbage points, transportation costs, and the potential negative impact of garbage transfer stations on residential areas to solve the optimal location and number of garbage transfer stations; finally, based on the optimal solution provided by the algorithm, an efficient path planning scheme is formulated for garbage collection activities in different cycles. From the above analysis, it can be seen that the embodiment of the present invention can effectively optimize the location and transportation routes of garbage transfer stations, reduce transportation costs, improve transportation efficiency, and reduce the impact of garbage transfer stations on residential areas while meeting garbage collection needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0094] Figure 1 This is a flow chart of a method for planning a domestic waste removal route based on timeliness, provided by one embodiment of the present invention;

[0095] Figure 2 1 is a flow chart of an improved NSGA-II algorithm provided by one embodiment of the present invention;

[0096] Figure 3 This is a schematic structural diagram of a device for planning a domestic waste removal route based on timeliness according to an embodiment of the present invention;

[0097] Figure 4 This is a structural diagram of a domestic waste removal route planning device based on timeliness provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0098] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0099] See also Figure 1 , is a flow chart of a method for planning a domestic waste removal route based on timeliness provided by an embodiment of the present invention. The method for planning a domestic waste removal route based on timeliness includes steps S10 to S13:

[0100] S10, obtaining the type and amount of garbage generated at each garbage generating point in the city during the garbage generating cycle;

[0101] S11, set the timeliness constraints for each garbage generation point based on the garbage type and amount generated, and establish an objective function to minimize the removal cost and the negative impact of the transfer station;

[0102] S12, using an improved multi-objective genetic algorithm to solve the objective function, taking into account the location distribution and removal costs of each garbage point, as well as the negative impact of garbage transfer stations on residential areas, to solve the optimal location and number of garbage transfer stations;

[0103] S13, based on the solution results, formulate the removal routes of various types of garbage at the garbage transfer station in different cycles.

[0104] The embodiment of the present invention first collects and analyzes the geographical coordinates, garbage types, and generation volume of each garbage generation point in the city; on this basis, corresponding timeliness constraints are set for different types of garbage to ensure that the garbage can be processed in a timely manner according to its characteristics; then, an improved multi-objective genetic algorithm is used to comprehensively evaluate the location distribution of garbage points, transportation costs, and the potential negative impact of garbage transfer stations on residential areas to solve the optimal location and number of garbage transfer stations; finally, based on the optimal solution provided by the algorithm, an efficient path planning scheme is formulated for garbage collection activities in different cycles. From the above analysis, it can be seen that the embodiment of the present invention can effectively optimize the location and transportation routes of garbage transfer stations, reduce transportation costs, improve transportation efficiency, and reduce the impact of garbage transfer stations on residential areas while meeting garbage collection needs.

[0105] For example, the city's garbage collection process is divided into three stages:

[0106] The first stage is the classified collection stage. The amount of garbage in this stage is small and scattered. It is mainly discarded by residents in trash cans or temporary storage areas, or by sanitation workers who clean up the garbage in public places such as streets and squares and then discard it in a classified manner.

[0107] The second stage is the transportation stage. Since residents or sanitation workers have already sorted the garbage and placed it in the corresponding temporary storage containers in the first stage, garbage trucks need to go to the temporary storage point to sort and transport the garbage to the transfer station.

[0108] The third stage is the centralized transportation stage. After the second stage, the garbage has been stored in the garbage transfer station. At this time, the garbage undergoes relatively simple operations such as compression and dehydration at the transfer station, and is then transported by large vehicles to a more distant garbage final treatment facility. Different types of garbage are transported to the corresponding final facilities for remanufacturing, composting, incineration, harmlessness and other treatments.

[0109] Among them, waste transfer stations are hubs connecting waste collection points with final waste disposal facilities. They provide basic waste processing and temporary storage, and their scale is determined by the amount of waste in the area. Roads connect various nodes in the domestic waste collection system. The flow of waste within the collection system is primarily achieved through roads. Urban roads are categorized as one-way or two-way, and for this study, these can be converted into directed and undirected arcs. Factors such as traffic conditions and route distances will have a certain impact on waste collection routes.

[0110] As an improvement to the above solution, the timeliness constraints for each garbage generation point are set according to the garbage type and amount, and an objective function is established to minimize the removal costs and the negative impact of the transfer station, including:

[0111] Classify and identify the garbage generated at each garbage generating point in the city and clarify the type of garbage it belongs to;

[0112] For different types of garbage, corresponding timeliness constraints are set based on their characteristics and impact on the environment and residents' health. For example, kitchen waste is set to be collected daily, recyclable waste is set to be collected 1-2 times a week, and hazardous waste is set to be collected 1-2 times every two weeks.

[0113] Establish an objective function to minimize the negative impact of transportation costs and transfer stations:

[0114]

[0115] Among them, d ij Represents the distance between node i and node j;

[0116] t ij represents the travel time of the cleaning truck from node i to node j;

[0117] t kvi represents the time required for vehicle kv to reach node i;

[0118] C k represents the fixed cost of the kth type of special removal vehicle;

[0119] C′ k represents the transportation cost per unit distance of the kth type of special transportation vehicle;

[0120] cap ew represents the maximum capacity of waste generation point e for w types of waste;

[0121] δ w represents the timeliness constraint of the wth type of garbage;

[0122] π d represents the fixed cost of building a transfer station at potential location D;

[0123] represents the amount of waste type w generated at the waste generation point e in the sth cycle;

[0124] It represents the number of waste collection vehicles kv used to collect waste type w at waste point e in cycle s;

[0125] Q kvw It represents the cabin capacity of vehicle kv loaded with type w garbage;

[0126] a i represents the earliest time that node i is allowed to be cleared, where i∈A, A is the set of all i and j points;

[0127] b i represents the latest time allowed for clearing at node i, where i∈A;

[0128] T i s It represents the time it takes for the cleaning vehicle to reach node i in the sth cycle, where i∈A;

[0129] α represents the waiting cost incurred if the vehicle arrives early;

[0130] β represents the penalty cost incurred by the vehicle if it arrives late;

[0131] The decision variables are as follows:

[0132]

[0133] In this embodiment, specifically:

[0134] This paper primarily involves a domestic waste collection network consisting of two layers of nodes: waste generation points and waste transfer stations, along with the paths connecting these nodes. The specific collection process involves garbage trucks departing from transfer stations, completing their collection work at the generation points, and returning to the transfer stations to unload the waste. This example focuses on the site selection of transfer stations and the types, number, and route planning of vehicles used in collection operations.

[0135] In recycling operations, special vehicles for various types of garbage are used as transportation tools. Special garbage trucks can only transport specific types of garbage. The transportation process includes S = {1,2,…,s n} decision cycle, and the removal process in each cycle needs to meet two removal time constraints. One is to ensure the timeliness constraint δ of w types of garbage in the removal system. w , the removal time does not exceed the timeliness of the garbage; secondly, it is to ensure that the maximum capacity constraint cap of the garbage generation point e is not exceeded ewWhen a certain type of garbage reaches the maximum capacity of a waste generation point, it must be promptly removed. This example considers four types of garbage collection timelines: kitchen waste, other garbage, recyclables, and hazardous waste. Assuming one day is a cycle, if the timelines for kitchen waste and other garbage are one cycle, for recyclables two cycles, and for hazardous waste three cycles, then at the end of each cycle, a collection truck will proceed to the garbage collection point for collection. Under these timelines, kitchen waste and other garbage must be collected in each cycle. If recyclables are not collected in the first cycle, they must be collected in the second cycle. The collection period for hazardous waste is relatively flexible, requiring collection once within three consecutive cycles. Unlike the classic vehicle routing problem, in this collection system, each collection station is not necessarily visited only once; each collection station to be collected must be visited at least once. However, a collection vehicle can only visit a collection station once at most. Furthermore, there are no priority constraints on the order in which different vehicles visit the same collection station.

[0136] When selecting a site for a waste transfer station, since these stations primarily process recycled waste in a centralized manner, residents prefer to locate them as far away from residential areas as possible; it's not appropriate to locate them near residential areas. Therefore, in addition to considering transportation costs, the site selection of a transfer station also needs to consider the negative effects on nearby residents. Therefore, this example draws on the research results of He Bo, Yang Chao, and others to construct a negative effect model that correlates the distance of the waste transfer station from residential areas and the amount of waste it handles, representing the extent of the impact of waste treatment facilities on nearby residents.

[0137] In order to make the established objective function more consistent with the actual situation, the following definition is made:

[0138] 1) The coordinates and service time window of each garbage point are known, the amount of garbage generated is known, and the amount of each type of garbage generated at each garbage generating point does not exceed the maximum carrying capacity of the garbage collection vehicle of that type;

[0139] 2) There are a certain number of vehicles at the transfer station;

[0140] 3) When a garbage truck arrives at a garbage collection point, it will make a judgment and only collect the garbage at that point when the corresponding type of garbage can meet the loading capacity of the collection truck (for example, a dedicated collection truck for recyclable garbage requires that the amount of recyclable garbage at the garbage collection point is less than or equal to the loading capacity of the vehicle). Otherwise, the garbage collection point will be skipped and other collection trucks will collect the garbage at that point.

[0141] 4) At the same garbage point, different types of garbage can be collected by multiple garbage collection vehicles;

[0142] 5) The vehicle is not affected by traffic conditions;

[0143] 6) The location of the garbage transfer station must be selected from candidate sites, and the garbage transfer station requires construction costs;

[0144] 7) Specialized vehicles are single-cabin vehicles that can only transport specific types of waste;

[0145] 8) There are undirected arcs between each garbage generating point, that is, a vehicle can go from garbage generating point i to garbage generating point j, or from garbage collecting point j to garbage collecting point i;

[0146] 9) Garbage collection trucks can start collecting garbage as soon as they arrive at residential areas, with no waiting time;

[0147] 10) Different types of garbage are transported by special vehicles and cannot be mixed;

[0148] 11) Garbage collection is done at the end of each cycle, meaning that the accumulated garbage and the garbage generated that day are collected together.

[0149] The following are the descriptions of each collection:

[0150] W{w|w=1,2,…,|W|} is a set of garbage types. There are a total of |W| types of garbage in the collection and transportation system, which represents the wth type of garbage. E{e|e=1,2,…,N} is a set of garbage generation points. D{d|d=1,2,…,M} is a set of transfer stations. A{i,j|i,j=1,2,…,M+N} is a collection of all points. V{v|v=1,2,…,|V|} is a set of vehicles. K{k|k=1,2,…,|K|} is a set of garbage recycling vehicle types, where k represents a special collection and transportation vehicle of the kth type. kv represents a specific garbage recycling vehicle. S{s|s=1,2,…,s n} is the decision cycle set.

[0151] Among them, the objective function is as follows:

[0152]

[0153] Objective function (3-1) corresponds to the economic cost of the overall model. It consists of four parts: the fixed vehicle and transportation costs in the first phase of the operation, the penalty cost for not meeting the node time requirements when collecting garbage, and the fixed cost of building transfer stations at potential locations. Objective function (3-2) minimizes the negative effects of the transfer station on the surrounding area. θ and r are parameters that reflect the degree of influence of the corresponding coefficients on utility, indicating that the negative effect of the garbage transfer station is inversely proportional to the distance from the garbage generation point and directly proportional to the amount of garbage temporarily stored at the transfer station.

[0154] The time constraints are as follows:

[0155]

[0156]

[0157] Among them, formula (3-3) is the maximum collection capacity constraint of the garbage point; formula (3-4) means that the garbage collection can only be carried out when the cabin capacity of the garbage w type is greater than the amount of garbage at the garbage generation point; formula (3-5) ensures that the load of the collection vehicle during collection does not exceed the maximum load of the vehicle; formula (3-6) is the garbage collection volume constraint; formula (3-7) is the garbage collection time constraint; formula (3-8) Each type of garbage at each garbage generation point can only be collected by one vehicle; formula (3-9) ensures that the vehicle can only collect the garbage at the garbage point when it arrives at the garbage point; formula (3-10) ensures that the construction of garbage transfer stations will not overlap with each other; formula (3-11) prohibits collection vehicles from traveling between transfer stations; formula (3-12) prohibits collection vehicles from entering It does not leave after entering the garbage generation point; Formula (3-13) A garbage source can be visited multiple times; Formula (3-14) ensures that each garbage truck can only be matched with one garbage transfer station at most; Formula (3-15) ensures that the garbage truck departs and returns from the same transfer station; Formula (3-16) Each garbage truck departs from the transfer station; Formulas (3-17)-(3-21) are 0-1 variable constraints; Formula (3-22) indicates that the time when vehicle k arrives at each node meets the time window requirements of each node; Formula (3-23) indicates that the time when the garbage truck arrives at garbage generation point j is equal to the time when the garbage truck arrives at the previous garbage generation point i plus the travel time from the previous garbage generation point i to the garbage generation point j, and the garbage truck's travel is continuous.

[0158] As an improvement to the above solution, the improved multi-objective genetic algorithm is used to solve the objective function. Taking into account the location distribution and transportation costs of each garbage point, as well as the negative impact of garbage transfer stations on residential areas, the optimal location and number of garbage transfer stations are solved, including:

[0159] Initialize the population: Generate the initial population using the population initialization method based on the good point set strategy to ensure the diversity and coverage of the population;

[0160] Fast non-dominated sorting: Perform non-dominated sorting on the current population, divide individuals into different non-dominated levels, and determine the ranking of each individual;

[0161] Calculate the crowding degree: Calculate the crowding degree of individuals in each non-dominated level to evaluate the distribution density of individuals in the objective function space;

[0162] Elite retention strategy: merge the parent and child populations, and select excellent individuals to form a new parent population through non-dominated sorting and crowding comparison;

[0163] Selection operation: According to the non-dominated sorting and crowding degree, individuals with good performance are selected to enter the next generation population;

[0164] Crossover operation: Perform a crossover operation on selected individuals to produce new offspring individuals by exchanging genetic information;

[0165] Mutation operation: perform mutation operations on offspring individuals to introduce new genetic diversity and prevent the algorithm from falling into local optimality;

[0166] Dynamic crowding distance strategy: During population evolution, the crowding calculation method is dynamically adjusted to maintain population diversity and uniform distribution;

[0167] Adaptive crossover and mutation operators: Adaptively adjust crossover and mutation probabilities based on the fitness distribution of the population to accelerate algorithm convergence and maintain population diversity;

[0168] Iterative evolution: Repeated selection, crossover, and mutation operations, and apply dynamic crowding distance strategy until the iteration termination condition is met;

[0169] Output Pareto optimal solution set: After the number of iterations or convergence criteria are met, the Pareto optimal solution set is output, which includes the location and number of garbage transfer stations for different schemes.

[0170] In this embodiment, specifically:

[0171] The Non-dominated Sorting Genetic Algorithm II (NSGA-II) is an algorithm developed by Deb et al. to solve complex multi-objective optimization problems. This algorithm is an improvement on the first-generation non-dominated sorting algorithm NSGA. NSGA-II retains the advantage of NSGA's uniform distribution of non-inferior solutions while also improving its shortcomings:

[0172] 1. The time complexity of NSGA algorithm in constructing Pareto optimal solution set is high, which is O(rN 3 ), where r represents the number of targets and N represents the size of the population. Since each evolution requires calculation of the non-dominated set, when the size of the evolutionary population is large, the calculation speed of the NSGA algorithm will be very slow. The NSGA-II algorithm proposes a fast non-dominated sorting method, which reduces the time complexity to O(rN 2 ), shortening the execution time of the algorithm.

[0173] 2. Shared parameter problem. In the process of evolution, the NSGA algorithm mainly uses the shared parameter σ share To maintain the distribution of the solution group, but σ shareThe value of is difficult to determine, and it is also difficult to dynamically modify and adjust the parameters. The NSGA-II algorithm uses crowding and crowding comparison operators to compare individuals of the same level without dominance relationships, so that the individuals in the Pareto front are evenly distributed to ensure the diversity of the population.

[0174] 3. The NSGA algorithm lacks a mechanism for retaining the best individuals (elitist). The NSGA-II algorithm introduces an elite retention strategy that retains the best individuals in the parent generation. These individuals are not subjected to crossover mutation and are directly passed on to the offspring, ensuring that the excellent genes are not destroyed and improving the algorithm's convergence speed.

[0175] The following is an introduction to the three improvements of the NSGA-II algorithm:

[0176] (1) Fast non-dominated sort

[0177] The fast non-dominated sorting used in the NSGA-II algorithm is mainly used to process the evolutionary population in layers. In multi-objective problems, two objectives are often in a competitive relationship, that is, they cannot reach the optimal solution at the same time, so the solution set needs to be processed in layers. The NSGA-II algorithm divides the evolutionary population into several layers according to the dominance relationship. The first layer is the non-dominated set calculated in the population, the second layer is the non-dominated set obtained after deleting the first-layer individuals in the population, and the third layer is the non-dominated set obtained after deleting the first and second-layer individuals, thus forming a multi-level relationship. The specific steps of fast non-dominated sorting are as follows:

[0178] Step 1: Assume that the size of the population Pop is N, set the parameters S(p) and the set M(p), where p∈Pop, S p Record the number of individuals dominated by individual p in the population, M p is the set of individuals dominated by individual p in the population;

[0179] Step 2: Calculate the parameter S(p) and the set M(p), and convert S p = 0 are placed in the first-level set I1, and the same non-dominated order p is set for the individuals in the set. rank =1;

[0180] Step 3: Traverse M(p) of individual p in set I1, remove the number of individuals p′ in set M(p) that are dominated by individuals in the first layer, and execute S(p′)=S(p′)-1. If S(p′)=0, put individual p′ into the set of the next layer, p′ rank =p rank +1.

[0181] Step 4: Repeat the above steps until all individuals in the entire population are stratified.

[0182] (2) Crowding and Crowding Comparison Operator

[0183] 1. Crowding: The results calculated in the previous section allow the population to be divided into different levels, and the excellence of individuals can be compared by level. However, when multiple individuals are at the same level, it is difficult to judge the relationship between them. Therefore, the NSGAII algorithm introduces the concept of crowding, which can maintain the diversity and distribution of the population. First, the crowding distance of each individual in the population is calculated. Then, a partially ordered set is constructed based on the individual level and crowding distance calculated in the previous section. When generating a new population, individuals are selected from the partially ordered set one at a time. The larger the crowding distance of individuals at the same level, the greater the difference between the individual and its neighbors. Individuals with large crowding distances are retained to ensure that the entire population is evenly distributed within the target space.

[0184] 2. Crowding comparison operator: The crowding operator mainly considers two factors: the non-dominated order p of individual p rank and its crowding distance D[p] distance , assuming that individuals p and p' are any two individuals in the population, and the crowding comparison operator is defined as n, then the following relationship holds:

[0185]

[0186] if(p rank <p′ rank )or(p rank =p′ rank )and(D[p] distance >D[p′] distance )

[0187] That is, when two individuals belong to different levels, the level p is given priority. rank Small individuals; when the level p rank When the conditions are the same, individuals with larger crowding distances are usually selected to be retained and allowed to evolve together with the next generation.

[0188] (3) Elite retention strategy: In order to retain excellent individuals and prevent them from being lost during evolution, the NSGA-II algorithm introduces an elite retention strategy. After merging the parent generation with its offspring, a non-dominated sort is performed. This way, the excellent individuals in both the parent generation and the offspring can be retained.

[0189] Algorithm improvements

[0190] (1) Population initialization based on the good point set strategy

[0191] The original NSGA-II algorithm uses random generation when initializing the population. Randomness represents uncertainty, which makes the initial population uneven across the entire space, making it difficult to ensure population diversity. This causes the algorithm to become stuck in a local optimum early on, unable to escape or requiring a large amount of computing power to do so. This results in degraded optimization performance during the iterative process.

[0192] In order to eliminate the uncertainty caused by random population initialization and the problem of uneven spatial distribution of the initial population, this embodiment introduces a population initialization method based on the good point set strategy, which is described in detail as follows:

[0193] Define Gs as an S-dimensional Euclidean geometric space, define r as a good point, r∈G s ,r=(r1,r2,…,r s ), where 0≤r i ≤1, i=1,2,…,s. P n (i) is the set of good points, Denote the good point set P n (i), A(r, μ) is a constant that is only related to r and μ. Then:

[0194] P n (i)={(r1i,r2i,...,r n i),i=2,...n} (3-27)

[0195]

[0196] According to the definition of the good point set, the initial population steps of the algorithm are:

[0197] Step 1: Define the initial population good point set R = {(r i1 ,r i2 ,...,r is )|i=1,2,...n};

[0198] Step 2: s is the dimension of the Euclidean geometric space, a is the smallest prime number that satisfies a≥2s+3|, and each point r in the good point set R i =(r i1 , r i2 ,...,r ij ,...,r is ), j=1,2,...,s,then according to formula (3-29) we can calculate r ij :

[0199]

[0200] Step 3: Definition The maximum and minimum values ​​of the domain of the independent variable of dimension j are adjusted by formula (3-30). ij position, ensuring r ij are within their respective domains:

[0201]

[0202] On a two-dimensional plane, 100 points are generated using the good point set strategy, while 100 points are randomly generated. The random initialization method is very concentrated in some areas and very scattered in others, while the good point set strategy method is more evenly distributed in space than the random generation method.

[0203] (2) Dynamic crowding distance strategy

[0204] The NSGA-II algorithm can significantly improve the uniformity of the Pareto front distribution by using crowding distance in the later stages of the algorithm. This is because in the later stages of the algorithm, individuals in the population are concentrated in the first level. At this point, individual selection by level cannot be performed, and the main basis for individual selection becomes crowding distance. However, when many individuals are concentrated in a certain area, the crowding distance selection method will eliminate all individuals in this area, which will reduce the uniformity of the Pareto front distribution. (a) shows the distribution of individuals in a certain level, and (b) shows the distribution of individuals after crowding distance screening. Because the individuals in the area in the figure are too dense, the calculated individual crowding distance is small, so these crowded individuals are screened out, resulting in blank areas in the dense area. In fact, after screening the individual with the smallest crowding distance, the crowding distance of individuals adjacent to the screened individual will change.

[0205] Therefore, this embodiment introduces a dynamic crowding distance strategy. Its core idea is to calculate the crowding level of each individual, filter out the individuals with the lowest crowding level, and then calculate the crowding distance of the remaining individuals. Using the recalculated result, the individuals with the lowest crowding level are filtered out again. The above process is repeated until the filtered individuals meet the population requirements.

[0206] (3) Adaptive crossover and mutation operators

[0207] The three basic operations in the NSGA-II algorithm are selection, crossover, and mutation. The selection operation in the NSGA-II algorithm only preserves high-quality individuals from the population; it cannot create individuals with new traits. The crossover operation, on the other hand, simulates the reproductive behavior of biological evolution: by exchanging partial gene segments, it preserves the best genes from the parent while simultaneously creating individuals with new traits. Therefore, in the NSGA-II algorithm, increasing the crossover probability accelerates the creation of individuals with new traits. However, a high crossover probability can impair the genetic mechanism; a low crossover probability can slow the algorithm's search and even prevent it from searching further. The mutation operation is designed to help the algorithm escape local optima. By simulating genetic mutations in organisms, it mutates some of an individual's genes, expanding the search space beyond existing combinations to obtain high-quality genes. Therefore, in the NSGA-II algorithm, a higher mutation probability yields a wider variety of individuals. However, a high mutation probability can make the algorithm's search process full of randomness, causing the population to lose its evolutionary direction; a low mutation probability can hinder the creation of new genetic structures. In the original NSGA-II algorithm, the crossover and mutation probabilities are fixed. In the long run, an algorithm with fixed crossover and mutation probabilities is not feasible. Therefore, this embodiment introduces an adaptive crossover and mutation operator that can adapt to the needs of population evolution.

[0208] The adaptive crossover and mutation operator enables adaptive adjustments during the evolutionary process as fitness changes. When the fitness of individuals in a population approaches consistency or a local optimum, the crossover and mutation probabilities are increased to accelerate the generation of new individuals and maintain diversity. When the fitness of individuals in a population disperses, the crossover and mutation probabilities are reduced to accelerate convergence. Furthermore, individuals with lower fitness than the population average are matched with lower crossover and mutation probabilities to protect them, while individuals with higher fitness are matched with higher crossover and mutation probabilities to filter them out. This adaptive crossover and mutation operator effectively adjusts the optimal probabilities, thereby maintaining population diversity while rapidly achieving optimization.

[0209] In the adaptive crossover mutation operator, the crossover and mutation probabilities are adjusted accordingly according to formulas (3-31) and (3-32), where the crossover probability is set to P c , the mutation probability is P m , Fit max Indicates the maximum fitness in the population, Fit avg represents the average fitness of the population; f maxIndicates the fitness of the two individuals to be crossed, which one has a larger fitness; f indicates the fitness of the individual to be mutated; k1, k2, k3, k4∈(0, 1).

[0210]

[0211] However, this adaptive crossover and mutation operator has limitations. Formulas (3-31) and (3-32) show that the closer an individual with a higher fitness is to its maximum fitness, the smaller the probability of crossover and mutation. When the individual's fitness equals the maximum fitness, the probability of crossover and mutation is zero. This approach hinders the algorithm's early evolution. Its biggest drawback is that it causes the algorithm to converge prematurely. That is, before the algorithm finds the global optimal solution, the offspring produced by the population evolution are no longer superior to the parent generation, and there is almost no difference between individuals in the offspring population. Thus, the excellent individuals in the early stages of the algorithm rarely change. However, these excellent individuals are not necessarily the global optimal solution at this time, which increases the possibility of the algorithm evolving to a local optimal solution. Formulas (3-33) and (3-34) are improvements to the above approach:

[0212]

[0213] Among them, P c1 =0.9, P c2 =0.6, P m1 =0.1, P m2 = 0.01. The improved adaptive crossover-mutation operator allows the crossover and mutation probabilities of individuals to change accordingly with evolution, which not only protects the excellent individuals in the population but also ensures that their probabilities are greater than 0, avoiding extreme situations and preventing excellent individuals from being in a state of almost no change.

[0214] The specific process of the improved NSGA-II algorithm is as follows Figure 2 As shown:

[0215] Step 1: Initialize the population using the good point set strategy, quickly sort the population using non-dominated methods, and then generate the first generation population through three basic operations: selection, crossover, and mutation.

[0216] Step 2: Following the steps of the elite retention strategy, the parent and offspring generations are first merged into a new population. At this time, the size of the new population is 2N. A fast non-dominated sort is performed on the composite population. In addition, the crowding degree of individuals in each non-dominated layer needs to be calculated to determine the optimal new parent population based on the non-dominated relationship and dynamic crowding degree.

[0217] Step 3: Perform selection, crossover, and mutation operations on the new parent population in Step 2 to generate a child population;

[0218] Step 4: When the maximum number of iterations is reached, output the Pareto optimal solution; otherwise, set Gen = Gen + 1 and return to Step 2 to repeat the cycle.

[0219] As an improvement to the above solution, the removal routes of various types of garbage at the garbage transfer station in different cycles are formulated based on the solution results, including:

[0220] Based on the solution to the optimal location and number of garbage transfer stations, for each decision cycle, according to the type and amount of garbage at the garbage generation point and the set timeliness constraints, a collection route that meets the timeliness and capacity constraints is planned.

[0221] In this embodiment, as an example:

[0222] According to the actual location of the city’s garbage transfer stations, a predetermined number of garbage generation points and the locations of the garbage transfer stations to be built are selected to ensure that the model and algorithm are implemented in actual scenarios.

[0223] Truck Cost Parameters: Fixed costs include the purchase of the truck, which is amortized daily using depreciation over a ten-year lifespan. The driver's salary is 6,000 yuan per month, or 200 yuan per day. Variable costs are the unit distance cost of transportation, primarily fuel costs, which vary depending on the distance traveled.

[0224] The speed of garbage collection vehicles is set at 40 km / h, in accordance with Zhuhai City regulations. Considering that food waste weighs more when compared to other types of garbage, the maximum volume of food waste at the garbage point is 120L, while the maximum volume of the other three types of garbage is 240L. Both early and late arrivals of garbage collection vehicles affect residents, so the waiting cost coefficient for early arrivals is set to α = 5, and the penalty cost coefficient for late arrivals is set to β = 10.

[0225] Frequency of Collection: Kitchen waste contains a large amount of organic matter and water, emitting a pungent odor that attracts mosquitoes and flies, significantly impacting residents' health and well-being. Therefore, it cannot be stored for long periods of time and must be collected daily. Other waste is produced in large quantities and is also prone to odor, requiring daily collection and removal. Recyclable waste has a smaller impact on the environment and can be stored for a longer period, typically requiring collection and removal once or twice a week. Hazardous waste is collected and temporarily stored at designated storage locations, typically requiring collection and removal once or twice a week. Based on the characteristics of Zhuhai's waste collection and transportation, this embodiment sets the timeliness for kitchen waste and other waste to one day, recyclable waste to three days, and hazardous waste to six days.

[0226] Driving distance: Based on the positional relationship between each garbage generation point and the garbage transfer station, draw a graph in Matlab to obtain the position of each node in the rectangular coordinate system.

[0227] Number of garbage transfer stations: The purpose of establishing a garbage transfer station is to temporarily store collected garbage pending transportation. Therefore, the number of garbage transfer stations needs to be sufficient to meet the collection and transportation volume. The multi-objective domestic garbage collection model established in this embodiment takes into account multi-cycle collection. That is, the garbage transfer station must at least meet the daily production of kitchen waste and other garbage, plus three days of recyclable waste, and six days of hazardous waste. This leads to the deduction that the number of garbage transfer stations is four.

[0228] The solution results are as follows:

[0229] The algorithm is applied to data from eight cycles. Under the garbage generation rate of eight cycles, in the improved NSGA-II algorithm, the population size popSize = 50 and the maximum number of iterations genMax = 100 are used. In multi-objective optimization problems, improving one sub-objective often degrades the performance of other objectives, making it impossible to optimize all objectives. Therefore, this example coordinates and compromises these two objectives, selecting the utopian solution on the Pareto frontier.

[0230] Site selection of garbage transfer stations: According to the previous analysis, four garbage transfer stations can meet the total amount of garbage generated by all residential areas. The addresses of the four transfer stations can be obtained by solving the problem.

[0231] Truck Dispatch Plan: Four waste transfer stations collect and transport four types of waste in the domestic waste collection system, resulting in an eight-cycle collection route plan. For kitchen waste and other waste, since both have a timeliness of 1, they are collected and transported every cycle, with the collection route varying based on the amount of waste to be collected at the source. For hazardous waste, collection is performed every six cycles, i.e., only when the timeliness is reached, not in advance. For recyclable waste, after the second cycle, it is collected and transported by the corresponding waste transfer station, and then every three cycles, i.e., when the timeliness is reached.

[0232] See also Figure 3 , is a schematic diagram of a structure of a domestic waste removal route planning device based on timeliness provided by one embodiment of the present invention. The domestic waste removal route planning device based on timeliness includes:

[0233] An acquisition module 10 is used to obtain the type and amount of garbage generated at each garbage generating point in the city during the garbage generation cycle;

[0234] Setting module 11, used to set the timeliness constraints of each garbage generation point according to the garbage type and generation amount, and establish an objective function to minimize the removal cost and the negative impact of the transfer station;

[0235] A solution module 12 is used to solve the objective function using an improved multi-objective genetic algorithm, taking into account the location distribution and transportation costs of each garbage point, as well as the negative impact of garbage transfer stations on residential areas, to determine the optimal location and number of garbage transfer stations;

[0236] The formulation module 13 is used to formulate the removal routes of various types of garbage at the garbage transfer station in different cycles according to the solution results.

[0237] The embodiment of the present invention first collects and analyzes the geographical coordinates, garbage types, and generation volume of each garbage generation point in the city; on this basis, corresponding timeliness constraints are set for different types of garbage to ensure that the garbage can be processed in a timely manner according to its characteristics; then, an improved multi-objective genetic algorithm is used to comprehensively evaluate the location distribution of garbage points, transportation costs, and the potential negative impact of garbage transfer stations on residential areas to solve the optimal location and number of garbage transfer stations; finally, based on the optimal solution provided by the algorithm, an efficient path planning scheme is formulated for garbage collection activities in different cycles. From the above analysis, it can be seen that the embodiment of the present invention can effectively optimize the location and transportation routes of garbage transfer stations, reduce transportation costs, improve transportation efficiency, and reduce the impact of garbage transfer stations on residential areas while meeting garbage collection needs.

[0238] As an improvement to the above solution, the setting module is specifically used to:

[0239] Classify and identify the garbage generated at each garbage generating point in the city and clarify the type of garbage it belongs to;

[0240] For different types of garbage, corresponding timeliness constraints are set based on their characteristics and impact on the environment and residents' health. For example, kitchen waste is set to be collected daily, recyclable waste is set to be collected 1-2 times a week, and hazardous waste is set to be collected 1-2 times every two weeks.

[0241] Establish an objective function to minimize the negative impact of transportation costs and transfer stations:

[0242]

[0243] Among them, d ij Represents the distance between node i and node j;

[0244] t ij represents the travel time of the cleaning truck from node i to node j;

[0245] t kvi represents the time required for vehicle kv to reach node i;

[0246] C k represents the fixed cost of the kth type of special removal vehicle;

[0247] C′ k represents the transportation cost per unit distance of the kth type of special transportation vehicle;

[0248] cap ew represents the maximum capacity of waste generation point e for w types of waste;

[0249] δ w represents the timeliness constraint of the wth type of garbage;

[0250] π d represents the fixed cost of building a transfer station at potential location D;

[0251] represents the amount of waste type w generated at the waste generation point e in the sth cycle;

[0252] represents the number of garbage collection vehicles kv used to transport type w garbage at garbage point e in cycle s; Q kvw It represents the cabin capacity of vehicle kv loaded with type w garbage;

[0253] a i represents the earliest time that node i is allowed to be cleared, where i∈A, A is the set of all i and j points;

[0254] b i represents the latest time allowed for clearing at node i, where i∈A, A is the set of all i and j points;

[0255] T i s It represents the time it takes for the truck to reach node i in the sth cycle, where i∈A, A is the set of all i and j points;

[0256] α represents the waiting cost incurred if the vehicle arrives early;

[0257] β represents the penalty cost incurred by the vehicle if it arrives late;

[0258] The decision variables are as follows:

[0259]

[0260] As an improvement to the above solution, the solution module is specifically used to:

[0261] Initialize the population: Generate the initial population using the population initialization method based on the good point set strategy to ensure the diversity and coverage of the population;

[0262] Fast non-dominated sorting: Perform non-dominated sorting on the current population, divide individuals into different non-dominated levels, and determine the ranking of each individual;

[0263] Calculate the crowding degree: Calculate the crowding degree of individuals in each non-dominated level to evaluate the distribution density of individuals in the objective function space;

[0264] Elite retention strategy: merge the parent and child populations, and select excellent individuals to form a new parent population through non-dominated sorting and crowding comparison;

[0265] Selection operation: According to the non-dominated sorting and crowding degree, individuals with good performance are selected to enter the next generation population;

[0266] Crossover operation: Perform a crossover operation on selected individuals to produce new offspring individuals by exchanging genetic information;

[0267] Mutation operation: perform mutation operations on offspring individuals to introduce new genetic diversity and prevent the algorithm from falling into local optimality;

[0268] Dynamic crowding distance strategy: During population evolution, the crowding calculation method is dynamically adjusted to maintain population diversity and uniform distribution;

[0269] Adaptive crossover and mutation operators: Adaptively adjust crossover and mutation probabilities based on the fitness distribution of the population to accelerate algorithm convergence and maintain population diversity;

[0270] Iterative evolution: Repeated selection, crossover, and mutation operations, and apply dynamic crowding distance strategy until the iteration termination condition is met;

[0271] Output Pareto optimal solution set: After the number of iterations or convergence criteria are met, the Pareto optimal solution set is output, which includes the location and number of garbage transfer stations for different schemes.

[0272] As an improvement to the above solution, the formulation module is specifically used to:

[0273] Based on the solution to the optimal location and number of garbage transfer stations, for each decision cycle, according to the type and amount of garbage at the garbage generation point and the set timeliness constraints, a collection route that meets the timeliness and capacity constraints is planned.

[0274] Another embodiment of the present invention provides a domestic waste collection route planning device based on timeliness, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the domestic waste collection route planning method based on timeliness described in the above-mentioned embodiment of the invention.

[0275] Another embodiment of the present invention provides a storage medium, wherein the computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the timeliness-based domestic waste collection path planning method described in the above-mentioned embodiment of the invention.

[0276] See also Figure 4 , is a schematic diagram of a time-effective domestic waste removal route planning device provided by an embodiment of the present invention. The time-effective domestic waste removal route planning device of this embodiment includes: a processor 100, a memory 101, and a computer program stored in the memory and executable on the processor 100, such as a time-effective domestic waste removal route planning program. When the processor 100 executes the computer program, the steps of each of the above-mentioned time-effective domestic waste removal route planning method embodiments are implemented. Alternatively, when the processor 100 executes the computer program, the functions of each module / unit in the above-mentioned device embodiments are implemented.

[0277] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution process of the computer program in the timeliness-based domestic waste removal route planning device.

[0278] The time-effectiveness-based domestic waste removal route planning device can be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The time-effectiveness-based domestic waste removal route planning device can include, but is not limited to, a processor and a memory. Those skilled in the art will understand that the schematic diagram is merely an example of a time-effectiveness-based domestic waste removal route planning device and does not constitute a limitation on the time-effectiveness-based domestic waste removal route planning device. It can include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the time-effectiveness-based domestic waste removal route planning device can also include input and output devices, network access devices, buses, etc.

[0279] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the time-based domestic waste removal route planning device, and utilizes various interfaces and lines to connect the various parts of the entire time-based domestic waste removal route planning device.

[0280] The memory can be used to store the computer program and / or module, and the processor realizes the various functions of the time-based domestic waste removal route planning device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created based on the use of the mobile phone (such as audio data, a phone book, etc.). In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0281] Wherein, if the module / unit integrated in the timeliness-based domestic waste removal route planning device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, it can implement the steps of the above-mentioned various method embodiments. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practices in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practices, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0282] It should be noted that the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed across multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. In addition, in the drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art can understand and implement the present invention without inventive effort.

[0283] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for planning a domestic waste removal route based on timeliness, characterized in that: include: Obtain the type and amount of garbage generated at each garbage generating point in the city during the garbage generation cycle; Set time constraints for each garbage generation point based on garbage type and generation volume, and establish an objective function that minimizes the cost of removal and the negative impact of transfer stations; An improved multi-objective genetic algorithm is used to solve the objective function. The optimal location and number of garbage transfer stations are determined by combining the location distribution and transportation costs of each garbage point, as well as the negative impact of garbage transfer stations on residential areas. According to the solution results, formulate the removal routes of various types of garbage at the garbage transfer station in different cycles; The improved multi-objective genetic algorithm is used to solve the objective function, and the optimal location and number of garbage transfer stations are solved by combining the location distribution and transportation costs of each garbage point, as well as the negative impact of garbage transfer stations on residential areas, including: Initialize the population: Generate the initial population using the population initialization method based on the good point set strategy to ensure the diversity and coverage of the population; Among them, the population initialization method based on the good point set strategy is introduced as follows: define Gs as an S-dimensional Euclidean geometric space, define r as a good point, , ,in , , For the best point collection, Represents the good point set The deviation, Is a The relevant constants are: ; According to the definition of the good point set, the steps for constructing the initial population of the algorithm are: Step 1: Define the initial population good point set containing n points ;Step2: s is the dimension of the Euclidean geometric space, is satisfied The minimum prime number of each point in the good point set R , then according to formula (3-29) we can calculate : ;;Step 3: Definition 、 The maximum and minimum values ​​of the domain of the independent variable of dimension j are adjusted by formula (3-30) Location, guaranteed are within their respective domains: ; Fast non-dominated sorting: Perform non-dominated sorting on the current population, divide individuals into different non-dominated levels, and determine the ranking of each individual; the specific steps are as follows: Step 1: Assume that the population The scale is N, and the parameter and collection ,in , Record the number of individuals dominated by individual p in the population, is the set of individuals dominated by individual p in the population; Step 2: Calculate the parameters and collection ,Will The individuals are placed in the first level collection In the set, the same non-dominated order is set for the individuals in the set ;Step3: Traverse the collection The individual p , for the set Individuals in Remove the number dominated by the first layer of individuals and execute ,like , then the individual Put it into the next level of collection, ; Step 4: Repeat the above steps until all individuals in the population are stratified; Calculate the crowding degree: Calculate the crowding degree of individuals in each non-dominated level to evaluate the distribution density of individuals in the objective function space; Elite retention strategy: merge the parent and child populations, and select excellent individuals to form a new parent population through non-dominated sorting and crowding comparison; Selection operation: According to the non-dominated sorting and crowding degree, individuals with good performance are selected to enter the next generation population; Crossover operation: Perform a crossover operation on selected individuals to produce new offspring individuals by exchanging genetic information; Mutation operation: perform mutation operations on offspring individuals to introduce new genetic diversity and prevent the algorithm from falling into local optimality; Dynamic crowding distance strategy: During population evolution, the crowding calculation method is dynamically adjusted to maintain population diversity and uniform distribution; Adaptive crossover and mutation operators: Adaptively adjust crossover and mutation probabilities based on the fitness distribution of the population to accelerate algorithm convergence and maintain population diversity; Iterative evolution: Repeated selection, crossover, and mutation operations, and apply dynamic crowding distance strategy until the iteration termination condition is met; Output Pareto optimal solution set: After the number of iterations or convergence criteria are met, the Pareto optimal solution set is output. This solution set includes the location and number of garbage transfer stations for different schemes. The timeliness constraints for each garbage generation point are set according to the type and amount of garbage generated, and an objective function is established to minimize the removal costs and the negative impact of the transfer station, including: Classify and identify the garbage generated at each garbage generating point in the city and clarify the type of garbage it belongs to; For different types of garbage, corresponding timeliness constraints are set based on their characteristics and impact on the environment and residents' health. For example, kitchen waste is set to be collected daily, recyclable garbage is set to be collected 1-2 times a week, and hazardous waste is set to be collected 1-2 times every two weeks. Establish an objective function to minimize the negative impact of transportation costs and transfer stations: ； in, Representation node To Node the distance between them; Representation node To Node The driving time of the cleaning truck; Indicates vehicle Arrival Node the time required; Indicates the Fixed costs of various types of specialized removal vehicles; Indicates the The transportation cost per unit distance of each type of special transportation vehicle; Indicates the point where garbage is generated right Maximum capacity of each type of garbage; Indicates the Time constraints on the production of garbage; Indicates potential location fixed costs of building a transfer station; Indicates the Cycle waste generation point Types of garbage The amount of production; Indicates the Cycle-use recycling vehicles At the garbage point Clearance The amount of garbage of this type; Indicates vehicle load The capacity of the vehicle compartment for garbage of this type; Representation node The earliest time allowed for removal, including , For all 、 A collection of points; Representation node The latest time allowed for removal, including ; Indicates the Periodic cleaning vehicle reaches the node The time at which ; represents the waiting cost incurred if the vehicle arrives early; represents the penalty cost incurred by the vehicle if it arrives late; The decision variables are as follows: ； ； ； ； 。 2. The method for planning a domestic waste removal route based on timeliness according to claim 1, characterized in that: According to the solution results, the removal routes of various types of garbage at the garbage transfer station in different cycles are formulated, including: Based on the solution to the optimal location and number of garbage transfer stations, for each decision cycle, according to the type and amount of garbage at the garbage generation point and the set timeliness constraints, a collection route that meets the timeliness and capacity constraints is planned.

3. A household garbage removal route planning device based on timeliness, characterized in that: include: An acquisition module is used to obtain the type and amount of garbage generated at each garbage generating point in the city during the garbage generation cycle; The setting module is used to set the timeliness constraints of each garbage generation point according to the garbage type and generation volume, and establish an objective function to minimize the removal cost and the negative impact of the transfer station; The solution module is used to solve the objective function using an improved multi-objective genetic algorithm. It combines the location distribution and transportation costs of each garbage point, as well as the negative impact of garbage transfer stations on residential areas, to determine the optimal location and number of garbage transfer stations. The formulation module is used to formulate the removal routes of various types of garbage at the garbage transfer station in different cycles based on the solution results; The solution module is specifically used for: Initialize the population: Generate the initial population using the population initialization method based on the good point set strategy to ensure the diversity and coverage of the population; Among them, the population initialization method based on the good point set strategy is introduced as follows: define Gs as an S-dimensional Euclidean geometric space, define r as a good point, , ,in , , For the best point collection, Represents the good point set The deviation, Is a The relevant constants are: ;; According to the definition of the good point set, the steps for constructing the initial population of the algorithm are: Step 1: Define the initial population good point set containing n points ;Step2: s is the dimension of the Euclidean geometric space, is satisfied The minimum prime number of each point in the good point set R , then according to formula (3-29) we can calculate : ;Step 3: Definition 、 The maximum and minimum values ​​of the domain of the independent variable of dimension j are adjusted by formula (3-30) Location, guaranteed are within their respective domains: ; Fast non-dominated sorting: Perform non-dominated sorting on the current population, divide individuals into different non-dominated levels, and determine the ranking of each individual; the specific steps are as follows: Step 1: Assume that the population The scale is N, and the parameter and collection ,in , Record the number of individuals dominated by individual p in the population, is the set of individuals dominated by individual p in the population; Step 2: Calculate the parameters and collection ,Will The individuals are placed in the first level collection In the set, the same non-dominated order is set for the individuals in the set ;Step3: Traverse the collection The individual p , for the set Individuals in Remove the number dominated by the first layer of individuals and execute ,like , then the individual Put it into the next level of collection, ; Step 4: Repeat the above steps until all individuals in the population are stratified; Calculate the crowding degree: Calculate the crowding degree of individuals in each non-dominated level to evaluate the distribution density of individuals in the objective function space; Elite retention strategy: merge the parent and child populations, and select excellent individuals to form a new parent population through non-dominated sorting and crowding comparison; Selection operation: According to the non-dominated sorting and crowding degree, individuals with good performance are selected to enter the next generation population; Crossover operation: Perform a crossover operation on selected individuals to produce new offspring individuals by exchanging genetic information; Mutation operation: perform mutation operations on offspring individuals to introduce new genetic diversity and prevent the algorithm from falling into local optimality; Dynamic crowding distance strategy: During population evolution, the crowding calculation method is dynamically adjusted to maintain population diversity and uniform distribution; Adaptive crossover and mutation operators: Adaptively adjust crossover and mutation probabilities based on the fitness distribution of the population to accelerate algorithm convergence and maintain population diversity; Iterative evolution: Repeated selection, crossover, and mutation operations, and apply dynamic crowding distance strategy until the iteration termination condition is met; Output Pareto optimal solution set: After the number of iterations or convergence criteria are met, the Pareto optimal solution set is output. This solution set includes the location and number of garbage transfer stations for different schemes. The setting module is specifically used for: Classify and identify the garbage generated at each garbage generating point in the city and clarify the type of garbage it belongs to; For different types of garbage, corresponding timeliness constraints are set based on their characteristics and impact on the environment and residents' health. For example, kitchen waste is set to be collected daily, recyclable garbage is set to be collected 1-2 times a week, and hazardous waste is set to be collected 1-2 times every two weeks. Establish an objective function to minimize the negative impact of transportation costs and transfer stations: ； in, Representation node To Node the distance between them; Representation node To Node The driving time of the cleaning truck; Indicates vehicle Arrival Node the time required; Indicates the Fixed costs of various types of specialized removal vehicles; Indicates the The transportation cost per unit distance of each type of special transportation vehicle; Indicates the point where garbage is generated right Maximum capacity of each type of garbage; Indicates the Time constraints on the production of garbage; Indicates potential location fixed costs of building a transfer station; Indicates the Cycle waste generation point Types of garbage The amount of production; Indicates the Cycle-use recycling vehicles At the garbage point Clearance The amount of garbage of this type; Indicates vehicle load The capacity of the vehicle compartment for garbage of this type; Representation node The earliest time allowed for removal, including , For all 、 A collection of points; Representation node The latest time allowed for removal, including ; Indicates the Periodic cleaning vehicle reaches the node The time at which ; represents the waiting cost incurred if the vehicle arrives early; represents the penalty cost incurred by the vehicle if it arrives late; The decision variables are as follows: ； ； ； ； 。 4. The time-effective domestic waste removal route planning device according to claim 3, characterized in that: The formulation module is specifically used for: Based on the solution to the optimal location and number of garbage transfer stations, for each decision cycle, according to the type and amount of garbage at the garbage generation point and the set timeliness constraints, a collection route that meets the timeliness and capacity constraints is planned.

5. A household garbage removal route planning device based on timeliness, characterized in that: It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the timeliness-based domestic waste removal path planning method as described in any one of claims 1 to 2.

6. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored computer program, wherein, when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the timeliness-based domestic waste removal path planning method as described in any one of claims 1 to 2.

Images