Municipal solid waste collection and transportation vehicle scheduling method based on genetic algorithm

Abstract

The invention discloses a municipal solid waste collection and transportation vehicle scheduling method based on a genetic algorithm. A basic data set in a service area is collected through an informatization means; according to the historical garbage amount data, calculating an average value of different types of garbage amounts every day, and predicting different types of garbage amounts every day in the future; different garbage collection points in the region are positioned, and clustering partition of the garbage collection points is realized according to the idea of a K-means clustering algorithm; the method comprises the following steps: performing qualitative analysis on targets and limiting conditions influencing classified collection and transportation of municipal solid waste, taking a collection and transportation link as a research object, adopting VRP, and establishing a waste reverse logistics network planning model by taking cost minimization as a target; and solving the garbage reverse logistics network optimization model by using a genetic algorithm, calculating the minimum configuration number of vehicles and vehicle paths, and forming a garbage collection and transportation vehicle scheduling scheme. According to the invention, the optimal configuration and route of the collection and transportation vehicles of a large number of garbage collection points within the range are intelligently analyzed.

Description

[0001] This application is a divisional application of the patent application entitled "A method for dispatching urban domestic waste collection and transportation vehicles based on genetic algorithm". The application date of the original application is December 28, 2021, and the application number is 202111623565.1. Technical Field

[0002] The present invention relates to the technical field of intelligent vehicle configuration, and in particular to a method for dispatching urban domestic waste collection and transportation vehicles based on a genetic algorithm. Background Art

[0003] The volume of domestic waste collected and transported in my country has been increasing year by year, reaching 242.06 million tons in 2019, and has maintained an annual growth rate of approximately 10% in recent years. Chinese cities need to deal with large quantities of domestic waste annually, and addressing the challenges of waste sorting at the source and at the end of life. Studying the scheduling of vehicles for sorted domestic waste collection and transportation from a reverse logistics perspective is of great practical significance. Optimizing waste collection and transportation vehicle scheduling can address the current issues of inefficiency and resource waste, providing a reference for regions experiencing poor waste sorting. Optimizing the design of urban waste collection and transportation routes can improve waste collection efficiency, reduce collection and transportation costs, and expedite the timely processing of large volumes of waste. Reasonable waste collection and transportation routing directly impacts the logistics and transportation costs of the reverse logistics network while ensuring the timely collection and treatment of waste at collection points, minimizing the impact on the living environment of surrounding residents. Summary of the Invention

[0004] In order to overcome the deficiencies in the prior art, the present invention aims to provide an online voice chat system based on instant translation.

[0005] To achieve the above object, the present invention provides the following solutions:

[0006] A method for dispatching urban domestic waste collection and transportation vehicles based on a genetic algorithm comprises the following steps:

[0007] (1) Collect basic data sets within the service area through information technology; information technology means include installing smart trash cans, issuing garbage classification score cards, and intelligent weighing of classification vehicles; the basic data sets include garbage classification categories, daily amount of different types of garbage, daily total amount of garbage, type of collection and transportation vehicles, fuel consumption of collection and transportation vehicles, number of collection and transportation vehicles, number of employees equipped for different types of collection and transportation vehicles, load capacity of collection and transportation vehicles, and trajectory data of collection and transportation vehicles;

[0008] (2) Based on historical garbage volume data, calculate the average daily volume of different types of garbage and predict the daily volume of different types of garbage in the future; the historical garbage volume data refers to the amount of different types of garbage per day, calculate and count the historical garbage volume in the service area, and predict the daily volume of four different types of garbage, namely, perishable garbage, recyclable garbage, hazardous garbage and other garbage in the future. By calculating the daily average values of the four types of garbage, find a regular curve and predict the daily average values of different types of garbage in the future;

[0009] (3) Locate different garbage collection points in the area and realize clustering and partitioning of garbage collection points based on the idea of K-means clustering algorithm;

[0010] (4) Conduct a qualitative analysis of the objectives and constraints that affect the classified collection and transportation of urban domestic waste, adopt VRP with the collection and transportation link as the research object, and establish a waste reverse logistics network planning model with the goal of cost minimization;

[0011] (5) Using genetic algorithms to solve the garbage reverse logistics network optimization model, calculate the minimum number of vehicles and vehicle routes, and form a garbage collection and transportation vehicle scheduling plan;

[0012] The cost in step (4) is the sum of transportation cost and vehicle fixed cost;

[0013] The step (4) comprises the following steps:

[0014] (41) Let N be the set of garbage collection points, where N = 0 represents the starting point, K is the set of collection vehicles, and S is the set of collection points visited by a certain vehicle. The model parameters are set according to this mathematical representation, the maximum load of the vehicle is set to P, and the distance between collection points i and j is set to d. ij , set the unit distance transportation cost of vehicle k to be c k , set the fixed cost of vehicle k to c0;

[0015] (42) Set the minimum number of collection and transportation vehicles within the garbage collection and transportation service area to min n;

[0016] (43) Assuming that each collection point can only be served by one vehicle and can only be visited once, according to the formula: and To impose restraints;

[0017] (44) Assume that the number of vehicles entering and leaving each collection point is equal except for the starting point and the end point. The collection and transportation vehicles entering a collection point must also leave from that point. According to the formula: Perform flow conservation constraints;

[0018] (45) Assume that each vehicle starts from the garbage vehicle collection point and must return to the garbage vehicle collection point after completing the service. According to the formula and To impose restraints;

[0019] (46) Set the capacity limit of the collection and transportation vehicles to ensure that the load of each vehicle cannot exceed the vehicle limit, according to the formula To impose restraints;

[0020] (47) x ijk and y ijk Defined for 0-1 integer decision variables:

[0021]

[0022] The step (5) comprises the following steps:

[0023] (51) Chromosome encoding mechanism and population initialization: Assume that the garbage collection center collects garbage from N garbage collection points, then the garbage collection points are numbered in sequence, from 1 to N; all the different numbered arrangements can be regarded as different chromosomes, and each chromosome represents the order in which the garbage collection station collects garbage from the collection points. At the same time, each garbage collection point has its own additional attribute, namely the amount of garbage;

[0024] (52) Fitness function: After generating the initial population, the fitness function is calculated for each chromosome. For a garbage collection center, the smaller the total distance traveled after collecting garbage from all garbage collection points, the greater the fitness. For the garbage reverse logistics network optimization model, the fitness function of x is defined as:

[0025] F(x)=C max -f(x)

[0026] In the formula, f(x) is the objective function value corresponding to individual x, F(x) is the relative fitness obtained, and C max is the maximum estimate of F(x). The larger the F(x) value, the better the individual is, that is, the smaller the travel distance;

[0027] While calculating the fitness function, the chromosome is also decoded to convert the chromosome into a vehicle path plan. The model has a constraint on the maximum load of the vehicle, and the path is divided when the constraint is met.

[0028] (53) Crossover operator: A sequential crossover algorithm is used to exchange garbage collection points between two paths, changing their positions to generate new service routes, thereby increasing the search range of the problem solution and improving the diversity of the population;

[0029] (54) Mutation operator: Using the double insertion method, two consecutive genes are extracted from a chromosome and inserted into other positions of the chromosome. The solution is recorded and compared with the original solution at each insertion position. If the current solution is better than the original solution, the original solution is replaced. Considering that the solution is a closed curve, in order to avoid duplication, the gene insertion position avoids the position before the first gene and the position after the last gene.

[0030] (55) Restore the optimal garbage collection and transportation sequence based on the obtained optimal garbage collection and transportation ordered sequence, and end;

[0031] The step (53) comprises the following steps:

[0032] (531) Two parent chromosomes P1 and P2 are randomly selected from the initial population, i.e., two service orders for garbage collection at garbage collection points; a single gene in the chromosome represents a single garbage collection point, and a gene fragment represents a set of multiple garbage collection points with service orders;

[0033] (532) Gene fragments at the same position in P1 and P2 were randomly selected and denoted as changel and change2, respectively;

[0034] (533) First find the position of change 1 in P2, then place change 1 in the same position in P2, and delete the gene in P2 that is identical to change 1;

[0035] (534) First find the position of change 2 in P1, then place change 2 in the same position in P1, and delete the gene in P1 that is the same as change 2. The crossover operation is completed to generate offspring C1 and C2.

[0036] Beneficial effects: Compared with the existing technology, the beneficial effects of the present invention are: the present invention can accurately calculate the transportation cost of garbage collection and transportation vehicles in the area, and intelligently analyze the optimal configuration and routes of collection and transportation vehicles for a large number of garbage collection points within the range. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0038] Figure 1 is a flow chart of the present invention;

[0039] Figure 2 Result graph for cluster partitioning solution;

[0040] Figure 3 Flowchart for solving the optimization model of waste reverse logistics network;

[0041] Figure 4 Schematic diagram of crossover operator;

[0042] Figure 5 It is a double insertion schematic diagram;

[0043] Figure 6 This is the result graph of genetic algorithm solution. DETAILED DESCRIPTION

[0044] 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. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0045] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0046] The terms "first," "second," "third," and "fourth," etc., in the specification, claims, and drawings of this application are used to distinguish between different items, not to describe a particular order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a statement that a sequence of steps, a process, or a method is included is not limited to the listed steps but may optionally include steps not listed, or may optionally include other steps inherent to the process, method, product, or apparatus.

[0047] The present invention provides a method for dispatching urban domestic waste collection and transportation vehicles based on genetic algorithm. Figure 1 As shown, the specific steps include:

[0048] Step 1: Collect basic data sets within the service area through information technology.

[0049] Information technology initiatives include installing smart trash cans, issuing waste sorting points cards, and intelligent weighing of waste sorting vehicles. Basic data sets include waste sorting categories, daily waste quantities by type, total daily waste volume, collection and transportation vehicle types, fuel consumption, number of collection and transportation vehicles, number of staff assigned to different types of collection and transportation vehicles, vehicle loads, and vehicle trajectory data.

[0050] Step 2: Based on historical garbage volume data, calculate the average daily volume of different types of garbage and predict the daily volume of different types of garbage in the future.

[0051] Historical garbage data refers to the amount of different types of garbage every day. The historical garbage volume in the service area is calculated and counted, and the future daily amount of four different types of garbage, namely, perishable garbage, recyclable garbage, hazardous garbage and other garbage, is predicted. By calculating the daily average values of the four types of garbage, a regular curve is found to predict the daily average values of different types of garbage in the future.

[0052] Step 3: Locate different garbage collection points in the area and implement clustering and partitioning of garbage collection points based on the idea of K-means clustering algorithm.

[0053] Assume that there are N unevenly distributed garbage collection points, randomly select k points as the initial cluster center points, calculate and record the distances from the remaining points to the k initial center points, select the smallest distance and classify them into the class of the corresponding initial center point, then calculate the average value in each class and update the initial center point until the clustering criterion function converges and stops updating. Finally, all garbage collection points in the area are divided into k areas. The specific solution is as follows Figure 2 shown.

[0054] Step 4: Conduct a qualitative analysis of the goals and constraints that affect the classified collection and transportation of urban domestic waste. Taking the collection and transportation link as the research object, use VRP-related knowledge to propose assumptions for establishing a waste reverse logistics network planning model and establish a corresponding mathematical model.

[0055] The garbage reverse logistics network planning model takes into account constraints such as vehicle load and number of collection and transportation times, and is established with the goal of minimizing costs (transportation costs + vehicle fixed costs).

[0056] Assume N is the set of garbage collection points, where N=0 represents the starting point, K is the set of collection vehicles, and S is the set of collection points visited by a certain vehicle. According to this mathematical representation, the model parameters are set, the maximum load of the vehicle is set to P, and the distance between collection points i and j is set to d. ij , set the unit distance transportation cost of vehicle k to be c k, set the fixed cost of vehicle k to c0. Set the minimum number of collection vehicles configured within the garbage collection and transportation service area to min n; set each collection point to be served by only one vehicle and can only be visited once, according to the formula: and Constraints are set; except for the starting point and the end point, the number of vehicles entering and leaving each collection point is equal, and the collection and transportation vehicles entering a collection point must also leave from this point, according to the formula: Carry out flow conservation constraints; assume that each vehicle starts from the garbage vehicle concentration point and must return to the garbage vehicle concentration point after service. According to the formula and Constraints are set; capacity limits for collection and transportation vehicles are set to ensure that the load of each vehicle does not exceed the vehicle limit, according to the formula Constraints on x ijk and y ijk Defined for 0-1 integer decision variables:

[0057] Step 5: Use genetic algorithms to analyze and calculate the configuration of collection and transportation vehicles within the work area to obtain the optimal vehicle configuration and path planning method, and form a garbage collection and transportation vehicle scheduling plan. The specific solution process is as follows: Figure 3 shown.

[0058] (1) Chromosome encoding mechanism and initialization population. The chromosome encoding rule in the algorithm is: Assuming that the garbage collection center collects garbage from N garbage collection points, the garbage collection points are numbered in sequence, from 1 to N. All the different numbered arrangements can be regarded as different chromosomes. Each chromosome represents the order in which the garbage collection station collects garbage collection points. At the same time, each garbage collection point has its own additional attribute, namely the amount of garbage. As shown in Table 1, in this chromosome, the garbage collection point numbered 5 is the first to be collected, and its garbage amount is 16.29; the garbage collection point numbered 4 is the second to be collected, and its garbage amount is 38.21. The initialization population contains a collection of multiple chromosomes mentioned above, and all chromosomes are generated by randomly permuting the numbers of N garbage collection points.

[0059] Table 1 Chromosome example table

[0060] 5 4 2 3 1 6 8 7 16.29 38.21 116.10 82.43 27.22 125.53 43.59 28.95

[0061] (2) Fitness function. After generating the initial population, the fitness function is calculated for each chromosome. The MSRCP problem uses travel distance as a measure of fitness. For a garbage collection center, the smaller the total distance traveled to collect garbage from all collection points, the greater the fitness.

[0062] For the garbage reverse logistics network optimization model, define the fitness function of x:

[0063] F(x)=C max -f(x)

[0064] In the formula, f(x) is the objective function value corresponding to individual x, F(x) is the relative fitness obtained, and C max is the maximum estimate of F(x). The larger the F(x) value, the better the individual is, that is, the smaller the travel distance.

[0065] While calculating the fitness function, the chromosomes are also decoded, converting them into vehicle routing solutions. The model imposes constraints on the vehicle's maximum load capacity, and the paths are divided based on these constraints. As shown in Table 1, the chromosomes are encoded as {5, 4, 2, 3, 1, 6, 8, 7}. Given the amount of garbage at each collection point, and assuming a maximum vehicle load capacity of 300, the first vehicle can collect garbage from five collection points numbered 5, 4, 2, 3, and 1, while the second vehicle can collect garbage from three collection points numbered 6, 8, and 7. This yields two paths: 5, 4, 2, 3, 1 → 6, 8, 7, completing the decoding process.

[0066] (3) Crossover operator. The sequential crossover algorithm is used to exchange garbage collection points between two paths, changing their positions to generate new service routes, which increases the search range of the problem solution and improves the diversity of the population. Figure 4 The specific steps are as follows:

[0067] S1: Randomly select two parent chromosomes P1 and P2 from the initial population, representing two service orders for garbage collection points. A single gene in the chromosome represents a single garbage collection point, and a gene segment represents a set of multiple garbage collection points with a service order.

[0068] S2: Randomly select gene fragments at the same position in P1 and P2, and record them as change1 and change2 respectively;

[0069] S3: First find the position of change 1 in P2, then put change 1 into the same position in P2, and delete the gene in P2 that is identical to change 1;

[0070] S4: First find the position of change 2 in P1, then put change 2 into the same position in P1, and delete the gene in P1 that is the same as change 2. The crossover operation is completed to generate offspring C1 and C2.

[0071] (4) Mutation operator. Figure 5As shown in Figure 1, the double insertion method uses two consecutive genes extracted from a chromosome and inserted into different locations on the chromosome. The solution for each insertion is recorded and compared with the original solution. If the current solution is better than the original, it is replaced. Again, considering the solution to be a closed curve, to avoid duplication, the gene insertion position avoids the position before the first gene and the position after the last gene.

[0072] (5) According to the obtained optimal garbage collection and transportation ordered sequence, the optimal garbage collection and transportation order is restored to obtain the optimal collection and transportation route plan for garbage collection and transportation vehicles, such as Figure 6 As shown, end.

[0073] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0074] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The above examples are only intended to help understand the method and core concept of the present invention. At the same time, those skilled in the art will find that the specific implementation methods and application scopes may vary based on the concept of the present invention. In summary, the contents of this specification should not be construed as limiting the present invention.

Claims

1. A method for dispatching municipal solid waste collection and transportation vehicles based on genetic algorithm, characterized in that: The following steps are involved: (1) Collect basic data sets within the service area through information technology; information technology means include installing smart trash cans, issuing garbage classification score cards, and intelligent weighing of classification vehicles; the basic data sets include garbage classification categories, daily amount of different types of garbage, daily total amount of garbage, type of collection and transportation vehicles, fuel consumption of collection and transportation vehicles, number of collection and transportation vehicles, number of employees equipped for different types of collection and transportation vehicles, load capacity of collection and transportation vehicles, and trajectory data of collection and transportation vehicles; (2) Based on historical garbage volume data, calculate the average daily volume of different types of garbage and predict the daily volume of different types of garbage in the future; the historical garbage volume data refers to the amount of different types of garbage per day, calculate and count the historical garbage volume in the service area, and predict the daily volume of four different types of garbage, namely, perishable garbage, recyclable garbage, hazardous garbage and other garbage in the future. By calculating the daily average values of the four types of garbage, find a regular curve and predict the daily average values of different types of garbage in the future; (3) Locate different garbage collection points in the area and realize clustering and partitioning of garbage collection points based on the idea of K-means clustering algorithm; (4) Conduct a qualitative analysis of the objectives and constraints that affect the classified collection and transportation of urban domestic waste, adopt VRP with the collection and transportation link as the research object, and establish a waste reverse logistics network planning model with the goal of cost minimization; (5) Using genetic algorithms to solve the garbage reverse logistics network optimization model, calculate the minimum number of vehicles and vehicle routes, and form a garbage collection and transportation vehicle scheduling plan; The cost in step (4) is the sum of transportation cost and vehicle fixed cost; The step (4) comprises the following steps: (41) Let N be the set of garbage collection points, where N = 0 represents the starting point, K is the set of collection vehicles, and S is the set of collection points visited by a certain vehicle. The model parameters are set according to this mathematical representation, the maximum load of the vehicle is set to P, and the distance between collection points i and j is set to d. ij , set the unit distance transportation cost of vehicle k to be c k , set the fixed cost of vehicle k to c0; (42) Set the minimum number of collection and transportation vehicles within the garbage collection and transportation service area to min n; (43) Assuming that each collection point can only be served by one vehicle and can only be visited once, according to the formula: and To impose restraints; (44) Assume that the number of vehicles entering and leaving each collection point is equal except for the starting point and the end point. The collection and transportation vehicles entering a collection point must also leave from that point. According to the formula: Perform flow conservation constraints; (45) Assume that each vehicle starts from the garbage vehicle collection point and must return to the garbage vehicle collection point after completing the service. According to the formula and To impose restraints; (46) Set the capacity limit of the collection and transportation vehicles to ensure that the load of each vehicle cannot exceed the vehicle limit, according to the formula To impose restraints; (47) x ijk and y ijk Defined for 0-1 integer decision variables: The step (5) comprises the following steps: (51) Chromosome encoding mechanism and population initialization: Assuming that the garbage collection center collects garbage from N garbage collection points, the garbage collection points are numbered in sequence from 1 to N; all the different numbered arrangements can be regarded as different chromosomes, and each chromosome represents the order in which the garbage collection station collects garbage from the collection points. At the same time, each garbage collection point has its own additional attribute, namely the amount of garbage; (52) Fitness function: After generating the initial population, the fitness function is calculated for each chromosome. For a garbage collection center, the smaller the total distance traveled after collecting garbage from all garbage collection points, the greater the fitness. For the garbage reverse logistics network optimization model, the fitness function of x is defined as: F(x)=C max -f(x) In the formula, f(x) is the objective function value corresponding to individual x, F(x) is the relative fitness obtained, and C max is the maximum estimate of F(x). The larger the F(x) value, the better the individual is, that is, the smaller the travel distance; While calculating the fitness function, the chromosome is also decoded to convert the chromosome into a vehicle path plan. The model has a constraint on the maximum load of the vehicle, and the path is divided when the constraint is met. (53) Crossover operator: A sequential crossover algorithm is used to exchange garbage collection points between two paths, changing their positions to generate new service routes, thereby increasing the search range of the problem solution and improving the diversity of the population; (54) Mutation operator: Using the double insertion method, two consecutive genes are extracted from a chromosome and inserted into other positions of the chromosome. The solution is recorded and compared with the original solution at each insertion position. If the current solution is better than the original solution, the original solution is replaced. Considering that the solution is a closed curve, in order to avoid duplication, the gene insertion position avoids the position before the first gene and the position after the last gene. (55) Restore the optimal garbage collection and transportation sequence based on the obtained optimal garbage collection and transportation ordered sequence, and end; The step (53) comprises the following steps: (531) Two parent chromosomes P1 and P2 are randomly selected from the initial population, i.e., two service orders for garbage collection at garbage collection points; a single gene in the chromosome represents a single garbage collection point, and a gene fragment represents a set of multiple garbage collection points with service orders; (532) Gene fragments at the same position in P1 and P2 were randomly selected and denoted as changel and change2, respectively; (533) First find the position of change 1 in P2, then place change 1 in the same position in P2, and delete the gene in P2 that is identical to change 1; (534) First find the position of change 2 in P1, then place change 2 in the same position in P1, and delete the gene in P1 that is the same as change 2. The crossover operation is completed to generate offspring C1 and C2.

Images