Simulation optimization method and system for recyclable express packaging recycling network

Abstract

The present invention belongs to the field of express recycling technology and discloses a simulation optimization method and system for a recyclable express packaging recycling network. The method includes: obtaining service facility data of the recyclable express packaging recycling network; defining intelligent agent types based on the service facility data, wherein the intelligent agent types include demand points and service nodes, the demand points realize the functions of communities or consumers, and the service nodes realize the functions of recycling centers, recycling stations, and recycling vehicles; constructing an optimization objective function based on vehicle service time and operating costs; after the demand points and the service nodes perform recycling station evolution, equilibrium evolution, and path evolution according to the optimization objective function, obtaining the optimization results of the optimization objective function, and realizing simulation optimization of the recyclable express packaging recycling network based on the optimization results. It can improve the recycling efficiency of recyclable express packaging while reducing operating costs.

Description

Technical Field

[0001] The present invention relates to the field of express recycling technology, and in particular to a simulation optimization method and system for a recyclable express packaging recycling network. Background Art

[0002] Reducing the resource and environmental burden caused by express packaging waste is urgent. Promoting the recycling of express packaging has become a key component of building green, low-carbon cities. This not only effectively controls packaging waste but also reduces carbon emissions and resource consumption associated with packaging materials. However, the high time and financial costs of recycling express packaging make it difficult for many express delivery companies to adopt recyclable packaging, leading to limited widespread adoption and low market acceptance. Therefore, establishing an efficient and low-cost recycling network for recyclable express packaging is a pressing issue for express delivery companies. Summary of the Invention

[0003] The main purpose of the present invention is to provide a simulation optimization method and system for a recyclable express packaging recycling network, aiming to solve the technical problem in the prior art that recyclable express packaging is difficult to promote and be recognized by the market due to its low efficiency and high cost.

[0004] To achieve the above objectives, the present invention provides a simulation optimization method for a recyclable express packaging recycling network, the method comprising the following steps:

[0005] Obtain service facility data of the recyclable express packaging recycling network;

[0006] Defining agent types according to the service facility data, wherein the agent types include demand points and service nodes, the demand points realizing the functions of a community or a consumer, and the service nodes realizing the functions of a recycling center, a recycling station, and a recycling vehicle;

[0007] Construct an optimization objective function based on vehicle service time and operating costs;

[0008] After the demand point and the service node execute recycling station evolution, balance evolution and path evolution according to the optimization objective function, the optimization result of the optimization objective function is obtained, and the simulation optimization of the recyclable express packaging recycling network is realized based on the optimization result.

[0009] Optionally, constructing an optimization objective function based on vehicle service time and operating cost includes:

[0010] Determine the vehicle service time function based on the recycling vehicle service route;

[0011] Determine the fixed cost function for opening recycling stations and using recycling trucks, as well as the transportation cost function for recycling trucks during their travels;

[0012] An optimization objective function is constructed based on the vehicle service time function, the fixed cost function, and the transportation cost function.

[0013] Optionally, determining the vehicle service time function according to the recycling vehicle service route includes:

[0014] Determine recycling truck service routes based on a collection of recycling centers, a collection of virtual recycling station locations, and a collection of communities or consumers;

[0015] Determine the service time window of the recycling truck in the community or consumer based on the pickup time of the recycling truck in the community or consumer's unit;

[0016] Determine the recycling time window and vehicle waiting time based on the unit service time of recycling stations for recycling recyclable express packaging;

[0017] A vehicle service time function is determined according to the recycling vehicle service route, service time window, recycling time window, and vehicle waiting time.

[0018] Optionally, determining a recycling vehicle service route based on the collection of recycling centers, the collection of virtual recycling station locations, and the collection of communities or consumers includes:

[0019] Determine the status of the recycling vehicle based on the remaining load of the recycling vehicle and the distance traveled by the vehicle;

[0020] When the recycling vehicle is in the state of going to recycling, the recycling route of the recycling vehicle to the community or consumer is obtained according to the community or consumer set;

[0021] When the recycling vehicle is in the state of heading to the collection station, the collection route of the recycling vehicle to the recycling station is obtained according to the virtual recycling station location set;

[0022] When the recycling vehicle status is completed, the return route of the recycling vehicle to the recycling center is obtained according to the recycling center set;

[0023] A recycling vehicle service route is determined according to the recycling route, the collection route, and the return route.

[0024] Optionally, determining the fixed cost function for opening a recycling station and using a recycling vehicle, and determining the transportation cost function for the recycling vehicle during travel, includes:

[0025] Determine the unit cost of opening a recycling station and the unit cost of using a recycling truck;

[0026] Determining a fixed cost function based on the unit opening cost and the unit usage cost;

[0027] Determine the energy consumption cost function based on the vehicle's unit fuel consumption and driving distance;

[0028] Determine the waiting cost function based on the penalty imposed when the recycling truck arrives at the recycling station early;

[0029] A transportation cost function is determined according to the energy consumption cost function and the waiting cost function.

[0030] Optionally, the recycling station evolution is a process of finding the optimal recycling station location, the balance evolution is a process of finding the optimal service plan, and the path evolution is a process of finding the optimal vehicle path. The recycling station evolution, balance evolution, and path evolution are independent and interactive; wherein,

[0031] After the demand point and the service node execute recycling station evolution, balance evolution, and path evolution according to the optimization objective function, an optimization result of the optimization objective function is obtained, including:

[0032] After the demand point and the service node execute the recycle bin evolution according to the optimization objective function, determining a recycle bin evolution result;

[0033] When the current evolution number is equal to the simulation round, performing balanced evolution using the determined recycle bin evolution result as input;

[0034] When the current number of evolutions is not equal to the number of simulation rounds, the determined recycle bin evolution result is used as input to continue executing recycle bin evolution until the current number of evolutions is equal to the number of simulation rounds, and then the current recycle bin evolution result is used as input to execute balanced evolution;

[0035] After executing path evolution according to the input and output results of the balanced evolution, the optimization result of the optimization objective function is obtained.

[0036] Optionally, the service node needs to meet service capacity constraints and coverage distance constraints; wherein,

[0037] After the demand point and the service node execute recycling station evolution, balance evolution, and path evolution according to the optimization objective function, an optimization result of the optimization objective function is obtained, including:

[0038] The optimization result of the optimization objective function is obtained after the demand point and the service node perform recycling station evolution, balance evolution and path evolution according to the optimization objective function while satisfying the service capacity constraint and the coverage distance constraint.

[0039] In addition, to achieve the above objectives, the present invention also proposes a simulation optimization system for a recyclable express packaging recycling network, the simulation optimization system for a recyclable express packaging recycling network comprising:

[0040] An acquisition module is used to obtain service facility data of the recyclable express packaging recycling network;

[0041] a definition module, configured to define agent types based on the service facility data, wherein the agent types include demand points and service nodes, wherein the demand points implement the functions of a community or a consumer, and the service nodes implement the functions of a recycling center, a recycling station, and a recycling vehicle;

[0042] A building module for constructing an optimization objective function based on vehicle service time and operating cost;

[0043] An execution module is used to obtain the optimization result of the optimization objective function after the demand point and the service node execute recycling station evolution, balance evolution and path evolution according to the optimization objective function, and realize simulation optimization of the recyclable express packaging recycling network based on the optimization result.

[0044] In addition, to achieve the above-mentioned purpose, the present invention also proposes a simulation optimization device for a recyclable express packaging recycling network, and the simulation optimization device for a recyclable express packaging recycling network includes: a memory, a processor, and a simulation optimization program for a recyclable express packaging recycling network stored on the memory and runnable on the processor. The simulation optimization program for a recyclable express packaging recycling network is configured to implement the steps of the simulation optimization method for a recyclable express packaging recycling network as described above.

[0045] In addition, to achieve the above-mentioned purpose, the present invention also proposes a storage medium, on which a simulation optimization program for a recyclable express packaging recycling network is stored. When the simulation optimization program for a recyclable express packaging recycling network is executed by a processor, the steps of the simulation optimization method for a recyclable express packaging recycling network as described above are implemented.

[0046] The present invention proposes a simulation optimization method and system for a recyclable express packaging recycling network. The method obtains service facility data of the recyclable express packaging recycling network; defines agent types based on the service facility data, wherein the agent types include demand points and service nodes, the demand points realize the functions of a community or consumer, and the service nodes realize the functions of a recycling center, a recycling station, and a recycling vehicle; constructs an optimization objective function based on vehicle service time and operating costs; after the demand points and the service nodes perform recycling station evolution, equilibrium evolution, and path evolution according to the optimization objective function, an optimization result of the optimization objective function is obtained, and simulation optimization of the recyclable express packaging recycling network is realized based on the optimization result. Through the above method, a recycling network with overlapping facility functions is designed by combining mathematical optimization modeling and agent simulation technology. The optimization algorithms of the three stages of recycling station evolution, equilibrium evolution, and path evolution are designed to solve the recycling station coverage site selection problem with margin, the demand point service allocation problem with overlapping node functions, and the vehicle route planning problem under the reverse time window, respectively. The method can effectively improve resource utilization, thereby reducing operating costs and improving the efficiency of recyclable express packaging recycling. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a structural diagram of a simulation optimization device for a recyclable express packaging recycling network in a hardware operating environment involved in an embodiment of the present invention;

[0048] Figure 2 This is a flow chart of a first embodiment of a simulation optimization method for a recyclable express packaging recycling network according to the present invention;

[0049] Figure 3 This is a state diagram of a demand point intelligent agent in the first embodiment of the simulation optimization method for a recyclable express packaging recycling network of the present invention;

[0050] Figure 4 This is a state diagram of a service node agent in the first embodiment of the simulation optimization method for a recyclable express packaging recycling network of the present invention;

[0051] Figure 5 A schematic diagram of vehicle service time in the first embodiment of the simulation optimization method for a recyclable express packaging recycling network of the present invention;

[0052] Figure 6 This is a control flow chart of the simulation optimization system in the first embodiment of the simulation optimization method for a recyclable express packaging recycling network of the present invention;

[0053] Figure 7 This is a schematic diagram of a visualization interface in the first embodiment of the simulation optimization method for a recyclable express packaging recycling network of the present invention;

[0054] Figure 8 This is a diagram of optimization results of different evolutionary stage combinations in the first embodiment of the simulation optimization method for recyclable express packaging recycling network of the present invention;

[0055] Figure 9 This is a flow chart of a second embodiment of a simulation optimization method for a recyclable express packaging recycling network according to the present invention;

[0056] Figure 10 Schematic diagram of the specific flow of three evolution processes in the second embodiment of the simulation optimization method for recyclable express packaging recycling network of the present invention;

[0057] Figure 11 This is a structural block diagram of the first embodiment of the simulation optimization device for recyclable express packaging recycling network of the present invention.

[0058] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0059] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0060] Reference Figure 1 , Figure 1 This is a schematic diagram of the structure of a simulation optimization device for a recyclable express packaging recycling network in the hardware operating environment involved in the embodiment of the present invention.

[0061] like Figure 1 As shown, the simulation optimization device for the recyclable express packaging recycling network may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) memory, or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. The memory 1005 may optionally be a storage device independent of the aforementioned processor 1001.

[0062] Those skilled in the art will understand that Figure 1 The structure shown in does not constitute a limitation on the simulation optimization device for the recyclable express packaging recycling network, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0063] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a simulation optimization program for a recyclable express packaging recycling network.

[0064] exist Figure 1 In the simulation optimization device for a recyclable express packaging recycling network shown, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the simulation optimization device for a recyclable express packaging recycling network of the present invention can be set in the simulation optimization device for a recyclable express packaging recycling network, and the simulation optimization device for a recyclable express packaging recycling network calls the simulation optimization program for a recyclable express packaging recycling network stored in the memory 1005 through the processor 1001, and executes the simulation optimization method for a recyclable express packaging recycling network provided in an embodiment of the present invention.

[0065] Based on the above hardware structure, an embodiment of the simulation optimization method of the present invention for a recyclable express packaging recycling network is proposed.

[0066] Reference Figure 2 , Figure 2 This is a flow chart of the first embodiment of a simulation optimization method for a recyclable express packaging recycling network according to the present invention.

[0067] In this embodiment, the simulation optimization method for the recyclable express packaging recycling network includes the following steps:

[0068] Step S10: Obtain service facility data of the recyclable express packaging recycling network.

[0069] It should be noted that the execution entity of this embodiment can be a computing service device with data processing, network communication, and program execution capabilities, such as a mobile phone, tablet computer, or personal computer, or an electronic device capable of performing the aforementioned functions, or a simulation and optimization device for a recyclable express packaging recycling network. This embodiment and the following embodiments will be described below using the simulation and optimization device for a recyclable express packaging recycling network as an example.

[0070] It should be noted that service facility data includes user-provided data on recycling centers, communities, or consumers, and recycling vehicles within the network. The geographic location and managed recycling area of ​​each node can be determined based on the input latitude and longitude. Users also need to define demand characteristics and scenario parameters related to simulation and optimization, such as the service capacity and coverage distance of recycling centers and recycling stations. Geographic data in the GIS is used to facilitate the visualization of the user interface. The recyclable express packaging recycling network consists of four main elements: primary nodes (recycling centers), secondary nodes (recycling stations), mobile nodes (mobile recycling vehicles), and tertiary nodes (demand points, such as a residential area, community, or consumer). While primary, secondary, and mobile nodes all have recycling capabilities, only primary nodes have processing capabilities. In other words, recyclable express packaging at the consumer end can be collected directly by a nearby recycling center or recycling station (within a walking distance limit, such as 10 minutes) or by a mobile recycling vehicle. Ultimately, recyclable express packaging will flow to a recycling center. The service range and volume of recycling centers and recycling stations are capped, and each recycling vehicle has a maximum load capacity and maximum service time.

[0071] Step S20: defining an intelligent agent type according to the service facility data, wherein the intelligent agent type includes a demand point and a service node, the demand point realizes the function of a community or a consumer, and the service node realizes the function of a recycling center, a recycling station, and a recycling vehicle.

[0072] It should be noted that dividing agents into two types, demand points and service nodes, can be used to simulate the functions and service logic of recycling centers, recycling stations, and vehicles. Service nodes implement the functions of recycling centers, recycling stations, and recycling vehicles. Service nodes will enter three different branch states: primary node, secondary node, and flow node according to their functions. Specifically, the agent types and their functional descriptions are shown in the following table:

[0073]

[0074] In the specific implementation, such as Figure 3 The state diagram of the demand point agent shown in Figure 3 It can be determined that the demand points are mainly in the states of "waiting for pickup" and "calling for pickup"; Figure 4 The state diagram of the service node agent shown in Figure 4 The status of recycling trucks, recycling bins, and recycling centers can be determined.

[0075] Step S30: constructing an optimization objective function based on vehicle service time and operating cost.

[0076] It should be noted that the overall optimization goal of the optimization objective function is to optimize operating costs and vehicle service time; the optimization objective function uses map information and routes to calculate the shortest path between nodes in the network and simulates the movement trajectory of the recycling vehicle, and then generates an optimized solution. The final set of optimized solutions is obtained through the non-dominated sorting strategy.

[0077] In one embodiment, constructing an optimization objective function based on vehicle service time and operating costs includes: determining a vehicle service time function based on a recycling truck service route; determining a fixed cost function for opening recycling stations and using recycling trucks, and determining a transportation cost function for recycling trucks during driving; and constructing an optimization objective function based on the vehicle service time function, the fixed cost function, and the transportation cost function.

[0078] It should be noted that the vehicle service time of the recycling vehicle refers to the time from the departure of the vehicle to the return of the vehicle to the recycling center, that is, the time the vehicle returns to the recycling center; the operating costs of the recyclable express packaging recycling network are composed of fixed costs and transportation costs, among which fixed costs refer to the fixed costs of opening recycling stations and using recycling vehicles, and transportation costs refer to the energy consumption costs and waiting costs of the recycling vehicles during driving, among which the energy consumption costs are related to the unit fuel consumption and driving distance of the vehicle, and the waiting costs are used to quantify the penalties when the vehicle arrives at the recycling station early.

[0079] In one embodiment, determining the vehicle service time function based on the recycling vehicle service route includes:

[0080] The recycling vehicle service route is determined based on the collection of recycling centers, the collection of virtual recycling station locations, and the collection of communities or consumers; the recycling vehicle service time window in the community or consumer is determined based on the unit pickup time of the recycling vehicle in the community or consumer; the recycling time window and vehicle waiting time are determined based on the unit service time of the recycling station for recycling recyclable express packaging; and the vehicle service time function is determined based on the recycling vehicle service route, service time window, recycling time window, and vehicle waiting time.

[0081] It should be noted that the service time of the mobile recycling vehicle m is calculated from the departure of the vehicle to the return of the vehicle to the recycling center h, that is, the time it takes for the vehicle to return to the recycling center like Figure 5 As shown, Figure 5 It also shows the time when the vehicle arrives at the node Time of leaving the node The relationship between them, the time for vehicle m to arrive at node j can be calculated as:

[0082]

[0083] Among them, H is the set of recycling centers, L is the set of virtual recycling station locations, and D is the set of demand points. ij is the driving distance between nodes i and j. s is the vehicle's speed. t s is the unit pickup time of the vehicle at the demand point, t′ is the service time of the vehicle to the recycling station, is the unit service time of recycling station for recycling recyclable express packaging, N i is the pickup quantity at the demand point, Indicates that node k is served by recycle bin i. is the service time window of demand point i (i.e., service time window). It represents the time when recycling station j completes the recycling task. The recycling station can be served by vehicles only after completing the recycling task. Therefore, the time window of recycling station j is (i.e. recycling time window), θ is the maximum tolerable waiting time after the recycling station completes the recycling task. If the vehicle reaches recycling station j before, it needs to wait for a waiting time of If the vehicle is If you arrive later, the service will start immediately upon arrival. represents the time when the vehicle starts serving recycling station j.

[0084] Therefore, the maximum service time T of a vehicle in the circular express packaging recycling network is expressed as (i.e., vehicle service time function):

[0085]

[0086] Among them, V h is the set of vehicles in the recycling center, h∈H. k hm Vehicle m representing recycling center h is used.

[0087] In one embodiment, determining a recycling truck service route based on a collection of recycling centers, a collection of virtual recycling station locations, and a collection of communities or consumers includes:

[0088] The recycling vehicle status is determined based on the remaining load of the recycling vehicle and the vehicle travel distance; when the recycling vehicle status is the state of going to recycling, the recycling route of the recycling vehicle to the community or consumer is obtained based on the community or consumer set; when the recycling vehicle status is the state of going to collection, the collection route of the recycling vehicle to the recycling station is obtained based on the virtual recycling station location set; when the recycling vehicle status is the completion state, the return route of the recycling vehicle to the recycling center is obtained based on the recycling center set; the recycling vehicle service route is determined based on the recycling route, the collection route and the return route.

[0089] It should be noted that the recycling center's logic is: the recycling center will directly collect express packaging from demand points within a certain range, and the recycling center's collection meets the service capacity and coverage distance constraints. The recycling station's logic is: the recycling station will directly collect express packaging from demand points within a certain range, and the recycling station's collection meets the service capacity and coverage distance constraints. After completing the service for the demand points, the recycling station waits for vehicle access. The vehicle runs logic on a certain path: the vehicle visits the demand point and the recycling station to provide recycling service. "Waiting for call" is essentially an optimization process of vehicle task allocation. In the simulation optimization system, guided by the optimization goal, the optimization program will assign the vehicle to visit the demand point based on the remaining load of the vehicle and the distance between the vehicle and the demand point to be served. Among them, (1) if there are demand points that have not been served, the vehicle enters the called state (i.e., goes to the recycling state). Here, calling means being needed. There is a "call" when there is a node that needs to be served. This is to indicate that the vehicle is needed and goes to the service node. When the demand point calls the vehicle to come to service, the vehicle will go to complete the demand point recycling task. If there are still demand points to be served at this time, the car will enter the called state again. If there are no demand points to be served, the car will enter the next stage. (2) If all demand points have been served, the vehicle enters the recycling station service process. When the recycling station calls the vehicle to serve, the vehicle will go to complete the recycling station's recycling task (i.e., go to collect state). If there are recycling stations to be served at this time, the car will enter the called state again. If there are no recycling stations to be served, the car will enter the next stage. (3) After completing the service tasks of all demand points and recycling stations, the car will directly return to the recycling center where it started to unload (i.e., completed state, i.e., return to recycling center state).

[0090] It is understandable that the calculation instructions for the vehicle arrival and departure times in the three states of "going to recycling", "going to collection" and "returning to recycling center" are all calculated through the "moving" state.

[0091] In one embodiment, determining the fixed cost function for opening a recycling station and using a recycling truck, as well as determining the transportation cost function for the recycling truck during travel, includes: determining the unit opening cost of opening the recycling station, and determining the unit usage cost of using the recycling truck; determining a fixed cost function based on the unit opening cost and the unit usage cost; determining an energy consumption cost function based on the unit fuel consumption and travel distance of the vehicle; determining a waiting cost function based on the penalty when the recycling truck arrives at the recycling station early; and determining a transportation cost function based on the energy consumption cost function and the waiting cost function.

[0092] It should be noted that the operating cost C of the recyclable express packaging recycling network consists of fixed costs and transportation costs, among which the fixed cost C FIt refers to the fixed cost of opening a recycling station and using recycling trucks, which can be calculated as follows:

[0093]

[0094] Among them, c fc is the unit fixed cost of opening a recycling station, c fv is the unit fixed cost of using a recycling truck, y l Indicates opening a recycling station at location l∈L.

[0095] It should be noted that the transportation cost C T It refers to the energy consumption cost and waiting cost of the recycling vehicle during driving. The energy consumption cost is related to the vehicle's unit fuel consumption and driving distance. The waiting cost is used to quantify the penalty when the vehicle arrives at the recycling station early. The transportation cost can be approximately calculated as:

[0096]

[0097] c o is the unit cost of fuel, f c is the energy consumption coefficient of the recycling vehicle, c w The unit waiting cost of the vehicle, The vehicle m representing the recycling center h passes through arc(i,j).

[0098] Based on the analysis of the two objective functions of time and cost, the complete optimization objective function is as follows:

[0099]

[0100]

[0101] Step S40: After the demand point and the service node execute recycling station evolution, balance evolution and path evolution according to the optimization objective function, the optimization result of the optimization objective function is obtained, and the simulation optimization of the recyclable express packaging recycling network is realized based on the optimization result.

[0102] It should be understood that recycling station evolution is the process of optimizing recycling station location, equilibrium evolution is the process of optimizing service allocation, and the purpose of path evolution is to find the best vehicle path; the scheduling decisions in these three stages are dynamically executed and optimized through heuristic optimization procedures, and the overall optimization goal is to optimize operating costs and vehicle service time.

[0103] It should be noted that the intelligent agent can simulate a single round of recycling plans. Users can interact with the system in real time through a designed graphical user interface. They can pause, restart, and control the optimization process at different evolutionary stages at any time. They can also change the simulation range of the experiment by defining parameters. For example, the number, service capacity, and coverage distance of service facilities can be adjusted to simulate urban communities with recycling tasks of different scales. In addition, simulation experiments can be carried out to compare different recycling strategies. For example, the simulated working time can be changed to evaluate the changes in the workload of service facilities under different service time limits. During and after the system operation, various optimization data and results can be displayed in the graphical user interface or statistical results.

[0104] In the specific implementation, such as Figure 6 As shown in the overall control flow chart, in the simulation, it is necessary to perform the simulation of the recycling station evolution, balance evolution and path evolution according to the optimization objective function in the calculation structure; Figure 7 The user visualization interface shown will display the optimal result (i.e., optimization result) of the recyclable express packaging recycling network on the user visualization interface after executing the recycling station evolution, equilibrium evolution, and path evolution.

[0105] In its implementation, the agent's simulation optimization was implemented using the AnyLogic 8.8.1 simulation software. The three-stage optimization algorithm was programmed in Java. To calculate vehicle service times and generate visual recycling plans, the simulation optimization system utilized network data from OpenStreetMap. Service planning and vehicle operation status were simulated within a real-world road network. The simulation process and results were presented to the user via a highly visual graphical user interface. The system could plot facility layouts and vehicle service routes within the network in real time. The user interface also enabled users to quickly adjust scenario parameters for comparative testing. Key process data and planning plans were displayed on the user interface both during and after the simulation.

[0106] In one embodiment, the service node needs to satisfy a service capacity constraint and a coverage distance constraint; wherein, after the demand point and the service node execute recycle bin evolution, balance evolution, and path evolution according to the optimization objective function, the optimization result of the optimization objective function is obtained, including: after the demand point and the service node execute recycle bin evolution, balance evolution, and path evolution according to the optimization objective function under the condition of satisfying the service capacity constraint and the coverage distance constraint, the optimization result of the optimization objective function is obtained.

[0107] It is understandable that the overall problem of planning a recycling network for recyclable express packaging can be divided into three aspects: the first is the recycling station site selection problem, the second is the service planning problem at the demand point, and the third is the vehicle routing problem with overlapping functions of mixed facilities and reverse time windows. Based on the route planning of mobile recycling vehicles, the strategic level recycling station site selection problem and service planning problem are optimized. The terms involved are defined as follows:

[0108] (1) Overlapping of facility functions: Recycling centers, recycling stations, and mobile recycling vehicles can all provide recycling services to demand points. On the premise of meeting the constraints of service distance and service capacity, it is crucial to scientifically divide the service scope of various types of facilities.

[0109] (2) Reverse time window: There is no pre-given node time window. The time window of the demand point served by the recycling truck is related to the order in which it is served. The time window of the demand point served by the recycling center or recycling station is related to the service volume of the cluster in which it is located. The time window of the recycling station served by the mobile recycling truck is related to the number of services it provides. The above node time windows will be reversely planned based on the optimization results.

[0110] (3) Route Planning: The mobile recycling vehicle service must first meet the recycling task at the demand point, then visit the recycling station on the return trip to retrieve the recyclable express packaging and transport it back to the recycling center for processing. The vehicle's visit to the recycling station must meet the recycling station's time window requirements.

[0111] In summary, to meet the service needs of the third-level nodes, the following decisions must be made: (1) the location and number of the second-level nodes; (2) the service planning of the third-level nodes and the RTW of the second-level nodes, that is, which type of facility will serve each demand point (recycling center, recycling station, or mobile recycling vehicle)? During which time period can the recycling station be served by a vehicle? (3) Route planning for mobile nodes, that is, determining the route of the mobile recycling vehicle. The dispatched vehicles can both meet the recycling service of the assigned demand points and be competent for the transportation task from the recycling station to the recycling center.

[0112] In the specific implementation, to analyze the current status of the simulation optimization system and the impact of key parameters, a simulation of a recyclable express packaging recycling network covering 111 residential communities (with a population of approximately 120,000) was constructed, focusing on selected communities in the Liangjiang New District of Chongqing, China. The coordinates of the recycling centers and demand points are real-world locations on the map. The pickup volume is a set of randomly generated data using a Poisson distribution. The following table summarizes the system parameters and the values ​​used in the simulation experiment:

[0113]

[0114] In order to verify the effectiveness of the proposed simulation optimization system, different evolution stage combinations are set to conduct numerical experiments. The results of different evolution stage combinations are as follows: Figure 8As shown, "1" refers to the recycle bin evolution, "2" is the balance evolution, and "3" is the path evolution. For example, "1-2-1-3" means that the execution order in the system is recycle bin evolution-balance evolution-recycle bin evolution-path evolution, where the recycle bin evolution stage is executed twice and each evolution stage runs 1000 rounds. Under the mixed constraints of the recycle bin's service capacity, coverage distance, and reverse time window, the design of the balance evolution stage has a significant impact on the optimization of the recycling scheme. Figure 8 It is clear that the maximum vehicle service time and operating cost achieved by executing combination "1-3" are significantly higher than those of the other three combinations. This combination plans vehicle routes based on facility locations that do not balance the recycling station and vehicle workload, resulting in increased vehicle usage and waiting time. The recycling station's service capacity is not fully utilized, with a coverage percentage of only 21%. Furthermore, a comparison of the other three combinations reveals that executing route evolution after balanced evolution leads to better solutions. Specifically, combinations "1-2-3" and "1-2-1-2-3" achieve better optimization results than "1-2-1-3." This is because they both seek optimal vehicle routes based on optimal recycling station locations and service planning. Among the four combinations, the solution with the shortest service time and cost is provided by combination "1-2-1-2-1-2-3," demonstrating the effectiveness of repeated iterations and optimizations in both the recycling station evolution and balanced evolution stages in finding the optimal solution.

[0115] This embodiment obtains service facility data of a recyclable express packaging recycling network; defines agent types based on the service facility data, wherein the agent types include demand points and service nodes, wherein the demand points realize the functions of a community or consumer, and the service nodes realize the functions of a recycling center, a recycling station, and a recycling vehicle; constructs an optimization objective function based on vehicle service time and operating costs; after the demand points and the service nodes execute recycling station evolution, equilibrium evolution, and path evolution according to the optimization objective function, obtains the optimization result of the optimization objective function, and implements simulation optimization of the recyclable express packaging recycling network based on the optimization result. Through the above method, a recycling network with overlapping facility functions is designed by combining mathematical optimization modeling and agent simulation technology, and an optimization algorithm for the three stages of recycling station evolution, equilibrium evolution, and path evolution is designed, which are used to solve the recycling station coverage site selection problem with margin, the demand point service allocation problem with overlapping node functions, and the vehicle route planning problem under the reverse time window, respectively. It can effectively improve resource utilization, thereby reducing operating costs and improving the efficiency of recyclable express packaging recycling.

[0116] refer to Figure 9 , Figure 9This is a flow chart of the second embodiment of a simulation optimization method for a recyclable express packaging recycling network according to the present invention.

[0117] Based on the first embodiment described above, in this embodiment of the simulation optimization method for a recyclable express packaging recycling network, the recycling station evolution is a process of finding the optimal recycling station location, the balance evolution is a process of finding the optimal service plan, and the path evolution is a process of finding the optimal vehicle path. The recycling station evolution, balance evolution, and path evolution are independent and interactive; wherein,

[0118] After the demand point and the service node execute recycling station evolution, balance evolution, and path evolution according to the optimization objective function, an optimization result of the optimization objective function is obtained, including:

[0119] Step S401: After the demand point and the service node execute the recycle bin evolution according to the optimization objective function, a recycle bin evolution result is determined.

[0120] Step S402: When the current evolution times are equal to the simulation rounds, the determined recycle bin evolution result is used as input to perform balanced evolution.

[0121] Step S403: When the current evolution number is not equal to the simulation round, the determined recycle bin evolution result is used as input to continue executing recycle bin evolution until the current evolution number is equal to the simulation round, and then the current recycle bin evolution result is used as input to execute balanced evolution.

[0122] Step S404: After executing path evolution according to the input and output results of the balance evolution, an optimization result of the optimization objective function is obtained.

[0123] It should be noted that recycling station evolution, balanced evolution, and path evolution are independent and interactive. The goal of the recycling station evolution phase is to find the optimal recycling station location. Based on the initial solution, a new solution is found by mutating the location, evaluated based on the optimal coverage ratio and coverage distance. The goal of balanced evolution is to find the optimal service plan given the optimal recycling station location. This process is achieved by mutating the recycling station's service capacity to balance the operating hours of the recycling station and vehicles. Improper recycling station service capacity settings can lead to excessively long vehicle wait times, increasing overall network operating costs and vehicle service time. Based on the initial value, recycling station service capacity is randomly adjusted according to pre-set parameter criteria to explore a trade-off between facility service volume and vehicle service volume. This trade-off results in a relatively better service plan and is the process of finding the optimal recycling station service capacity. Recycling station evolution and balanced evolution require multiple rounds of iteration and optimization to achieve the desired results. The goal of the path evolution phase is to find the optimal vehicle path. The path evolution results need to be determined by taking the results of recycling station evolution and equilibrium evolution as input (that is, the optimal recycling station location and the optimal service planning as input). This phase performs path variations of recycling stations and demand points to solve for a better path solution.

[0124] It is understandable that if Figure 10 As shown in the figure, the recycling station evolution optimizes the recycling station location by optimizing the demand coverage ratio and coverage distance, and the balanced evolution realizes service planning by balancing the working hours of the recycling station and the vehicle (i.e., the recycling vehicle). The conversion between the recycling station evolution and the balanced evolution is controlled by setting the simulation rounds. For example, when executing the recycling station evolution, when t = MaxRounds 1 (i.e., the set simulation rounds), the result of the recycling station evolution is directly used as input to execute the balanced evolution; once again, when t = MaxRounds 2, the recycling station evolution is continued based on the result of the balanced evolution, and the result of the second recycling station evolution is used as input to execute the balanced evolution. The input of the balanced evolution is determined according to the simulation rounds, and this cycle is repeated until t = MaxRounds n, and finally the path evolution is executed. The output of the previous stage is the input of the next stage. The results of the three stages influence each other according to the logic of "optimize-update-re-optimize". This process enables the solution to converge to a better solution. The non-dominated sorting strategy is used to screen simulation solutions. The final Pareto set is composed of non-dominated solutions with minimum cost and shortest vehicle service time in the optimal solution. The algorithm can independently find the optimal solution to the sub-problem while considering the interaction between several sub-problems, and find a better global solution through alternating multi-stage local search.

[0125] This embodiment determines the recycle bin evolution result after the demand point and the service node execute the recycle bin evolution according to the optimization objective function; when the current number of evolutions is equal to the simulation round, the determined recycle bin evolution result is used as input to execute the balanced evolution; when the current number of evolutions is not equal to the simulation round, the determined recycle bin evolution result is used as input to continue executing the recycle bin evolution until the current number of evolutions is equal to the simulation round, and the current recycle bin evolution result is used as input to execute the balanced evolution; after executing the path evolution according to the input and output results of the balanced evolution, the optimization result of the optimization objective function is obtained. In the above manner, the number of iterations of the recycle bin evolution and the balanced evolution can be controlled by setting the simulation rounds, and the output of the previous stage can be used as the input of the next stage, so that the results of the three stages influence each other according to the logic of "optimization-update-re-optimization". This process enables the solution to converge to a better solution.

[0126] In addition, an embodiment of the present invention also proposes a storage medium, on which a simulation optimization program for a recyclable express packaging recycling network is stored. When the simulation optimization program for a recyclable express packaging recycling network is executed by a processor, the steps of the simulation optimization method for a recyclable express packaging recycling network as described above are implemented.

[0127] Reference Figure 11 , Figure 11 This is a structural block diagram of the first embodiment of the simulation optimization system for recyclable express packaging recycling network of the present invention.

[0128] like Figure 11 As shown, the simulation optimization system for the recyclable express packaging recycling network proposed in the embodiment of the present invention includes:

[0129] The acquisition module 10 is used to obtain service facility data of the recyclable express packaging recycling network.

[0130] The definition module 20 is used to define the intelligent agent type according to the service facility data, wherein the intelligent agent type includes a demand point and a service node, the demand point realizes the function of a community or a consumer, and the service node realizes the function of a recycling center, a recycling station and a recycling vehicle.

[0131] The construction module 30 is used to construct an optimization objective function based on vehicle service time and operation cost.

[0132] The execution module 40 is used to obtain the optimization result of the optimization objective function after the demand point and the service node execute the recycling station evolution, balance evolution and path evolution according to the optimization objective function, and realize the simulation optimization of the recyclable express packaging recycling network based on the optimization result.

[0133] It should be understood that the above is only an example and does not constitute any limitation to the technical solution of the present invention. In specific applications, those skilled in the art can make settings as needed, and the present invention does not impose any limitation on this.

[0134] This embodiment obtains service facility data of a recyclable express packaging recycling network; defines agent types based on the service facility data, wherein the agent types include demand points and service nodes, wherein the demand points realize the functions of a community or consumer, and the service nodes realize the functions of a recycling center, a recycling station, and a recycling vehicle; constructs an optimization objective function based on vehicle service time and operating costs; after the demand points and the service nodes execute recycling station evolution, equilibrium evolution, and path evolution according to the optimization objective function, obtains the optimization result of the optimization objective function, and implements simulation optimization of the recyclable express packaging recycling network based on the optimization result. Through the above method, a recycling network with overlapping facility functions is designed by combining mathematical optimization modeling and agent simulation technology, and an optimization algorithm for the three stages of recycling station evolution, equilibrium evolution, and path evolution is designed, which are used to solve the recycling station coverage site selection problem with margin, the demand point service allocation problem with overlapping node functions, and the vehicle route planning problem under the reverse time window, respectively. It can effectively improve resource utilization, thereby reducing operating costs and improving the efficiency of recyclable express packaging recycling.

[0135] In one embodiment, the building module 30 is further configured to:

[0136] Determine the vehicle service time function based on the recycling vehicle service route;

[0137] Determine the fixed cost function for opening recycling stations and using recycling trucks, as well as the transportation cost function for recycling trucks during their travels;

[0138] An optimization objective function is constructed based on the vehicle service time function, the fixed cost function, and the transportation cost function.

[0139] In one embodiment, the building module 30 is further configured to:

[0140] Determine recycling truck service routes based on a collection of recycling centers, a collection of virtual recycling station locations, and a collection of communities or consumers;

[0141] Determine the service time window of the recycling truck in the community or consumer based on the pickup time of the recycling truck in the community or consumer's unit;

[0142] Determine the recycling time window and vehicle waiting time based on the unit service time of recycling stations for recycling recyclable express packaging;

[0143] A vehicle service time function is determined according to the recycling vehicle service route, service time window, recycling time window, and vehicle waiting time.

[0144] In one embodiment, the building module 30 is further configured to:

[0145] Determine the status of the recycling vehicle based on the remaining load of the recycling vehicle and the distance traveled by the vehicle;

[0146] When the recycling vehicle is in the state of going to recycling, the recycling route of the recycling vehicle to the community or consumer is obtained according to the community or consumer set;

[0147] When the recycling vehicle is in the state of heading to the collection station, the collection route of the recycling vehicle to the recycling station is obtained according to the virtual recycling station location set;

[0148] When the recycling vehicle status is completed, the return route of the recycling vehicle to the recycling center is obtained according to the recycling center set;

[0149] A recycling vehicle service route is determined according to the recycling route, the collection route, and the return route.

[0150] In one embodiment, the building module 30 is further configured to:

[0151] Determine the unit cost of opening a recycling station and the unit cost of using a recycling truck;

[0152] Determining a fixed cost function based on the unit opening cost and the unit usage cost;

[0153] Determine the energy consumption cost function based on the vehicle's unit fuel consumption and driving distance;

[0154] Determine the waiting cost function based on the penalty imposed when the recycling truck arrives at the recycling station early;

[0155] A transportation cost function is determined according to the energy consumption cost function and the waiting cost function.

[0156] In one embodiment, the recycle station evolution is a process of finding the optimal recycle station location, the balance evolution is a process of finding the optimal service plan, and the path evolution is a process of finding the optimal vehicle path. The recycle station evolution, balance evolution, and path evolution are independent and interactive; wherein,

[0157] The execution module 40 is further configured to:

[0158] After the demand point and the service node execute the recycle bin evolution according to the optimization objective function, determining a recycle bin evolution result;

[0159] When the current evolution number is equal to the simulation round, performing balanced evolution using the determined recycle bin evolution result as input;

[0160] When the current number of evolutions is not equal to the number of simulation rounds, the determined recycle bin evolution result is used as input to continue executing recycle bin evolution until the current number of evolutions is equal to the number of simulation rounds, and then the current recycle bin evolution result is used as input to execute balanced evolution;

[0161] After executing path evolution according to the input and output results of the balanced evolution, the optimization result of the optimization objective function is obtained.

[0162] In one embodiment, the service node needs to meet the service capacity constraint and the coverage distance constraint; wherein,

[0163] The execution module 40 is further configured to:

[0164] The optimization result of the optimization objective function is obtained after the demand point and the service node perform recycling station evolution, balance evolution and path evolution according to the optimization objective function while satisfying the service capacity constraint and the coverage distance constraint.

[0165] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of it according to actual needs to achieve the purpose of the embodiment scheme, and no limitation is made here.

[0166] In addition, for technical details not fully described in this embodiment, please refer to the simulation optimization method for recyclable express packaging recycling network provided in any embodiment of the present invention, which will not be repeated here.

[0167] In addition, it should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or system. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or system comprising the element.

[0168] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0169] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, or of course by hardware, but in many cases the former is a better embodiment. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as a read-only memory (ROM) / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0170] The above are only preferred embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A simulation optimization method for a recyclable express packaging recycling network, characterized in that: The simulation optimization method for the recyclable express packaging recycling network includes: Obtain service facility data of the recyclable express packaging recycling network; Defining agent types according to the service facility data, wherein the agent types include demand points and service nodes, the demand points realizing the functions of a community or a consumer, and the service nodes realizing the functions of a recycling center, a recycling station, and a recycling vehicle; Construct an optimization objective function based on vehicle service time and operating costs; After the demand point and the service node execute recycling station evolution, balance evolution, and path evolution according to the optimization objective function, an optimization result of the optimization objective function is obtained, and simulation optimization of the recyclable express packaging recycling network is implemented based on the optimization result; The recycling station evolution is a process of finding the optimal recycling station location, the balance evolution is a process of finding the optimal service plan, and the path evolution is a process of finding the optimal vehicle path. The recycling station evolution, balance evolution, and path evolution are independent and interactive; wherein, After the demand point and the service node execute recycling station evolution, balance evolution, and path evolution according to the optimization objective function, an optimization result of the optimization objective function is obtained, including: After the demand point and the service node execute the recycle bin evolution according to the optimization objective function, determining a recycle bin evolution result; When the current evolution number is equal to the simulation round, performing balanced evolution using the determined recycle bin evolution result as input; When the current number of evolutions is not equal to the number of simulation rounds, the determined recycle bin evolution result is used as input to continue executing recycle bin evolution until the current number of evolutions is equal to the number of simulation rounds, and then the current recycle bin evolution result is used as input to execute balanced evolution; After executing path evolution according to the input and output results of the balanced evolution, the optimization result of the optimization objective function is obtained.

2. The method according to claim 1, wherein The optimization objective function is constructed based on vehicle service time and operating cost, including: Determine the vehicle service time function based on the recycling vehicle service route; Determine the fixed cost function for opening recycling stations and using recycling trucks, as well as the transportation cost function for recycling trucks during their travels; An optimization objective function is constructed based on the vehicle service time function, the fixed cost function, and the transportation cost function.

3. The method according to claim 2, wherein The method of determining the vehicle service time function according to the recycling vehicle service route includes: Determine recycling truck service routes based on a collection of recycling centers, a collection of virtual recycling station locations, and a collection of communities or consumers; Determine the service time window of the recycling truck in the community or consumer based on the pickup time of the recycling truck in the community or consumer's unit; Determine the recycling time window and vehicle waiting time based on the unit service time of recycling stations for recycling recyclable express packaging; A vehicle service time function is determined according to the recycling vehicle service route, service time window, recycling time window, and vehicle waiting time.

4. The method according to claim 3, wherein Determining a recycling vehicle service route based on the collection of recycling centers, the collection of virtual recycling station locations, and the collection of communities or consumers includes: Determine the status of the recycling vehicle based on the remaining load of the recycling vehicle and the distance traveled by the vehicle; When the recycling vehicle is in the state of going to recycling, the recycling route of the recycling vehicle to the community or consumer is obtained according to the community or consumer set; When the recycling vehicle is in the state of heading to the collection station, the collection route of the recycling vehicle to the recycling station is obtained according to the virtual recycling station location set; When the recycling vehicle status is completed, the return route of the recycling vehicle to the recycling center is obtained according to the recycling center set; A recycling vehicle service route is determined according to the recycling route, the collection route, and the return route.

5. The method according to claim 2, wherein The fixed cost function for opening a recycling station and using a recycling truck, as well as the transportation cost function for the recycling truck during its operation, includes: Determine the unit cost of opening a recycling station and the unit cost of using a recycling truck; Determining a fixed cost function based on the unit opening cost and the unit usage cost; Determine the energy consumption cost function based on the vehicle's unit fuel consumption and driving distance; Determine the waiting cost function based on the penalty imposed when the recycling truck arrives at the recycling station early; A transportation cost function is determined according to the energy consumption cost function and the waiting cost function.

6. The method according to claim 1, wherein The service node needs to meet the service capacity constraint and coverage distance constraint; wherein, After the demand point and the service node execute recycling station evolution, balance evolution, and path evolution according to the optimization objective function, an optimization result of the optimization objective function is obtained, including: The optimization result of the optimization objective function is obtained after the demand point and the service node perform recycling station evolution, balance evolution and path evolution according to the optimization objective function while satisfying the service capacity constraint and the coverage distance constraint.

7. A simulation optimization system for a recyclable express packaging recycling network, characterized in that: The simulation optimization system for the recyclable express packaging recycling network includes: An acquisition module is used to obtain service facility data of the recyclable express packaging recycling network; a definition module, configured to define agent types based on the service facility data, wherein the agent types include demand points and service nodes, wherein the demand points implement the functions of a community or a consumer, and the service nodes implement the functions of a recycling center, a recycling station, and a recycling vehicle; A building module for constructing an optimization objective function based on vehicle service time and operating cost; an execution module, configured to obtain an optimization result of the optimization objective function after executing recycling station evolution, balance evolution, and path evolution at the demand point and the service node according to the optimization objective function, and implement simulation optimization of the recyclable express packaging recycling network based on the optimization result; The recycling station evolution is a process of finding the optimal recycling station location, the balance evolution is a process of finding the optimal service plan, and the path evolution is a process of finding the optimal vehicle path. The recycling station evolution, balance evolution, and path evolution are independent and interactive; wherein, The execution module is further configured to: After the demand point and the service node execute the recycle bin evolution according to the optimization objective function, determining a recycle bin evolution result; When the current evolution number is equal to the simulation round, performing balanced evolution using the determined recycle bin evolution result as input; When the current number of evolutions is not equal to the number of simulation rounds, the determined recycle bin evolution result is used as input to continue executing recycle bin evolution until the current number of evolutions is equal to the number of simulation rounds, and then the current recycle bin evolution result is used as input to execute balanced evolution; After executing path evolution according to the input and output results of the balanced evolution, the optimization result of the optimization objective function is obtained.

8. A simulation optimization device for a recyclable express packaging recycling network, characterized in that: The device includes: a memory, a processor, and a simulation optimization program for a recyclable express packaging recycling network stored in the memory and executable on the processor. The simulation optimization program for a recyclable express packaging recycling network is configured to implement the steps of a simulation optimization method for a recyclable express packaging recycling network as described in any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium stores a simulation optimization program for a recyclable express packaging recycling network. When the simulation optimization program for a recyclable express packaging recycling network is executed by the processor, the steps of the simulation optimization method for a recyclable express packaging recycling network as described in any one of claims 1 to 6 are implemented.

Images