Multimodal transport path planning method based on adaptive large-scale neighborhood search, storage medium and equipment

Abstract

The invention discloses a multimodal transport path planning method based on adaptive large-scale neighborhood search, a storage medium and equipment, and the method comprises the steps: determining the transport nodes of multimodal transport according to the start and end nodes of a cargo transport task through road network data, and building a multimodal transport network; according to the transportation nodes and the transportation modes in the multi-connected transportation network, the transportation cost and the cargo owner preference degree between the transportation nodes are obtained, and the transfer cost of each transportation node is determined; establishing a first-level objective function and a second-level objective function in combination with the transportation cost, the transportation cost and the goods owner preference degree according to whether the transportation paths among the transportation nodes and the transportation modes on the transportation nodes have constraint conditions for establishing multimodal transportation or not; and carrying out iterative optimization solution on the primary objective function and the secondary objective function by using a self-adaptive large-scale neighborhood search algorithm to find an optimal multimodal transport path. According to the method, more intelligent and comprehensive path planning is realized by introducing adaptive large-scale neighborhood search and cargo owner preference.

Description

Technical Field

[0001] The present invention relates to the technical field of multimodal transport path planning, and in particular to a multimodal transport path planning method, storage medium and device based on adaptive large-scale neighborhood search. Background Art

[0002] In modern society, with the rapid development of globalization and logistics industry, efficient cargo transportation and distribution have become increasingly important. In order to achieve optimal resource allocation, reduce costs and improve transportation efficiency, multimodal transport has become a commonly used logistics strategy. Multimodal transport refers to the combination of different modes of transportation such as road, rail, water, etc. in cargo transportation, so as to give full play to the advantages of various modes of transportation, reduce the use of high-cost modes such as air transportation and road transportation, and achieve the goal of reducing logistics costs and environmental impact.

[0003] However, in practical applications, multimodal transport faces a series of challenges and problems. Traditional path planning methods, such as the Dijkstra algorithm and the A* algorithm, usually only consider transportation costs or time to find the shortest path or the best path, and it is difficult to take into account the preferences of shippers and the conversion costs between different modes of transport. In addition, the complex relationship between nodes and modes of transport in large-scale networks of multimodal transport makes path planning more difficult. Therefore, how to intelligently plan the optimal path for goods in a multimodal transport network, taking into account multiple factors, has become a research hotspot in the field of logistics. Summary of the invention

[0004] In view of the problems existing in the prior art, the present invention provides a multimodal transport path planning method, storage medium and device based on adaptive large-scale neighborhood search. By introducing adaptive large-scale neighborhood search and shipper preference factors, smarter and more comprehensive path planning is achieved, thereby optimizing the utilization of logistics resources, reducing costs, improving efficiency, and meeting the personalized needs of shippers.

[0005] To achieve the above technical objectives, the present invention adopts the following technical solution: a multimodal transport path planning method based on adaptive large-scale neighborhood search, specifically comprising the following steps:

[0006] Step 1: According to the starting and ending nodes of the cargo transportation task, use the road network data to determine the transportation nodes of multimodal transport and establish a multimodal transport network;

[0007] Step 2: According to the transport nodes and transport modes in the multimodal transport network, the transport costs and cargo owners' preferences between transport nodes are obtained, and the transshipment cost of each transport node is determined;

[0008] Step 3: Based on the transportation paths between transportation nodes and whether there are constraints for establishing multimodal transport in the transshipment mode on the transportation nodes, the primary objective function and the secondary objective function are established in combination with the transportation cost, transshipment cost and the preference of the cargo owner;

[0009] Step 4: Use an adaptive large-scale neighborhood search algorithm to iteratively optimize and solve the primary and secondary objective functions to find the optimal multimodal transport path.

[0010] Furthermore, the multimodal transport network established in step 1 is represented by a graph G=(N,R), wherein N represents a set of transport nodes in the multimodal transport network, and R represents a set of transport modes supported by the multimodal transport network.

[0011] Furthermore, the first-level objective function C1 in step 3 is:

[0012]

[0013] Among them, c i,j,r represents the transportation cost from transportation node i to transportation node j using transportation mode r, i,j∈N; x i,j,r Indicates whether there is a transportation path between transportation node i and transportation node j. t i,r,r′ represents the transshipment cost of changing the transport mode r at transport node i to another transport mode r′, r,r′∈R; y i,r,r′ Indicates whether there is a transshipment method at transport node i,

[0014] Furthermore, the secondary objective function C2 in step 3 is:

[0015]

[0016] Among them, c min represents the minimum value of the first-level objective function C1, N represents the number of intermediate transfers between the starting and ending nodes of the cargo transportation task when the first-level objective function C1 takes the minimum value at the current iteration number, and p i,j,r It indicates the preference of the cargo owner for transporting from transport node i to transport node j using transport mode r.

[0017] Furthermore, the constraints of multimodal transport in step 3 are:

[0018]

[0019] Among them, o represents the starting node of the transportation task, d represents the target node of the transportation task, and x j,h,r represents the transport from transport node j to transport intermediate node h using mode r, I represents the set of transport nodes, I / (o,d) represents the set of transport nodes excluding the starting point o and the destination node d, y j,r,r′ Indicates whether there is a transshipment method at transport node j, x j,h,r′ Indicates whether there is a transfer path from transport node j to transport intermediate node h.

[0020] Furthermore, step 4 includes the following sub-steps:

[0021] Step 4.1: Based on the multimodal transport network established for the cargo transportation task, randomly generate several solutions that meet the constraint conditions [x i,j,r ,y i,r,r′ ] Put it into the feasible solution pool, set the destruction operator and the repair operator, initialize the scores of the destruction operator and the repair operator, initialize the annealing temperature, set the maximum number of iterations, and set the acceptance probability threshold for each iteration;

[0022] Step 4.2: According to the scoring weight of the destruction operator and the scoring weight of the repair operator, a destruction operator and a repair operator are randomly selected by the roulette wheel method to destroy and rebuild the solutions in the feasible solution pool, and the updated solutions are added to the feasible solution pool;

[0023] Step 4.3: Use the solution in the feasible solution pool to calculate the first-level objective function C1 and find the minimum value c of the first-level objective function C1 under the current number of iterations. min and its corresponding number of transfers N;

[0024] Step 4.4: Use the solution in the feasible solution pool and c at the current iteration number again min and N, calculate the secondary objective function C2, sort the calculated values ​​of the secondary objective function C2 in ascending order, take the first corresponding solution as the optimal solution under the current number of iterations, and take the second corresponding solution as the suboptimal solution under the current number of iterations;

[0025] Step 4.5: Generate the probability of acceptance of the optimal solution under the current number of iterations according to the annealing temperature. If the probability of acceptance is less than the acceptance probability threshold of the current iteration, accept the optimal solution under the current number of iterations, and add 1 to the scores of the destruction operator and the repair operator used by the optimal solution under the current number of iterations, and update the score weight of the destruction operator and the score weight of the repair operator; otherwise, accept the suboptimal solution, and the scores of the destruction operator and the repair operator used by the optimal solution under the current number of iterations remain unchanged;

[0026] Step 4.6: In the next iteration, the accepted solution is repeated in steps 4.2-4.5 using the updated scoring weights of the destruction operator and the scoring weights of the repair operator until the maximum number of iterations is reached. The solution when the secondary objective function C2 is the minimum is taken as the final solution to obtain the optimal multimodal transport path.

[0027] Furthermore, the destruction operators include: a random destruction operator, a cluster destruction operator, a path cutting operator and a worst-case destruction operator, and the repair operators include: a greedy repair operator, a nearest neighbor repair operator and a path reconstruction operator.

[0028] Furthermore, in step 4.5, the probability p of the optimal solution being accepted under the current number of iterations is generated according to the annealing temperature. a The specific process is:

[0029]

[0030] in, represents the secondary objective function value corresponding to the optimal solution under the a-th iteration number, T a represents the annealing temperature at the ath iteration, T a =αT a-1 , α represents the annealing temperature drop coefficient.

[0031] Furthermore, the present invention also provides a computer-readable storage medium storing a computer program, wherein the computer program enables a computer to execute the multimodal transport path planning method based on adaptive large-scale neighborhood search.

[0032] Furthermore, the present invention also provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the multimodal transport path planning method based on adaptive large-scale neighborhood search is implemented.

[0033] Compared with the prior art, the present invention has the following beneficial effects: the present invention introduces an adaptive large-scale neighborhood search algorithm into the multimodal transport path planning method based on adaptive large-scale neighborhood search, integrates the cargo owner's preference with the transportation cost and the transshipment cost, and performs comprehensive optimization, which not only reduces the logistics cost, but also improves the practicality and intelligence of the path planning; by effectively coordinating different modes of transportation, minimizing the transshipment cost and meeting the needs of cargo owners, the method has significant innovation and application potential in the field of modern logistics, and provides a beneficial solution for improving resource utilization efficiency and reducing environmental impact. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 A flowchart of a multimodal transport path planning method based on adaptive large-scale neighborhood search according to the present invention;

[0035] Figure 2 The figure is a flow chart of iteratively optimizing and solving the primary objective function and the secondary objective function using the adaptive large-scale neighborhood search algorithm in the present invention. DETAILED DESCRIPTION

[0036] The technical solution of the present invention is further explained below in conjunction with the accompanying drawings.

[0037] like Figure 1 Flow chart of the multimodal transport path planning method based on adaptive large-scale neighborhood search of the present invention, the multimodal transport path planning method specifically includes the following steps:

[0038] Step 1: According to the starting and ending nodes of the cargo transportation task, the multimodal transport nodes are determined using the road network data to establish a multimodal transport network; the multimodal transport network established in the present invention is represented by a graph G = (N, R), wherein N represents the set of transport nodes in the multimodal transport network, and R represents the set of transport modes supported by the multimodal transport network.

[0039] Step 2. According to the transport nodes and transport modes in the multimodal transport network, obtain the transportation costs and shipper preferences between transport nodes, and determine the transshipment cost of each transport node. The transportation cost refers to the actual cost of transporting goods from one transport node to another in the multimodal transport network; the transshipment cost refers to the cost incurred in transferring goods from one mode of transport to another in the multimodal transport network, including the costs of loading and unloading, warehousing, etc. at the transshipment nodes, as well as the costs related to the transfer of goods between different modes of transport; the shipper preference refers to the preferences and requirements of the shipper or shipper for different modes of transport, routes, etc.

[0040] Step 3: Whether there are constraints for establishing multimodal transport based on the transportation paths between transportation nodes and the transshipment methods on the transportation nodes, it is difficult to measure the consignor's preference directly because it lacks a clear quantitative dimension. If the cost of the consignor's preference is set manually, the result is easily affected by the setting method. Therefore, the present invention establishes a primary objective function through transportation cost and transshipment cost, uses the obtained result to naturally quantify the consignor's preference cost, and constructs a secondary objective function by combining transportation cost, transshipment cost and consignor's preference cost.

[0041] The first-level objective function C1 in the present invention is:

[0042]

[0043] Among them, c i,j,r represents the transportation cost from transportation node i to transportation node j using transportation mode r, i,j∈N; x i,j,r Indicates whether there is a transportation path between transportation node i and transportation node j. t i,r,r′ represents the transshipment cost of changing the transport mode r at transport node i to another transport mode r′, r,r′∈R; y i,r,r′ Indicates whether there is a transshipment method at transport node i,

[0044] The secondary objective function C2 in the present invention is:

[0045]

[0046] Among them, c min represents the minimum value of the first-level objective function C1, N represents the number of intermediate transfers between the starting and ending nodes of the cargo transportation task when the first-level objective function C1 takes the minimum value at the current iteration number, and p i,j,r represents the preference of the cargo owner for transporting from transport node i to transport node j using transport mode r, p i,j,r ∈[0,1], 1 represents strongly recommended, 0 represents strongly not recommended. The penalty cost is the consignor's preference. The path with a high preference will have a lower penalty cost, while the path with a low preference will have a higher penalty cost. The secondary objective function will be optimized taking into account the consignor's preference to find a balanced solution between the total transportation cost and the consignor's preference.

[0047] The constraints of multimodal transport in the present invention are:

[0048]

[0049] Among them, o represents the starting node of the transportation task, d represents the target node of the transportation task, and x j,h,r represents the transport from transport node j to transport intermediate node h using mode r, I represents the set of transport nodes, I / (o,d) represents the set of transport nodes excluding the starting point o and the destination node d, y j,r,r′ Indicates whether there is a transshipment method at transport node j, x j,h,r′ Indicates whether there is a transfer path from transport node j to transport intermediate node h. Formulas (1) and (2) represent that the transport start node and the target node must use a transport method to leave or enter the node in a unique path. Formula (3) represents the flow balance constraint of the transport node. represents the number of paths entering transportation node j, and represents the number of path modes leaving transport node j. The equality of the two means that the entry and exit of the transport node are conserved. Specifically, if the number of entering transport node j is zero, the number of leaving transport node j is also zero; if the number of entering transport node j is 1, the number of leaving transport node j is also 1. Equations (4) and (5) represent the intrinsic connection between transshipment and transportation. Equation (4) limits the consistency of transportation activities and the corresponding transportation mode selection to prevent unreasonable transportation arrangements, such as arranging transportation without selecting a certain mode, and limits the number of mode conversions at the node level to ensure the rationality and simplicity of the plan. Equation (5) binds mode conversion to transportation flow to ensure that mode conversion can only occur when the transportation path and flow are reasonably arranged.

[0050] Step 4: Use the adaptive large-scale neighborhood search algorithm to iteratively optimize and solve the primary and secondary objective functions to find the optimal multimodal transport path; Figure 2 , specifically including the following sub-steps:

[0051] Step 4.1: Based on the multimodal transport network established for the cargo transportation task, randomly generate several solutions that meet the constraint conditions [x i,j,r ,y i,r,r′ ] Put it into the feasible solution pool, set the destruction operator and the repair operator, initialize the scores of the destruction operator and the repair operator, initialize the annealing temperature, set the maximum number of iterations, and set the acceptance probability threshold for each iteration;

[0052] Step 4.2: According to the scoring weight of the destruction operator and the scoring weight of the repair operator, the roulette method is used to dynamically adapt to the change of the operator scoring weight, and a destruction operator and a repair operator are randomly selected to destroy and rebuild the solution in the feasible solution pool, and the updated solution is added to the feasible solution pool. The scoring weight of the destruction operator is the proportion of the score of the destruction operator to the scores of all destruction operators, and the scoring weight of the repair operator is the proportion of the score of the repair operator to the scores of all repair operators. The destruction operators include: random destruction operators, cluster destruction operators, path cutting operators and worst destruction operators. The random destruction operator refers to randomly removing some existing transportation paths to break the current solution. structure; the cluster destruction operator refers to removing the transportation paths that form tight clusters to destroy the local structure of the solution; the path cutting operator refers to dividing the path into smaller fragments, thereby destroying the continuity of the current solution; the worst destruction operator refers to removing the section with the highest cost in the current path, that is, the part with the greatest impact on the objective function value; the repair operators include: greedy repair operator, nearest neighbor repair operator and path reconstruction operator. The greedy repair operator refers to using a greedy method to reinsert the damaged path into the solution and try to repair its structure; the nearest neighbor repair operator refers to inserting the damaged elements to the nearest position to maintain the connectivity of the solution; the path reconstruction operator refers to reconstructing the damaged path or route fragment to satisfy the constraints.

[0053] Step 4.3: Use the solution in the feasible solution pool to calculate the first-level objective function C1 and find the minimum value c of the first-level objective function C1 under the current number of iterations. min and its corresponding number of transfers N;

[0054] Step 4.4: Use the solution in the feasible solution pool and c at the current iteration number again min and N, calculate the secondary objective function C2, sort the calculated values ​​of the secondary objective function C2 in ascending order, take the first corresponding solution as the optimal solution under the current number of iterations, and take the second corresponding solution as the suboptimal solution under the current number of iterations;

[0055] Step 4.5: Generate the probability of the optimal solution being accepted under the current number of iterations based on the annealing temperature This reduces the randomness of the search and improves the convergence speed of the algorithm. represents the secondary objective function value corresponding to the optimal solution under the a-th iteration number, T a represents the annealing temperature at the ath iteration, T a =αT a-1 , α represents the annealing temperature drop coefficient;

[0056] If the probability of acceptance is less than the acceptance probability threshold of the current iteration, the optimal solution under the current iteration number is accepted, and the scores of the destruction operator and the repair operator used in the optimal solution under the current iteration number are increased by 1, and the scoring weight of the destruction operator and the scoring weight of the repair operator are updated; otherwise, the suboptimal solution is accepted, and the scores of the destruction operator and the repair operator used in the optimal solution under the current iteration number remain unchanged;

[0057] Step 4.6: In the next iteration, the accepted solution is repeated in steps 4.2-4.5 using the updated scoring weights of the destruction operator and the scoring weights of the repair operator until the maximum number of iterations is reached, and the solution when the secondary objective function C2 is the minimum is taken as the final solution to obtain the optimal multimodal transport path. The multimodal transport path planning method based on adaptive large-scale neighborhood search of the present invention combines simulated annealing, roulette technology, and adaptive parameter adjustment, and can efficiently search for the optimal solution in a large-scale neighborhood, which not only avoids the local optimal trap, but also balances the efficiency of exploration and development, and significantly improves the robustness, convergence speed and applicability of the algorithm to complex problems.

[0058] The method for multimodal transport path planning based on adaptive large-scale neighborhood search of the present invention introduces an algorithm for adaptive large-scale neighborhood search, integrates the preferences of shippers with transportation costs and transshipment costs, and performs comprehensive optimization, which not only reduces logistics costs, but also improves the practicality and intelligence of path planning; by effectively coordinating different modes of transportation, minimizing transshipment costs and meeting the needs of shippers, the method has significant innovation and application potential in the field of modern logistics, and provides a useful solution for improving resource utilization efficiency and reducing environmental impact.

[0059] In a technical solution of the present invention, a computer-readable storage medium is also provided, storing a computer program, wherein the computer program enables a computer to execute the multimodal transport path planning method based on adaptive large-scale neighborhood search.

[0060] In a technical solution of the present invention, an electronic device is also provided, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the multimodal transport path planning method based on adaptive large-scale neighborhood search is implemented.

[0061] In the embodiments disclosed in the present application, the computer storage medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. The computer storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the above. More specific examples of computer storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above.

[0062] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in this application can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0063] The above are only preferred embodiments of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should be regarded as the protection scope of the present invention.

Claims

1. A multimodal transport path planning method based on adaptive large-scale neighborhood search, characterized in that: The specific steps include: Step 1: According to the starting and ending nodes of the cargo transportation task, use the road network data to determine the transportation nodes of multimodal transport and establish a multimodal transport network; Step 2: According to the transport nodes and transport modes in the multimodal transport network, the transport costs and cargo owners' preferences between transport nodes are obtained, and the transshipment cost of each transport node is determined; Step 3: Based on the transportation paths between transportation nodes and whether there are constraints for establishing multimodal transport in the transshipment mode on the transportation nodes, the primary objective function and the secondary objective function are established in combination with the transportation cost, transshipment cost and the cargo owner's preference; Step 4: Use an adaptive large-scale neighborhood search algorithm to iteratively optimize and solve the primary and secondary objective functions to find the optimal multimodal transport path.

2. The multimodal transport path planning method based on adaptive large-scale neighborhood search according to claim 1, characterized in that: The multimodal transport network established in step 1 is represented by a graph G = (N, R), where N represents the set of transport nodes in the multimodal transport network, and R represents the set of transport modes supported by the multimodal transport network.

3. The multimodal transport path planning method based on adaptive large-scale neighborhood search according to claim 2 is characterized in that: The first-level objective function C1 in step 3 is: Among them, c i,j,r represents the transportation cost from transportation node i to transportation node j using transportation mode r, i,j∈N; x i,j,r Indicates whether there is a transportation path between transportation node i and transportation node j. t i,r,r′ represents the transshipment cost of changing the transport mode r at transport node i to another transport mode r′, r,r′∈R; y i,r,r′ Indicates whether there is a transshipment method at transport node i, 4. The multimodal transport path planning method based on adaptive large-scale neighborhood search according to claim 3 is characterized in that: The secondary objective function C2 in step 3 is: Among them, c min represents the minimum value of the first-level objective function C1, N represents the number of intermediate transfers between the starting and ending nodes of the cargo transportation task when the first-level objective function C1 takes the minimum value at the current iteration number, and p i,j,r It indicates the preference of the cargo owner for transporting from transport node i to transport node j using transport mode r.

5. A multimodal transport path planning method based on adaptive large-scale neighborhood search according to claim 3 or 4, characterized in that: The constraints for multimodal transport in step 3 are: Among them, o represents the starting node of the transportation task, d represents the target node of the transportation task, and x j,h,r represents the transport from transport node j to transport intermediate node h using mode r, I represents the set of transport nodes, I / (o,d) represents the set of transport nodes excluding the starting point o and the destination node d, y j,r,r′ Indicates whether there is a transshipment method at transport node j, x j,h,r′ Indicates whether there is a transfer path from transport node j to transport intermediate node h.

6. The multimodal transport path planning method based on adaptive large-scale neighborhood search according to claim 5, characterized in that: Step 4 includes the following sub-steps: Step 4.1: Based on the multimodal transport network established for the cargo transportation task, a number of solutions [x i,j,r ,y i,r,r′ ] Put it into the feasible solution pool, set the destruction operator and the repair operator, initialize the scores of the destruction operator and the repair operator, initialize the annealing temperature, set the maximum number of iterations, and set the acceptance probability threshold for each iteration; Step 4.2: According to the scoring weight of the destruction operator and the scoring weight of the repair operator, a destruction operator and a repair operator are randomly selected by the roulette wheel method to destroy and rebuild the solutions in the feasible solution pool, and the updated solutions are added to the feasible solution pool; Step 4.3: Use the solution in the feasible solution pool to calculate the first-level objective function C1 and find the minimum value c of the first-level objective function C1 under the current number of iterations. min and its corresponding number of transfers N; Step 4.4: Use the solution in the feasible solution pool and c at the current iteration number again min and N, calculate the secondary objective function C2, sort the calculated values ​​of the secondary objective function C2 in ascending order, take the first corresponding solution as the optimal solution under the current number of iterations, and take the second corresponding solution as the suboptimal solution under the current number of iterations; Step 4.5: Generate the probability of the optimal solution being accepted under the current iteration number according to the annealing temperature. If the probability of acceptance is less than the acceptance probability threshold of the current iteration, accept the optimal solution under the current iteration number, and add 1 to the scores of the destruction operator and the repair operator used by the optimal solution under the current iteration number, and update the score weight of the destruction operator and the score weight of the repair operator; Otherwise, the suboptimal solution is accepted, and the scores of the destruction operator and repair operator used by the optimal solution under the current iteration number remain unchanged; Step 4.6: In the next iteration, the accepted solution is repeated in steps 4.2-4.5 using the updated scoring weights of the destruction operator and the scoring weights of the repair operator until the maximum number of iterations is reached. The solution when the secondary objective function C2 is the minimum is taken as the final solution to obtain the optimal multimodal transport path.

7. The multimodal transport path planning method based on adaptive large-scale neighborhood search according to claim 6, characterized in that: The destruction operators include: random destruction operator, cluster destruction operator, path cutting operator and worst destruction operator, and the repair operators include: greedy repair operator, nearest neighbor repair operator and path reconstruction operator.

8. The multimodal transport path planning method based on adaptive large-scale neighborhood search according to claim 6, characterized in that: In step 4.5, the probability p of the optimal solution being accepted under the current number of iterations is generated according to the annealing temperature. a The specific process is: in, represents the secondary objective function value corresponding to the optimal solution under the a-th iteration number, T a represents the annealing temperature at the ath iteration, T a =αT a-1 , α represents the annealing temperature drop coefficient.

9. A computer-readable storage medium storing a computer program, characterized in that: The computer program enables the computer to execute the multimodal transport path planning method based on adaptive large-scale neighborhood search as described in any one of claims 1-8.

10. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the multimodal transport path planning method based on adaptive large-scale neighborhood search as described in any one of claims 1 to 8 is implemented.

Images