Container port berth and storage yard distribution combined planning operation method and system

Abstract

The invention discloses a container port berth and storage yard allocation combined planning operation method and system based on a cluster strategy, and the method comprises the steps: collecting the information of ships, container trucks and storage yards in a target time period, including the planned arrival time of the ships, the number and types of containers carried by the ships, the stockpiling state of the storage yards, and the planned arrival time of outer container trucks; the collected information is input into a pre-constructed multi-target mixed integer programming model, and an optimal programming strategy is calculated and comprises berth plans of all ships in a specified time period and loading and unloading operation plans of container batches; wherein the pre-established multi-target mixed integer programming model comprises three target functions, and the targets are the shortest ship berthing deviation expected turnover time, the minimum container transportation total distance between a berth and a storage yard container area and the minimum workload imbalance of the storage yard container area respectively; and executing ship and storage yard operation according to the optimal planning strategy. The overall operation efficiency of the wharf can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of container terminal operation resource allocation, and in particular to a combined planning method and system for container port berth and yard allocation based on a clustering strategy. Background Art

[0002] With the booming development of global trade, maritime transportation plays a crucial role in the global economic and trade system. According to statistics, more than 80% of the world's goods rely on ship transportation. In recent years, the global container trade volume has shown a continuous growth trend, and serious congestion has even occurred in some Asian ports. Against this background, improving the operation efficiency of container terminals has become a key requirement for the industry's development, and the operation efficiency of container terminals depends to a large extent on the smoothness of container operations and the effective utilization of terminal resources. Among them, berths and yards, as the most critical and limited resources of the terminal, their reasonable allocation is of decisive significance for the efficient operation of the entire terminal operation.

[0003] Currently, most ports generally adopt a consignment strategy to manage the yard blocks, that is, the yard is divided into several sub-blocks, each sub-block has a fixed number of continuous bays, and then the containers are stored in these sub-blocks. However, due to the uncertainty of the arrival and departure times of containers, during certain specific time periods, there may be overloading or overcrowding in some yard blocks; while other yard blocks are idle for a long time. This unbalanced workload distribution cannot achieve the optimal allocation of resources and severely restricts the improvement of the overall terminal operation efficiency. Summary of the Invention

[0004] The main object of the present invention is to provide a combined planning operation method and system for container port berth and yard allocation that can improve the overall operation efficiency of the terminal.

[0005] The technical solution adopted by the present invention is as follows: Provide a combined planning operation method for container port berth and yard allocation based on a clustering strategy, including the following steps: S1. Collect information on ships, container trucks, and yards during the target time period, including the planned arrival time of ships, the quantity and type of containers carried by ships, the stacking status of the yard, and the planned arrival time of external container trucks; S2. Input the collected information into a pre-built multi-objective mixed integer programming model to calculate the optimal planning strategy, including the berth plan of all ships in a specified time period and the loading and unloading operation plan of container batches. The berth plan includes the arrival time, berthing position and berthing time of the ship. The loading and unloading operation plan of the container batch includes the yard container area, loading and unloading route and loading and unloading time allocated to the container batch on the corresponding ship or container truck; wherein the pre-built multi-objective mixed integer programming model includes three objective functions, respectively aiming at minimizing the expected turnaround time of the ship berthing, minimizing the total container transportation distance between the berth and the yard container area, and minimizing the workload imbalance in the yard container area; S3. Execute ship and yard operations according to the optimal planning strategy.

[0006] Following the above technical solution, in step S1, the containers on the same ship or container truck are divided into multiple batches according to their destinations, and then the batches with the same destination are grouped into a container cluster, and the container cluster is assigned to a container area template using an integer coding scheme, and then the container area template is assigned to a specific container yard area; the ship or container truck itself is used as the destination.

[0007] Following the above technical solution, when solving a multi-objective mixed integer programming model, a fitness evaluation mechanism FCE-FEM based on fuzzy correlation entropy is used to select the optimal solution.

[0008] Following the above technical solution, in the process of screening the optimal solution based on the fitness evaluation mechanism FCE-FEM based on fuzzy correlation entropy, the global search capability is improved through an improved taboo search strategy. Specifically, based on the taboo search and multi-neighborhood search structure, a variety of neighborhood movement rules are designed to increase the neighborhood solution set, and the mutated neighborhood solution set is re-optimized.

[0009] Following the above technical solution, multiple neighborhood movement rules include Exchange rule, Fragment Insert rule and Intermingle Swap rule, wherein the Exchange rule is to randomly select two container slots and exchange the genes of the two container areas; the Fragment Insert rule is to first randomly select two container slots, remove the genes between the two container slot numbers, and then randomly select a position in the remaining chromosomes to insert the removed genes into the position; the Intermingle swap rule is to randomly generate several container area positions and disrupt the gene order at the corresponding ship position.

[0010] Continuing with the above technical solution, the constraint conditions of the multi-objective mixed-integer programming model include: Each ship can only choose one berth for berthing. Two ships berthing at the same berth must have a front-to-back berthing order. Each ship can only berth and depart once. The start and end loading and unloading times of the ship are specified. It is stipulated that the operation starts immediately after the ship berths, and the ship leaves the berth immediately after the operation ends. The loading and unloading operation time of the container batch is within the loading and unloading time of the corresponding ship.

[0011] Continuing with the above technical solution, when solving the mixed-integer programming model, according to the three constructed objective function formulas, calculate the objective function values corresponding to each planning strategy in a specific order. First, add the berthing time of the ship to the known time in port to accurately calculate the departure time of the ship, and then calculate the cost generated by the ship deviating from the expected turnover time interval according to the relevant formula. Second, within the ship's berthing time range, generate the loading and unloading operation plan for the corresponding container batch, and calculate the workload imbalance within the planned range. Finally, according to the loading and unloading operation plan and the ship's berthing position information, determine the storage location of each container batch in the yard, calculate the average transportation distance of the container batch, and then accumulate the average moving distances of all container batches according to the formula to finally obtain the total container moving cost.

[0012] The present invention also provides a joint planning operation system for container port berths and yards based on a clustering strategy, including: An information collection module, used to collect information on ships, container trucks, and yards during the target time period, including the planned arrival time of the ship, the quantity and type of containers carried by the ship, the stacking status of the yard, and the planned arrival time of external container trucks; An optimal planning strategy solving module, used to input the collected information into a pre-constructed multi-objective mixed-integer programming model to calculate the optimal planning strategy, including the berth plan for all ships during the specified time period, the loading and unloading operation plan for the container batch. The berth plan includes the arrival time, berthing position, and port stay time of the ship. The loading and unloading operation plan for the container batch includes the yard block area, loading and unloading route, and loading and unloading time allocated to the container batch on the corresponding ship or container truck; Among them, the pre-established multi-objective mixed-integer programming model includes three objective functions, respectively aiming at minimizing the shortest deviation of ship berthing from the expected turnover time, minimizing the total container transportation distance between the berth and the yard block area, and minimizing the workload imbalance of the yard block area; An execution mechanism, used to execute ship and yard operations according to the optimal planning strategy.

[0013] Continuing with the above technical solution, when the optimal planning strategy solving module solves the multi-objective mixed-integer programming model, it specifically screens the optimal solution based on the fitness evaluation mechanism FCE-FEM of fuzzy correlation entropy.

[0014] The present invention also provides a computer storage medium, which stores a computer program executable by a processor. The computer program executes the joint planning operation method for container port berth and yard allocation based on the cluster strategy described in the above technical solution.

[0015] The beneficial effects of the present invention are as follows: The present invention constructs a multi-objective mixed integer programming model, where the multi-objectives are respectively aimed at the shortest deviation of ship berthing from the expected turnover time, the minimum total distance of container transportation between the berth and the yard block, and the minimum imbalance of yard block workload. And the three objectives are comprehensively considered from three different perspectives of port berthing planning, yard transportation route, and yard workload. Moreover, the three objectives are closely linked. The berth plan of the ship is generated through the first objective, clarifying the berthing position and berthing time, aiming to minimize the deviation from the ship's expected turnover time interval. On the basis of the first objective, various loading and unloading routes of the container can be determined to obtain the loading and unloading plan with the minimum transportation distance, achieving the second objective. On the basis of the second objective, calculate whether the workload of the yard block is balanced, and find the most balanced workload plan to achieve the third objective. The present invention solves the complex port operation through a mathematical model, can efficiently obtain the container port berth and yard space allocation plan for a future time period, and is beneficial to improving the yard space utilization rate and reducing yard-side congestion.

[0016] Furthermore, in the process of screening the optimal solution by the fitness evaluation mechanism FCE-FEM based on fuzzy correlation entropy, through the improved tabu search, three new neighborhood movement rules are designed to increase the neighborhood solution set, and the mutated neighborhood solution set is re-optimized, thereby improving the global search ability of the algorithm.

[0017] Of course, it is not necessary for any product implementing the present invention to achieve all the above-mentioned advantages simultaneously. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0019] Figure 1 is a flowchart of the joint planning operation method for container port berth and yard allocation based on the cluster strategy according to an embodiment of the present invention; Figure 2 is a schematic diagram of the container terminal layout according to an embodiment of the present invention; Figure 3 is a flowchart of the adaptive multi-objective evolutionary algorithm according to an embodiment of the present invention; Figure 4 Schematic diagram of the container yard area for the entry and exit of a container cluster according to an embodiment of the present invention; Figure 5 Design diagram of an improved tabu search neighborhood movement rule according to an embodiment of the present invention; Figure 6A Schematic diagram of the objective function value of the ship berthing deviation time under different berth passing capacities according to an embodiment of the present invention; Figure 6B Schematic diagram of the objective function value of workload imbalance under different berth passing capacities according to an embodiment of the present invention; Figure 6C Schematic diagram of the objective function value of the container transportation distance under different berth passing capacities according to an embodiment of the present invention. Detailed implementation manners

[0020] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0021] It should be noted that the diagrams provided in the embodiments of the present invention only illustrate the basic concept of the present invention in a schematic manner. Therefore, only the components related to the present invention are shown in the diagrams, rather than being drawn according to the number, shape and size of the components in actual implementation. The type, quantity and proportion of each component in actual implementation can be arbitrarily changed, and the component layout type may also be more complex.

[0022] In the present invention, it should also be noted that when terms such as "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. appear, the orientation or positional relationship indicated is based on the orientation or positional relationship shown in the accompanying drawings. It is only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation to the present application. In addition, when terms such as "first" and "second" appear, they are only used for descriptive and distinguishing purposes and cannot be understood as indicating or implying relative importance.

[0023] In addition, it should also be noted that the features of various embodiments of the present invention can be partially or wholly combined or integrated, and as can be understood by those skilled in the art, they can interact and operate in different ways. Each embodiment can be implemented independently of each other or in an associated relationship.

[0024] Embodiment 1 As Figure 1As shown in the figure, the joint planning operation method for berth and yard allocation in a container port based on a cluster strategy according to an embodiment of the present invention includes the following steps: S1. Collect information on ships, container trucks, and yards during the target time period, including the planned arrival time of ships, the quantity and type of containers carried by ships, the storage status of yards, and the planned arrival time of external container trucks; S2. Input the collected information into a pre-constructed multi-objective mixed-integer programming model to calculate the optimal planning strategy, including the berth plan for all ships during the specified time period, the loading and unloading operation plan for container batches. The berth plan includes the arrival time, berthing position, and port stay time of the ship. The loading and unloading operation plan for container batches includes the yard block area, loading and unloading route, and loading and unloading time allocated to the container batches on the corresponding ship or container truck. Among them, the pre-established multi-objective mixed-integer programming model includes three objective functions, aiming at minimizing the shortest deviation of ship berthing from the expected turnover time, minimizing the total container transportation distance between the berth and the yard block area, and minimizing the imbalance of yard block area workload; S3. Execute ship and yard operations according to the optimal planning strategy.

[0025] Further, in step S1, the containers on the same ship or container truck are specifically divided into multiple batches according to the destination, and then the batches with the same destination are grouped into a container cluster. An integer coding scheme is used to allocate the container cluster to the block template, and then the block template is allocated to the specific yard block area; the ship or container truck itself is used as the destination. The block template can be regarded as a simple copy of the yard block area. The block template is a combination of clusters composed of different container batches. These clusters are stacked together within the specification range to form a block template, so as to reduce the total workload gap between the block templates (yard block areas) within the specification range. Finally, a yard block area is allocated to each block template to minimize the moving distance of all container clusters.

[0026] When solving the multi-objective mixed-integer programming model, an optimal solution is specifically screened based on the fitness evaluation mechanism FCE-FEM of fuzzy correlation entropy.

[0027] In the process of screening the optimal solution based on the fitness evaluation mechanism FCE-FEM of fuzzy correlation entropy, the global search ability is improved through an improved tabu search strategy. Specifically, based on the tabu search and multi-neighborhood search structure, a variety of neighborhood movement rules are designed to increase the neighborhood solution set, and the mutated neighborhood solution set is re-optimized.

[0028] Among them, the multiple neighborhood movement rules include the Exchange rule, the Fragment Insert rule, and the Intermingle Swap rule. The Exchange rule randomly selects the positions of two containers and exchanges the genes of the two container areas; the Fragment Insert rule first randomly selects the positions of two containers, removes the genes between the two position numbers, and then randomly selects a position in the remaining chromosome and inserts the removed genes into this position; the Intermingle swap rule randomly generates the container area positions of several containers and disrupts the gene order at the corresponding ship positions.

[0029] Furthermore, the constraint conditions of the multi-objective mixed integer programming model include: each ship can only choose one berth to berth at, two ships berthing at the same berth must have a front-to-back berthing order, each ship can only berth and depart once, the start and end loading and unloading times of the ship are specified, it is stipulated that the operation starts immediately after the ship berths, and the ship leaves the berth immediately after the operation ends, and the loading and unloading operation time of the container batch is within the loading and unloading time of the corresponding ship.

[0030] Preferably, when solving the mixed integer programming model, according to the three constructed objective function formulas, the objective function values corresponding to each planning strategy are calculated in a specific order. First, the berthing time of the ship is added to the known time in port to accurately calculate the departure time of the ship, and then the cost generated by the ship deviating from the expected turnover time interval is obtained according to the relevant formula; secondly, within the ship berthing time range, the loading and unloading operation plan of the corresponding container batch is generated, and the workload imbalance within the planning range is calculated; finally, according to the loading and unloading operation plan and the ship berthing position information, the storage position of each container batch in the yard is determined, the average transportation distance of this container batch is calculated, and then the average moving distances of all container batches are accumulated according to the formula, and finally the total container moving cost is obtained.

[0031] In addition to screening the optimal solution using the fitness evaluation mechanism FCE-FEM based on fuzzy correlation entropy, other fitness calculation methods can also be applied to screen for better solutions. For example, in the NSGA-II algorithm (multi-objective genetic algorithm), the diversity of the population is maintained through non-dominated sorting and crowding distance calculation, and the optimal solution set is gradually approximated. The final solution is usually selected from the optimal solution set of the last generation according to the preferences of the decision maker or specific rules after the algorithm runs to completion. Among them, non-dominated sorting means that if a solution is not better than another solution in all objective functions and is strictly inferior to another solution in at least one objective function, then this solution is said to be dominated by the other solution. For example, when solving three minimization objective functions, assume that the three objective functions of solution A are (60, 70, 85) and the three objective functions of solution B are (65, 75, 86). Since all three solutions in A are better than the three solutions in B, it is said that A dominates B. A is a non-dominated solution and B is a dominated solution, and so on. After several iterations of the algorithm, a set of non-dominated solution sets, that is, the optimal solution sets, will be found, and these are all optimal solutions.

[0032] The present invention constructs a multi-objective mixed integer programming model, where the multi-objectives are respectively to minimize the shortest deviation of ship berthing from the expected turnover time, to minimize the total distance of container transportation between the berth and the yard block, and to minimize the imbalance of yard block workload. The three objectives are comprehensively considered from three different perspectives: port berthing planning, yard transportation route, and yard workload, and the three objectives are closely linked. The present invention solves the complex port operation through a mathematical model, can efficiently obtain the container port berth and yard space allocation plan for a future time period, and is beneficial to improving the yard space utilization rate and reducing yard-side congestion.

[0033] Embodiment 2 This embodiment is a specific optimization based on Embodiment 1. In this embodiment, a mixed-integer programming model with multiple objectives of minimizing the deviation of ship berthing from the expected turnover time, the total distance of container transportation between the berth and the yard block, and the imbalance of yard block workload is established in advance, considering constraints such as container storage area limitations, uniqueness of cluster allocation, consistency of container destinations within the cluster, balance of yard block workload, limitation of the total number of bays in the yard block, and limitation of the number of bays in the cluster. To solve the complex model, a cluster stacking strategy can be used to allocate yard space. Here, a cluster refers to several adjacent bays in the yard block. Containers are divided into several container batches according to the discharging ship (truck) and the loading ship (truck). Each ship is regarded as a departure or destination. Similarly, trucks arriving at the port during the same time period are regarded as departure or destinations. Therefore, several container clusters can be divided according to the destination of the containers. Container batches with the same destination form a cluster and are stacked in the corresponding yard block. And the concept of yard block template is designed. The yard block template can be regarded as a simple copy of the yard block. The yard block template is a combination of clusters composed of different container batches. These clusters are stacked together within the specification range to form the yard block template, so as to reduce the total workload gap between yard block templates (yard blocks) within the specification range, and a yard block is allocated to each yard block template to minimize the moving distance of all container clusters.

[0034] In this embodiment, an adaptive multi-objective evolutionary algorithm is designed to solve the mixed-integer programming model. In the algorithm, a fitness evaluation mechanism FCE-FEM based on fuzzy correlation entropy is proposed to evaluate the multi-objective method, and an adaptive local reinforcement search strategy is introduced to improve the global search ability.

[0035] After the above model and solution algorithm are determined, the corresponding data is collected according to the parameters required by the model and then input into the model for solution, so as to obtain the best planning strategy within a specified time. The data collected includes data and information such as the expected arrival time of the ship, the quantity and type of containers carried by the ship, the storage status of the yard, and the arrival time of external trucks. According to the origin ship or truck and the destination ship or truck of the container, the container batches are divided into multiple container clusters. A cluster stacking strategy can be used to allocate yard space. A cluster refers to several adjacent bays in the yard block. Containers are divided into several container batches according to the discharging ship (truck) and the loading ship (truck). Each ship is regarded as a departure or destination. Similarly, trucks arriving at the port during the same time period are regarded as departure or destinations. Therefore, several container clusters can be divided according to the destination of the containers. Container batches with the same destination form a cluster and are stacked in the corresponding yard block.

[0036] Specifically, in this embodiment, a multi-objective mixed-integer programming model for the joint planning problem of container port berth and yard allocation based on a clustering strategy is given, expressed as:

[0037]

[0038]

[0039]

[0040] In the formula, the objective function is to simultaneously minimize the deviation of the ship from the expected turnover time interval, the total distance of container movement, and the workload imbalance in the yard block. represents the deviation of the ship's berthing from the expected turnover time, represents the total transportation distance of the container group between the berth and the yard block, represents the workload imbalance in the yard block. ship actual berthing time; ship actual unberthing time; is the expected turnover service time interval of ship ; represents the maximum workload processed in all yard blocks during the time period; represents the minimum workload processed in all yard blocks during the time period; represents 1 if the ship with containers to be unloaded is berthed at berth , otherwise 0; represents 1 if the ship with containers to be loaded is berthed at berth , otherwise 0; represents 1 if there is a group of containers unloaded from ship and finally loaded on ship , otherwise 0; represents 1 if the container batch belongs to the cluster , otherwise 0; represents the number of berths allocated to the cluster in the yard block template during the time period; ; represents 1 if the yard block template is allocated to the yard block , otherwise 0; represents the yard block distance from the berth The average distance between Denote the set of time periods within the problem cycle; Denote the set of berths; Denote the set of ships; Denote the set of ships (trucks) that need to unload containers; Denote the set of ships (trucks) that need to load containers; Denote the set of container blocks; Denote the set of clusters; Denote the set of container block templates.

[0041] To decompose the highly complex optimization model, first, through the formula, generate the berthing plan for the ships, specifying the berthing location and berthing time, with the aim of minimizing the deviation from the expected turnover time interval of the ships. Secondly, based on the actual berthing time and departure time of the ships determined by f1, stack different batches of containers at different yard container block templates according to their destinations. The yard container block template can be regarded as a simple copy of the yard container block. While stacking to form the yard container block template, use the formula f3 to minimize the workload imbalance of the yard container block template. Among them, the workload of each time period of the yard container block template refers to the sum of the container volume entering the container block template and the container volume leaving the container block template during that time period. For example, in the second time period, 3 bays of container volume enter the container block template k, and 4 bays of containers leave, then in the second time period, the workload of the yard template k is 7. Similarly, calculate the workloads of other yard container block templates to obtain the workload imbalance (maximum minus minimum) of the yard container block templates during that time period. Finally, assign a yard container block to each container block template, and use the formula f2 to minimize the moving distance of all container clusters.

[0042] Furthermore, the constraint conditions of the multi-objective mixed-integer programming model include: 1) Each ship can only choose one berth to berth at

[0043] where is a 0-1 variable. If berth is assigned to ship then it is 1, otherwise it is 0.

[0044] 2) Two ships berthing at the same berth must have a front-to-back berthing order

[0045]

[0046] is a 0-1 variable. If berth Allocated to the ship And the ship And the ship At the ship Docks at the berth before Is 1; otherwise 0.

[0047] 3) Each ship can only berth and depart once

[0048]

[0049] Is a 0-1 variable, indicating that during the Time period, when the ship Berths, it is 1; otherwise 0; Is a 0-1 variable, indicating that during the Time period, when the ship Leaves the berth, it is 1; otherwise 0.

[0050] 4) Specify the start and end loading and unloading times of the ship

[0051]

[0052] Is a 0-1 variable, indicating that during the Time period, the ship Starts loading and unloading operations, it is 1; otherwise 0; Is a 0-1 variable, indicating that during the Time period, the ship Completes loading and unloading operations, it is 1; otherwise 0.

[0053] 5) Specify that the operation starts immediately after the ship berths and the ship leaves the berth immediately after the operation ends

[0054]

[0055] 6) Represent the start and end loading and unloading constraints of the ship

[0056]

[0057] Among them, Represents the ship The time when loading and unloading operations start; Represents the ship The time to end the loading and unloading operation.

[0058] 7) Constraining the relationship between the start time and the end time of the ship's operation

[0059] Among them, represents the ship The time of the loading and unloading operation.

[0060] 8) The relationship between the operation times of the front and rear ships at the same bay

[0061] Among them, represents a large positive constant.

[0062] 9) Indicating that the start time and the end time of the ship's operation must be within the feasible service time window

[0063]

[0064] Among them, represents the ship The feasible service time period.

[0065] 10) Indicating that the quay workload generated by loading and unloading containers on the ship must comply with the handling capacity of the berth

[0066] Among them, is a 0-1 variable. If the container batch is a transit container, it is 1; otherwise, it is 0; is a 0-1 variable. If the container batch is an export container, it is 1; otherwise, it is 0; is a 0-1 variable. If the container batch is an import container, it is 1; otherwise, it is 0. represents the maximum workload that can be handled by berth b within a unit time period.

[0067] 11) Indicating that the operation volume of each container batch should be equal to its task volume

[0068]

[0069] Among them, represents the workload of unloading the container batch from the ship to the yard during the time period; Indicates that during the time period, the workload of loading container batches from the yard to the ship.

[0070] 12) Indicates that the operation time of the container batch should be within the loading and unloading time of the corresponding ship

[0071]

[0072] Among them, is a 0-1 variable. During the time period, if the container batch is unloaded from the ship to the yard, it is 1; otherwise, it is 0. is a 0-1 variable. During the time period, if the container batch is loaded from the yard to the ship, it is 1; otherwise, it is 0.

[0073] 13) Indicates that export containers and transit containers are placed in the export container area, and import containers are placed in the import container area

[0074]

[0075] Among them, indicates that if the cluster is assigned to the container area template it is 1; otherwise, it is 0. represents the set of export container areas; represents the set of import container areas.

[0076] 14) Ensure that all containers in the cluster have storage locations, and the storage locations vacated for the containers loaded onto the ship should be equal to the locations released by the corresponding cluster

[0077]

[0078] Among them, indicates that during the time period, due to the release of the cluster the additional empty bays in the container area template .

[0079] 15) Indicates that a container batch can only be assigned to one cluster

[0080] 16) A block area template can only be assigned to one yard block area. Similarly, one yard block area can only select one block area template.

[0081]

[0082] 17) It means that containers with the same destination should be stored in the same cluster. For any containers stored in a cluster, the destination of these containers can only be one.

[0083]

[0084] Among them, is a 0-1 variable. If the cluster is reserved for the container batch to be loaded onto the ship (truck), it is 1, otherwise it is 0.

[0085] 18) It means that the workload of each block area is balanced within the time period.

[0086]

[0087] Among them, represents the total number of bays required for the container batch . is a 0-1 variable. If the export container batch arrives at the yard within the time period, it is 1, otherwise it is 0; is a 0-1 variable. If the import container batch arrives at the yard within the time, it is 1, otherwise it is 0; represents the set of clusters located in the yard block area .

[0088] 19) It means that the bays occupied by the clusters of the same block area template cannot exceed the total number of bays of the block area template.

[0089] Among them, represents the total number of bays of the yard block area template.

[0090] 20) It means that the number of container bays assigned to a cluster cannot exceed the maximum number of bays that the cluster can accommodate.

[0091] Among them, represents the cluster The maximum number of bays that can be accommodated.

[0092] 21) represents the decision variable constraint Furthermore, the steps of the adaptive multi-objective evolutionary algorithm are as follows: 1) Encoding and decoding A two-layer integer encoding scheme is adopted to encode the ship berthing plan. The first-layer integer is used to represent the berthing time of the ship, and the second-layer integer represents the berthing position of the ship. At the same time, according to the container destination information, the container batches are divided into several clusters, and an integer encoding scheme is used to allocate the clusters to the block templates, and then the block templates are allocated to the specific yard blocks.

[0093] In the decoding process, according to the objective function formula of the established multi-objective mixed integer programming model, the objective function values corresponding to each encoding scheme are calculated in a specific order. First, the berthing time of the ship is added to the known in-port time to accurately calculate the departure time of the ship, and then the cost caused by the ship deviating from the expected turnover time interval is calculated according to the relevant formula. Secondly, according to the allocation plan of the clusters and the block templates, the cluster set to which the block template belongs is determined in detail. Within the ship berthing time range, a loading and unloading operation plan for the corresponding container batches is generated, and based on this, the loading and unloading operation plan of the block template and the comprehensive loading and unloading operation plan of all block templates are further obtained, and the imbalance of the block workload within the planning range is calculated through the corresponding formula. Finally, according to the allocation plan between the block templates and the blocks and the ship berthing position information, the storage positions of each cluster and container batch in the yard are determined, the average transportation distance between the berth and the block for this container batch is calculated, and then the average moving distances of all container batches are accumulated according to the formula to finally obtain the objective function value of the total container moving cost.

[0094] 2) Fitness evaluation mechanism based on fuzzy correlation entropy (FCE - FEM method) Construct comparison points, dynamic reference points and dynamic worst points. The calculation formula of the comparison points is determined according to the objective function values of the population individuals at different iteration stages, and is used to measure the relative position relationship between individuals in the objective space. The calculation formula of the dynamic reference points comprehensively considers factors such as the number of iterations, individual objective values and the total number of objectives, and provides a dynamic reference standard for evaluating individual performance. The calculation formula of the dynamic worst points is also based on the population individual information and is used to determine the worst performance of individuals in the objective space.

[0095] The membership function of the sub-objective is mapped by using the relative membership function. By introducing the upper and lower bound factors, the sub-objective values are converted into membership function values, making different objectives comparable and facilitating subsequent calculation and evaluation.

[0096] Convert the comparison points and dynamic reference points into comparison fuzzy sets and ideal fuzzy sets, and use fuzzy set theory to fuzzify the performance of individuals in the multi-objective space to more accurately describe the advantages and disadvantages of individuals.

[0097] Calculate the fuzzy entropy, fuzzy partial entropy, fuzzy correlation entropy, and fuzzy correlation entropy coefficient of the comparison fuzzy set and the ideal fuzzy set. Fuzzy entropy is used to measure the degree of uncertainty of the fuzzy set, fuzzy partial entropy further evaluates the deviation degree of the individual from the ideal point on a specific objective, fuzzy correlation entropy reflects the similarity between the individual and the ideal individual by calculating the correlation degree between two fuzzy sets, and finally, by calculating the fuzzy correlation entropy coefficient (FCE coefficient), the multi-objective problem is transformed into a simple and intuitive coefficient for evaluating the performance of the solution. The higher the coefficient, the better the performance of the solution.

[0098] Among them, the fuzzy correlation entropy fitness evaluation mechanism (FCE-FEM) has the following specific steps: Step1: Construct the comparison points , the dynamic reference points and the dynamic worst points .

[0099]

[0100]

[0101]

[0102] In the formula: represents the -th iteration of the -th objective of the individual , , refers to the population individuals, , refers to the maximum number of iterations; and respectively represent the optimal value and the worst value of the -th iteration of the -th objective, , refers to the total number of objectives.

[0103] Step2: Map the membership degree value of the sub-objective using the relative membership degree function.

[0104]

[0105] In the formula: , , and respectively represent the upper and lower bound factors ( ).

[0106] Step3: Convert the comparison point and the dynamic reference point into a comparison fuzzy set and the ideal fuzzy set .

[0107]

[0108]

[0109] Step4: Calculate the fuzzy entropy of and , where , .

[0110]

[0111]

[0112] Step5: Calculate the fuzzy partial entropy of with respect to ; Similarly, calculate the fuzzy partial entropy of with respect to .

[0113]

[0114]

[0115] Step6: Calculate the fuzzy correlation entropy between and .

[0116]

[0117] Step7: Calculate the fuzzy correlation entropy coefficient between and , which is represented by .

[0118]

[0119] In the formula:

[0120] 3) Evolution operator Selection operation based on FCE coefficient: Using the roulette wheel rule, the calculated FCE coefficient is used to determine the selection probability and cumulative probability of individuals. The formula for calculating the selection probability is determined according to the ratio of the FCE coefficient of an individual to the sum of the FCE coefficients of all individuals in the population, and the cumulative probability is obtained by successively adding the individual selection probabilities. In this way, in the selection operation, individuals with higher fitness (i.e., larger FCE coefficients) are more likely to be selected, ensuring that the population evolves towards the optimal solution.

[0121] Cooperative single-point crossover: For the berth planning scheme, the allocation scheme between the cluster and the block module, and the allocation scheme between the block template and the block, the cooperative single-point crossover operation is carried out in sequence. The crossover probability adopts an adaptive adjustment mechanism, and its calculation formula comprehensively considers factors such as the upper and lower bounds of the crossover probability, the fuzzy correlation entropy coefficient of the individual, the maximum fuzzy correlation entropy coefficient and the average correlation entropy coefficient in the population. During the crossover operation, first a real number is randomly generated and compared with the crossover probability. If it is less than the crossover probability, two parent chromosomes are randomly selected from the population after the selection operation based on FCE. Then a crossover point is randomly generated, and the genes in the specified part of the parent chromosomes are exchanged to form two new chromosomes. Finally, it is checked whether there are duplicate block numbers in the genes of the newly generated chromosomes. If so, they are corrected to ensure the feasibility of the new chromosomes.

[0122] 2-Opt reverse order mutation: The 2-Opt reverse order mutation operation is carried out on the above three types of chromosomes in sequence. The mutation probability also adopts an adaptive adjustment mechanism, and its calculation formula is related to the upper and lower bounds of the mutation probability. During the mutation operation, a real number is randomly generated. If it is less than the mutation probability, a chromosome is randomly selected from the population, and then two bin positions are randomly generated, and the gene segment between these two bin positions is reversed to form the mutated offspring chromosome. This mutation method causes a large perturbation to the parent chromosome, which helps to increase the population diversity and avoid premature convergence of the algorithm.

[0123] 4) Adaptive local reinforcement search strategy Adaptive strategy based on pseudo-entropy theory: Integrate the FCE coefficient into the pseudo-entropy theory, and calculate the pseudo-entropy value of the multi-objective problem through a specific formula. The calculation of the pseudo-entropy value comprehensively considers factors such as the FCE coefficient of the population individuals, the total number of objectives, and the number of iterations, and is used to measure the distribution of the population in the multi-objective space. According to the pseudo-entropy value, it is judged whether to start the local search. When the pseudo-entropy value meets certain conditions, it indicates that the population diversity is low and may fall into a local optimum. At this time, the local search is started to improve the ability of the algorithm to jump out of the local optimum solution.

[0124] Improved taboo search: Based on taboo search and multi-neighborhood search structure, three neighborhood movement rules are designed, namely Exchange, Fragment Insert, and Intermingle swap. The Exchange rule randomly selects two bins and exchanges the genes of the two bins; the Fragment Insert rule first randomly selects two bins, removes the genes between the two bin numbers, and then randomly selects a position in the remaining chromosome to insert the removed genes into the position; the Intermingle swap rule randomly generates several bin positions and disrupts the gene order at the corresponding ship position. When executing the improved taboo search, first define the parameters such as neighborhood structure, maximum number of iterations, number of iterations, taboo length, taboo table, and number of neighborhood solutions. Then randomly select an individual from the current solution set, generate a new neighborhood solution set for the individual according to the neighborhood rules, and calculate its fitness value. Find the individual with the highest fitness value in the neighborhood solution set. If it meets certain conditions (such as not in the taboo table and the fitness value is better than the current optimal solution), update the current optimal solution and the taboo table; otherwise, select the individual with the best fitness value that is not in the taboo table from the neighborhood solution set as the new current solution, and update the taboo table. Repeat the above process until the maximum number of iterations is reached, and output the optimal solution, so as to further optimize the mutated solution and improve the global search ability of the algorithm.

[0125] Specifically, the adaptive local enhanced search strategy includes: 1) Adaptive strategy based on quasi-entropy theory The fitness value coefficient is integrated into the pseudo-entropy theory to calculate the pseudo-entropy value of the multi-objective problem, and whether to start local enhanced search is determined based on the pseudo-entropy value.

[0126]

[0127]

[0128] Where: is the pseudo-entropy value of the g-th iteration.

[0129] 2) Improved tabu search Define three neighborhood structures including Exchange-based neighborhood movement rules ( ), Neighborhood movement rules based on FragmentInsert ( ) and the neighborhood movement rule based on Intermingle swap ( ), re-optimize the mutated solution. If , then select the mutated individuals to perform the following operations: Step 1: Define the neighborhood structure ; Maximum number of iterations Gen; Iteration number ; Tabu length ; Tabu list ; Number of neighborhood solutions .

[0130] Step2: Randomly select an individual from the above solution set , and let .

[0131] Step3: For the individual generate a new neighborhood solution set according to the neighborhood rule , and calculate its fitness value at the same time.

[0132] Step4: Find the highest fitness value, that is , and record the corresponding solution set .

[0133] Step5: If , let . Update the tabu list , and execute Step 7; otherwise, execute Step 6. Step6: Select from the neighborhood solution set the solution set with the best fitness value and not in the tabu list . Let , and update the tabu list .

[0134] Example 3 This example is a specific implementation of the above method example, where data collection and preparation are specifically as follows: 1) Instance data generation This disclosure example generates a set of test instances based on the actual operating conditions of a container terminal with an annual throughput of 2 million TEUs. The container terminal layout and container transfer process are as Figure 2 ​As shown in the figure. It is determined that the number of berths is 5, the number of import container areas and export container areas are 2 and 8 respectively; the number of ships is 10, the number of container batches is 34, the number of bays in each yard container area is set to 50, the problem period is 18 time periods, each time period is 3 hours, the passing capacity of the berth is 25 bays per time period, the maximum container volume that the cluster can accommodate is 30 bays, and the container volume of 1 bay is 50 TEU. The distance from the berth to the yard container area is regarded as the Manhattan distance between the central points. For each container batch, the required number of container bays follows a uniform distribution [5, 10]; the loading and unloading time of each ship also follows a uniform distribution [2, 3]. Randomly generate the type of each container batch (import, export or transit) to ensure that all test instances meet the feasibility requirements of actual operations.

[0135] 2) Algorithm parameter setting After multiple groups of parameter experiments, the parameter settings of the adaptive multi-objective evolutionary algorithm are as follows: the population size is 600, the maximum number of iterations is 100, the minimum crossover probability is 0.4, the maximum crossover probability is 0.99, the minimum mutation probability is 0.2, the maximum mutation probability is 0.6, the upper bound factor and the lower bound factor .

[0136] The process of the multi-objective evolutionary algorithm is as Figure 3 shown, and the specific steps are as follows: 1) Encoding scheme First, adopt a double-layer integer encoding scheme to represent the ship berthing plan. The first layer represents the berthing time of the ship , and the second layer represents the berthing position of the ship , where and represent the berthing time and berthing position of the th ship respectively. According to the container destination, the container batches are divided into several clusters, and then an integer encoding scheme is used to assign the clusters to the block templates and assign the block templates to the yard container areas , where represents the number of the block template assigned to the fth cluster, and represents the number of the yard container area assigned to the kth block template.

[0137] 2) Decoding process During decoding, according to the encoding information and the model calculation rules, calculate the objective function value of each scheme.

[0138] Calculate the deviation of the ship from the expected turnover time interval: For each ship, its berthing time is , and the departure time is The ship deviates from the expected turnover time interval by , where and are the left and right boundaries of the expected turnover service time of the ship respectively.

[0139] Calculate the total distance of container transportation: According to the allocation plan of the cluster and the block template, determine the loading and unloading positions of each container batch, calculate the transportation distances from the berth to the yard block and from the yard block to the berth, and accumulate to obtain the total moving distance of all container batches, including the moving distances of transit containers, export containers, and import containers.

[0140] Calculate the workload imbalance of the yard block: Consider the arrival and departure times and workload distributions of containers in the yard under the cluster strategy. Since the cluster reserves space for the container during its stay time, once the container is removed, the cluster will be released. Therefore, when calculating the workload, it is necessary to accurately count the number of berths for loading and unloading operations in the block during each time period according to the arrival and departure times of the containers in the cluster, as shown in Figure 4 . For a block containing multiple clusters, when calculating the workload imbalance, it is necessary to consider the loading and unloading conditions of the containers in each cluster separately, as well as the operation time differences between different clusters, to ensure accurate calculation of the workload of the block during different time periods, and then obtain an accurate workload imbalance value.

[0141] 3) Fitness evaluation mechanism based on fuzzy correlation entropy (FCE - FEM method) For each individual in the population, calculate the fitness value according to the FCE - FEM method of the above - mentioned embodiment.

[0142] 4) Selection operation Based on the calculated FCE coefficient, perform the selection operation using the roulette wheel rule. Calculate the selection probability of individual and the cumulative probability . By randomly generating a real number , if , then select individual to enter the next - generation population, and repeat this process until the appropriate number of individuals is selected.

[0143] 5) Cooperative single - point crossover operation Perform the cooperative single - point crossover operation on the selected individuals. Taking the allocation plan between the block template and the block as an example. First, randomly generate a real number , compare it with the crossover probability , and the crossover probability is obtained by an adaptive adjustment mechanism. If , randomly select two parental chromosomes and Randomly generate a crossover point and swap the chromosomes of the parents and from to columns to form two new chromosomes and . Secondly, check whether there are duplicate block area numbers in the genes of the newly generated chromosomes and . If there are, find the duplicate block area numbers and record them as and , and swap in the chromosomes and from to form two new feasible chromosomes. Similar crossover operations are also performed on the berth planning scheme and the allocation scheme between the cluster and the block area module.

[0144] 6) 2-Opt inversion reverse mutation operation Taking the allocation scheme between the block area template and the block area as an example, randomly generate a real number . If the mutation probability , where the mutation probability is calculated according to the adaptive adjustment mechanism, then randomly select a chromosome from the population that has undergone the selection operation, randomly generate two bin positions and , and reverse the gene segment between these two bin positions in the chromosome to form an offspring chromosome . Similar mutation operations are also performed on the berth planning chromosome and the allocation plan chromosome of the cluster and the block area template.

[0145] 7) Adaptive local intensification search ① Adaptive strategy based on pseudo-entropy theory According to the FCE coefficient of the individuals in the current population, calculate the pseudo-entropy value at the th iteration. Set a threshold (which can be determined according to experience or experiments). If , it indicates that the population diversity is low and may be trapped in a local optimum. At this time, start the improved tabu search; otherwise, continue with the next iteration.

[0146] ② Improved tabu search Taking the allocation plan between the yard block area template and the block area as an example, define the neighborhood structure, including three neighborhood movement rules: Exchange, Fragment Insert, and Intermingle swap, as Figure 5 shown.

[0147] 8) Algorithm End and Result Output Repeat the steps of fitness evaluation, evolutionary operations (selection, crossover, mutation), and adaptive local reinforcement search until the set maximum number of iterations is reached. When the algorithm reaches the maximum number of iterations, the algorithm ends and the finally obtained optimal solution is output, and the values of each objective function are as Figure 6A , 6B and shown in 6C.

[0148] Example 4 This example is a system example corresponding to the above method example.

[0149] The joint planning operation system for container port berth and yard allocation based on the cluster strategy includes: An information collection module, which is used to collect information on ships, container trucks, and yards during the target time period, including the planned arrival time of ships, the quantity and type of containers carried by ships, the storage status of yards, and the planned arrival time of external container trucks; An optimal planning strategy solving module, which is used to input the collected information into a pre-constructed multi-objective mixed integer programming model to calculate the optimal planning strategy, including the berth plan for all ships during the specified time period, the loading and unloading operation plan for container batches. The berth plan includes the arrival time, berthing position, and port stay time of the ship, and the loading and unloading operation plan for container batches includes the yard block area, loading and unloading route, and loading and unloading time allocated to the container batches on the corresponding ship or container truck; among them, the pre-established multi-objective mixed integer programming model includes three objective functions, which are respectively aimed at minimizing the shortest deviation of ship berthing from the expected turnover time, minimizing the total distance of container transportation between berths and yard block areas, and minimizing the imbalance of yard block area workload; An execution mechanism, which is used to execute ship and yard operations according to the optimal planning strategy.

[0150] Among them, when the optimal planning strategy solving module solves the multi-objective mixed integer programming model, it specifically screens the optimal solution based on the fitness evaluation mechanism FCE-FEM of fuzzy correlation entropy.

[0151] Each module or mechanism is mainly used to implement each step of the above method example, which will not be elaborated here one by one.

[0152] Example 5 The present application also provides a computer-readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, a server, an App application mall, etc., on which a computer program is stored, and when the program is executed by a processor, corresponding functions are implemented. When the computer-readable storage medium of this embodiment is executed by a processor, it implements the combined planning operation method for container port berth and yard allocation in the method embodiment.

[0153] It should be noted that, according to the needs of implementation, the various steps / components described in the present application can be split into more steps / components, or two or more steps / components or partial operations of steps / components can be combined into new steps / components to achieve the purpose of the present invention.

[0154] In the above embodiments, the magnitudes of the sequence numbers of the steps do not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0155] It should be understood that those of ordinary skill in the art can make improvements or transformations according to the above description, and all such improvements and transformations should fall within the protection scope of the appended claims of the present invention.

Claims

1. A combined planning operation method for container port berth and yard allocation based on a cluster strategy, characterized in that, The following steps are involved: S1. Collect information on ships, container trucks and storage yards during the target time period, including the planned arrival time of the ship, the number and type of containers on board the ship, the storage status of the storage yard and the planned arrival time of the container trucks; S2. Input the collected information into a pre-built multi-objective mixed integer programming model to calculate the optimal planning strategy, including the berth plan of all ships in a specified time period and the loading and unloading operation plan of container batches. The berth plan includes the arrival time, berthing position and berthing time of the ship. The loading and unloading operation plan of the container batch includes the yard container area, loading and unloading route and loading and unloading time allocated to the container batch on the corresponding ship or container truck; wherein the pre-built multi-objective mixed integer programming model includes three objective functions, respectively aiming at minimizing the expected turnaround time of the ship berthing, minimizing the total container transportation distance between the berth and the yard container area, and minimizing the workload imbalance in the yard container area; S3. Execute ship and yard operations according to the optimal planning strategy.

2. The joint planning operation method for container port berth and yard allocation based on the cluster strategy according to claim 1, characterized in that In step S1, the containers on the same ship or container truck are divided into multiple batches according to their destinations, and the batches with the same destination are grouped into a container cluster. The container cluster is assigned to a container area template using an integer coding scheme, and the container area template is then assigned to a specific container area in the yard; the ship or container truck itself is used as the destination.

3. The joint planning operation method for container port berth and yard allocation based on the cluster strategy according to claim 1, characterized in that, When solving multi-objective mixed integer programming models, the fitness evaluation mechanism FCE-FEM based on fuzzy correlation entropy is used to select the optimal solution.

4. The joint planning operation method for container port berth and yard allocation based on the cluster strategy according to claim 3, characterized in that In the process of screening the optimal solution based on the fitness evaluation mechanism FCE-FEM of fuzzy correlation entropy, the global search capability is improved through the improved taboo search strategy. Specifically, based on the taboo search and multi-neighborhood search structure, a variety of neighborhood movement rules are designed to increase the neighborhood solution set, and the mutated neighborhood solution set is re-optimized.

5. The joint planning operation method for container port berth and yard allocation based on the cluster strategy according to claim 4, characterized in that, Various neighborhood movement rules include Exchange rule, Fragment Insert rule and Intermingle Swap rule. The Exchange rule randomly selects two container slots and exchanges the genes of the two container areas; the Fragment Insert rule first randomly selects two container slots, removes the genes between the two container slot numbers, and then randomly selects a position in the remaining chromosomes to insert the removed genes into the position; the Intermingle swap rule randomly generates several container area positions and disrupts the gene order at the corresponding ship position.

6. The combined planning operation method for container port berth and yard allocation based on the cluster strategy according to any one of claims 1-5, characterized in that, The constraints of the multi-objective mixed integer programming model include: each ship can only choose one berth to berth, two ships berthed at the same berth must have a berthing order, each ship can only berth and leave the berth once, the start and end time of loading and unloading of the ship are specified, the ship is required to start operations immediately after berthing, and leave the berth immediately after finishing operations, and the loading and unloading operation time of the container batch is within the loading and unloading time of the corresponding ship.

7. The joint planning operation method for container port berth and yard allocation based on the cluster strategy according to any one of claims 1-5, characterized in that, When solving the mixed-integer programming model, according to the three constructed objective function formulas, calculate the objective function values corresponding to each planning strategy in a specific order. First, add the berthing time of the ship to the known time in port to accurately calculate the departure time of the ship, and then calculate the cost generated by the ship deviating from the expected turnover time interval according to the relevant formula. Second, within the berthing time range of the ship, generate the loading and unloading operation plans for the corresponding container batches and calculate the workload imbalance within the planning range. Finally, according to the loading and unloading operation plans and the ship berthing position information, determine the storage positions of each container batch in the yard, calculate the average transportation distance of the container batch, and then accumulate the average moving distances of all container batches according to the formula to finally obtain the total container moving cost.

8. A joint planning operation system for berth and yard allocation in a container port based on a cluster strategy, characterized in that, Including: An information collection module for collecting information on ships, container trucks, and yards during the target time period, including the planned arrival time of the ship, the quantity and type of containers carried by the ship, the yard storage status, and the planned arrival time of external container trucks. An optimal planning strategy solving module for inputting the collected information into a pre-constructed multi-objective mixed-integer programming model to calculate the optimal planning strategy, including the berth plans for all ships during the specified time period and the loading and unloading operation plans for container batches. The berth plan includes the arrival time, berthing position, and port stay time of the ship, and the loading and unloading operation plan for the container batch includes the yard block area, loading and unloading route, and loading and unloading time allocated to the container batch on the corresponding ship or container truck. Among them, the pre-established multi-objective mixed-integer programming model includes three objective functions, aiming to minimize the shortest deviation of ship berthing from the expected turnover time, the minimum total container transportation distance between the berth and the yard block area, and the minimum workload imbalance in the yard block area respectively. An execution mechanism for executing ship and yard operations according to the optimal planning strategy.

9. The joint planning operation system for container port berth and yard allocation based on the cluster strategy according to claim 8, characterized in that, When solving the multi-objective mixed-integer programming model, the optimal planning strategy solving module specifically screens the optimal solution based on the fitness evaluation mechanism FCE-FEM of fuzzy correlation entropy.

10. A computer storage medium, characterized in that, It stores a computer program executable by a processor, and this computer program executes the joint planning operation method for container port berth and yard allocation based on the cluster strategy described in any one of claims 1-7.

Images