Ship and port resource coordinated scheduling method and device

Abstract

The invention relates to a ship port resource coordinated scheduling method and device, and belongs to the technical field of port resource optimized scheduling, and the method comprises the steps: building a target function with the maximization of the anchor ground utilization rate, the maximization of the berth utilization rate and the minimization of the ship waiting time as targets; solving the objective function by using MILP and a particle swarm algorithm to obtain an initial scheduling scheme meeting constraint conditions; the initial scheduling scheme comprises anchor ground distribution, berth distribution, berthing time and leaving time; clustering the initial scheduling scheme based on the multi-core weighted distance of the initial scheduling scheme to obtain a clustered scheduling scheme; and optimizing the clustered scheduling scheme based on a game theory model to obtain a target scheduling scheme. According to the ship and port resource coordinated scheduling method provided by the invention, global optimization of ship berth allocation, channel use and anchor ground scheduling is realized, and high efficiency and safety of ship operation are ensured while channel resource conflicts are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of port resource optimization and scheduling, and in particular to a method and device for coordinated scheduling of ship and port resources. Background Art

[0002] With the growth of global trade and increased port throughput, the complexity of ship scheduling and management has intensified, particularly in the scheduling of port, waterway, and anchorage resources. Traditional ship scheduling methods, which rely heavily on manual scheduling or simple queuing algorithms, struggle to effectively address the dynamic changes in resources and the complexity of ship behavior. This leads to problems such as waterway congestion, excessive waiting times for ships, and wasted berth resources, severely impacting the overall operational efficiency and safety of ports. Furthermore, the scheduling of anchorages and berth resources is often poorly coordinated, resulting in wasted time spent waiting for berths at anchorages, and berths not being allocated promptly to waiting ships when they become available, leading to inefficient utilization of port resources. Furthermore, multi-vessel interactions and conflicts with ships operating within the waterway during berthing and unberthing remain a major challenge in port management. When the number of ships operating is too high, it is often difficult for ships to find the right time to operate. Therefore, determining the appropriate timing to ensure safe berthing and unberthing operations for ships has become a key challenge in current scheduling systems.

[0003] Therefore, how to use modern technology to improve the intelligence and automation level of ship scheduling information, optimize the port's resource allocation, reduce ship operation waiting time, avoid conflicts and improve scheduling efficiency has become an urgent need for the development of port transportation. Summary of the Invention

[0004] In view of this, it is necessary to provide a method and device for coordinating and dispatching ship port resources to avoid collisions between ships and improve dispatching efficiency.

[0005] To achieve the above objectives, in a first aspect, the present invention provides a method for coordinating and scheduling ship and port resources, comprising: The objective function is constructed with the goals of maximizing anchorage utilization, maximizing berth utilization and minimizing ship waiting time; The objective function is solved by using MILP and particle swarm optimization to obtain an initial scheduling plan that meets the constraints; the initial scheduling plan includes anchorage allocation, berth allocation, berthing time and unberthing time; Clustering the initial scheduling scheme based on the multi-core weighted distance of the initial scheduling scheme to obtain a clustered scheduling scheme; The clustered scheduling scheme is optimized based on a game theory model to obtain a target scheduling scheme; the game theory model is determined based on the collision risk of ships.

[0006] In a possible implementation, solving the objective function by using the MILP and the particle swarm algorithm to obtain an initial scheduling plan that satisfies the constraint conditions includes: Solving the objective function by using the MILP to obtain the anchorage allocation and the berth allocation; Using the particle swarm algorithm to determine the berthing time and the unberthing time.

[0007] In a possible implementation, using the particle swarm algorithm to determine the berthing time and the unberthing time includes: Generating initial particles through a chaotic sequence; the positions of the initial particles are used to represent the berthing time and the unberthing time of the ships, and the velocities of the initial particles are used to represent the search step size; Updating the positions and velocities of the initial particles based on the random perturbation term and the inertia weight of the t-distribution to determine the optimal particles; Based on the positions of the optimal particles, determining the berthing time and the unberthing time.

[0008] In a possible implementation, clustering the initial scheduling plan based on the multi-core weighted distance of the initial scheduling plan to obtain a clustered scheduling plan includes: Calculating the multi-core weighted distance of the initial scheduling plan by using multiple kernel functions; Based on the multi-core weighted distance, performing density estimation on the initial scheduling plan to determine the similarity between the initial scheduling plans; Based on the similarity, clustering the initial scheduling plan to obtain the clustered scheduling plan.

[0009] In a possible implementation, optimizing the clustered scheduling plan based on the game theory model to obtain a target scheduling plan includes: Based on the clustered scheduling plan, determining the collision risk between ships; Based on the collision risk, constructing the game theory model; Based on the Q-learning algorithm, optimizing the game theory model to obtain a reinforced game theory model; Based on the reinforced game theory model, obtaining the target scheduling plan.

[0010] In a possible implementation, the expression of the objective function is as follows:

[0011]

[0012] Wherein, is the ship The arrival waiting time, ( ) is the departure delay time of the ship , is the ship berth deviation, , and are the time weights respectively, represents the occurrence probability of the scenario , represents the additional scheduling cost or deviation penalty under the scenario , represents the anchorage utilization rate.

[0013] In a possible implementation manner, the constraint conditions include: Time constraint, berth capacity constraint, anchorage capacity constraint and safety distance constraint.

[0014] In a second aspect, the present invention further provides a ship port resource coordinated scheduling device, including: A construction unit, configured to construct an objective function with the goals of maximizing the anchorage utilization rate, maximizing the berth utilization rate, and minimizing the ship waiting time; A solving unit, configured to solve the objective function by using the MILP and particle swarm algorithms to obtain an initial scheduling plan that satisfies the constraint conditions; the initial scheduling plan includes anchorage allocation, berth allocation, berthing time, and departure time; A clustering unit, configured to cluster the initial scheduling plan based on the multi-core weighted distance of the initial scheduling plan to obtain a clustered scheduling plan; An optimization unit, configured to optimize the clustered scheduling plan based on a game theory model to obtain an objective scheduling plan; the game theory model is determined based on the collision risk of the ship.

[0015] In a third aspect, the present invention further provides an electronic device, including a memory and a processor, wherein, The memory is configured to store a program; The processor is coupled to the memory and is configured to execute the program stored in the memory to implement the ship port resource coordinated scheduling method in any of the above implementation manners.

[0016] In a fourth aspect, the present invention further provides a computer-readable storage medium, configured to store a computer-readable program or instruction, and when the program or instruction is executed by a processor, it can implement the steps in the ship port resource coordinated scheduling method in any of the above implementation manners.

[0017] The beneficial effects of the present invention are as follows: The ship port resource coordinated scheduling method and device provided by the present invention construct an objective function with the goals of maximizing the utilization rate of the anchorage, maximizing the utilization rate of the berth, and minimizing the waiting time of the ship. The MILP and particle swarm algorithms are used to solve the objective function to obtain the anchorage allocation, berth allocation, berthing time, and unberthing time of the ship. The initial scheduling plan generated is clustered according to the multi-core weighted distance of the initial scheduling plan, aggregating similar configuration structures together, and at the same time eliminating invalid or unreasonable plans, significantly reducing the number of feasible solutions. A game theory model constructed in combination with the ship collision risk is used to further optimize the clustered scheduling plan, and the final target scheduling plan is obtained by minimization, realizing the global optimization of ship berth allocation, waterway use, and anchorage scheduling. While reducing waterway resource conflicts, it ensures the efficiency and safety of ship operations. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0019] Figure 1 It is a schematic flowchart of an embodiment of the ship port resource coordinated scheduling method provided by the present invention; Figure 2 It is a schematic flowchart of an embodiment of the improved DBSCAN method provided by the present invention; Figure 3 It is a schematic flowchart of an embodiment of the improved particle swarm algorithm provided by the present invention; Figure 4 It is a technical roadmap of the port and shipping integrated scheduling provided by the present invention; Figure 5 It is a schematic structural diagram of an embodiment of the ship port resource coordinated scheduling device provided by the present invention; Figure 6 It is a schematic structural diagram of an embodiment of the electronic device provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, rather than all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present invention.

[0021] In the description of the embodiments of the present invention, unless otherwise specified, the meaning of "a plurality" is two or more. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone.

[0022] In the embodiments of the present invention, the descriptions such as "first", "second", etc. are only for descriptive purposes, and cannot be understood as indicating or implying their relative importance or implicitly specifying the quantity of the indicated technical features. Therefore, the technical features defined with "first" and "second" may explicitly or implicitly include at least one such feature.

[0023] Referring to "embodiments" herein means that the specific features, structures, or characteristics described in connection with the embodiments may be included in at least one embodiment of the present invention. The occurrence of this phrase at various positions in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art explicitly and implicitly understand that the embodiments described herein may be combined with other embodiments.

[0024] The present invention provides a method and device for coordinating and scheduling ship port resources, which will be described separately below.

[0025] Figure 1 It is a schematic flowchart of an embodiment of the method for coordinating and scheduling ship port resources provided by the present invention, as Figure 1 shown. The method for coordinating and scheduling ship port resources includes: S101. Construct an objective function with the goals of maximizing the utilization rate of the anchorage, maximizing the utilization rate of the berth, and minimizing the waiting time of the ship.

[0026] Maximizing the utilization rates of the anchorage and the berth is one of the important goals of port and shipping scheduling optimization. As the core resource for ships to load and unload goods, the improvement of the utilization rate of the berth not only depends on the efficient allocation in terms of time, but also requires comprehensive optimization in combination with the berth operation capacity and cargo handling efficiency. By reasonably arranging the berthing sequence and operation duration of ships, ensure that the berth operates efficiently within the scheduling period. By coordinating the resource allocation of the berth and the anchorage, the overall operation efficiency of the port can be significantly improved. The waiting time of the ship is an important indicator for evaluating the port scheduling efficiency. An overly long waiting time will significantly increase the operating cost of the ship.

[0027] S102. Solve the objective function by using the MILP and particle swarm algorithms to obtain an initial scheduling plan that meets the constraint conditions; the initial scheduling plan includes anchorage allocation, berth allocation, berthing time, and unberthing time.

[0028] Mixed-Integer Linear Programming (MILP) refers to a mathematical programming problem where the objective function and constraints are both linear, and some decision variables are restricted to integers. MILP is used to solve problems that contain both continuous and discrete variables. Based on linear programming, the constraints and objective function are linearized, enabling the problem to find the optimal solution under the constraints.

[0029] MILP obtains berth allocation and anchorage allocation by precisely expressing the objective function and constraints. Berth allocation refers to the berth assigned to a ship, and anchorage allocation refers to the anchorage assigned to a ship.

[0030] The Particle Swarm Optimization (PSO) algorithm searches for the optimal solution of the objective function by updating the position and velocity of particles in the search space. Using the PSO algorithm, the berthing time and unberthing time of a ship can be obtained.

[0031] By combining the particle swarm optimization algorithm with the MILP method, and leveraging the global search ability of PSO in complex problems, the key decision variables in the MILP model are optimized, thereby achieving the global optimization of ship berth allocation, channel use, and anchorage scheduling.

[0032] S103. Cluster the initial scheduling plan based on the multi-core weighted distance of the initial scheduling plan to obtain the clustered scheduling plan.

[0033] Calculate the multi-core weighted distance of the initial scheduling plan through multiple kernel functions, perform density clustering and screening on the generated initial scheduling plan, aggregate similar configuration structures together to obtain the clustered scheduling plan. At the same time, eliminate invalid or unreasonable plans, thereby significantly reducing the number of feasible solutions, effectively reducing the computational complexity of the optimization model, and improving the optimization efficiency.

[0034] S104. Optimize the clustered scheduling plan based on the game theory model to obtain the target scheduling plan; the game theory model is determined based on the collision risk of ships.

[0035] In order to further improve the timeliness of ship berthing and unberthing operations and the channel passing efficiency, the present invention determines the game theory model according to the collision risk of ships, optimizes the clustered scheduling plan according to the game theory model, dynamically adjusts the ship berthing time and unberthing time to obtain the final target scheduling plan. By dynamically adjusting the ship berthing and unberthing times, while reducing channel resource conflicts, the efficiency and safety of ship operations are ensured.

[0036] In summary, the ship port resource coordinated scheduling method provided by the embodiments of the present invention constructs an objective function with the goals of maximizing the anchorage utilization rate, maximizing the berth utilization rate, and minimizing the ship waiting time. The MILP and particle swarm algorithms are used to solve the objective function to obtain the anchorage allocation, berth allocation, berthing time, and unberthing time of the ship. The initial scheduling plan generated is clustered according to the multi-core weighted distance of the initial scheduling plan, similar configuration structures are aggregated together, and invalid or unreasonable plans are eliminated at the same time, significantly reducing the number of feasible solutions. A game theory model constructed in combination with the ship collision risk is used to further optimize the clustered scheduling plan, and the final target scheduling plan is obtained by minimization, realizing the global optimization of ship berth allocation, waterway use, and anchorage scheduling, reducing the conflict of waterway resources while ensuring the efficiency and safety of ship operations.

[0037] In some embodiments of the present invention, the expression of the objective function is as follows:

[0038]

[0039] where, is the arrival waiting time of the ship ; ( ) is the unberthing delay time of the ship ; is the ship berth deviation; , and are the time weights respectively; represents the occurrence probability of scenario ; represents the additional scheduling cost or deviation penalty under scenario ; represents the anchorage utilization rate.

[0040] The goal of port and shipping scheduling optimization is to make full use of existing resources, reduce ship operating costs, and at the same time improve the robustness and adaptability of the scheduling plan.

[0041] The optimization goals of the present invention include the following three core parts: maximizing the anchorage utilization rate, maximizing the utilization rate of the berth, and minimizing the ship waiting time.

[0042] Maximizing the utilization rate of anchorage and berths is one of the important objectives of port and shipping scheduling optimization. As the core resource for ships to load and unload goods, improving the utilization rate of berths not only depends on efficient time allocation but also requires comprehensive optimization in combination with berth operation capabilities and cargo handling efficiency. By reasonably arranging the berthing sequence and operation duration of ships, ensure that the berths operate efficiently within the scheduling cycle. By coordinating the resource allocation of berths and anchorage, the overall operation efficiency of the port can be significantly improved, laying a foundation for further optimizing other scheduling objectives.

[0043] The waiting time of ships is an important indicator for evaluating port scheduling efficiency. Excessive waiting time will significantly increase the operating costs of ships. The present invention aims to reduce the waiting time of ships from arrival at the port to the start of operation by optimizing the scheduling sequence and resource allocation. The formula is as follows: (1) Where is the berthing time of the ship, is the arrival time of the ship at the port, is the ship 's priority weight, used to distinguish the priority between dangerous goods ships and general cargo ships. Dangerous goods ships have a higher priority for berthing and unberthing operations.

[0044] The optimization objective function of the present invention plays a core role in the scheduling model. By comprehensively considering multiple influencing factors, ensure the efficiency of ship scheduling and the rationality of resource allocation. The optimization objective function simultaneously includes the following key optimization factors: (1) Minimize the waiting time of ships.

[0045] The waiting time of ships is an important indicator affecting port operation efficiency and ship scheduling costs. This objective reduces the time difference between the arrival of ships at the port and the start of operation by optimizing the ship arrival sequence and berth allocation strategy, thereby significantly improving the operation efficiency and resource utilization rate of ships.

[0046] Optimizing the waiting time can also effectively reduce the fuel consumption and operating costs of ships during their stay in the port.

[0047] The formula is as follows: + ( ) + } (2) is the arrival waiting time of ship , ( ) is the departure delay time of ship , is the ship berth deviation, , and are the time weights for each, to achieve the balance between different times, and by optimizing the waiting time, operation time and berth deviation of ships arriving at the port, the overall time cost of the scheduling plan is reduced.

[0048] (2) Minimize the delay of the departure time and the deviation of the berth position. <>

[0049] By optimizing the ship departure time plan, ensure the timely completion of operations and reduce the delay of the departure time.

[0050] At the same time, in order to further improve the rationality of berth resource allocation, a penalty term for berth deviation is added to the optimization objective, striving to minimize the deviation between the actual berthing position of the ship and the planned position, so as to avoid additional resource waste and scheduling conflicts caused by unreasonable berth allocation.

[0051] The formula is as follows: (3) In formula (3), by considering the occurrence probabilities of different scenarios, the model can pre-optimize the possible deviations, so as to better adapt to dynamic changes during actual execution, and at the same time preprocess the possible dynamic change situations, thereby enhancing the robustness of the scheduling plan.

[0052] In this formula represents the occurrence probability of scenario , which is used to reflect the possibility weights of each scenario. For example, certain specific scenarios may be more likely to occur due to weather or operating habits, and their probability values will be higher. represents the set of all possible scenarios, which includes different dynamic scenarios, such as the ship arriving at the port earlier or later, the operation time increasing or decreasing, etc. And represents the additional scheduling cost or deviation penalty under scenario , including the cost of increased waiting time, reduced resource utilization efficiency or increased conflict risk.

[0053] (4) In formula (4), represents a certain ship in the ship set, and represents the weight, corresponding to the weight coefficients of variables respectively. By changing the weight coefficients of , the relative importance of each deviation is adjusted. represents the variable of ship under scenario The positive adjustment amount and negative adjustment amount are used to describe the deviation between the actual scheduling plan and the target plan.

[0054] Among them, is the compensation time required when the actual waiting time exceeds the expected time. is the time released when the actual waiting time is less than the expected time. By adjusting the waiting time, the scheduling stability of the ship is ensured; is the buffer time required for the actual departure time to be delayed. is the idle time caused by the actual departure time being advanced. The departure time is dynamically adjusted to reduce scheduling conflicts caused by the uncertainty of the departure time; is the positive adjustment for the actual berth position deviating from the target berth. is the negative adjustment for the actual berth position deviating from the target berth. By adjusting the berth deviation, the rationality and efficiency of berth allocation are improved.

[0055] (3) Maximize the utilization rate of anchorage resources.

[0056] As an important berthing resource before the ship arrives at the port, the utilization efficiency of the port anchorage is directly related to the scheduling flexibility of the ship and the port throughput.

[0057] This goal is achieved by introducing an optimization function for the anchorage utilization rate, reasonably allocating the anchorage space, and improving its utilization efficiency in terms of time and space. In particular, the resource requirements of large ships or special ships are preferentially allocated.

[0058] The improvement of the anchorage utilization rate can not only alleviate the problem of anchorage congestion, but also improve the overall efficiency of ship arrival scheduling.

[0059] The formula is as follows: (5) is the anchorage utilization rate, which represents the utilization efficiency of the anchorage resources per unit area. represents the th ship occupies the area of the anchorage area. is the number of ships in the anchorage. represents the length of the anchorage. then represents the width of the anchorage.

[0060] In some embodiments of the present invention, the constraint conditions include: Time constraint, berth capacity constraint, anchorage capacity constraint, and safety distance constraint.

[0061] (1) Time constraint condition.

[0062] The time constraint condition in the scheduling optimization model is mainly used to ensure that the scheduling time arrangement of the ship at the berth conforms to the actual operation logic.

[0063] The formula is as follows: ≥ (6) ≥ + (7) Formula (6) represents that the berthing time of the ship cannot be earlier than its actual arrival time at the port. This is a logical condition that conforms to the actual situation, ensuring that the ship can start berth operations only after arriving at the port. It avoids the error of "pre-arrangement" in the scheduling process, that is, arranging the berth use of the ship before it arrives at the port.

[0064] Formula (7) represents that the departure time of the ship is at least its berthing time plus the operation time. This ensures that all berth operations can be completed before the ship departs. It guarantees that the ship will not leave the berth before the operations are completed, thus ensuring the integrity of the operations and the rationality of the plan.

[0065] (2) Berth capacity constraint conditions.

[0066] The berth capacity constraint condition in the scheduling optimization model is used to ensure that at most one ship can be accommodated at each berth at any time period.

[0067] The formula is as follows: ≤1, (8) represents a binary decision variable. If = 1, it means that the ship is assigned to the berth. represents the summation of all ships , calculates the allocation situation of all ships on the berth , and ensures that at most one ship can be accommodated at the berth at any moment.

[0068] (3) Anchorage capacity constraint conditions.

[0069] The anchorage capacity constraint condition in the scheduling optimization model is used to ensure that during the anchorage allocation process, the actual allocation quantity of the anchorage does not exceed its capacity limit. The formula is as follows: ≤ , (9) is a binary decision variable used to represent whether the ship is assigned to the anchorage , is the anchorage Capacity limit. This constraint stipulates that the number of ships allocated to each anchorage cannot exceed its capacity limit , that is, at any given moment, the total number of ships in the anchorage cannot be greater than its maximum capacity.

[0070] (4) Safety distance constraint condition.

[0071] The safety distance constraint condition in the scheduling optimization model serves to ensure that sufficient safety distance is maintained between ships in the waterway or anchorage to avoid collisions or other potential risks.

[0072] The formula is as follows: ≥ , (10) This constraint requires that the distance between any two ships cannot be less than the specified minimum safety distance . By enforcing this condition, the scheduling model can effectively avoid collisions or other safety hazards between ships.

[0073] Based on formulas (2), (3), (4), and (5), the corresponding objective function can be obtained. By solving through formulas (6)-(10), that is, the constraint conditions, an initial ship scheduling plan can be generated.

[0074] In some embodiments of the present invention, clustering the initial scheduling plan based on the multi-core weighted distance of the initial scheduling plan to obtain the clustered scheduling plan includes: Calculating the multi-core weighted distance of the initial scheduling plan using multiple kernel functions; Based on the multi-core weighted distance, performing density estimation on the initial scheduling plan to determine the similarity between the initial scheduling plans; Based on the similarity, clustering the initial scheduling plan to obtain the clustered scheduling plan.

[0075] By introducing an improved DBSCAN clustering method, performing density clustering and screening on the generated resource allocation plan, aggregating similar configuration structures together, and at the same time eliminating invalid or unreasonable plans, thereby significantly reducing the number of feasible solutions, effectively reducing the computational complexity of the optimization model, and improving the optimization efficiency.

[0076] DBSCAN is a density-based clustering algorithm. DBSCAN does not need to pre-define the number of clusters in advance, is applicable to clustering of data sets of any shape, and can discover the isolated points in the data set. However, for all core points, DBSCAN sequentially visits the core points that have not been assigned to any cluster, and divides the data points density-connected to this core point into a cluster. Moreover, DBSCAN uses the Euclidean distance to measure the distance between data points.

[0077] It can be seen that the anti-noise ability and time complexity are important factors affecting the application effect of DBSCAN. Therefore, the present invention proposes an improved DBSCAN (improved DBSCAN, IDBSCAN), Figure 2 which is a schematic flowchart of an embodiment of the improved DBSCAN method provided by the present invention. As Figure 2 shown, a multi-core weighted distance metric and a dynamic parallel operation strategy are introduced to improve the clustering efficiency of IDBSCAN.

[0078] Considering that the number of initial scheduling schemes is huge and the direct solution complexity is relatively high, the present invention introduces an improved DBSCAN clustering algorithm to perform clustering analysis on the initial schemes.

[0079] Density estimation is performed on the initial scheduling schemes according to the multi-core weighted distance, the similarity between the initial scheduling schemes is calculated, and the initial scheduling schemes are clustered according to the similarity. The high-density similar schemes are clustered into a group to obtain the clustered scheduling schemes.

[0080] Exemplarily, density estimation is performed on the schemes by the multi-core weighted distance metric method, and combined with the dynamic parallel operation strategy, the high-density similar schemes are clustered into a group, and at the same time, the isolated points (low-density invalid schemes) are identified and removed, so as to screen out a representative set of scheduling schemes.

[0081] (1) Multi-core weighted distance metric.

[0082] The multi-core induced distance is used to replace the Euclidean distance, that is, the distance D( and ) between the data points can be described as: , ) can be described as: D( , ) = - 2(11) In the formula, , is the high-dimensional space mapping representation, E is the number of high-dimensional mappings, is the weighted value, 0 < < 1, and = 1.

[0083] When (1 ≤ a ≤ E, 1 ≤ b ≤ E) satisfies the Mercer condition, it is called a kernel function, and all positive semi - definite functions are kernel functions.

[0084] For the convenience of problem description, take E = 2, and define 3 kernel functions: = (12) = (13) = (14) It can be obtained that: D( , ) = - 2 + + 2 - 2 + + - + (15) (2)Dynamic parallel operation strategy.

[0085] From the clustering process of DBSCAN, it can be seen that each core point needs to judge its spatial relationship with other data points in the dataset one by one, so the computational complexity is relatively high.

[0086] To improve the running efficiency of IDBSCAN in clustering, the present invention designs a dynamic parallel operation strategy. In the t - th iteration of the particle swarm algorithm, the solution space is dynamically divided into sub - spaces, and the IDBSCAN operation is performed on the data points in each sub - space respectively through the way of partition processing.

[0087] Subsequently, the clustering results of each sub - space are integrated to form a global clustering result. To reasonably determine the number of sub - space partitions , the present invention uses the Kernel Density Estimation (KDE) method for dynamic estimation.

[0088] For the dataset D, the probability density function at the data point X is: = = (16)​​​ where n is the number of data points included in D, h is the bandwidth, is the kernel function, and the Gaussian kernel function is selected in the present invention.

[0089] According to the minimization of the AMISE criterion, the mean square error function MISE(h) is used to derive the value of the bandwidth h, and the calculation formula of MISE(h) is defined as: MISE(h) = (17) where is the sample variance.

[0090] According to the rule of thumb, the unknown function can be replaced with the normal density matching the variance and the sample difference , and by taking the derivative of Equation (6) and setting the first derivative to 0, we can obtain: h = (18) The bandwidth value at this time is obtained using Equation (18) , and the calculation formula of is defined as: (19) More samples are concentrated in the area near the optimal solution, and the number of sample subspaces becomes smaller, which is conducive to improving the operation efficiency of IDBSCAN.

[0091] In some embodiments of the present invention, solving the objective function using MILP and the particle swarm algorithm to obtain an initial scheduling plan that meets the constraint conditions includes: Solving the objective function using MILP to obtain the anchorage allocation and the berth allocation; Using the particle swarm algorithm to determine the berthing time and the unberthing time.

[0092] In some embodiments of the present invention, using the particle swarm algorithm to determine the berthing time and the unberthing time includes: Generating initial particles through a chaotic sequence; the positions of the initial particles are used to represent the berthing time and the unberthing time of the ship, and the velocities of the initial particles are used to represent the search step size; Updating the positions and velocities of the initial particles based on the random perturbation term and the inertia weight of the t-distribution to determine the optimal particles; Based on the positions of the optimal particles, determining the berthing time and the unberthing time.

[0093] MILP refers to a mathematical programming problem where both the objective function and the constraints are linear, and some decision variables are restricted to integers. Specifically, its constraints support equality constraints and inequality constraints. The variable types include 0-1 variables, integer variables, and real variables.

[0094] MILP is widely used to solve problems that contain both continuous variables and discrete variables. Its theoretical basis stems from linear programming, which linearizes the constraints and the objective function, enabling the problem to find the optimal solution under the constraints.

[0095] In port and waterway resource scheduling, with its powerful modeling ability, MILP can accurately express the objective function, constraints, and decision variables, and is used to solve complex problems such as berth allocation, anchorage allocation, and ship scheduling.

[0096] The solution of MILP effectively generates the optimal allocation plan by analyzing linear equations and inequalities.

[0097] In port and waterway resource scheduling, MILP solves the key variables such as berth allocation, anchorage allocation, and ship priority order by accurately expressing the objective function and constraints.

[0098] According to formulas (2), (3), (4), and (5), the corresponding objective function can be obtained: Z = + ( ) + } + (20) In addition to formula (1), it is also necessary to solve through formulas (6)-(10), that is, the constraints, to generate the initial ship scheduling plan, and then adjust the initial scheduling plan through the IPSO algorithm.

[0099] PSO is an optimization algorithm based on swarm intelligence, developed inspired by the foraging behavior of bird flocks.

[0100] Optionally, the position of the particle is used to represent the berthing time and departure time of the ship, and the velocity of the particle is used to represent the search step size. The PSO algorithm updates the position and velocity of the particle in the search space to find the optimal solution of the objective function.

[0101] Although the PSO algorithm performs well in solving continuous optimization problems, it still has deficiencies in dealing with dynamic and complex discrete optimization problems such as port and waterway scheduling. In the later stage of the search, the diversity of the particle swarm decreases, which may cause the algorithm to be unable to jump out of the local optimal solution. Ordinary PSO has limited performance in dealing with dynamic variables such as ship arrival time and departure time.

[0102] Therefore, the present invention improves the PSO algorithm. Figure 3Schematic diagram of a process for an embodiment of the improved particle swarm algorithm provided by the present invention, which improves the global search ability of the algorithm and the adaptability to uncertain environments.

[0103] (1) Dynamic inertia weight adjustment.

[0104] Dynamic inertia weight adjustment is an important improvement in the algorithm, aiming to balance the global search ability and local convergence efficiency of the algorithm at different optimization stages. Improving the global search ability in the initial stage helps to explore a larger solution space, while enhancing the local search ability in the later stage helps to quickly converge to the optimal solution.

[0105] The formula is as follows: (21) Where is the inertia weight, and and are the current iteration number and the maximum iteration number respectively. In the initial stage of the algorithm , the closer the inertia weight is to the maximum inertia weight , the greater the velocity of the particle is maintained, thus having a stronger global search ability. In the present invention, T = 5 is selected, and this value is the choice of most empirical values.

[0106] In the later stage of the algorithm , the inertia weight gradually decreases to the minimum inertia weight , thus focusing on local search and improving the accuracy of the solution. Dynamically adjusting the inertia weight can dynamically adjust the search strategy according to the optimization process of the algorithm, ensuring an organic combination of extensive exploration in the initial stage and rapid convergence in the later stage.

[0107] (2) Chaotic initialization strategy.

[0108] The chaotic initialization strategy is used to enhance the diversity of the initial particle swarm and avoid falling into local optimal solutions. The velocity and position of the initial particles are generated through a chaotic sequence. This method utilizes the ergodicity and randomness of the chaotic system to provide a better search starting point for the particle swarm.

[0109] The formula is as follows: = (1 ), 0 < < 1 (22) is the current chaotic sequence value, is the next chaotic sequence value, is the parameter of the chaotic system.

[0110] (3) Application of the t-distribution in particle swarm optimization.

[0111] Enhance the randomness of the algorithm by introducing t-distribution perturbations, thereby improving the global search ability and diversity of the particle swarm optimization algorithm. The velocity and position update formulas of the particles are as follows, with a random perturbation term based on the t-distribution added: = + ( )+ ( )+ (23) = + × (iter)(24) is the random perturbation term based on the t-distribution, and respectively represent the current historical best position of the particle and the global best position of the group.

[0112] Among them the expression is: = (25) where v is the degree of freedom, used to control the intensity of randomness, is the gamma function.

[0113] In order to give full play to the precision of MILP and the dynamic adaptation ability of IPSO, the present invention proposes a two-stage joint solution strategy to achieve efficient solution and dynamic adjustment of the port and shipping scheduling optimization model.

[0114] This combined strategy, through the synergistic effect of precise modeling and heuristic optimization, improves the ability of the model to cope with uncertain environments on the basis of ensuring the precision of the solution.

[0115] The first stage is to use a mixed integer linear programming (MILP) model to model and solve the berth allocation and anchorage allocation problems, and generate an initial scheduling plan.

[0116] The second stage uses the IPSO algorithm to optimize the dynamic variables that are not fully considered in the solution process of the first stage.

[0117] MILP provides an exact solution for static optimization, while PSO makes up for the deficiencies of MILP in dynamic problems and realizes adaptive optimization for complex environments. Multiple rounds of feedback adjustment make the combination of MILP and PSO not limited to a single interaction, but form a closed-loop optimization process, significantly improving the solution efficiency and the quality of the scheduling plan.

[0118] In some embodiments of the present invention, optimizing the clustered scheduling scheme based on the game theory model to obtain the target scheduling scheme includes: Based on the clustered scheduling scheme, determining the collision risk between ships; Based on the collision risk, constructing the game theory model; Optimizing the game theory model based on the Q-learning algorithm to obtain the enhanced game theory model; Based on the enhanced game theory model, obtaining the target scheduling scheme.

[0119] To optimize the berthing and unberthing operation timing of ships in the port, ensure the efficient utilization of waterway resources and the fairness of ship scheduling, the present invention proposes a method combining reinforcement learning and dynamic game. Through the real-time response ability of reinforcement learning to the dynamic environment and the modeling advantage of cooperative game for multi-ship strategy interaction, the intelligent decision-making optimization of ship berthing and unberthing operations is realized.

[0120] (1) Establishment of the dynamic game theory model.

[0121] During the process of ship berthing and unberthing, multiple ships share limited berth resources and waterway resources. To solve the problem of the impact of berthing and unberthing ships on normal navigation ships in the waterway, the present invention proposes a strategy optimization model combining dynamic game and reinforcement learning, aiming to achieve the efficient utilization of waterway resources, ensure navigation safety and improve the overall traffic efficiency.

[0122] The berthing ship arrives at the berth within the specified time according to the generated scheduling scheme and starts the berthing operation. It can complete its own berthing operation through operation. However, due to the large turning water area of the ship, the berthing operation may affect normal navigation ships. Therefore, the upstream and downstream ships need to adjust their own ship speeds to avoid the collision risk with the berthing ship and quickly pass through the port waters.

[0123] The formula of the game theory model is as follows: = + (26) Wherein, is the time for ship to pass through the port area, is the conflict cost between ships, and is the speed stability.

[0124] The conflict cost is used to quantify the collision risk between two ships. By comprehensively considering two key indicators, the closest distance of approach (DCPA) and the time to the closest point of approach (TCPA), the conflict risk between ships is evaluated and quantified.

[0125] Its formula is expressed as follows: = ( )(27) is the closest distance of approach of the ship , and is the closest time of approach of the ship . is a very small constant to prevent the denominator from being zero. By quantifying the conflict cost, the formula provides a clear optimization direction for the strategy selection between ships.

[0126] (2) Reinforcement learning algorithm.

[0127] Reinforcement learning learns the optimal strategy through the state-action-reward mechanism. In the dynamic game theory model, the goal of reinforcement learning is to enable the ship to achieve the optimal benefit through multiple rounds of games, while avoiding conflicts and improving the overall scheduling efficiency.

[0128] Q Learning is a model-free reinforcement learning algorithm that learns the expected benefit of taking a certain action in a specific state by updating the state-action value function .

[0129] Q The core update formula of learning is: + (28) is the expected benefit of choosing action A in the current state S; R is the immediate benefit, which is the immediate reward brought by the current action A; is the discount factor, and its value range is 0 ≤ ≤ 1, indicating the balance between short-term and long-term benefits; is the learning rate, which is used to control the weight of the update of the old and new values; is the next state 's maximum expected benefit.

[0130] Q The learning algorithm first defines the state space S and the action space A. The initial is 0 or a random value. Set the learning rate , the discount factor and the exploration probability . At state , select action with the exploration probability :

[0131] The ship moves according to the selected Execute the corresponding speed adjustment and enter the next state , calculate the immediate reward based on the profit function Then update according to the formula , gradually optimizing the expected reward of each state-action pair.

[0132] Repeat the above steps until Convergence or maximum number of iterations reached.

[0133] (3) Combination of reinforcement learning and game theory models.

[0134] The combination of reinforcement learning and game theory models, by utilizing the mathematical framework provided by the game theory model (including participants, strategies and payoff functions) and combining it with the dynamic optimization capabilities of reinforcement learning, obtains a reinforcement game theory model, achieving gradual improvement in strategy selection during the game process.

[0135] During this process, a game theory model defines the interaction rules and initial strategies between ships, while reinforcement learning dynamically optimizes each round of game strategies based on a state-action-reward mechanism. In particular, through the dynamic adjustment of time buffer variables and conflict costs, the model's adaptability and efficiency in complex and uncertain environments are improved. This combination combines the mathematical precision of game theory models with the adaptive optimization capabilities of reinforcement learning, not only improving the overall efficiency of ship scheduling but also significantly enhancing the robustness and safety of the solution.

[0136] This paper proposes an integrated optimization model for port and shipping scheduling based on multi-resource coordination, the combination of game theory and reinforcement learning, and the combination of an improved particle swarm optimization algorithm and mixed integer linear programming to solve problems such as conflicts in the allocation of port channels, anchorages and berth resources, and the impact of berthing and unberthing operations on channels.

[0137] Figure 4 The integrated technology roadmap for port and shipping dispatching provided by the present invention is as follows: Figure 4As shown, the present invention combines game theory, reinforcement learning (RL), mixed integer linear programming (MILP), and improved particle swarm optimization algorithm (IPSO), etc., to construct an efficient ship scheduling optimization system. By dynamically adjusting the inertia weight of IPSO, introducing a chaotic initialization strategy and t-distribution random perturbation, the global search ability and convergence speed are enhanced. MILP provides an exact solution for berth and anchorage allocation; reinforcement learning combines with a dynamic game theory model to optimize the strategy selection between ships, minimizing the conflict cost and resource waste, and improving the navigation efficiency. In addition, through the introduction of time buffer variables and multi-round iterative optimization, high adaptability to the dynamic environment and the robustness of the system are achieved. This method has significant application value and technical advantages in port management, waterway scheduling, and intelligent scheduling of special scenarios.

[0138] First, the present invention constructs a port and waterway scheduling optimization model, with the objective function of maximizing resource utilization rate, minimizing ship waiting time, and reducing waterway conflicts. By combining the improved particle swarm optimization algorithm (IPSO) with the mixed integer linear programming (MILP) method, using the global search ability of PSO in complex problems to optimize the key decision variables in the MILP model, so as to achieve the global optimization of ship berth allocation, waterway use, and anchorage scheduling.

[0139] Next, by introducing the improved DBSCAN clustering method, density clustering and screening are performed on the generated resource allocation schemes, aggregating similar configuration structures together, and at the same time eliminating invalid or unreasonable schemes, thus significantly reducing the number of feasible solutions, effectively reducing the computational complexity of the optimization model, and improving the optimization efficiency.

[0140] Finally, in order to further improve the timeliness of berthing and unberthing operations and the waterway passage efficiency, the present invention proposes an optimization method for berthing and unberthing timing based on the combination of game theory and reinforcement learning. By dynamically adjusting the berthing and unberthing timing of ships, while reducing waterway resource conflicts, ensuring the high efficiency and safety of ship operations. The overall optimization model can provide intelligent decision support for multi-resource dynamic scheduling and multi-ship interaction, not only significantly improving the port scheduling efficiency and resource utilization rate, but also enhancing the adaptability and robustness of the system in complex dynamic environments, providing a strong technical guarantee for the efficient and intelligent management of inland waterway shipping systems.

[0141] The present invention proposes an efficient multi-resource joint scheduling scheme by combining reinforcement game, improved particle swarm algorithm, and mixed integer linear programming method. This scheme can perform global optimization and coordinated scheduling among resources such as berths, anchorages, and waterways, effectively avoiding resource waste and system bottlenecks while ensuring the efficient use of resources. By optimizing the use allocation of waterways, berths, and anchorages, not only the utilization efficiency of the overall resources is improved, but also the waiting time and scheduling conflict rate of ships are reduced.

[0142] The present invention introduces a reinforced game theory model to optimize the in-port and out-port sequences of ships. By dynamically adjusting the ship speeds and timings, while ensuring the smoothness of the waterway, it effectively avoids interaction conflicts between ships. Especially during ship berthing and unberthing operations, the model combining reinforcement learning and game theory can accurately select berthing and unberthing timings, minimizing the impact of ship berthing and unberthing operations on the waterway, thereby ensuring the smoothness of the waterway and the efficiency of port operations.

[0143] This model is particularly applicable to dynamic and changeable multi-ship interaction scenarios. It can adjust decision-making strategies in real time, globally optimize the in-port and out-port sequences of ships, berth allocation, and waterway utilization, significantly enhancing the flexibility and safety of port scheduling. In a dynamic resource environment, the intelligent optimization model provided by the present invention can efficiently coordinate various resources, reduce scheduling conflicts and resource waste, providing strong technical support for intelligent port operation and automated scheduling.

[0144] To better implement the ship port resource coordination and scheduling method in the embodiments of the present invention, correspondingly, based on the ship port resource coordination and scheduling method, as Figure 5 shown, the embodiments of the present invention also provide a ship port resource coordination and scheduling device. The ship port resource coordination and scheduling device 500 includes: A construction unit 501, configured to construct an objective function with the goals of maximizing anchorage utilization rate, maximizing berth utilization rate, and minimizing ship waiting time; A solving unit 502, configured to solve the objective function by using the MILP and particle swarm algorithms to obtain an initial scheduling plan that meets the constraint conditions; the initial scheduling plan includes anchorage allocation, berth allocation, berthing time, and unberthing time; A clustering unit 503, configured to cluster the initial scheduling plan based on the multi-core weighted distance of the initial scheduling plan to obtain a clustered scheduling plan; An optimization unit 504, configured to optimize the clustered scheduling plan based on a game theory model to obtain a target scheduling plan; the game theory model is determined based on the collision risk of ships.

[0145] The ship port resource coordination and scheduling device 500 provided in the above embodiments can implement the technical solutions described in the embodiments of the ship port resource coordination and scheduling method. The specific implementation principles of the above modules or units can be referred to the corresponding content in the embodiments of the ship port resource coordination and scheduling method, which will not be elaborated here.

[0146] As Figure 6 shown, the present invention also correspondingly provides an electronic device 600. The electronic device 600 includes a processor 601, a memory 602, and a display 603. Figure 6Only some components of the electronic device 600 are shown, but it should be understood that it is not required to implement all the shown components, and more or fewer components can be implemented alternatively.

[0147] In some embodiments, the processor 601 may be a central processing unit (CPU), a microprocessor, or other data processing chips, and is used to run the program code stored in the memory 602 or process data, such as the ship port resource coordination and scheduling method in the present invention.

[0148] In some embodiments, the processor 601 may be a single server or a server group. The server group may be centralized or distributed. In some embodiments, the processor 601 may be local or remote. In some embodiments, the processor 601 may be implemented on a cloud platform. In some embodiments, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-cloud, etc., or any combination of the above.

[0149] In some embodiments, the memory 602 may be an internal storage unit of the electronic device 600, such as the hard disk or memory of the electronic device 600. In some other embodiments, the memory 602 may also be an external storage device of the electronic device 600, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the electronic device 600.

[0150] Furthermore, the memory 602 may also include both the internal storage unit of the electronic device 600 and the external storage device. The memory 602 is used to store the application software installed in the electronic device 600 and various types of data.

[0151] In some embodiments, the display 603 may be an LED display, a liquid crystal display, a touch liquid crystal display, an Organic Light-Emitting Diode (OLED) toucher, etc. The display 603 is used to display the information in the electronic device 600 and to display a visual user interface. The components 601-603 of the electronic device 600 communicate with each other through a system bus.

[0152] In one embodiment, when the processor 601 executes the ship port resource coordination and scheduling program in the memory 602, the following steps can be achieved: Construct an objective function with the goal of maximizing the utilization rate of the anchorage, maximizing the utilization rate of the berth, and minimizing the waiting time of the ship; Solve the objective function using the MILP and particle swarm algorithms to obtain an initial scheduling plan that satisfies the constraint conditions; the initial scheduling plan includes anchorage allocation, berth allocation, berthing time, and departure time. Cluster the initial scheduling plan based on the multi-core weighted distance of the initial scheduling plan to obtain a clustered scheduling plan. Optimize the clustered scheduling plan based on the game theory model to obtain the target scheduling plan; the game theory model is determined based on the collision risk of the ships.

[0153] It should be understood that when the processor 601 executes the ship port resource coordination and scheduling program in the memory 602, in addition to the above functions, other functions can also be realized. For specific details, please refer to the description of the corresponding method embodiments above.

[0154] Furthermore, the type of the electronic device 600 mentioned in the embodiments of the present invention is not specifically limited. The electronic device 600 can be a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop computer, or other portable electronic devices. Exemplary embodiments of portable electronic devices include, but are not limited to, portable electronic devices running IOS, android, microsoft, or other operating systems. The above portable electronic devices can also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (such as a touch panel). It should also be understood that in some other embodiments of the present invention, the electronic device 600 may not be a portable electronic device, but a desktop computer with a touch-sensitive surface (such as a touch panel).

[0155] Correspondingly, the embodiments of the present invention also provide a computer-readable storage medium. The computer-readable storage medium is used to store computer-readable programs or instructions. When the programs or instructions are executed by a processor, the steps or functions in the ship port resource coordination and scheduling methods provided by the above method embodiments can be realized.

[0156] Those skilled in the art can understand that all or part of the processes of implementing the above method embodiments can be completed by instructing relevant hardware (such as a processor, a controller, etc.) through a computer program. The computer program can be stored in a computer-readable storage medium. Among them, the computer-readable storage medium is a magnetic disk, an optical disk, a read-only memory, or a random access memory, etc.

[0157] The above has introduced in detail the ship port resource coordination and scheduling method and device provided by the present invention. Specific examples are used in this article to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those skilled in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A method for coordinating and scheduling ship port resources, characterized in that, Including: Construct an objective function aiming to maximize the utilization rate of the anchorage, maximize the utilization rate of the berth, and minimize the waiting time of ships; Solve the objective function by using MILP and the particle swarm algorithm to obtain an initial scheduling plan that meets the constraint conditions; The initial scheduling plan includes anchorage allocation, berth allocation, berthing time, and unberthing time; Cluster the initial scheduling plan based on the multi-core weighted distance of the initial scheduling plan to obtain a clustered scheduling plan; Optimize the clustered scheduling plan based on the game theory model to obtain the target scheduling plan; the game theory model is determined based on the collision risk of ships.

2. The ship port resource coordinated scheduling method according to claim 1, characterized in that, The step of using MILP and the particle swarm algorithm to solve the objective function to obtain an initial scheduling plan that meets the constraint conditions includes: Solve the objective function by using MILP to obtain the anchorage allocation and the berth allocation; Use the particle swarm algorithm to determine the berthing time and the unberthing time.

3. The ship port resource coordinated scheduling method according to claim 2, wherein The step of using the particle swarm algorithm to determine the berthing time and the unberthing time includes: Generate initial particles through a chaotic sequence; the positions of the initial particles are used to represent the berthing time and the unberthing time of ships, and the velocities of the initial particles are used to represent the search step size; Update the positions and velocities of the initial particles based on the random perturbation term and the inertia weight of the t-distribution to determine the optimal particles; Determine the berthing time and the unberthing time based on the positions of the optimal particles.

4. The ship port resource coordinated scheduling method according to claim 1, wherein, The step of clustering the initial scheduling plan based on the multi-core weighted distance of the initial scheduling plan to obtain a clustered scheduling plan includes: Calculate the multi-core weighted distance of the initial scheduling plan by using multiple kernel functions; Perform density estimation on the initial scheduling plan based on the multi-core weighted distance to determine the similarity between the initial scheduling plans; Cluster the initial scheduling plan based on the similarity to obtain the clustered scheduling plan.

5. The ship port resource coordinated scheduling method according to claim 1, characterized in that The step of optimizing the clustered scheduling plan based on the game theory model to obtain the target scheduling plan includes: Determine the collision risk between ships based on the clustered scheduling plan; Construct the game theory model based on the collision risk; Optimize the game theory model based on the Q-learning algorithm to obtain a reinforced game theory model; Obtain the target scheduling plan based on the reinforced game theory model.

6. The ship port resource coordinated scheduling method according to claim 1, wherein The expression of the objective function is as follows: Among them, is the waiting time of the ship for arrival at the port, ( ) is the departure delay time of the ship , is the ship berth deviation, 、 and are the time weights respectively, represents the occurrence probability of the scenario , represents the additional scheduling cost or deviation penalty under the scenario , represents the anchorage utilization rate.

7. The ship port resource coordinated scheduling method according to claim 1, characterized in that, The constraint conditions include: Time constraint, berth capacity constraint, anchorage capacity constraint, and safety distance constraint.

8. A ship port resource coordinated scheduling device, characterized in that, Including: A construction unit for constructing an objective function aiming to maximize the utilization rate of the anchorage, maximize the utilization rate of the berth, and minimize the waiting time of ships; A solving unit for solving the objective function by using MILP and the particle swarm algorithm to obtain an initial scheduling plan that meets the constraint conditions; The initial scheduling plan includes anchorage allocation, berth allocation, berthing time, and unberthing time; A clustering unit for clustering the initial scheduling plan based on the multi-core weighted distance of the initial scheduling plan to obtain a clustered scheduling plan; An optimization unit is configured to optimize the clustered scheduling scheme based on a game theory model to obtain a target scheduling scheme; the game theory model is determined based on the collision risk of ships.

9. An electronic device, characterized in that, It includes a memory and a processor, wherein, The memory is used to store programs; The processor is coupled to the memory and is configured to execute the programs stored in the memory to implement the steps in the ship port resource coordinated scheduling method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, It is used to store computer-readable programs or instructions, and when the programs or instructions are executed by the processor, the steps in the ship port resource coordinated scheduling method according to any one of claims 1 to 7 can be implemented.

Images