Marine autonomous surface ship berth allocation method in mixed scene

Abstract

The invention provides a marine autonomous water surface ship berth allocation method in a mixed scene, and the method comprises the steps: dividing the types of berths berthed at a port into a class A and a class B. The class A berths refer to traditional berths which can only meet the berth of manned ships; b-type berths refer to mixed berths which meet the berthing requirements of MASS and manned ships at the same time; meanwhile, whether the number of manned ships is far greater than the number of MASSs in a long period of time in the future can be predicted; the demand of A-type berths is far greater than that of B-type berths; when the number of the A-type berths of the port can completely meet the berthing use of the manned ship, designing an MASS and manned ship separated berth allocation strategy; and when the number of the A-type berths of the port cannot meet the berthing use of the manned ship, designing an MASS and manned ship hybrid berth allocation strategy. The technical problem to be solved by the invention is how to optimize the port berth utilization efficiency and the overall operation benefit by establishing an effective berth allocation strategy in a MASS and manned ship mixed operation scene.

Description

Technical Field

[0001] The present invention relates to the field of port management and maritime transportation technology, and in particular to a method for allocating berths for autonomous surface ships at sea in a mixed scenario. Background Art

[0002] At present, the port berth allocation problem (BAP) has been widely studied, especially in the optimization of berth allocation for manned ships and port resource scheduling. Most traditional berth allocation strategies adopt a fixed berth mode, that is, allocating specific berths according to the type of ship, which is not suitable for the mixed operation scenario of MASS and manned ships. In this case, the traditional berth allocation strategy is difficult to meet the needs of MASS and manned ships to share berth resources, resulting in low efficiency of port berth utilization, increasing ship berthing waiting time and operating costs.

[0003] The development of MASS has led to an increasing demand for autonomous berth allocation, but existing research has mostly focused on autonomous navigation, obstacle avoidance, and navigation path optimization of MASS, and has failed to explore the berth allocation strategy of MASS in depth. Very few literatures involve MASS berth allocation, such as reducing fuel consumption and delay costs by optimizing berth allocation and speed, but still fail to solve the problem of collaborative allocation of berth resources shared by MASS and manned ships.

[0004] At present, a few ports have tried to use some manned ship berths to berth MASS, but no systematic research has been conducted on the mixed berthing of MASS and manned ships, especially the lack of strategies and models that can adapt to the shared berths of different types of ships. The existing berth scheduling model cannot meet the needs of coordinated operation of MASS and manned ships. In the mixed scenario of MASS and manned ships, how to improve the efficiency of port berth utilization by reasonably allocating berths is still an unsolved problem.

[0005] In summary, significant progress has been made in the research of autonomous navigation and safety of MASS, especially in path planning and obstacle avoidance, which shows good application prospects. However, the berth allocation problem, especially the berth allocation in the mixed operation scenario of MASS and manned ships, still lacks sufficient research. Summary of the invention

[0006] According to the above-mentioned technical problems of berth allocation in the mixed operation scenario of MASS and manned ships, a method for allocating berths for autonomous surface ships at sea in a mixed scenario is provided to improve the utilization efficiency of port berths and the overall operational benefits. The mixed integer programming model established by the present invention can not only achieve the optimal configuration of berth resources and reduce the operating costs of ships in ports, but also promote the collaborative operation of MASS and manned ships through effective berth allocation strategies, thereby improving the operational efficiency of ports. In addition, through sensitivity analysis, the impact of different numbers of MASS dedicated berths on the total cost of ship berthing can be evaluated, providing scientific decision-making support for ports in the face of changes in ship types, berth resources and operational needs.

[0007] The technical means adopted by the present invention are as follows:

[0008] A method for allocating berths for autonomous surface ships at sea in a mixed scenario, comprising:

[0009] S1. The types of berths for port berthing are divided into Class A and Class B. Class A berths refer to traditional berths, which can only meet the berthing requirements of manned ships; Class B berths refer to mixed berths, which can meet the berthing requirements of both MASS and manned ships. At the same time, it can be foreseen that for a long time in the future, the number of manned ships will far exceed the number of MASS: the demand for Class A berths is far greater than that for Class B berths;

[0010] S2. When the number of Class A berths in the port is sufficient to meet the needs of manned ships, a berth allocation strategy for MASS and manned ships is designed;

[0011] S3. When the number of Class A berths in the port cannot meet the needs of manned ships, a mixed berth allocation strategy of MASS and manned ships is designed.

[0012] Furthermore, the method further comprises the step of assuming, and the specific assumptions are as follows:

[0013] It is assumed that the communication between MASS and manned ships and with the port management system is reliable without packet loss, bit error or delay;

[0014] It is assumed that the port equipment and berth structure in the MASS exclusive berth can adapt to the berthing and loading and unloading needs of manned ships;

[0015] It is assumed that all maritime vessels, whether manned or MASS, strictly comply with all laws and regulations related to navigation and docking;

[0016] Assume that the research object is a discrete dynamic BAP, and the arrival time and loading and unloading time of all ships are known;

[0017] It is assumed that the physical factors of the separate berths and the combined berths can accommodate and serve all eligible vessels calling at the port;

[0018] Assume that berth preference is between general berth and special berth;

[0019] Assume that all ship loading and unloading operations are performed immediately after the ship berths, ignoring the time of some equipment adaptation processes, and the cargo loading and unloading time of each ship is fixed;

[0020] Assume that each ship leaves the port immediately after completing cargo loading and unloading;

[0021] It is assumed that during the execution of berth allocation, environmental factors such as wind speed, current speed and other sea conditions are known and relatively stable.

[0022] Further, step S2 specifically includes:

[0023] S21. According to the scenario of split berth allocation, a multi-objective mathematical model with cost and time as optimization objectives is constructed to optimize the allocation strategies of Class A and Class B berths respectively. The multi-objective mathematical model is as follows:

[0024]

[0025]

[0026] Among them, C1 and C2 represent these two parts of costs respectively and are optimized as the main objectives; B represents the set of port berths, B = {B_1, B_2, ... B_m}, B_m represents the total number of port berths; I represents the set of ships arriving at a port, I = {I_1, I_2, ... I_m}, I_m represents the total number of ships arriving at the port; I l It represents the MASS set of a certain port. l = {I l _1,I l _2...I l _n}), I l _n indicates the total number of MASS arriving at the port; C i (op) represents the operating cost per unit time of manned ship i in port, in ten thousand yuan; C i (run) MASS i The unit time operating cost in Hong Kong is 10,000 yuan; C i (handling) represents the unit time loading and unloading cost of manned ship i at ordinary berths, in ten thousand yuan; C i (load) MASS iThe unit time loading and unloading cost for loading and unloading operations at the MASS exclusive berth is in ten thousand yuan; i represents the loading and unloading time of ship i at ordinary berths, in hours; y ir represents a 0-1 variable. If ship i berths at berth r in a port, then y ir =1, otherwise y ir =0; b ir represents the actual berthing time of ship i at berth r of a port; a i represents the arrival time of manned ship i;

[0027] S22. To improve berth utilization, an improved optimization model is designed. The berth idle time objective optimization function T3 is added to the objective function to minimize the berth idle time, which includes the time in port: berthing waiting time, anchoring time and loading and unloading time. The berth idle time objective optimization function T3 is as follows:

[0028]

[0029] Among them, b jr represents the actual berthing time of ship j at berth r of a port; z i，j，r represents a 0-1 variable. If ships i and j berth at berth r of a port, and i berths earlier than j, then z i，j，r =1, otherwise z i，j，r =0;

[0030] S23. According to the above description, parameters and decision variables, the multi-objective optimization model is expressed as the following objective function:

[0031] [Model1]minC=C1+C2+T3

[0032] Among them, the objective function Model 1 is used to minimize the total cost of ship berthing for all ships within the planning period;

[0033] S24. Set constraints for the objective function as follows:

[0034] Constraint 1:

[0035] Constraint 2:

[0036] Constraint three:

[0037] Constraint 4:

[0038] Constraint 5:

[0039] Constraint 6: n≤n(max)

[0040] Constraint Seven:

[0041] Constraint 8:

[0042] Constraint Nine:

[0043] Constraint 10:

[0044] Constraint 11:

[0045] Constraint 12:

[0046] Constraint Thirteen:

[0047] Constraint 14: n ≥ 0

[0048] Constraint Fifteen:

[0049] Constraint 16:

[0050] Constraint 17: Among them, constraint one is used to ensure that each ship is docked at a certain berth; constraint two is the main difference between the model and the traditional BAP model after considering the MASS dedicated berth, which is used to ensure that MASS cannot dock it at other ordinary berths, but can only dock it at the MASS exclusive berth; constraint three is used to ensure that manned ships cannot dock it at the MASS exclusive berth, but can only dock it at the manned ship berth; constraint four is used to ensure that if the port has set up a MASS dedicated berth, it will definitely berth at this berth to avoid the waste of dedicated berth resources; constraint five is used to calculate the number of MASS dedicated berths for port transformation; constraint six is ​​used to ensure that the number of MASS dedicated berths in the port cannot exceed the upper limit; constraint seven expresses y ir With b ir The relationship between them; Constraint 8 is used to ensure that the ship's berthing time is not earlier than the arrival time; Constraint 9 is used to ensure that the ship's actual berthing time is equal to the sum of the ship's basic berthing time and the anchoring time; Constraint 10 is used to ensure that the berthing time of two ships serving consecutively at the same berth is not earlier than the loading and unloading completion time of the former; Constraints 11 and 12 express y ir With z i,j，r is used to ensure that two ships docked at the same berth do not conflict in time; Constraints 13-17 give the value range of the decision variables; M represents a sufficiently large positive number; K r represents a 0-1 variable. If a port sets berth r as a MASS dedicated berth, then K r =1, otherwise Kr =0;n (max) It indicates the maximum number of MASS-dedicated berths in a port; n indicates the number of MASS-dedicated berths in a port.

[0051] Furthermore, in step S24, constraints 2 to 6 are restrictions related to the MASS dedicated berth, and other constraints are restrictions considered in the traditional BAP model; constraints 2 and 3 characterize the impact on the berth selection of ships after the port renovates the MASS dedicated berth; constraints 4, 5 and 6 characterize the mode of the MASS dedicated berth and the restrictions it is subject to.

[0052] Further, step S3 specifically includes:

[0053] S31. Based on the improved multi-objective optimization model, a hybrid berth allocation mathematical model is constructed as follows:

[0054]

[0055] Among them, β represents the discount coefficient of loading and unloading time of manned ships at the MASS exclusive berth;

[0056] S32. Calculate the discount coefficient for loading and unloading time of manned ships at the MASS exclusive berth. The calculation formula is as follows:

[0057]

[0058] Among them, T MASS Indicates the loading and unloading time of Class B berth; T prep It indicates the additional preparation time of manned ships at MASS berths, including the equipment commissioning and personnel coordination time required when manned ships berth at Class B berths; T man Indicates the loading and unloading time of Class A berths; the calculation formulas are as follows:

[0059]

[0060]

[0061] Among them, the loading and unloading time of Class B berth is T MASS and automation equipment efficiency R MASS , loading and unloading demand D MASS and equipment quantity and scheduling optimization E MASS Related; Class A berth loading and unloading time T man The operating rate R of the port loading and unloading equipment man , crew operation adjustment time A man and loading and unloading demand D man Related;

[0062] S33, adding the berth idle time target optimization function T3 to the objective function, as follows:

[0063]

[0064] S34. Based on the above description, parameters and decision variables, the multi-objective optimization model is expressed as the following objective function:

[0065] [Model2]minC=C1+C2+T3

[0066] Among them, the objective function Model 2 is used to minimize the total cost of ship berthing for all ships within the planning period;

[0067] S35. Set constraints for the objective function as follows:

[0068] Constraint 18:

[0069] Constraint 19:

[0070] Constraint 20:

[0071] Constraint 21:

[0072] Constraint 22: n≤n(max)

[0073] Constraint 23:

[0074] Constraint 24:

[0075] Constraint 25:

[0076] Constraint 26:

[0077] Constraint Twenty-Seven:

[0078] Constraint 28:

[0079] Constraint Twenty-Nine:

[0080] Constraint 30: n ≥ 0

[0081] Constraint Thirty-One:

[0082] Constraint Thirty-Two:

[0083] Constraint Thirty-Three: Among them, constraint 18 ensures that each ship is docked at a certain berth; constraint 19 is the main difference between the model and the traditional BAP model after considering the MASS dedicated berth, which is used to ensure that MASS cannot dock it at other ordinary berths, but can only dock at the MASS exclusive berth; constraint 20 is used to ensure that if the port has set up a MASS dedicated berth, it will definitely berth at this berth to avoid the waste of dedicated berth resources; constraint 21 is used to calculate the number of MASS dedicated berths for port transformation; constraint 22 is used to ensure that the number of MASS dedicated berths in the port cannot exceed the upper limit; constraint 23 expresses y ir With b ir Constraint 24 is used to ensure that the ship's berthing time is not earlier than the arrival time; Constraint 25 is used to ensure that the ship's actual berthing time is equal to the sum of the ship's basic berthing time and the anchoring time; Constraint 26 is used to ensure that the berthing time of two ships serving the same berth is not earlier than the loading and unloading completion time of the former; Constraints 27 and 28 express y ir With z i,j,r The relationship between them ensures that the two ships docked at the same berth do not conflict in time; Constraints 29 to 33 give the value range of the decision variables.

[0084] Furthermore, in step S35, constraints 19 to 23 are restriction conditions related to the MASS dedicated berth, and other constraints are restriction conditions considered in the traditional BAP model; constraints 19 and 20 characterize the impact on the berth selection of ships after the port renovates the MASS dedicated berth; constraints 21, 22 and 23 characterize the mode of the MASS dedicated berth and the restrictions it is subject to.

[0085] Compared with the prior art, the present invention has the following advantages:

[0086] 1. The present invention provides a method for allocating berths for autonomous surface ships at sea in a hybrid scenario. By constructing a mixed integer programming model, the efficient collaborative berth allocation of MASS and manned ships is realized, and the berth idle time is reduced. The experimental results show that the hybrid berth allocation strategy improves the berth utilization efficiency compared with the traditional berth allocation strategy when the port berth resources are tight, helps to make full use of the existing berth resources, and avoids the phenomenon of berth idleness and resource waste.

[0087] 2. The present invention provides a method for allocating berths for autonomous surface ships at sea in a hybrid scenario. Its berth allocation strategy effectively reduces the time ships spend in port and the overall operating cost by optimizing berth scheduling and reducing ship waiting time. When berth resources are limited, the hybrid berth allocation strategy can shorten the time ships spend in port by about 7% compared with the traditional strategy, significantly reducing the operating cost of the port and improving the port's operating efficiency.

[0088] 3. The present invention provides a method for allocating berths for autonomous surface ships at sea in a mixed scenario. It introduces collaborative optimization in berth allocation, enables MASS and manned ships to coexist efficiently in the same port, solves the technical problem of mixed berth allocation for MASS and manned ships, and ensures the smooth berthing and loading and unloading of different types of ships. This strategy provides strong support for the efficient operation of MASS in traditional port environments, and promotes the development of intelligent port operation management.

[0089] 4. The present invention provides a method for allocating berths for autonomous surface ships at sea in a hybrid scenario. The proposed berth allocation strategy realizes the intelligent berth scheduling of MASS and manned ships under the condition of existing berth resources, which is suitable for the needs of future intelligent port management. This technology provides a new solution for port managers to optimize berth resources, helps promote the progress of ports in intelligence and automation, and supports the large-scale application of MASS in ports.

[0090] In summary, by optimizing the berth allocation strategy, MASS and manned ships can work together efficiently in the same port, which not only improves the utilization rate of berth resources, but also effectively reduces the port operating costs, providing solid technical support for the future intelligent management of ports and the development of autonomous maritime transportation systems.

[0091] Based on the above reasons, the present invention can be widely promoted in the fields of port management and marine transportation. BRIEF DESCRIPTION OF THE DRAWINGS

[0092] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0093] Figure 1 The figure is a flow chart of the method of the present invention.

[0094] Figure 2 A schematic diagram of a separated berth allocation problem provided in an embodiment of the present invention.

[0095] Figure 3 A single-target separated berth allocation strategy is provided in an embodiment of the present invention.

[0096] Figure 4 A multi-objective separated berth allocation strategy is provided in an embodiment of the present invention.

[0097] Figure 5 A schematic diagram of a hybrid berth allocation problem provided in an embodiment of the present invention.

[0098] Figure 6 A hybrid berth allocation strategy is provided in an embodiment of the present invention.

[0099] Figure 7 A line chart comparing the total cost impact of separate and hybrid docking provided in an embodiment of the present invention.

[0100] Figure 8 A diagram showing the impact of the number of MASS berths provided in the separated berth strategy on the total cost of ship berthing provided in an embodiment of the present invention.

[0101] Fig. 9 A diagram showing the impact of the number of berths set up in the hybrid berth strategy MASS provided in an embodiment of the present invention on the total cost of ship berthing. DETAILED DESCRIPTION

[0102] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0103] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0104] like Figure 1 As shown, the present invention provides a method for allocating berths for autonomous surface ships at sea in a mixed scenario, comprising:

[0105] S1. The berth allocation problem for manned ships and MASS faces the following practical application problems: the existing manned ship berths are not suitable for MASS berthing. The most realistic and feasible strategy is to transform the existing manned ship berths so that they can adapt to the berthing needs of both manned ships and MASS. In view of the above situation, the present invention divides the berth types of port berthing into Class A and Class B during analysis, among which Class A berths refer to traditional berths - which can only meet the berthing needs of manned ships; Class B berths refer to mixed berths - which meet the berthing requirements of MASS and manned ships at the same time; at the same time, it can be foreseen that for a long time in the future, the number of manned ships will still far exceed the number of MASS: the demand for Class A berths is far greater than that for Class B berths; therefore, the present invention discusses the berth allocation strategy in two scenarios;

[0106] S2. The first scenario: When the number of Class A berths in the port is sufficient to meet the needs of manned ships, a separate berth allocation strategy for MASS and manned ships is designed; that is, ships are docked at corresponding berths strictly according to different ship types; for example, manned ships are docked at Class A berths, and MASS are docked at Class B berths. Mathematical modeling is used to optimize the berth allocation for manned ships and MASS respectively; Figure 2 shown.

[0107] S3. The second scenario: When the number of Class A berths in the port is insufficient for manned ships to berth, a mixed berth allocation strategy for MASS and manned ships is designed. For example, when manned ships and MASS arrive at the port at the same time, the basic principle of berthing is that MASS berths at Class B berths first, and manned ships berths at Class A berths; if Class A berths are full, manned ships can be flexibly adjusted to Class B berths; if Figure 5 shown.

[0108] In the specific implementation, as a preferred embodiment of the present invention, the method further includes the step of assumptions, and the specific assumptions are as follows:

[0109] It is assumed that the communication between MASS and manned ships and with the port management system is reliable without packet loss, bit error or delay;

[0110] It is assumed that the port equipment and berth structure in the MASS exclusive berth can adapt to the berthing and loading and unloading needs of manned ships;

[0111] It is assumed that all marine vessels, whether manned or MASS, strictly comply with all laws and regulations related to navigation and docking, such as navigation rules, safety distances, etc.;

[0112] Assume that the research object is a discrete dynamic BAP, and the arrival time and loading and unloading time of all ships are known;

[0113] It is assumed that the physical factors of the separate berths and the combined berths can accommodate and serve all eligible vessels calling at the port;

[0114] Assume that berth preference is between general berth and special berth;

[0115] Assume that all ship loading and unloading operations are performed immediately after the ship berths, ignoring the time of some equipment adaptation processes, and the cargo loading and unloading time of each ship is fixed;

[0116] Assume that each ship leaves the port immediately after completing cargo loading and unloading;

[0117] It is assumed that during the execution of berth allocation, environmental factors such as wind speed, current speed and other sea conditions are known and relatively stable.

[0118] In specific implementation, as a preferred embodiment of the present invention, in step S2, for the separated berth allocation scenario, a separated berth allocation mathematical model is constructed and solved based on the improved multi-objective optimization model. The specific application scenario is described as follows: according to the historical records of ship berthing at the port, if the number of Class A berths at the port can meet the needs of manned ships, a strategy for separate berthing of MASS and manned ships is given. For example: after manned ship 5 arrives at the port (such as Figure 2 ), you must choose a Class A berth to berth. Even if the Class A berth is full, you still need to wait for other manned ships to leave the berth before you can berth. At this time, you cannot berth even if there is a free Class B berth; similarly, MASS can only choose a Class B berth to berth. Specifically include:

[0119] S21. According to the scenario of split berth allocation, a multi-objective mathematical model with cost and time as optimization targets is constructed (in this embodiment, target optimization modeling is performed based on time and cost. First, the most important consideration for berthing is cost. Berth berthing costs mainly include: operating costs related to the time the ship is in port and loading and unloading costs related to cargo loading and unloading time, which are represented by C1 and C2 respectively, and are optimized as the main targets) to optimize the allocation strategies of Class A and Class B berths respectively. The multi-objective mathematical model is as follows:

[0120]

[0121]

[0122] Among them, C1 and C2 represent these two parts of costs respectively and are optimized as the main objectives; B represents the set of port berths, B = {B_1, B_2, ... B_m}, B_m represents the total number of port berths; I represents the set of ships arriving at a port, I = {I_1, I_2, ... I_m}, I_m represents the total number of ships arriving at the port; I lIt represents the MASS set of a certain port. l = {I l _1,I l _2...I l _n}), I l _n indicates the total number of MASS arriving at the port; C i (op) represents the operating cost per unit time of manned ship i in port, in ten thousand yuan; C i (run) MASS i The unit time operating cost in Hong Kong is 10,000 yuan; C i (handling) represents the unit time loading and unloading cost of manned ship i at ordinary berths, in ten thousand yuan; C i (load) MASS i The unit time loading and unloading cost for loading and unloading operations at the MASS exclusive berth is in ten thousand yuan; i represents the loading and unloading time of ship i at ordinary berths, in hours; y ir represents a 0-1 variable. If ship i berths at berth r in a port, then y ir =1, otherwise y ir =0; b ir represents the actual berthing time of ship i at berth r of a port; a i represents the arrival time of manned ship i;

[0123] S22. After solving the above berth allocation model, it is found that the berth utilization efficiency of this solution is low. Figure 2 As shown in the figure): When there is a Class A idle berth in the port, ship No. 5 is still in a waiting state and cannot enter the idle berth in time, resulting in a waste of resources. In order to improve the berth utilization rate, an improved optimization model is designed, and the berth idle time target optimization function T3 is added to the objective function to minimize the berth idle time. The time in port involved includes: berthing waiting time, anchoring time and loading and unloading time; the berth idle time target optimization function T3 is as follows:

[0124]

[0125] Among them, b jr represents the actual berthing time of ship j at berth r of a port; z i,j,r represents a 0-1 variable. If ships i and j berth at a port berth r, and i berths earlier than j, then z i,j,r =1, otherwise z i,j,r =0;

[0126] S23. According to the above description, parameters and decision variables, the multi-objective optimization model is expressed as the following objective function:

[0127] [Model1]minC=C1+C2+T3

[0128] Among them, the objective function Model 1 is used to minimize the total cost of ship berthing for all ships within the planning period;

[0129] S24. Set constraints for the objective function as follows:

[0130] Constraint 1:

[0131] Constraint 2:

[0132] Constraint three:

[0133] Constraint 4:

[0134] Constraint 5:

[0135] Constraint 6: n≤n(max)

[0136] Constraint Seven:

[0137] Constraint 8:

[0138] Constraint Nine:

[0139] Constraint 10:

[0140] Constraint 11:

[0141] Constraint 12:

[0142] Constraint Thirteen:

[0143] Constraint 14: n ≥ 0

[0144] Constraint Fifteen:

[0145] Constraint 16:

[0146] Constraint 17: Among them, constraint one is used to ensure that each ship is docked at a certain berth; constraint two is the main difference between the model and the traditional BAP model after considering the MASS dedicated berth, which is used to ensure that MASS cannot dock it at other ordinary berths, but can only dock it at the MASS exclusive berth; constraint three is used to ensure that manned ships cannot dock it at the MASS exclusive berth, but can only dock it at the manned ship berth; constraint four is used to ensure that if the port has set up a MASS dedicated berth, it will definitely berth at this berth to avoid the waste of dedicated berth resources; constraint five is used to calculate the number of MASS dedicated berths for port transformation; constraint six is ​​used to ensure that the number of MASS dedicated berths in the port cannot exceed the upper limit; constraint seven expresses y ir With b ir The relationship between them; Constraint 8 is used to ensure that the ship's berthing time is not earlier than the arrival time; Constraint 9 is used to ensure that the ship's actual berthing time is equal to the sum of the ship's basic berthing time and the anchoring time; Constraint 10 is used to ensure that the berthing time of two ships serving consecutively at the same berth is not earlier than the loading and unloading completion time of the former; Constraints 11 and 12 express y ir With z i,j,r is used to ensure that two ships docked at the same berth do not conflict in time; Constraints 13-17 give the value range of the decision variables; M represents a sufficiently large positive number; K r represents a 0-1 variable. If a port sets berth r as a MASS dedicated berth, then K r =1, otherwise K r =0;n (max) It indicates the maximum number of MASS-dedicated berths in a port; n indicates the number of MASS-dedicated berths in a port.

[0147] In specific implementation, as a preferred embodiment of the present invention, in step S24, constraints two to six are restrictions related to MASS dedicated berths, and other constraints are restrictions considered in the traditional BAP model; constraints two and three characterize the impact on the berth selection of ships after the port transforms the MASS dedicated berths; constraints four, five and six characterize the mode of the MASS dedicated berth and the restrictions it is subject to.

[0148] In an embodiment of the present invention, a solution process of the separated berth allocation strategy model is also provided, as follows:

[0149] This example analyzes the berth allocation strategy for a port with 6 berths, and analyzes how to berth 12 ships (9 of which are manned ships and 3 are MASS). Figure 3 As shown in the figure, the number of MASS berths (B-type berths) is set to 2, namely berths 1# and 2#; the number of manned ship berths (A-type berths) is set to 4, namely berths 3# to 6#. This verifies the feasibility of the model in practical application.

[0150] The operating environment of this embodiment is as follows: based on the AIS ship information arriving at a port in a certain week in 2024, 12 ships' arrival time information is randomly selected and applied to the above mathematical model; the computer operating system is Windows 11, the main frequency is 2.6GHz, and the running memory is 8G; the Matlab 2021a compiled algorithm program is used to solve the model; the berth allocation diagrams using single-target and multi-target separated berth strategies are obtained, such as Figure 3 and 4 shown.

[0151] The model was solved using the Gurobi solver, and the results were simulated and analyzed. Figure 3 and Figure 4 As shown in the figure. The horizontal axis represents the berth number and the vertical axis represents the time. Figure 3 and Figure 4 In the red part shown, the multi-objective optimization method shortens the ship's time in port by about 12% compared with the single-objective optimization strategy. This shows that the reasonable introduction of the objective function to minimize the sum of idle time can improve the utilization of port resources while optimizing the scheduling of ships in port.

[0152] In specific implementation, as a preferred embodiment of the present invention, in step S3, according to the historical records of ship berthing at the port, if the number of Class A berths at the port cannot meet the needs of manned ships, a hybrid berth allocation strategy is provided. The basic principle of hybrid berth allocation is that when all Class A berths are occupied, manned ships can choose Class B berths for berthing, while MASS does not allow them to choose Class A berths for berthing. Figure 5 As shown, if the manned ship 5 originally planned to berth at the Class A berth, but the Class A berth is full, it can only change the plan to berth at the Class B berth. To solve the above mixed berth allocation problem, specifically include:

[0153] S31, based on the improved multi-objective optimization model (this embodiment establishes a multi-objective optimization model based on cost and time, the cost still mainly includes the operating cost and cargo loading and unloading cost of the ship when it is in the port, and the time refers to the idle time of the berth. The main difference between the hybrid strategy model and the separation strategy model is the time the ship is in the port. The time the ship is in the port is mainly composed of the berthing waiting time, the anchoring time and the loading and unloading time. Figure 6 Middle red box. When manned ships can berth at Class B berths, since Class B berths are newly renovated MASS berths, the degree of automation and intelligence is higher than that of Class A berths, resulting in a shorter loading and unloading time for manned ships at Class B berths. Therefore, in the hybrid berth allocation model, the loading and unloading time discount coefficient β of manned ships at Class B berths is added to construct a hybrid berth allocation mathematical model as follows:

[0154]

[0155]

[0156] Among them, β represents the discount coefficient of loading and unloading time of manned ships at the MASS exclusive berth;

[0157] S32. Calculate the discount coefficient for loading and unloading time of manned ships at the MASS exclusive berth. The calculation formula is as follows:

[0158]

[0159] Among them, T MASS Indicates the loading and unloading time of Class B berth; T prep It indicates the additional preparation time of manned ships at MASS berths, including the equipment commissioning and personnel coordination time required when manned ships berth at Class B berths; T man Indicates the loading and unloading time of Class A berths; the calculation formulas are as follows:

[0160]

[0161]

[0162] Among them, the loading and unloading time of Class B berth is T MASS and automation equipment efficiency R MASS , loading and unloading demand D MASS and equipment quantity and scheduling optimization E MASS Related; Class A berth loading and unloading time T man The operating rate R of the port loading and unloading equipment man , crew operation adjustment time A man and loading and unloading demand D man Related;

[0163] S33, adding the berth idle time target optimization function T3 to the objective function, as follows:

[0164]

[0165] S34. Based on the above description, parameters and decision variables, the multi-objective optimization model is expressed as the following objective function:

[0166] [Model2]minC=C1+C2+T3

[0167] Among them, the objective function Mode1 2 is used to minimize the total cost of ship berthing for all ships within the planning period;

[0168] S35. Set constraints for the objective function as follows:

[0169] Constraint 18:

[0170] Constraint 19:

[0171] Constraint 20:

[0172] Constraint 21:

[0173] Constraint 22: n≤n(max)

[0174] Constraint 23:

[0175] Constraint 24:

[0176] Constraint 25:

[0177] Constraint 26:

[0178] Constraint Twenty-Seven:

[0179] Constraint 28:

[0180] Constraint Twenty-Nine:

[0181] Constraint 30: n ≥ 0

[0182] Constraint Thirty-One:

[0183] Constraint Thirty-Two:

[0184] Constraint Thirty-Three: Among them, constraint 18 ensures that each ship is docked at a certain berth; constraint 19-constraint 23 are restrictions related to MASS special berths, and other constraints are restrictions considered in the traditional BAP model; constraint 19 and constraint 20 characterize the impact of the port's transformation of MASS special berths on the berthing selection of ships; constraint 21, constraint 22 and constraint 23 characterize the way and restrictions of MASS special berths. Constraint 19 is the main difference between the model and the traditional BAP model after considering MASS special berths. It is used to ensure that MASS cannot dock it at other ordinary berths, but only at MASS exclusive berths; constraint 20 is used to ensure that if a port has set up a MASS special berth, it will definitely berth at this berth to avoid the waste of special berth resources; constraint 21 is used to calculate the number of MASS special berths transformed by the port; constraint 22 is used to ensure that the number of MASS special berths in the port cannot exceed the upper limit; constraint 23 expresses y ir With b ir Constraint 24 is used to ensure that the ship's berthing time is not earlier than the arrival time; Constraint 25 is used to ensure that the ship's actual berthing time is equal to the sum of the ship's basic berthing time and the anchoring time; Constraint 26 is used to ensure that the berthing time of two ships serving the same berth is not earlier than the loading and unloading completion time of the former; Constraints 27 and 28 express y ir With z i,j,r The relationship between them ensures that the two ships docked at the same berth do not conflict in time; Constraints 29 to 33 give the value range of the decision variables.

[0185] In the embodiment of the present invention, a hybrid berth allocation model solution and example analysis process are also provided, as follows:

[0186] Since the objective function of the hybrid berth allocation strategy model Model 2 contains nonlinear parts K r y ir , so first convert Model 2 into a linear model for solution.

[0187] Model linearization: This example introduces a 0-1 auxiliary variable u ir =K r y ir If a port remodels berth r and its ship i berths at the berth, then u ir =1, otherwise, u ir = 0. In addition, when ship i is not berthed at berth r, y lr = 0, the berthing time b of ship i at berth r ir is also 0. At this time, the objective function can be expressed as:

[0188]

[0189] At the same time, the following constraints need to be introduced:

[0190]

[0191]

[0192]

[0193] For Model 2 proposed above, the gurobi solver is used directly for solution.

[0194] Example Analysis: This embodiment still analyzes the mixed berth allocation strategy for the example of 6 berths (4 Class A berths and 2 Class B berths) and 12 ships docking. Figure 6 As shown in the figure, the specific mixed berth strategies for 12 ships were obtained, which verified the effectiveness of the model. By comparing the separated berth allocation strategy and the mixed berth allocation strategy ( Figure 4 and Figure 6 ) and found that under the same conditions, the hybrid berth allocation strategy can save at least 7% of the ship's time in port compared with the separate strategy (see the red part in the figure for details).

[0195] Example

[0196] This embodiment mainly includes the analysis of the total cost of ship berthing under two berthing strategies and the analysis of the impact of the number of MASS berths (Class B berths) on the total cost of ship berthing under the two berthing strategies.

[0197] Analysis of total ship berthing cost under two berth allocation strategies:

[0198] This embodiment first estimates the total cost of berthing for manned ships and MASS ships respectively, then calculates the discount coefficient β of the loading and unloading time of manned ships at Class B berths, and finally compares and analyzes the separated berth and mixed berth strategies. The total cost of ship berthing consists of ship operating costs and loading and unloading costs. Therefore, it is necessary to estimate the ship operating costs and loading and unloading costs first. Because there are significant differences between MASS and manned ships in operating procedures, equipment requirements and human resources, it is difficult to directly compare the operating costs and loading and unloading costs of the two in actual applications. Therefore, the scientificity and rationality of the estimation of MASS operating costs and loading and unloading costs are the difficulties of this article.

[0199] The total cost estimation process of manned ship docking is as follows:

[0200] In this study, the arriving ships are divided into 4 groups, with 3 ships in each group, as shown in Table 1. The total cost of a ship's berthing is composed of the ship's operating cost and loading and unloading cost. Among them, loading and unloading cost = unit loading and unloading cost × loading and unloading time. Among them, the loading and unloading time is randomly generated with the average loading and unloading time as the expected uniform distribution. As shown in Table 1.

[0201]

[0202] Calculate the loading and unloading cost per unit time of manned ships

[0203] Table 1 Ship loading and unloading time information

[0204]

[0205] Ship operating cost = ship time in port × unit operating cost, where the ship arrival time is obtained from AIS data, as shown in Table 2.

[0206]

[0207] Calculate the unit time operating cost of manned ships

[0208] Table 2 Example AIS data

[0209]

[0210] The estimation process of the total cost of MASS ship docking is as follows:

[0211] Set the MASS unit time operation cost to:

[0212]

[0213] Among them, it is assumed that the maintenance of MASS is mainly concentrated on the monitoring of the onshore control center and the technical support for port maintenance. Then the maintenance expenditure of the onshore maintenance team is about 135,000 US dollars per year; due to the risk uncertainty of autonomous ships, the insurance cost is estimated to be slightly higher than that of traditional ships. Assuming that the insurance cost accounts for about 1% of the total operating cost of traditional ships, it is calculated that the hourly insurance cost of autonomous ships is about 20CNY; the labor cost of the onshore control center is about 33,000 US dollars per ship per year; other operating costs: including communications, port berthing and other expenses, are expected to increase by about 10%. After substituting into the calculation, the unit time operating cost of MASS is obtained as follows:

[0214] Calculate the MASS loading and unloading cost per unit time:

[0215]

[0216] It is reasonable to speculate that the technical cost of autonomous loading and unloading equipment is in the range of several hundred yuan per hour. And considering the high investment in the automation of loading and unloading equipment, setting the rental fee at 800CNY / hour can reflect the advantages of automated loading and unloading to a certain extent, while also maintaining moderate cost control. Therefore, it is assumed that the rental fee for autonomous loading and unloading equipment is about 800CNY per hour. According to the actual situation of domestic ports, the average hourly wage for positions such as loading and unloading operations usually ranges from 50 to 80CNY, depending on the region and the skill requirements of the job. If overtime pay, night shift allowances and the need for technical support are taken into account, especially the special skill requirements for assisting the operation of autonomous equipment, the actual hourly wage may be higher. Therefore, based on a rate of 100CNY / hour per person, assuming that 4-5 staff members are required to assist, the total labor cost of about 478CNY / hour can be obtained. Setting the labor assistance fee at 478CNY / hour can also cover the labor costs of some technicians; after substituting the above equipment rental fee and labor and auxiliary costs into the calculation, the MASS unit time loading and unloading cost is obtained.

[0217] The calculation process of the discount coefficient β for loading and unloading time of manned ships at Class B berths is as follows:

[0218] Assumption parameter: MASS automated loading and unloading rate R MASS = 30 standard containers / hour, the number of available equipment per MASS is E MASS = 2. Loading and unloading rate of manned ships R man = 20 standard containers / hour, each operation adjustment time A man = 1 hour. Assume that the loading and unloading demand is D MASS =120 and D man = 120 standard containers, then:

[0219]

[0220]

[0221] Additional preparation time T prep : Considering that the additional preparation time for manned ships to adapt to the MASS automated berth may include equipment debugging, personnel coordination, etc., it is assumed to be 1 hour.

[0222] According to the above rough calculation, β = 0.57 (retain two decimal places). The upper limit of the number of dedicated berths n (max) =[|B|] (B is the number of berths).

[0223] On a computer with Windows 11 operating system, main frequency of 2.6 GHz and running memory of 8 GB, the algorithm program was compiled in Python and Gurobi 9.5.2 was called to solve the model in this article, and the maximum solution time was set to 1 hour.

[0224] The comparative analysis process of separated berth and mixed berth strategies is as follows:

[0225] In this example, the study compared and analyzed the impact of the two berth allocation strategies, the separate and hybrid, on the total cost of ship berthing. The study showed that the hybrid berth allocation strategy has significant advantages in berth utilization and operating costs. The total cost of ship berthing under the two berth allocation strategies with different numbers of MASS dedicated berths was quantified, and the configuration results with the lowest cost were summarized in Table 3.

[0226] Table 3 Comparison of berth planning effects under different MASS dedicated berth usage conditions

[0227]

[0228] Figure 7 The cost performance of the separated berth allocation strategy and the hybrid berth allocation strategy are represented by yellow and blue broken lines respectively. In the figure, the horizontal axis represents the number of dedicated berths for MASS, and the vertical axis represents the total cost of ship berthing (unit: 10,000 yuan). This embodiment compares and analyzes the impact of MASS dedicated berths and manned ship berth allocation methods on the total cost of ship berthing by conducting multiple sets of repeated experiments. Figure 7 The effect of the configuration of the number of dedicated berths on the total cost of ship berthing under different berth numbers is shown. As can be seen from the figure, with the increase of the number of MASS dedicated berths, the total cost of ship berthing of the two berthing strategies shows a downward trend. However, the cost of the hybrid berth allocation strategy is significantly lower than that of the separate berth strategy. Specifically, only when the number of dedicated berths is 1, the cost of the separate berth strategy is slightly lower than that of the hybrid berth allocation strategy, where the total cost of ship berthing at the separate berth is about 550,000 yuan, while the total cost of ship berthing at the mixed berth is close to 600,000 yuan. But then as the number of dedicated berths increases to 2, the cost of the hybrid berth allocation strategy begins to be lower than that of the separate berth strategy. When the number of dedicated berths increases to 3, the cost of the hybrid berth allocation strategy tends to stabilize and remains at around 400,000 yuan. The cost of the separate berth strategy also tends to stabilize when the number of dedicated berths reaches 3, remaining at about 475,000 yuan. It can be clearly seen from the figure that when the number of MASS dedicated berths is the same in the two strategies, the cost saving effect of the hybrid berth allocation strategy is more significant. In addition, through Table 3 and Figure 7The data show that the hybrid berth allocation strategy can significantly reduce the total cost of ship berthing by at least 17% compared with the separate berth strategy. This comparison shows that the hybrid berth configuration can more effectively reduce the waiting time of ships in the port and improve the utilization efficiency of berth resources, thereby reducing the overall operating costs of the port.

[0229] Analysis of the impact of the number of MASS berths on the total cost of ship berthing under two berthing strategies:

[0230] This embodiment mainly includes the analysis of the impact of the number of MASS berths on the total cost of ship berthing under two berthing strategies.

[0231] The impact of the number of MASS berths in the separated berthing strategy on the total cost of ship berthing: This embodiment analyzes the impact of the number of MASS dedicated berths on the total cost of ship berthing under the separated berthing strategy. By controlling the increase or decrease in the number of MASS berths, the total cost of ship berthing can be significantly affected. When the number of MASS berths is small, the total cost of ship berthing is high; as the number of berths increases, the addition of dedicated berths helps to optimize berthing efficiency and reduce ship waiting time, thereby reducing overall operating costs. The results show that the reasonable configuration of the number of MASS dedicated berths has a significant effect on the economic benefits of the separated berthing strategy. As shown in Table 4, the changes in the number of berths are analyzed: the impact of increasing or decreasing the number of different types of berths on the total cost of ship berthing:

[0232] Table 4 Impact of the number of MASS berths in the separated berth strategy on the total cost of ship berthing

[0233]

[0234] Figure 8 The middle horizontal axis is the number of dedicated berths in the port, the left vertical axis is the total number of berths in the port, and the right vertical axis is the total cost of ship berthing.

[0235] The impact of the number of MASS berths on the total cost of ship berthing under the mixed berthing strategy is shown in Table 5:

[0236] Table 5 The impact of the number of MASS berths on the total cost of ship berthing under the mixed berthing strategy

[0237]

[0238] Fig. 9The middle horizontal axis is the number of special berths in the port, the left vertical axis is the total number of berths in the port, and the right vertical axis is the total cost of ship berthing. With the increase in the number of MASS special berths, the total cost of ship berthing under the hybrid strategy is significantly reduced. When the number of MASS special berths is low, the total cost of ship berthing is high; but when the number of MASS special berths is moderately increased, berth resources can be fully utilized, reducing ship waiting time and optimizing berth utilization efficiency, thereby significantly reducing overall operating costs.

[0239] This embodiment analyzes the impact of the number of MASS dedicated berths on the total cost of ship berthing under different berthing strategies. The study shows that in the separated berthing strategy, increasing the number of MASS dedicated berths can effectively reduce the berthing competition between manned ships and MASS ships, thereby improving the utilization efficiency of berth resources, reducing the waiting time and operating costs of ships, and making the total cost of ship berthing show a downward trend. In the hybrid berthing strategy, the impact of the number of MASS berths on the total cost is particularly significant: when the number of MASS berths is small, the total cost of ship berthing is high; with the moderate increase in the number of MASS berths, the total cost of ship berthing is significantly reduced. This strategy flexibly arranges berths so that manned ships can use MASS berths when necessary, further improving the utilization efficiency and scheduling flexibility of berths, thereby significantly reducing the overall operating cost. In summary, the reasonable configuration of the number of MASS berths, especially under the hybrid berthing strategy, can optimize the utilization efficiency of berth resources, significantly reduce the total cost of ship berthing, and provide a useful reference for the allocation and management of port berth resources.

[0240] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for allocating berths for autonomous surface ships at sea in a mixed scenario, characterized in that: include: S1. The types of berths for port berthing are divided into Class A and Class B. Class A berths refer to traditional berths, which can only meet the berthing requirements of manned ships; Class B berths refer to mixed berths, which can meet the berthing requirements of both MASS and manned ships. At the same time, it can be foreseen that for a long time in the future, the number of manned ships will far exceed the number of MASS: the demand for Class A berths is far greater than that for Class B berths; S2. When the number of Class A berths in the port is sufficient to meet the needs of manned ships, a berth allocation strategy for MASS and manned ships is designed; S3. When the number of Class A berths in the port cannot meet the needs of manned ships, a mixed berth allocation strategy of MASS and manned ships is designed.

2. The method for allocating berths for autonomous surface ships at sea in a mixed scenario according to claim 1 is characterized in that: The method further comprises the step of assuming that: It is assumed that the communication between MASS and manned ships and with the port management system is reliable without packet loss, bit error or delay; It is assumed that the port equipment and berth structure in the MASS exclusive berth can adapt to the berthing and loading and unloading needs of manned ships; It is assumed that all maritime vessels, whether manned or MASS, strictly comply with all laws and regulations related to navigation and docking; Assume that the research object is a discrete dynamic BAP, and the arrival time and loading and unloading time of all ships are known; It is assumed that the physical factors of the separate berths and the combined berths can accommodate and serve all eligible vessels calling at the port; Assume that berth preference is between general berth and special berth; Assume that all ship loading and unloading operations are performed immediately after the ship berths, ignoring the time of some equipment adaptation processes, and the cargo loading and unloading time of each ship is fixed; Assume that each ship leaves the port immediately after completing cargo loading and unloading; It is assumed that during the execution of berth allocation, environmental factors such as wind speed, current speed and other sea conditions are known and relatively stable.

3. The method for allocating berths for autonomous surface ships at sea in a mixed scenario according to claim 1 is characterized in that: Step S2 specifically includes: S21. According to the scenario of split berth allocation, a multi-objective mathematical model with cost and time as optimization objectives is constructed to optimize the allocation strategies of Class A and Class B berths respectively. The multi-objective mathematical model is as follows: Among them, C1 and C2 represent these two parts of costs respectively and are optimized as the main objectives; B represents the set of port berths, B = {B_1, B_2, ... B_m}, B_m represents the total number of port berths; I represents the set of ships arriving at a port, I = {I_1, I_2, ... I_m}, I_m represents the total number of ships arriving at the port; I l It represents the MASS set of a certain port. l = {I l _1,I l _2...I l _n}), I l _n indicates the total number of MASS arriving at the port; C i (op) represents the operating cost per unit time of manned ship i in port, in ten thousand yuan; C i (run) MASS i The unit time operating cost in Hong Kong is 10,000 yuan; C i (handling) represents the unit time loading and unloading cost of manned ship i at ordinary berths, in ten thousand yuan; C i (load) MASS i The unit time loading and unloading cost for loading and unloading operations at the MASS exclusive berth is in ten thousand yuan; i represents the loading and unloading time of ship i at ordinary berths, in hours; y ir represents a 0-1 variable. If ship i berths at berth r in a port, then y ir =1, otherwise y ir =0; b ir represents the actual berthing time of ship i at berth r of a port; a i represents the arrival time of manned ship i; S22. To improve berth utilization, an improved optimization model is designed. The berth idle time objective optimization function T3 is added to the objective function to minimize the berth idle time, which includes the time in port: berthing waiting time, anchoring time and loading and unloading time. The berth idle time objective optimization function T3 is as follows: Among them, b jr represents the actual berthing time of ship j at berth r of a port; z i,j,r represents a 0-1 variable. If ships i and j berth at a port berth r, and i berths earlier than j, then z i,j,r =1, otherwise z i,j,r =0; S23. According to the above description, parameters and decision variables, the multi-objective optimization model is expressed as the following objective function: [Model1]minC=C1+C2+T3 Among them, the objective function Model 1 is used to minimize the total cost of ship berthing for all ships within the planning period; S24. Set constraints for the objective function as follows: Constraint 1: Constraint 2: Constraint three: Constraint 4: Constraint 5: Constraint 6: n≤n(max) Constraint Seven: Constraint 8: Constraint Nine: Constraint 10: Constraint 11: Constraint 12: Constraint Thirteen: Constraint 14: n ≥ 0 Constraint Fifteen: Constraint 16: Constraint 17: Among them, constraint one is used to ensure that each ship is docked at a certain berth; constraint two is the main difference between the model and the traditional BAP model after considering the MASS dedicated berth, which is used to ensure that MASS cannot dock it at other ordinary berths, but can only dock it at the MASS exclusive berth; constraint three is used to ensure that manned ships cannot dock it at the MASS exclusive berth, but can only dock it at the manned ship berth; constraint four is used to ensure that if the port has set up a MASS dedicated berth, it will definitely berth at this berth to avoid the waste of dedicated berth resources; constraint five is used to calculate the number of MASS dedicated berths for port transformation; constraint six is ​​used to ensure that the number of MASS dedicated berths in the port cannot exceed the upper limit; constraint seven expresses y ir With b ir The relationship between them; Constraint 8 is used to ensure that the ship's berthing time is not earlier than the arrival time; Constraint 9 is used to ensure that the ship's actual berthing time is equal to the sum of the ship's basic berthing time and the anchoring time; Constraint 10 is used to ensure that the berthing time of two ships serving consecutively at the same berth is not earlier than the loading and unloading completion time of the former; Constraints 11 and 12 express y ir With z i,j,r is used to ensure that two ships docked at the same berth do not conflict in time; Constraints 13-17 give the value range of the decision variables; M represents a sufficiently large positive number; K r represents a 0-1 variable. If a port sets berth r as a MASS dedicated berth, then K r =1, otherwise K r =0;n (max) It indicates the maximum number of MASS-dedicated berths in a port; n indicates the number of MASS-dedicated berths in a port.

4. The method for allocating berths for autonomous surface ships at sea in a mixed scenario according to claim 1 is characterized in that: In step S24, constraints 2 to 6 are restrictions related to the MASS dedicated berth, and other constraints are restrictions considered in the traditional BAP model; constraints 2 and 3 characterize the impact on the berth selection of ships after the port transforms the MASS dedicated berth; constraints 4, 5 and 6 characterize the mode of the MASS dedicated berth and the restrictions it is subject to.

5. The method for allocating berths for autonomous surface ships at sea in a mixed scenario according to claim 1 is characterized in that: Step S3 specifically includes: S31. Based on the improved multi-objective optimization model, a hybrid berth allocation mathematical model is constructed as follows: Among them, β represents the discount coefficient of loading and unloading time of manned ships at the MASS exclusive berth; S32. Calculate the discount coefficient for loading and unloading time of manned ships at the MASS exclusive berth. The calculation formula is as follows: Among them, T MASS Indicates the loading and unloading time of Class B berth; T prep It indicates the additional preparation time of manned ships at MASS berths, including the equipment commissioning and personnel coordination time required when manned ships berth at Class B berths; T man Indicates the loading and unloading time of Class A berths; the calculation formulas are as follows: Among them, the loading and unloading time of Class B berth is T MASS and automation equipment efficiency R MASS , loading and unloading demand D MASS and equipment quantity and scheduling optimization E MASS Related; Class A berth loading and unloading time T man The operating rate R of the port loading and unloading equipment man , crew operation adjustment time A man and loading and unloading demand D man Related; S33, adding the berth idle time target optimization function T3 to the objective function, as follows: S34. Based on the above description, parameters and decision variables, the multi-objective optimization model is expressed as the following objective function: [Model2]minC=C1+C2+T3 Among them, the objective function Model 2 is used to minimize the total cost of ship berthing for all ships within the planning period; S35. Set constraints for the objective function as follows: Constraint 18: Constraint 19: Constraint 20: Constraint 21: Constraint 22: n≤n(max) Constraint 23: Constraint 24: Constraint 25: Constraint 26: Constraint Twenty-Seven: Constraint 28: Constraint Twenty-Nine: Constraint 30: n ≥ 0 Constraint Thirty-One: Constraint Thirty-Two: Constraint Thirty-Three: Among them, constraint 18 ensures that each ship is docked at a certain berth; constraint 19 is the main difference between the model and the traditional BAP model after considering the MASS dedicated berth, which is used to ensure that MASS cannot dock it at other ordinary berths, but can only dock at the MASS exclusive berth; constraint 20 is used to ensure that if the port has set up a MASS dedicated berth, it will definitely berth at this berth to avoid the waste of dedicated berth resources; constraint 21 is used to calculate the number of MASS dedicated berths for port transformation; constraint 22 is used to ensure that the number of MASS dedicated berths in the port cannot exceed the upper limit; constraint 23 expresses y ir With b ir Constraint 24 is used to ensure that the ship's berthing time is not earlier than the arrival time; Constraint 25 is used to ensure that the ship's actual berthing time is equal to the sum of the ship's basic berthing time and the anchoring time; Constraint 26 is used to ensure that the berthing time of two ships serving the same berth is not earlier than the loading and unloading completion time of the former; Constraints 27 and 28 express y ir With z i,j,r The relationship between them ensures that the two ships docked at the same berth do not conflict in time; Constraints 29 to 33 give the value range of the decision variables.

6. The method for allocating berths for autonomous surface ships at sea in a mixed scenario according to claim 5 is characterized in that: In step S35, constraints 19 to 23 are restrictions related to the MASS dedicated berth, and the other constraints are restrictions considered in the traditional BAP model; constraints 19 and 20 characterize the impact on the berth selection of ships after the port renovates the MASS dedicated berth; constraints 21, 22 and 23 characterize the mode of the MASS dedicated berth and the restrictions it is subject to.

Images