A method, system, equipment and storage medium for the operation and maintenance scheduling of offshore wind farms.

Abstract

This invention relates to a method, system, equipment, and storage medium for the operation and maintenance scheduling of offshore wind farms. The method includes acquiring basic scheduling data, which is relevant data used for scheduling maintenance of offshore wind turbines; determining multiple initial solutions based on preset initial solution construction rules and the basic scheduling data; determining a first optimal solution among the multiple initial solutions based on a preset solution model and the multiple initial solutions; optimizing the first optimal solution according to a preset first optimization rule to generate a second optimal solution; and optimizing the second optimal solution based on a preset second optimization rule to determine a target optimal solution. This invention improves the efficiency of solving the operation and maintenance scheduling model.

Description

Technical Field

[0001] This application relates to the technical field of offshore wind farms, and in particular to an offshore wind farm operation and maintenance scheduling method, system, equipment and storage medium. Background Technology

[0002] Wind power is one of the most important clean energy sources globally and has become a hot research topic worldwide. Due to significantly better wind conditions at sea than onshore, offshore wind power has become a major development trend globally. However, compared to onshore wind power, offshore wind turbines face more complex conditions and are more susceptible to damage. Currently, the availability rate of offshore wind turbines is significantly lower than that of onshore turbines. Furthermore, maintenance of offshore wind turbines requires the use of specialized equipment such as ships and helicopters, resulting in higher maintenance costs. Therefore, developing a reasonable maintenance plan to improve turbine utilization and reduce maintenance costs is crucial.

[0003] Because maintenance planning involves multiple factors such as docks, ships, personnel, tools, spare parts, and tides, the operation and maintenance scheduling model built according to the actual scenario is very complex. Therefore, some researchers choose to simplify the model to build a mixed integer programming model, but the simplified model cannot meet the actual industrial needs; other researchers have built very complex integer programming models based on the actual scenario and used algorithms such as DW decomposition and local search to solve them, but the solution efficiency cannot meet the solution efficiency requirements of practical applications.

[0004] The existing technical solutions mentioned above have the following drawbacks: the solution efficiency of the operation and maintenance scheduling model is low. Summary of the Invention

[0005] To improve the low solution efficiency of operation and maintenance scheduling models, this application provides an operation and maintenance scheduling method, system, equipment, and storage medium for offshore wind farms.

[0006] In a first aspect of this application, a method for operation and maintenance scheduling of offshore wind farms is provided. The method includes:

[0007] Obtain basic scheduling data, which is relevant data used for scheduling maintenance of offshore wind turbines;

[0008] Based on the preset initial solution construction rules and the scheduling basic data, multiple initial solutions are determined;

[0009] Based on the preset solution model and the multiple sets of initial solutions, determine the first optimal solution among the multiple sets of initial solutions;

[0010] The first optimal solution is optimized according to a preset first optimization rule to generate a second optimal solution;

[0011] Based on the preset second optimization rule, the second optimal solution is optimized to determine the target optimal solution.

[0012] As can be seen from the above technical solutions, by acquiring basic scheduling information and constructing rules based on the initial solution, preliminary scheduling is performed on the basic scheduling information, resulting in multiple initial solutions. Obtaining multiple initial solutions increases the possibility of scheduling results, improving the optimal performance of the first optimal solution. Then, the first optimal solution is further optimized to obtain the final target optimal solution. By optimizing the first optimal solution, the problem of simple operation and maintenance scheduling models not being applicable to actual needs can be improved, and at the same time, the solution efficiency is improved to a certain extent compared with complex operation and maintenance scheduling models.

[0013] In one possible implementation, determining multiple initial solutions based on preset initial solution construction rules and the scheduling base data includes:

[0014] The scheduling basic data includes time window information, task information, and ship information. The time window information includes multiple window data, the task information includes multiple task data, the task data includes task identifier and task completion time, and the ship information includes multiple ship data.

[0015] Based on the task completion time, the task data is sorted in ascending order to determine the task data sequence;

[0016] The task data is obtained sequentially from the task data sequence;

[0017] Based on the task data, the window data, the ship data, and the preset scheduling calculation rules, determine the task end time corresponding to the task data;

[0018] Obtain the next task data, and determine whether the next task data can be added to the time range corresponding to the window data according to the preset scheduling judgment rules;

[0019] If not, retrieve the data for the next window;

[0020] When all window data in the time window information or all ship data in the ship information are scheduled, the first initial solution is determined.

[0021] Based on the preset initial solution transformation rules, multiple initial solutions are determined according to the first set of initial solutions.

[0022] In one possible implementation, the step of determining multiple sets of initial solutions based on a preset initial solution transformation rule and according to the first set of initial solutions includes:

[0023] Randomly select task data from the task data sequence;

[0024] Determine the second set of initial solutions according to the preset scheduling rules;

[0025] Based on the preset sorting of the task information, the task data of the first group of initial solutions and the second group of initial solutions are adjusted to determine the third group of optimal solutions and the fourth group of optimal solutions.

[0026] After removing duplicate solutions from the first set of initial solutions, the second set of initial solutions, the third set of optimal solutions, and the fourth set of optimal solutions, the remaining first set of initial solutions, the second set of initial solutions, the third set of optimal solutions, and the fourth set of optimal solutions form multiple sets of initial solutions.

[0027] In one possible implementation, the step of optimizing the first optimal solution according to a preset first optimization rule to generate a second optimal solution includes:

[0028] Define multiple perturbation neighborhoods and search neighborhoods;

[0029] Based on the preset perturbation rules and the perturbation neighborhood, the first optimal solution is randomly perturbed to generate a first intermediate solution;

[0030] Based on the first intermediate solution, the search neighborhood, and the preset search rules, determine the optimal solution in the first neighborhood;

[0031] Based on the preset perturbation rules and the perturbation neighborhood, the optimal solution in the first neighborhood is randomly perturbed to generate a second intermediate solution;

[0032] Based on the second intermediate solution, the search neighborhood, and the preset search rules, determine the optimal solution in the second neighborhood;

[0033] Each random perturbation uses a different perturbation neighborhood. When no new perturbation neighborhood exists, the optimal solution in the second neighborhood is the second optimal solution.

[0034] In one possible implementation, determining the optimal solution in the second neighborhood based on the second intermediate solution, the search neighborhood, and a preset search rule includes:

[0035] The search neighborhood includes multiple search sub-neighborhoods, and the neighborhood ranges of the search sub-neighborhoods are different.

[0036] Based on the ascending order of the neighborhood range of the searched sub-neighborhood, the search is performed sequentially according to the second intermediate solution to obtain the sub-neighborhood solution;

[0037] According to the preset optimal solution judgment rules, the better solution among the sub-neighborhood solution and the second intermediate solution is determined;

[0038] When all the search sub-neighborhoods have been searched, the better solution is the optimal solution of the second neighborhood.

[0039] In one possible implementation, optimizing the second optimal solution based on a preset second optimization rule to determine the target optimal solution includes:

[0040] The second optimal solution includes maintenance time;

[0041] When the maintenance time is within the time range of the window data;

[0042] Multiple random times are generated using a preset random algorithm;

[0043] The maintenance time corresponding to the second optimal solution is changed according to the random time.

[0044] According to the wind power loss calculation rules, the wind power loss corresponding to the maintenance time is determined, and each random time corresponds to one wind power loss;

[0045] The second optimal solution corresponding to the minimum wind power loss is the target optimal solution.

[0046] In one possible implementation, the preset solution model is the MIP model.

[0047] In a second aspect of this application, an operation and maintenance scheduling system for offshore wind farms is provided. The system includes:

[0048] The data acquisition module is used to acquire basic scheduling data;

[0049] The initial solution determination module is used to determine multiple initial solutions based on preset initial solution construction rules and the scheduling basic data; the optimal solution determination module is used to determine the first optimal solution among the multiple initial solutions based on preset solution model and the multiple initial solutions.

[0050] The first optimization module is used to optimize the first optimal solution according to a preset first optimization rule and generate a second optimal solution;

[0051] The second optimization module is used to optimize the second optimal solution based on the preset second optimization rules to determine the target optimal solution.

[0052] In a third aspect of this application, an electronic device is provided. The electronic device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the program to implement the method described above.

[0053] In a fourth aspect of this application, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the method according to the first aspect of this application.

[0054] In summary, this application includes at least one of the following beneficial technical effects:

[0055] 1. By acquiring basic scheduling information and constructing rules based on initial solutions, preliminary scheduling is performed on the basic scheduling information, resulting in multiple initial solutions. Using these initial solutions and a pre-defined solution model, a first optimal solution is determined. This first optimal solution is then further optimized to obtain the final target optimal solution. Optimizing the first optimal solution can address the issue of simple operation and maintenance scheduling models being unsuitable for actual needs, and also improves solution efficiency to a certain extent compared to complex operation and maintenance scheduling models. Attached Figure Description

[0056] Figure 1 This is a flowchart illustrating the offshore wind farm operation and maintenance scheduling method provided in this application.

[0057] Figure 2 This is a schematic diagram of the offshore wind farm operation and maintenance scheduling system provided in this application.

[0058] Figure 3 This is a schematic diagram of the structure of the electronic device provided in this application.

[0059] In the diagram, 200 is the offshore wind farm operation and maintenance scheduling system; 201 is the data acquisition module; 202 is the initial solution determination module; 203 is the optimal solution determination module; 204 is the first optimization module; 205 is the second optimization module; 301 is the CPU; 302 is the ROM; 303 is the RAM; 304 is the I / O interface; 305 is the input section; 306 is the output section; 307 is the storage section; 308 is the communication section; 309 is the driver; and 310 is the removable medium. Detailed Implementation

[0060] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0061] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article, unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.

[0062] The embodiments of this application will now be described in further detail with reference to the accompanying drawings.

[0063] This application provides an offshore wind farm operation and maintenance scheduling method, the main process of which is described below.

[0064] like Figure 1 As shown:

[0065] Step S101: Obtain basic scheduling data.

[0066] Specifically, the scheduling baseline data is used for scheduling maintenance of offshore wind turbines. This baseline data includes time window information, task information, vessel information, personnel information, and spare parts information. The time window information includes multiple window data entries, representing the time periods during which offshore wind turbine maintenance tasks can be performed. Each time period represents one window data entry. The window data in the time window information is sorted in ascending order of the start time of the time period. Due to the complexity of offshore conditions, offshore maintenance tasks cannot be performed at any time, hence the time window information. The task information includes multiple task data entries, including a task identifier and task completion time. Each task data entry corresponds to a wind turbine maintenance task. The task identifier is a unique identifier for the task, reducing the problem of missed or duplicate scheduling. The vessel information includes multiple vessel data entries. Offshore wind turbine maintenance requires the use of vessels to travel between the various turbines to be maintained. Vessels depart from the dock and proceed to the location of the turbine to be maintained. After completing one maintenance task, vessels can choose to proceed to the next turbine to be maintained or return to the dock. Vessels have capacity limitations, and they must return to the dock after completing all tasks. The personnel information above includes the number of maintenance engineers and maintenance experts. The spare parts information above includes the number of tools required for maintenance and the number of parts that need to be replaced on the wind turbine.

[0067] Offshore maintenance scheduling primarily targets two types of tasks. One type involves immediate turbine shutdown upon a failure, with power generation loss calculated from the moment of shutdown until the turbine is reconnected to the grid after the task is completed; this is typically troubleshooting-related maintenance. The other type involves turbine shutdown only after the task begins, with power generation loss calculated from task start to completion; this is generally planned inspections or predictive maintenance. Different tasks for the same turbine can be combined, and the required personnel, tools, and spare parts information are synchronized and integrated.

[0068] Step S102: Determine multiple initial solutions based on the preset initial solution construction rules and scheduling basic data.

[0069] Specifically, all task data is acquired. Based on the task completion time corresponding to each task data item, the task data is sorted in ascending order to determine the task data sequence. The task data is then sequentially retrieved from this sequence. Next, a window of data is sequentially retrieved from the time window information, and a vessel data item is randomly retrieved from the vessel information. The vessel data and task data are then added to the retrieved window of data. Based on the task completion time in the task data, the task's end time can be obtained. The process proceeds sequentially: Retrieve the next task data in sequence and add it to the window data. Based on the completion time of the second task and the end time of the first task, calculate the end times of both tasks. If the end times of both tasks are less than the end time of the window data, retrieve the next task data and add it to the window data. If the end times of both tasks are greater than the end time of the window data, the second task cannot be added to the current window data. Retrieve the next window data in sequence and add the second task data to the new window data. If the end times of both tasks are equal to the end time of the window data, the second task can be added to the current window data, but the next task data needs to be added to the new window data. Retrieve the next window data and task data in sequence, and continue the above checks to schedule the task data. Scheduling ends when all window data in the time window information or all ship data in the ship information is scheduled. The result of this scheduling is the first initial solution.

[0070] The method for determining the second set of initial solutions differs from that of the first set in that it is not necessary to obtain the task data in the task data sequence sequentially; instead, task data can be obtained randomly. Each time a task data point is obtained, it is marked to avoid repeatedly obtaining the same task data. The other determination processes for the first and second sets of initial solutions are the same and will not be elaborated upon here.

[0071] The method for determining the third set of initial solutions is to modify and adjust the first set of initial solutions based on the preset order of the task information. Specifically, the preset order of the task information means that a certain type of task or a certain task must precede or follow a certain type of task or a certain task. Based on this preset order, the order of tasks in the first set of initial solutions is rearranged, and the resulting solution is the third set of initial solutions. The method for determining the fourth set of initial solutions is to modify and adjust the second set of initial solutions based on the preset order of the task information.

[0072] Traverse the first, second, third, and fourth initial solutions mentioned above, filter out duplicate solutions that appear in the above multiple initial solutions, and delete any one of the duplicate solutions. The first, second, third, and fourth initial solutions after deleting duplicate solutions form multiple initial solutions.

[0073] Step S103: Based on the preset solution model and multiple initial solutions, determine the first optimal solution among the multiple initial solutions.

[0074] Specifically, the preset solution model is the MIP model. By inputting the above-mentioned multiple initial solutions into the MIP model, the first optimal solution can be obtained. The above-mentioned MIP model is a technical means known to those skilled in the art, and will not be elaborated here.

[0075] Step S104: Optimize the first optimal solution according to the preset first optimization rule to generate the second optimal solution.

[0076] Specifically, multiple perturbation neighborhoods and search neighborhoods are defined. Based on preset perturbation rules and the aforementioned perturbation neighborhoods, the first optimal solution is randomly perturbed to generate a first intermediate solution. The perturbation neighborhoods and search neighborhoods are manually set by the designers according to the business scenario. The random perturbation is a well-known technique and will not be elaborated upon here. Based on the defined search neighborhoods and preset search rules, the obtained first intermediate solution is modified and compared to determine the first neighborhood optimal solution. Then, the first neighborhood optimal solution is randomly perturbed again based on the perturbation neighborhoods to generate a second intermediate solution. The same operations as with the first intermediate solution are performed on the second intermediate solution to determine the second neighborhood optimal solution. Each time a random perturbation is performed, the perturbation neighborhoods used are different. When no new perturbation neighborhoods exist, the aforementioned second neighborhood optimal solution is the second optimal solution.

[0077] The process described above, based on the search neighborhood and preset search rules, to determine the optimal solution in the first or second neighborhood according to the first or second intermediate solution, includes (taking the second intermediate solution as an example):

[0078] The search neighborhood includes multiple search sub-neighborhoods, each with a different neighborhood size. Based on the ascending order of the neighborhood sizes of these sub-neighborhoods, the search proceeds sequentially according to the second intermediate solution to obtain sub-neighborhood solutions. The second intermediate solution is denoted as x', and the sub-neighborhood solutions are denoted as x”. f(x) follows a preset calculation rule: when f(x”) < f(x'), it indicates that the sub-neighborhood solution is better than the second intermediate solution, and thus the sub-neighborhood solution is considered a better solution; when f(x”) ≥ f(x'), it indicates that the second intermediate solution is better than the sub-neighborhood solution, and thus the second intermediate solution is considered a better solution. When all the search sub-neighborhoods have been searched, the final better solution is determined to be the optimal solution of the second neighborhood.

[0079] In one example, the first optimal solution is denoted as x. The first optimal solution is a single solution. Different solutions can be obtained based on different perturbation neighborhoods and the first optimal solution. These different solutions form a solution set. The solution set is then placed in a process pool and solved according to a preset calculation rule to determine x'. The preset calculation rule is the MIP model. Based on the search sub-neighborhood and x', x' is determined. When x' is better than x', x' is assigned to x'. Then x' continues to determine the solution set based on the perturbation neighborhood until all search sub-neighborhoods have been searched. At this point, x' is the second neighborhood optimal solution.

[0080] By placing the solution set into a process pool, multi-process solution can be implemented, which can improve the solution efficiency.

[0081] In this embodiment, the search neighborhood includes three sub-neighborhoods, each corresponding to a neighborhood operator. The neighborhood operators with search ranges from smallest to largest are: changing the start and end points of the window data, changing the task data of the ship in each window, and changing the window data where the task data is located. These three neighborhood operators are numbered 1, 2, and 3 in sequence. For a certain maintenance scenario, there are 5 wind turbines, i.e., 5 maintenance tasks to be performed. Numbers starting with D represent the sending node, numbers starting with P represent the receiving node, and the number 0 represents the dock. Assuming there are 2 ships and 2 maintenance time windows, the first optimal solution is as follows:

[0082] V1: [0,D1,P2,2],[2,D3,P3,D5,0];

[0083] V2: [0,D2,P1,1],[1,D4,P4,P5,0];

[0084] The first optimal solution described above means that ship V1 departs from dock 0, takes maintenance personnel to wind turbine 1 to perform maintenance tasks, and then goes to wind turbine 2 to pick up personnel. At this time, the ship movement in the first time window ends, and the ship docks next to wind turbine 2. At the beginning of the second time window, the ship takes personnel from wind turbine 2 to wind turbine 3 to perform maintenance tasks. After the maintenance tasks on wind turbine 3 are completed, the ship picks up the personnel, then takes the personnel to wind turbine 5 to perform maintenance tasks, and finally returns to the dock. The interpretation rules for ship V2 are the same as those for ship V1, and will not be repeated here.

[0085] In one example, the neighborhood operator 1 is used to transform the first optimal solution. However, the starting and ending points are selected only from the last task node of the previous time window and the first task node of the next time window for the corresponding ship. Therefore, there are a total of four cases. For ship V1, in the first optimal solution, the last task node of the previous window is P2, and the first task node of the next time window is D3. So ship V1 can choose to dock at wind turbines 2 and 3. For ship V2, in the first optimal solution, the last task node of the previous window is P1, and the first task node of the next time window is D4. So ship V2 can choose to dock at wind turbines 1 and 4. When ship V1 chooses to dock at wind turbine 3 and ship V2 chooses to dock at wind turbine 4, the corresponding solutions after transformation are as follows:

[0086] V1: [0,D1,P2,3],[3,D3,P3,D5,0];

[0087] V2: [0,D2,P1,4],[4,D4,P4,P5,0].

[0088] The neighborhood operator 2 is used to further transform the first optimal solution. This time, the window data containing the tasks remains unchanged. Only one node can be transformed between ships. For example, for ship V1, there are two task nodes, D1 and P2, in the first time window; for ship V2, there are two task nodes, D2 and P1, in the first time window. D1 of ship V1 can be swapped with D2 and P1 of ship V2, and P2 of ship V1 can be swapped with D2 and P1 of ship V2. Therefore, for the first time window, there are 2*2 = 4 possible combinations. Similarly, for the second window, there are 3*3 = 9 possible combinations. For ships V1 and V2, there are a total of 4 + 9 = 13 possible combinations. If the transformed node is the beginning or end node of the time window, the neighborhood operator 1 can be used for further transformation. The solution obtained after swapping task node D1 in ship V1 and task node D2 in ship V2 is as follows:

[0089] V1: [0,D2,P2,3],[3,D3,P3,D5,0];

[0090] V2: [0,D1,P1,4],[4,D4,P4,P5,0].

[0091] The first optimal solution is transformed using neighborhood operator 3. Assuming only one task is changed at a time, in this embodiment there are 5 tasks and 2 time windows. Tasks 1 and 2 are in the first time window, and tasks 3, 4, and 5 are in the second time window. Any task in the first time window can be swapped with a task in the second time window, resulting in 3*2=6 swap possibilities. After the transformation, neighborhood operator 2 and / or neighborhood operator 1 can be used for further transformation. Each task has a receiving node and a sending node; when a task is transformed, the receiving and sending nodes are also transformed accordingly. Task 4 in the second time window was swapped with Task 1 in the first time window. The transformed solution is as follows:

[0092] V1:[0,D4,P2,2],[2,D3,P3,D5,0];

[0093] V2:[0,D2,P4,1],[1,D1,P1,P5,0].

[0094] Step S105: Based on the preset second optimization rule, optimize the second optimal solution to determine the target optimal solution.

[0095] Specifically, the second optimal solution includes maintenance time. When the maintenance time falls within the time range of the aforementioned window data, the second optimal solution can be further optimized. First, multiple random times are generated using a preset random algorithm. Based on these random times, the wind power loss corresponding to each random time is calculated. Each random time corresponds to a wind power loss. The second optimal solution corresponding to the random time with the minimum wind power loss is selected as the target optimal solution. The method for calculating the wind power loss described above is well-known to those skilled in the art and will not be elaborated upon here.

[0096] In this embodiment, the time range of the window data is from 8:00 to 20:00 on a certain day, while the maintenance time for vessel V1 is from 8:00 to 16:00. A random algorithm is used to randomly generate time points between 16:00 and 20:00. Assuming a random time point is 18:00, the maintenance time for vessel V1 is postponed by two hours, i.e., the maintenance time is from 10:00 to 18:00. The first wind power loss incurred during wind turbine maintenance from 8:00 to 16:00 and the second wind power loss incurred during wind turbine maintenance from 10:00 to 18:00 are calculated separately. The first and second wind power losses are compared. If the first wind power loss is less than or equal to the second wind power loss, wind turbine maintenance is performed from 8:00 to 16:00; if the first wind power loss is greater than the second wind power loss, wind turbine maintenance is performed from 10:00 to 18:00. This calculation and judgment are performed for each random time to determine the maintenance time with the minimum wind power loss.

[0097] This application provides an offshore wind farm operation and maintenance scheduling system 200, with reference to... Figure 2 The offshore wind farm operation and maintenance dispatch system 200 includes:

[0098] Data acquisition module 201 is used to acquire basic scheduling data;

[0099] The initial solution determination module 202 is used to determine multiple initial solutions based on preset initial solution construction rules and the scheduling basic data;

[0100] The optimal solution determination module 203 is used to determine the first optimal solution among the multiple initial solutions based on the preset solution model and the multiple initial solutions;

[0101] The first optimization module 204 is used to optimize the first optimal solution according to a preset first optimization rule and generate a second optimal solution;

[0102] The second optimization module 205 is used to optimize the second optimal solution based on the preset second optimization rules to determine the target optimal solution.

[0103] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the described module can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0104] This application discloses an electronic device. (Refer to...) Figure 3 The electronic device includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes based on a program stored in a read-only memory (ROM) 302 or a program loaded from a storage section 307 into a random access memory (RAM) 303. The RAM 303 also stores various programs and data required for system operation. The CPU 301, ROM 302, and RAM 303 are interconnected via a bus. An input / output (I / O) interface 304 is also connected to the bus.

[0105] The following components are connected to I / O interface 304: an input section 305 including a keyboard, mouse, etc.; an output section 306 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 307 including a hard disk, etc.; and a communication section 308 including a network interface card such as a LAN card, modem, etc. The communication section 308 performs communication processing via a network such as the Internet. A drive 309 is also connected to I / O interface 304 as needed. A removable medium 310, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 309 as needed so that computer programs read from it can be installed into storage section 307 as needed.

[0106] Specifically, according to embodiments of this application, the flowchart above refers to... Figure 1 The described process can be implemented as a computer software program. For example, embodiments of this application include a computer program product comprising a computer program carried on a machine-readable medium, the computer program containing program code for performing the methods shown in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network via communication section 308, and / or installed from removable medium 310. When the computer program is executed by central processing unit (CPU) 301, it performs the functions defined in the apparatus of this application.

[0107] It should be noted that the computer-readable medium shown in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0108] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the foregoing application concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions claimed in this application.

Claims

1. A method for operation and maintenance scheduling of offshore wind farms, characterized in that, include: Obtain basic scheduling data, which is relevant data used for scheduling maintenance of offshore wind turbines; Based on the preset initial solution construction rules and the scheduling basic data, multiple initial solutions are determined; Based on the preset solution model and the multiple sets of initial solutions, determine the first optimal solution among the multiple sets of initial solutions; The first optimal solution is optimized according to a preset first optimization rule to generate a second optimal solution; Based on the preset second optimization rule, the second optimal solution is optimized to determine the target optimal solution; The step of determining multiple initial solutions based on preset initial solution construction rules and the scheduling base data includes: the scheduling base data includes time window information, task information, and ship information; the time window information includes multiple window data entries; the task information includes multiple task data entries, each including a task identifier and a task completion duration; and the ship information includes multiple ship data entries. The task data is sorted in ascending order based on the task completion duration to determine a task data sequence. The task data is then sequentially obtained from the task data sequence. The task completion time corresponding to each task data entry is determined based on the task data, the window data, the ship data, and preset scheduling calculation rules. The next task data entry is obtained, and based on preset scheduling judgment rules, it is determined whether the next task data entry can be added to the time range corresponding to the window data. If not, the next window data entry is obtained. When all window data entries in the time window information or all ship data entries in the ship information are scheduled, a first initial solution is determined. Multiple initial solutions are determined based on the first initial solution according to preset initial solution transformation rules. The step of optimizing the first optimal solution according to a preset first optimization rule to generate a second optimal solution includes: defining multiple perturbation neighborhoods and search neighborhoods; randomly perturbing the first optimal solution according to the preset perturbation rule and the perturbation neighborhoods to generate a first intermediate solution; determining the first neighborhood optimal solution according to the first intermediate solution, the search neighborhood, and the preset search rule; randomly perturbing the first neighborhood optimal solution according to the preset perturbation rule and the perturbation neighborhood to generate a second intermediate solution; and determining the second neighborhood optimal solution according to the second intermediate solution, the search neighborhood, and the preset search rule. Each time a random perturbation is performed, the perturbation neighborhood used is different. When no new perturbation neighborhood exists, the second neighborhood optimal solution is the second optimal solution.

2. The offshore wind farm operation and maintenance scheduling method according to claim 1, characterized in that, The method based on the preset initial solution transformation rule, and determining multiple initial solutions according to the first set of initial solutions, includes: randomly acquiring task data from the task data sequence; determining a second set of initial solutions according to the preset scheduling rule; adjusting the task data of the first and second sets of initial solutions according to the preset sorting of the task information to determine a third and fourth set of optimal solutions; removing duplicate solutions from the first, second, third, and fourth sets of optimal solutions, and then forming multiple initial solutions from the removed first, second, third, and fourth sets of optimal solutions.

3. The offshore wind farm operation and maintenance scheduling method according to claim 1, characterized in that, The step of determining the optimal solution of the second neighborhood based on the second intermediate solution, the search neighborhood, and the preset search rules includes: the search neighborhood includes multiple search sub-neighborhoods, and the search sub-neighborhoods have different neighborhood ranges; based on the ascending order of the neighborhood ranges of the search sub-neighborhoods, the search is performed sequentially according to the second intermediate solution to obtain sub-neighborhood solutions; according to the preset optimal solution judgment rules, a better solution is determined between the sub-neighborhood solutions and the second intermediate solution; when all the search sub-neighborhoods have been searched, the better solution is the optimal solution of the second neighborhood.

4. The offshore wind farm operation and maintenance scheduling method according to claim 1, characterized in that, The optimization of the second optimal solution based on the preset second optimization rule to determine the target optimal solution includes: the second optimal solution includes maintenance time; when the maintenance time is within the time range of the window data; multiple random times are generated through a preset random algorithm; the maintenance time corresponding to the second optimal solution is changed according to the random times; the wind power loss corresponding to the maintenance time is determined according to the wind power loss calculation rule, with each random time corresponding to a wind power loss; the second optimal solution corresponding to the minimum wind power loss is the target optimal solution.

5. The offshore wind farm operation and maintenance scheduling method according to claim 1, characterized in that, The preset solution model is the MIP model.

6. An offshore wind farm operation and maintenance dispatch system, characterized in that, include: The data acquisition module (201) is used to acquire basic scheduling data; The initial solution determination module (202) is used to determine multiple initial solutions based on the preset initial solution construction rules and the scheduling basic data; The optimal solution determination module (203) is used to determine the first optimal solution among the multiple initial solutions based on the preset solution model and the multiple initial solutions; The first optimization module (204) is used to optimize the first optimal solution according to the preset first optimization rule and generate the second optimal solution; The second optimization module (205) is used to optimize the second optimal solution based on the preset second optimization rules to determine the target optimal solution; The initial solution determination module (202) is used to determine multiple initial solutions based on preset initial solution construction rules and the scheduling basic data, including: the scheduling basic data includes time window information, task information, and ship information; the time window information includes multiple window data; the task information includes multiple task data; the task data includes a task identifier and a task completion duration; and the ship information includes multiple ship data. The task data is sorted in ascending order according to the task completion duration to determine a task data sequence. The task data is obtained sequentially from the task data sequence. The task end time corresponding to the task data is determined according to the task data, the window data, the ship data, and preset scheduling calculation rules. The next task data is obtained, and the next task data is determined according to preset scheduling judgment rules to determine whether it can be added to the time range corresponding to the window data. If not, the next window data is obtained. When all window data in the time window information or all ship data in the ship information is scheduled, a first initial solution is determined. Based on preset initial solution transformation rules, multiple initial solutions are determined according to the first initial solution. The first optimization module (204) is used to optimize the first optimal solution according to a preset first optimization rule and generate a second optimal solution, including: defining multiple perturbation neighborhoods and search neighborhoods; randomly perturbing the first optimal solution according to the preset perturbation rule and the perturbation neighborhoods to generate a first intermediate solution; determining the first neighborhood optimal solution according to the first intermediate solution, the search neighborhoods and the preset search rule; randomly perturbing the first neighborhood optimal solution according to the preset perturbation rule and the perturbation neighborhoods to generate a second intermediate solution; determining the second neighborhood optimal solution according to the second intermediate solution, the search neighborhoods and the preset search rule; the perturbation neighborhoods used for each random perturbation are different, and when there are no new perturbation neighborhoods, the second neighborhood optimal solution is the second optimal solution.

7. An electronic device, characterized in that, It includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the program to implement the method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements the method as described in any one of claims 1 to 5.

Images