Method and device for determining optimal maintenance window period of wind power plant

Abstract

The invention relates to a method and a device for determining an optimal maintenance window period of a wind power plant. The method for determining the optimal maintenance window period of the wind power plant comprises the steps of obtaining electricity price prediction data and wind power plant generation power prediction data in a target maintenance period of the wind power plant; the target maintenance period is divided into a plurality of maintenance window periods, values of target functions of the maintenance window periods are determined, and the target functions are constructed based on the electricity price prediction data and the wind power plant generation power prediction data; and determining the maintenance window period with the minimum value of the target function as the optimal maintenance window period of the wind power plant. By the adoption of the method and device, electricity selling benefit loss in the wind power plant overhaul period can be reduced, and safety and reasonability of the wind power plant in the overhaul window setting period are improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of wind power generation, and more particularly, to a method and device for determining an optimal maintenance window period of a wind farm. Background Art

[0002] The formulation of the maintenance window period of a wind farm has an important impact on aspects such as the operation, safety, and economic benefits of the wind farm, and multiple factors need to be comprehensively considered to effectively plan the maintenance window period. By reasonably arranging the maintenance window period, the downtime and failure rate of the units can be minimized to the greatest extent, and the production plan can be optimized, which helps to improve the production efficiency of the wind farm and ensure the safe execution of the maintenance work at the same time. The traditional maintenance window period of a wind farm is generally formulated according to the predicted wind speed in the future. In order to minimize the power generation loss of the wind farm as much as possible, the maintenance work is usually carried out during the time window with a relatively small predicted wind speed. Summary of the Invention

[0003] The present disclosure provides a method and device for determining an optimal maintenance window period of a wind farm, a computing system, and a computer-readable storage medium.

[0004] According to another aspect of the present disclosure, there is provided a method for determining an optimal maintenance window period of a wind farm, the method for determining an optimal maintenance window period of the wind farm comprising: obtaining electricity price prediction data and wind farm power generation prediction data during a target maintenance period of the wind farm; dividing the target maintenance period into a plurality of maintenance window periods, and determining the value of an objective function of the maintenance window period, wherein the objective function is constructed based on the electricity price prediction data and the wind farm power generation prediction data; and determining the maintenance window period with the minimum value of the objective function as the optimal maintenance window period of the wind farm.

[0005] Optionally, the step of determining the value of the objective function of the maintenance window period comprises: dividing the maintenance window period into a plurality of time periods; based on the electricity price prediction data and the wind farm power generation prediction data, determining the predicted power of each wind turbine generator to be maintained in the wind farm during each of the plurality of time periods and the predicted electricity price during each of the plurality of time periods; and determining the value of the objective function of the maintenance window period based on the total number of the plurality of time periods, the number of wind turbine generators to be maintained, the predicted power, and the predicted electricity price.

[0006] Optionally, the step of determining the value of the objective function for the maintenance window period includes: obtaining extreme weather prediction data; in response to the maintenance window period not including the moments when extreme weather occurs, dividing the maintenance window period into multiple time periods; based on the electricity price prediction data and the wind farm power generation prediction data, determining the predicted power of each wind turbine generator to be maintained in the wind farm for each of the multiple time periods and the predicted electricity price for each of the multiple time periods; based on the total number of the multiple time periods, the number of wind turbine generators to be maintained, the predicted power, and the predicted electricity price, determining the value of the objective function for the maintenance window period.

[0007] Optionally, the maintenance window period is an uninterrupted continuous time period.

[0008] Optionally, the predicted power is the product of the predicted power of the wind farm for the corresponding time period and the ratio of the capacity of the corresponding wind turbine generator to the capacity of the wind farm.

[0009] Optionally, the step of determining the value of the objective function for the maintenance window period includes: for each time period of the maintenance window period, determining a first function value for each wind turbine generator to be maintained, and determining the sum of the first function values of all the wind turbine generators to be maintained as a second function value, where the first function value of each wind turbine generator to be maintained is the product of the predicted power of the wind turbine generator in the time period, the predicted electricity price in the time period, and a predetermined coefficient; determining the sum of the second function values of all the time periods as the value of the objective function for the maintenance window period.

[0010] According to another aspect of the present disclosure, there is provided a device for determining an optimal maintenance window period of a wind farm. The device for determining an optimal maintenance window period of a wind farm includes: a data acquisition unit that acquires electricity price prediction data and wind farm power generation prediction data within a target maintenance period of the wind farm; an objective function determination unit that divides the target maintenance period into multiple maintenance window periods and determines the value of the objective function for the maintenance window period, where the objective function is constructed based on the electricity price prediction data and the wind farm power generation prediction data; and an optimal maintenance window period determination unit that determines the maintenance window period with the minimum value of the objective function as the optimal maintenance window period of the wind farm.

[0011] Optionally, the objective function determination unit is configured to: divide the maintenance window period into a plurality of time periods; based on the electricity price prediction data and the wind farm power generation power prediction data, determine the predicted power of each wind turbine generator to be maintained in the wind farm for each of the plurality of time periods and the predicted electricity price for each of the plurality of time periods; and determine the value of the objective function for the maintenance window period based on the total number of the plurality of time periods, the number of wind turbine generators to be maintained, the predicted power, and the predicted electricity price.

[0012] Optionally, the objective function determination unit is configured to: obtain extreme weather prediction data; in response to the maintenance window period not including a time when extreme weather occurs, divide the maintenance window period into a plurality of time periods; based on the electricity price prediction data and the wind farm power generation power prediction data, determine the predicted power of each wind turbine generator to be maintained in the wind farm for each of the plurality of time periods and the predicted electricity price for each of the plurality of time periods; and determine the value of the objective function for the maintenance window period based on the total number of the plurality of time periods, the number of wind turbine generators to be maintained, the predicted power, and the predicted electricity price.

[0013] Optionally, the maintenance window period is an uninterrupted continuous time period.

[0014] Optionally, the predicted power is the product of the predicted power of the wind farm for the corresponding time period and the ratio of the capacity of the corresponding wind turbine generator to the capacity of the wind farm.

[0015] Optionally, the objective function determination unit is configured to: for each time period of the maintenance window period, determine a first function value of each wind turbine generator to be maintained, and determine the sum of the first function values of all the wind turbine generators to be maintained as a second function value, where the first function value of each wind turbine generator to be maintained is the product of the predicted power of the wind turbine generator in the time period, the predicted electricity price in the time period, and a predetermined coefficient; and determine the sum of the second function values of all the time periods as the value of the objective function for the maintenance window period.

[0016] According to another aspect of the present disclosure, there is provided a computing system including at least one computing device and at least one storage device storing instructions, where, when the instructions are run by the at least one computing device, the at least one computing device is caused to execute the method for determining the optimal maintenance window period of a wind farm as described above.

[0017] According to another aspect of the present disclosure, there is provided a computer-readable storage medium storing instructions, wherein when the instructions are run by at least one computing device, the at least one computing device is caused to execute the method for determining the optimal maintenance window period of a wind farm as described above.

[0018] By adopting the present disclosure, it is possible to help reduce the loss of power sales benefits during the maintenance of a wind farm and improve the safety and rationality of formulating the maintenance window period of the wind farm. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] By describing embodiments with reference to the accompanying drawings below, the above and / or other objects and advantages of the present disclosure will become clearer, wherein:

[0020] Figure 1 is a flowchart showing a method for determining the optimal maintenance window period of a wind farm according to an exemplary embodiment of the present disclosure;

[0021] Figure 2 is a flowchart showing a method for determining the optimal maintenance window period of a wind farm according to an embodiment of the present disclosure;

[0022] Figure 3 is a graph showing the loss of power sales benefits during the window period and the average predicted wind speed according to an embodiment of the present disclosure;

[0023] Figure 4 is a block diagram showing a device for determining the optimal maintenance window period of a wind farm according to an exemplary embodiment of the present disclosure;

[0024] Figure 5 is a block diagram showing a computing system including at least one computing device and at least one storage device storing instructions according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0025] The following provides a description of specific embodiments in conjunction with the accompanying drawings to help the reader obtain a comprehensive understanding of the methods, devices, and / or systems described herein. However, various changes, modifications, and equivalents of the methods, devices, and / or systems described herein will be apparent after understanding the disclosure of the present application. For example, the order of operations described herein is merely exemplary and is not limited to those set forth herein, but may be changed as will be apparent after understanding the disclosure of the present application, except for operations that must occur in a specific order. In addition, descriptions of features known in the art may be omitted for greater clarity and conciseness.

[0026] When a wind farm participates in electricity market transactions as an independent market entity, the market electricity price level directly affects the electricity sales benefits of the wind farm. Moreover, it is possible that the electricity price level is relatively low when the new energy generation capacity is strong, while the electricity price level is relatively high when the new energy generation capacity is weak. In this case, the loss of electricity sales benefits caused by the wind farm choosing to carry out maintenance during the period with weak power generation capacity may be higher than that during the period with strong power generation capacity. Therefore, the present disclosure proposes to consider the impact of electricity price on the loss of electricity sales benefits during maintenance when determining the maintenance window period of the wind farm.

[0027] Figure 1 It is a flowchart showing a method for determining the optimal maintenance window period of a wind farm according to an exemplary embodiment of the present disclosure.

[0028] As Figure 1 shown, in step S101, obtain the electricity price prediction data and the wind farm power generation prediction data during the target maintenance period of the wind farm. In the example, consider factors such as the needs of the wind farm's own operation strategy and the type of unit failure to determine the target maintenance period. For example, the target maintenance period is between the upper and lower limits of the time when the wind farm is allowed to start maintenance (for example, t s <t0<t e , where, t s and t e are respectively the upper and lower limits of the time when the wind farm is allowed to start maintenance, and the time between t s and t e is the entire maintenance cycle, and t0 is the maintenance start time).

[0029] In step S102, the target maintenance period of the wind farm is divided into multiple maintenance windows, and the value of the objective function of the maintenance window is determined, where the objective function is constructed based on the electricity price prediction data and the wind farm power generation prediction data during the target maintenance period of the wind farm. In the example, the maintenance window is divided into multiple time periods; based on the electricity price prediction data and the wind farm power generation prediction data during the target maintenance period of the wind farm, the predicted power of each wind turbine generator to be maintained in the wind farm in each of the multiple time periods and the predicted electricity price in each of the multiple time periods are determined; based on the total number of the multiple time periods, the number of wind turbine generators to be maintained, the predicted power of each wind turbine generator in each of the multiple time periods, and the predicted electricity price in each time period, the value of the objective function of the maintenance window is determined. For example, for each time period of the maintenance window, the first function value of each wind turbine generator to be maintained is determined, and the sum of the first function values of all the wind turbine generators to be maintained is determined as the second function value, where the first function value of each wind turbine generator to be maintained is the product of the predicted power of the wind turbine generator in the time period, the predicted electricity price in the time period, and a predetermined coefficient; the sum of the second function values of all the time periods is determined as the value of the objective function of the maintenance window. In the example, the predicted power of each wind turbine generator to be maintained in the wind farm in each of the multiple time periods is the product of the predicted power of the wind farm in the corresponding time period and the ratio of the capacity of the corresponding wind turbine generator to the capacity of the wind farm.

[0030] For example, the objective function established with the goal of minimizing the loss of electricity sales benefits during the maintenance period is as follows:

[0031]

[0032]

[0033] In formula (1), T is the total number of time periods within the maintenance window. For example, when the time resolution of both the predicted power and the predicted electricity price is 15 minutes, 15 minutes is taken as one time period. If the maintenance window is 2 days, then the total number of time periods within the maintenance window is 192; N is the number of wind turbine generators to be maintained; P(k,t) is the predicted power of the maintenance unit k in the t-th time period, and P(k,t) is obtained by multiplying the full-field predicted power by the ratio of the capacity of unit k to the full-field capacity; ρ(t) is the predicted electricity price in the t-th time period. The solution space of the optimization problem is the entire maintenance cycle. If the wind farm needs to determine the maintenance window within the next n days, then the solution space of this model is the maintenance cycle of n days.

[0034] In the example, the maintenance window period is an uninterrupted continuous time period. The maintenance continuity constraint means that the maintenance work should be carried out continuously after it starts and there should be no interruption in the middle, that is:

[0035]

[0036] In Equation (2), x i is the status of the maintenance work at time t i When in the maintenance state, it takes 1, and when in the non-maintenance state, it takes 0. t is the maintenance duration (i.e., the maintenance time length), and [t0, t0 + t] is the maintenance window period.

[0037] In another example, obtain extreme weather prediction data; in response to the maintenance window period not including the moments when extreme weather occurs, divide the maintenance window period into multiple time periods; based on the electricity price prediction data and the wind farm power generation prediction data within the target maintenance period of the wind farm, determine the predicted power of each wind turbine that needs to be maintained in the wind farm for each of the multiple time periods and the predicted electricity price for each of the multiple time periods; based on the total number of the multiple time periods, the number of wind turbines that need to be maintained, the predicted power for each time period, and the predicted electricity price for each time period, determine the value of the objective function of the maintenance window period.

[0038] Since wind farms are generally located in remote areas with frequent extreme weather, the occurrence of extreme weather will directly affect the safety of maintenance personnel, bring great impacts to the normal operation and maintenance of the power plant, and may also cause huge losses to the operation of the wind farm. For example, to ensure the safe execution of the maintenance work in the wind farm, maintenance work should not be arranged under such weather conditions as icing, cold snap, and sand and dust. According to the extreme weather warning results, the following extreme weather constraints can be obtained:

[0039]

[0040] In Equation (3), l i is the extreme weather warning event label. When l i = 0, it means that there is no extreme weather event at time t i and the maintenance work can be carried out normally. When l i = 1, it means that there is an extreme weather warning label at time t i and the maintenance work cannot be carried out. To ensure the smooth progress of the maintenance work, when there is a situation where l i = 1 within the maintenance window period, it means that there is an extreme weather warning event within the maintenance window period, and then this maintenance window period is regarded as an infeasible solution. Thus, it can be avoided that the normal execution of the maintenance work is affected by not considering extreme weather, and at the same time, it can be avoided from causing unnecessary safety hazards to the operation of the wind farm.

[0041] In step S103, the maintenance window period with the minimum value of the objective function is determined as the optimal maintenance window period of the wind farm. In the example, the maintenance window period with the minimum value of the objective function corresponds to the maintenance window period with the minimum loss of power sales benefit. In another example, the maintenance window period with the minimum value of the objective function corresponds to the maintenance window period with the minimum loss of power sales benefit and simultaneously satisfying the above-mentioned maintenance start time constraint, maintenance continuity constraint, and / or extreme weather constraint.

[0042] By adopting the method for determining the optimal maintenance window period of a wind farm according to the exemplary embodiments of the present disclosure, considering the impact of electricity price on the loss of power sales benefit during the maintenance period of the wind farm when formulating the maintenance window period, the benefit loss during the maintenance period can be effectively reduced.

[0043] Figure 2 It is a flowchart showing the method for determining the optimal maintenance window period of a wind farm according to the embodiments of the present disclosure.

[0044] In the example, the optimal maintenance window period is determined by determining the maintenance window period that minimizes the value of the objective function established with the goal of minimizing the loss of power sales benefit during the maintenance period in a future period of time and simultaneously satisfying constraint conditions such as extreme weather constraints. The specific algorithm flow is as Figure 2 shown. In step S201, obtain the electricity price prediction data, wind farm power prediction data, wind farm extreme weather warning data, and maintenance information data such as the target maintenance period T, maintenance duration t, and maintenance capacity formulated by the wind farm according to its own needs during the target maintenance period. Here, the maintenance start time is set as t0, and the maintenance end time is set as t e . In step S202, exclude the night time period and other time periods that do not meet the actual operation requirements of the power plant itself within the entire maintenance period T according to the maintenance time constraint. In step S203, determine whether the maintenance window period [t0, t0 + t] satisfies the extreme weather constraint. If it is determined in step S203 that the maintenance window period [t0, t0 + t] satisfies the extreme weather constraint, proceed to step S204; otherwise, proceed to step S205. In step S204, calculate the target function C of the loss of power sales benefit within the maintenance window period [t0, t0 + t] according to the predicted power, predicted electricity price, and maintenance capacity. For example, the target function C of the loss of power sales benefit can be determined with reference to Equation (1). After step S204, proceed to step S205, and set t0 = t0 + 15, that is, start calculating the value of the target function of the next maintenance window period. In this example, the set time period duration is 15 minutes. It should be understood that this duration can also be any other value (for example, 10 minutes or 20 minutes, etc.). Next, in step S206, determine whether the difference between the current maintenance start time and the maintenance end time is less than the maintenance duration, that is, determine whether t e - t0 < t is satisfied. If it is determined in step S206 that te - If t0 < t, it indicates that the maintenance start time constraint is not satisfied. To determine the value of the objective function for the last time period within the target maintenance period, proceed to step S207 at this time. If it is determined in step S206 that t e - t0 < t, return to step S203. In step S207, output the optimal maintenance window period that optimizes the objective function and satisfies the constraint conditions.

[0045] By adopting the method for determining the optimal maintenance window period of a wind farm according to this example, an optimization objective function is established with the minimum loss of electricity sales benefit during the wind farm maintenance period as the goal. At the same time, considering constraint conditions such as extreme weather constraints, maintenance start time constraints, and maintenance continuity constraints, the economic efficiency, safety, and rationality during the maintenance period are taken into account when formulating the maintenance window period, which helps to improve the refined level of wind farm operation.

[0046] Figure 3 is a graph showing the loss of electricity sales benefit and the average predicted wind speed during the window period according to an embodiment of the present disclosure.

[0047] Next, the method for determining the optimal maintenance window period of a wind farm according to an embodiment of the present disclosure will be compared with the traditional method of determining the maintenance window period only based on the magnitude of the predicted wind speed. The following two experimental schemes are set. Scheme 1: According to the traditional method, only rely on the magnitude of the meteorological forecast wind speed to select the time period corresponding to the smaller wind speed interval as the maintenance window period. Among them, the magnitude of the predicted wind speed within the maintenance window period takes the average value of the predicted wind speeds during the period. Scheme 2: Adopt the method for determining the optimal maintenance window period of a wind farm according to an embodiment of the present disclosure.

[0048] In the example, taking a wind farm in Shanxi as an example, the power plant started formulating a maintenance window period with a maintenance duration of 10 hours within the next 7 days on April 2, 2023. Then the maintenance cycle is 7 days, with 15 minutes as a time period, a total of 672 time periods, and the maintenance window period duration is 10 hours, a total of 40 time periods. The specific maintenance information of the wind farm is shown in Table 1 below.

[0049] Table 1

[0050]

[0051] During the maintenance cycle from April 3, 2023 to April 9, 2023, through Figure 1 the processes and steps shown, a total of 237 feasible maintenance window periods can be obtained. Based on the predicted electricity price, predicted power, and maintenance capacity, the predicted loss of electricity sales benefit within each feasible maintenance window period can be calculated. Based on the actual electricity price and actual power, the actual loss of electricity sales benefit within each maintenance window period can be calculated a posteriori. The predicted loss of electricity sales benefit, the a posteriori actual loss of electricity sales benefit, and the average predicted wind speed curve within each feasible maintenance window period are asFigure 3 As shown, among them, the average predicted wind speed is calculated by taking the average value of the predicted wind speed magnitudes during the maintenance window period.

[0052] Figure 3 Each time point on the abscissa represents a maintenance window period with that time as the start time of maintenance. It can be seen that the differences in the actual electricity sales benefit losses during different maintenance window periods are very large. Among all feasible maintenance window periods, the maximum actual electricity sales benefit loss reaches 125,864.1 yuan, while the minimum actual electricity sales benefit loss is only 3,180.3 yuan.

[0053] In the case of adopting Scheme 1, the selected window period according to the minimum average predicted wind speed is [2023-04-07 07:00:00, 2023-04-07 17:00:00]. The average predicted wind speed within this window period is 4.18 m / s, and the corresponding posterior actual electricity sales benefit loss is 22,667.3 yuan. The optimal maintenance window period calculated by adopting Scheme 2 is [2023-04-06 07:00:00, 2023-04-06 17:00:00], and the posterior actual electricity sales benefit loss is 3,180.3 yuan. The statistical results of the two schemes are shown in Table 2 below.

[0054] Table 2

[0055]

[0056]

[0057] As can be seen from Table 2 above, the posterior actual electricity sales benefit loss in the case of adopting Scheme 1 is 22,667.3 yuan, and the posterior actual electricity sales benefit loss of the optimal maintenance window period calculated in the case of adopting Scheme 2 is 3,180.3 yuan. Compared with Scheme 1, the electricity sales loss can be reduced by 19,487 yuan. Thus, it can be seen that adopting the method for determining the optimal maintenance window period of a wind farm according to the exemplary embodiments of the present disclosure can significantly reduce the benefit loss of the wind farm during maintenance and improve the refined level of wind farm operation.

[0058] Figure 4 is a block diagram showing a device for determining the optimal maintenance window period of a wind farm according to the exemplary embodiments of the present disclosure.

[0059] As Figure 4As shown in the figure, the device 400 for determining the optimal maintenance window period of a wind farm includes: a data acquisition unit 401 that acquires electricity price prediction data and wind farm power generation prediction data during the target maintenance period of the wind farm; a target function determination unit 402 that divides the target maintenance period into multiple maintenance window periods and determines the value of the target function of the maintenance window period, where the target function is constructed based on the electricity price prediction data and the wind farm power generation prediction data; and an optimal maintenance window period determination unit 403 that determines the maintenance window period with the minimum value of the target function as the optimal maintenance window period of the wind farm.

[0060] In an example, the target function determination unit 402 is configured to: divide the maintenance window period into multiple time periods; based on the electricity price prediction data and the wind farm power generation prediction data, determine the predicted power of each wind turbine generator to be maintained in the wind farm during each of the multiple time periods and the predicted electricity price during each of the multiple time periods; and determine the value of the target function of the maintenance window period based on the total number of the multiple time periods, the number of wind turbine generators to be maintained, the predicted power during each time period, and the predicted electricity price during each time period.

[0061] In an example, the target function determination unit 402 is configured to: acquire extreme weather prediction data; in response to the maintenance window period not including the moments when extreme weather occurs, divide the maintenance window period into multiple time periods; based on the electricity price prediction data and the wind farm power generation prediction data, determine the predicted power of each wind turbine generator to be maintained in the wind farm during each of the multiple time periods and the predicted electricity price during each of the multiple time periods; and determine the value of the target function of the maintenance window period based on the total number of the multiple time periods, the number of wind turbine generators to be maintained, the predicted power during each time period, and the predicted electricity price during each time period.

[0062] In an example, the maintenance window period is an uninterrupted continuous time period.

[0063] In an example, the predicted power is the product of the predicted power of the wind farm during the corresponding time period and the ratio of the capacity of the corresponding wind turbine generator to the capacity of the wind farm.

[0064] In an example, the target function determination unit 402 is configured to: for each time period of the maintenance window period, determine the first function value of each wind turbine generator to be maintained, and determine the sum of the first function values of all the wind turbine generators to be maintained as the second function value, where the first function value of each wind turbine generator to be maintained is the product of the predicted power of the wind turbine generator during this time period, the predicted electricity price during this time period, and a predetermined coefficient; and determine the sum of the second function values of all the time periods as the value of the target function of the maintenance window period.

[0065] Combined aboveFigure 1 and Figure 2 The specific operations shown are respectively executed by corresponding units in the determining device 400 for the optimal maintenance window period of the wind farm shown in Figure 4 Here, the details of the specific operations will not be elaborated. By adopting the determining device for the optimal maintenance window period of the wind farm according to the exemplary embodiments of the present disclosure, the economic benefits, safety and rationality during the maintenance period can be taken into account when formulating the maintenance window period, which helps to improve the refined level of the operation of the wind farm.

[0066] Figure 5 is a block diagram showing a computing system including at least one computing device and at least one storage device storing instructions according to an exemplary embodiment of the present disclosure.

[0067] As Figure 5 shown, the computing system 500 provided according to the exemplary embodiment of the present invention includes a computing device 501 and a storage device 502. Computer-executable instructions are stored in the storage device 502. When the computer-executable instructions are executed by the computing device 501, the method for determining the optimal maintenance window period of the wind farm described in any of the foregoing embodiments is executed.

[0068] The computing device 501 is deployed in a server or a client, and can also be deployed on a node device in a distributed network environment. In addition, the computing device 501 can be a PC computer, a tablet device, a personal digital assistant, a smart phone, a web application or other devices capable of executing the above instruction set. Here, the computing device does not have to be a single computing device, and can also be a collection of any devices or circuits that can execute the above instructions (or instruction sets) alone or jointly. The computing device can also be a part of an integrated control system or a system manager, or can be configured to be interconnected with a portable electronic device locally or remotely (for example, via wireless transmission). In the computing device, the processor includes a central processing unit (CPU), a graphics processing unit (GPU), a programmable logic device, a dedicated processor system, a microcontroller or a microprocessor. By way of example and not limitation, the processor also includes an analog processor, a digital processor, a microprocessor, a multi-core processor, a processor array, a network processor, etc.

[0069] According to another aspect of the present disclosure, there is provided a computer-readable storage medium storing instructions, which, when executed by at least one computing device, cause the at least one computing device to execute the method for determining the optimal maintenance window period of a wind farm described in any of the foregoing embodiments. The computer-readable storage medium includes magnetic media such as floppy disks and magnetic tapes, optical media (including CD-ROMs and DVD-ROMs), magneto-optical media such as floppy optical disks, hardware devices such as ROMs and RAMs designed to store and execute program commands, and flash memories. The instructions may include language codes executable by a computer using an interpreter and machine language codes generated by a compiler.

[0070] By adopting the present disclosure, it is possible to help reduce the loss of electricity sales benefits during the maintenance of a wind farm and improve the safety and rationality of formulating the maintenance window period of the wind farm.

[0071] The processes, methods, or algorithms disclosed herein may be transmitted to or implemented by a processing device, a controller, or a computer, which may include any existing programmable electronic control unit or a dedicated electronic control unit. Similarly, the processes, methods, or algorithms may be stored in various forms as data and instructions executable by a controller or a computer, the various forms including but not limited to information being permanently stored on a non-writable storage medium (such as a ROM device) and information being variably stored on a writable storage medium (such as a floppy disk, a magnetic tape, a CD, a RAM device, and other magnetic and optical media). The processes, methods, or algorithms may also be implemented in a software-executable object. Optionally, the processes, methods, or algorithms may be implemented in whole or in part using suitable hardware components (such as ASICs, FPGAs, state machines, controllers, or other hardware components or devices) or a combination of hardware components, software components, and firmware components.

[0072] Although the present disclosure includes specific examples, it will be apparent to those of ordinary skill in the art that various changes in form and detail may be made in these examples without departing from the spirit and scope of the claims and their equivalents. The examples described herein are to be considered in a descriptive sense only and not for purposes of limitation. The description of each feature or aspect in an example is to be considered applicable to similar features or aspects in other examples. Suitable results may be obtained if the described techniques are performed in a different order, and / or if components in the described systems, architectures, devices, or circuits are combined in a different manner, and / or replaced or supplemented with other components or their equivalents. Accordingly, the scope of the present disclosure is not limited by the specific embodiments, but is defined by the claims and their equivalents, and all variations within the scope of the claims and their equivalents are to be construed as being included in the present disclosure.

Claims

1. A method for determining the optimal maintenance window period of a wind farm, characterized in that, The method for determining the optimal maintenance window period of the wind farm includes: Obtaining the electricity price prediction data and the wind farm power generation prediction data within the target maintenance period of the wind farm; Dividing the target maintenance period into multiple maintenance window periods, and determining the value of the objective function of the maintenance window period, wherein the objective function is constructed based on the electricity price prediction data and the wind farm power generation prediction data; Determining the maintenance window period with the minimum value of the objective function as the optimal maintenance window period of the wind farm.

2. The method for determining the optimal maintenance window period of a wind farm according to claim 1, wherein The step of determining the value of the objective function of the maintenance window period includes: Dividing the maintenance window period into multiple time periods; Based on the electricity price prediction data and the wind farm power generation prediction data, determining the predicted power of each wind turbine generator to be maintained in the wind farm in each of the multiple time periods and the predicted electricity price in each of the multiple time periods; Based on the total number of the multiple time periods, the number of wind turbine generators to be maintained, the predicted power, and the predicted electricity price, determining the value of the objective function of the maintenance window period.

3. The method for determining the optimal maintenance window period of a wind farm according to claim 1, wherein The step of determining the value of the objective function of the maintenance window period includes: Obtaining extreme weather prediction data; In response to the maintenance window period not including the time when extreme weather occurs, dividing the maintenance window period into multiple time periods; Based on the electricity price prediction data and the wind farm power generation prediction data, determining the predicted power of each wind turbine generator to be maintained in the wind farm in each of the multiple time periods and the predicted electricity price in each of the multiple time periods; Based on the total number of the multiple time periods, the number of wind turbine generators to be maintained, the predicted power, and the predicted electricity price, determining the value of the objective function of the maintenance window period.

4. The method for determining the optimal maintenance window period of a wind farm according to claim 2 or 3, characterized in that The maintenance window period is an uninterrupted continuous time period.

5. The method for determining the optimal maintenance window period of a wind farm according to claim 2 or 3, characterized in that The predicted power is the product of the predicted power of the wind farm in the corresponding time period and the ratio of the capacity of the corresponding wind turbine generator to the capacity of the wind farm.

6. The method for determining the optimal maintenance window period of a wind farm according to claim 2 or 3, characterized in that, The step of determining the value of the objective function of the maintenance window period includes: For each time period of the maintenance window period, determining the first function value of each wind turbine generator to be maintained, and determining the sum of the first function values of all the wind turbine generators to be maintained as the second function value, wherein the first function value of each wind turbine generator to be maintained is the product of the predicted power of the wind turbine generator in the time period, the predicted electricity price in the time period, and a predetermined coefficient; Determining the sum of the second function values of all the time periods as the value of the objective function of the maintenance window period.

7. A device for determining the optimal maintenance window period of a wind farm, characterized in that, The device for determining the optimal maintenance window period of the wind farm includes: A data acquisition unit, which acquires the electricity price prediction data and the wind farm power generation prediction data within the target maintenance period of the wind farm; An objective function determination unit, which divides the target maintenance period into multiple maintenance window periods and determines the value of the objective function of the maintenance window period, wherein the objective function is constructed based on the electricity price prediction data and the wind farm power generation prediction data; The optimal maintenance window determination unit determines the maintenance window with the minimum value of the objective function as the optimal maintenance window of the wind farm.

8. A computing system comprising at least one computing device and at least one storage device storing instructions, characterized in that, When the instruction is run by the at least one computing device, it causes the at least one computing device to execute the method for determining the optimal maintenance window of the wind farm according to any one of claims 1-6.

9. A computer-readable storage medium storing instructions, characterized in that, When the instruction is run by at least one computing device, it causes the at least one computing device to execute the method for determining the optimal maintenance window of the wind farm according to any one of claims 1-6.

Images