Wind power plant electric quantity calculation method and device, computer equipment and storage medium

Abstract

The invention relates to the field of wind power generation, and discloses a wind power plant electric quantity calculation method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining a power generation income change matrix and resource data of a wind power plant in a preset time period; processing the resource data according to a division rule of the power generation income change matrix to obtain a plurality of resource data items; and calculating the effective generating capacity of the wind power plant based on the power generation income change matrix and the resource data items. The method solves the problem that the existing fan arrangement optimization technology only aims at maximizing the total generating capacity of the wind power plant and does not consider the generating capacity difference in different time periods caused by generating income fluctuation, so that the optimal layout of the wind power plant cannot be realized.

Description

Technical Field

[0001] This invention relates to the field of wind power generation, specifically to a method, apparatus, computer equipment, and storage medium for calculating the power output of a wind farm. Background Technology

[0002] As the global energy structure transitions towards cleaner and lower-carbon energy, wind power, as a crucial component of the new energy sector, has become a key driver of the energy revolution through its large-scale development and efficient utilization. Optimizing wind turbine layout is a core aspect of wind farm planning and design, directly determining the power generation level, operational efficiency, and overall profitability of the wind farm. Accurate wake assessment and scientific layout strategies are essential for achieving this goal. The marketization of the new energy industry is an inevitable trend, meaning that wind power revenue will no longer be constant but will fluctuate dynamically based on factors such as power platform supply and demand and periodic load characteristics. This results in significant differences in the economic value of wind farm power generation at different times, posing new challenges to the traditional planning logic centered on power generation.

[0003] Existing wind turbine layout optimization technologies are all based on the premise that wind farm power generation revenue is constant, assuming that the power generated by a wind farm has the same economic value at any given time. However, in the context of platform-based wind power generation revenue, this technical approach does not incorporate revenue fluctuation factors into the optimization objective system. This leads to a situation where, even if power generation is maximized, the mismatch between high-generation periods and low-generation periods may prevent the wind farm from achieving optimal overall revenue. Furthermore, the neglect of power generation contribution in existing methods causes the optimization results to be out of touch with the actual needs of the current environment, making it difficult to support the efficiency decisions of wind farms and hindering their development. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a method, apparatus, computer equipment and storage medium for calculating wind farm power generation, in order to solve the problem that existing wind turbine layout optimization technologies only aim to maximize the total power generation of the wind farm, without considering the differences in power generation at different times caused by fluctuations in power generation revenue, thus failing to achieve the optimal wind farm layout.

[0005] In a first aspect, embodiments of the present invention provide a method for calculating the power generation of a wind farm, the method comprising: Obtain the power generation revenue change matrix and resource data of the wind farm within a preset time period; The resource data is processed according to the partitioning rules of the power generation revenue change matrix to obtain multiple resource data items; The effective power generation of the wind farm is calculated based on the power generation revenue change matrix and the resource data items.

[0006] Furthermore, obtaining the power generation revenue change matrix of the wind farm within a preset time period includes: Obtain the power generation revenue fluctuation data of the wind farm within a preset time period; The power generation revenue fluctuation data is divided into multiple interval fluctuation data according to a preset time interval; The average revenue for different periods within each time unit is calculated based on the aforementioned interval fluctuation data, and a power generation revenue change matrix is ​​constructed using the average revenue for different periods within each time unit.

[0007] Furthermore, the resource data is processed according to the partitioning rules of the power generation revenue change matrix to obtain multiple resource data items, including: Extract the preset time interval from the division rules; The resource data is divided into multiple interval resource data according to the preset time interval; Extract the time period resource data for each time unit in the interval resource data, and use the time period resource data to generate the corresponding resource data item.

[0008] Furthermore, the calculation of the effective power generation of the wind farm based on the power generation revenue change matrix and the resource data items includes: Calculate the power generation of the wind farm under each of the resource data items; A power generation matrix is ​​constructed using the power generation under each of the resource data items, and the effective power generation of the wind farm is determined based on the power generation revenue change matrix and the power generation matrix.

[0009] Furthermore, calculating the power generation of the wind farm under each of the resource data items includes: Obtain the current wind turbine layout strategy of the wind farm, wherein the current wind turbine layout strategy includes the initial position coordinates and initial configuration parameters of each wind turbine; The power generation corresponding to each resource data item is calculated based on the resource data item, the current wind turbine layout strategy, and the preset wake model.

[0010] Furthermore, determining the effective power generation of the wind farm based on the power generation revenue change matrix and the power generation matrix includes: Based on the power generation revenue change matrix and the power generation matrix, calculate the contribution value corresponding to each time unit in different time intervals; The contribution values ​​corresponding to each time unit in different time intervals are summed to obtain the sum of contributions; The contribution and value are taken as the effective power generation of the wind farm.

[0011] Furthermore, after calculating the effective power generation of the wind farm based on the power generation revenue change matrix and the resource data items, the method further includes: Detect whether the effective power generation meets the preset optimization conditions; If the preset optimization conditions are not met, the placement coordinates of the wind turbines in the current wind turbine layout strategy are adjusted to obtain a candidate wind turbine layout strategy. The effective power generation calculation and placement coordinate adjustment operations are iteratively executed until the candidate effective power generation corresponding to the candidate wind turbine layout strategy meets the preset optimization conditions. Then, the candidate wind turbine layout strategy is taken as the target wind turbine layout strategy. Alternatively, if preset optimization conditions are met, the current wind turbine layout strategy of the wind farm will be used as the target wind turbine layout strategy.

[0012] Secondly, embodiments of the present invention provide a wind farm power calculation device, the device comprising: The acquisition module is used to acquire the power generation revenue change matrix and resource data of the wind farm within a preset time period; The processing module is used to process the resource data according to the partitioning rules of the power generation revenue change matrix to obtain multiple resource data items; The calculation module is used to calculate the effective power generation of the wind farm based on the power generation revenue change matrix and the resource data items.

[0013] Thirdly, embodiments of the present invention provide a computer device, including: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the method described in the first aspect or any corresponding embodiment thereof.

[0014] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing computer instructions for causing a computer to perform the method described in the first aspect or any corresponding embodiment thereof.

[0015] The method provided in this application has the following beneficial effects: The method provided in this application lays a precise data foundation for subsequent calculations by acquiring a power generation revenue change matrix and resource data within a preset time period, ensuring that the data is highly compatible with the time and revenue dimensions of the actual operation of the wind farm. By processing the resource data according to the power generation revenue change matrix segmentation rules, multiple resource data items are obtained, achieving dimensional alignment between the resource data and the revenue matrix. This avoids calculation deviations caused by data fragmentation and allows the detailed dimensions of the resource data to accurately match the revenue change patterns. The method calculates the effective power generation based on both, deeply integrating revenue change characteristics with resource conditions. This breaks away from the limitations of traditional general calculation methods, enabling the calculation results of effective power generation to reflect both the actual resource supply and the revenue fluctuation patterns. This significantly improves the accuracy and relevance of the calculation of effective power generation in wind farms, providing a reliable quantitative basis for wind farm operation optimization, revenue forecasting, and resource allocation. Attached Figure Description

[0016] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0017] Figure 1 This is a flowchart illustrating the wind farm power calculation method according to an embodiment of the present invention; Figure 2 This is a schematic diagram illustrating the distribution of power generation revenue over a time interval according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the time variation curve of power generation revenue within a time unit according to an embodiment of the present invention; Figure 4 This is a flowchart illustrating another wind farm power calculation method according to an embodiment of the present invention; Figure 5 This is a structural block diagram of a wind farm power calculation device according to an embodiment of the present invention; Figure 6 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] According to embodiments of the present invention, a method, apparatus, computer equipment, and storage medium for calculating the power of a wind farm are provided. It should be noted that the steps shown in the flowcharts in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowcharts, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0020] This embodiment provides a method for calculating the power generation of a wind farm. Figure 1 This is a flowchart of a wind farm power calculation method according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps: Step S101: Obtain the power generation revenue change matrix and resource data of the wind farm within a preset time period.

[0021] In this embodiment, firstly, the power generation revenue fluctuation data of the wind farm within a preset time period (e.g., one year) is obtained. Power generation revenue can refer to the real-time revenue of the power platform, and its fluctuation data is the historical revenue sequence. Next, the power generation revenue fluctuation data is divided into multiple interval fluctuation data according to a preset time interval (e.g., four quarters), and each interval can be one quarter. Then, based on the fluctuation data of each interval, the average power generation revenue of each smaller time period (e.g., dividing a day into N hours) within different time units (e.g., each day) is further calculated to capture intraday variation patterns. Finally, a multidimensional power generation revenue variation matrix is ​​constructed using the average power generation revenue of different time periods within all these time units. The rows of this matrix typically represent different time units, the columns represent different intraday time periods, and the matrix elements are the normalized average power generation revenue of the corresponding time period.

[0022] In addition to the aforementioned examples of quarterly and fixed-hourly segmentation, dynamic time windows can be used instead of fixed quarterly divisions. For instance, clustering algorithms (such as K-means) can be used to identify multiple time periods with similar price characteristics based on historical revenue fluctuations. When constructing the matrix, in addition to the average value, other statistical characteristics of power generation revenue data (such as standard deviation and quantiles) can be introduced to build a richer matrix to characterize price uncertainty. The division of preset time intervals can also be customized based on the specific revenue cycle or electricity demand characteristics of the local wind farm, rather than natural quarters (such as flood season / dry season).

[0023] Step S102: Process the resource data according to the division rules of the power generation revenue change matrix to obtain multiple resource data items.

[0024] In this embodiment, the division rules for the power generation revenue change matrix are first extracted. These rules are defined by a preset time interval (one quarter) and time periods (every N hours) within a time unit (one day). Next, the acquired raw wind resource data for one year (including wind speed, wind direction, etc.) is divided into multiple interval resource data according to the same preset time interval (i.e., four quarters). Then, for the interval resource data of each quarter, time period resource data (every N hours) within each time unit (one day) is further extracted. Finally, corresponding resource data items are generated using these time period resource data. Each resource data item represents the wind resource status of a specific N-hour period within a specific quarter and a specific day, thereby ensuring that the temporal division of wind resource data is completely consistent with the structure of the power generation revenue change matrix, providing a basis for subsequent calculation of value-weighted power generation.

[0025] In addition to the above-mentioned implementation with fixed quarterly and hourly intervals, the preset time intervals in the division rules may not be based on natural quarters, but rather on the seasonal characteristics of wind resources themselves (such as strong wind seasons and weak wind seasons). The time period length N may also be variable, dynamically adjusted according to the intensity of price fluctuations in the power generation revenue change matrix. For example, a smaller N value (shorter time period) can be used to obtain higher resolution during periods of high price fluctuations. When generating resource data items, the original observation values ​​may not be used directly. Instead, the statistical characteristics (such as mean and Weibull distribution parameters) of the resource data within each time period can be calculated to generate more representative data items.

[0026] Step S103: Calculate the effective power generation of the wind farm based on the power generation revenue change matrix and resource data items.

[0027] In this embodiment, firstly, for each resource data item (representing wind conditions during a specific N-hour period in a specific quarter or day), based on the current wind turbine layout strategy (including turbine location coordinates and configuration parameters) and a preset wake model, the power generation of the wind farm under that resource data item is calculated, forming a power generation matrix that completely corresponds to the power generation revenue change matrix structure. Then, based on the power generation revenue change matrix (a normalized matrix representing power revenue in different time periods) and the power generation matrix, the contribution value of each time unit (day) in each time interval (quarter) is calculated for different time periods (every N hours). This contribution value is the product of the power generation for the corresponding time period and its power generation revenue (normalized revenue). Finally, the contribution values ​​for all time periods in all time units across all time intervals are summed to obtain the sum of contributions, which is the effective power generation of the wind farm. This effective power generation comprehensively considers the differences in market value of power generation in different time periods, reflecting the actual revenue potential of the wind farm in the electricity market environment.

[0028] In addition to the above-mentioned embodiment of directly multiplying and summing power generation and revenue, a weighting coefficient can be introduced when calculating the contribution value to amplify the contribution of specific high-price periods or periods with high power generation potential, thereby optimizing the layout more accurately. Furthermore, a threshold can be set based on the power generation revenue distribution (such as variance) in the power generation revenue change matrix, calculating the contribution only for high-value periods where revenue exceeds a specific threshold, ignoring low-value periods. The contribution value can be calculated not using simple arithmetic multiplication, but rather using net revenue considering wind farm operating costs, making the effective power generation more closely reflect actual economic benefits.

[0029] In this embodiment of the application, obtaining the power generation revenue change matrix of a wind farm within a preset time period includes the following steps A1-A4: Step A1: Obtain data on the fluctuation of power generation revenue of the wind farm within a preset time period.

[0030] Specifically, historical power generation revenue data for the wind farm's location within a preset time period (usually more than one year) is obtained from power platforms or relevant management agencies. This data constitutes power generation revenue fluctuation data, reflecting the raw sequence of power generation revenue changes over time. This data may include timestamps and corresponding power generation revenues, with a time resolution typically at the hourly level or higher to ensure accurate capture of the intraday power generation revenue fluctuation characteristics of the power platform. The acquired data needs to be preprocessed, including data cleaning (handling missing values ​​and outliers), format standardization, and chronological arrangement, laying the foundation for subsequent time interval division and revenue average calculation. In addition to the above-mentioned embodiment of directly obtaining historical data from the power market trading platform, when complete historical data is lacking, synthetic power generation revenue fluctuation data conforming to power laws can be generated using power simulation models. Based on the acquired historical data, weather forecast data (such as temperature and load forecasts) can also be introduced as an aid to interpret and enhance the raw power generation revenue fluctuation data.

[0031] Step A2: Divide the power generation revenue fluctuation data into multiple interval fluctuation data according to the preset time interval.

[0032] Specifically, the acquired power generation revenue fluctuation data (i.e., historical revenue series) is divided into four corresponding interval fluctuation datasets according to preset time intervals (four quarters). Based on seasonal time division rules (spring March-May, summer June-August, autumn September-November, winter December, and the following year January-February), the original power generation revenue fluctuation data is categorized into these four time intervals, with each interval containing power generation revenue data for all periods within that quarter. This division ensures that subsequent analysis can capture the seasonal characteristics of power platform power generation revenue, providing a data foundation for constructing a power generation revenue change matrix that reflects the patterns of power generation revenue in different quarters.

[0033] As an example, such as Figure 2 As shown, the horizontal axis is set with 24 hours per day, and the vertical axis is set with the first, second, and third time intervals (which can correspond to seasonality or custom time period groupings). Three textured color blocks are used to identify peak, off-peak, and off-peak power generation revenue, respectively. Within different time intervals, the duration and distribution of peak (dark texture), off-peak (medium texture), and off-peak (light texture) revenue differ. For example, in one time interval, peak revenue is concentrated between 2 PM and 10 PM, while in another interval it may expand or contract; off-peak and off-peak revenue also exhibit unique time period proportions based on the interval. The segmented interval fluctuation data is transformed into the distribution characteristics of revenue types for each time period, providing an intuitive data mapping for subsequent analysis of power generation revenue patterns in different time intervals (such as revenue fluctuation patterns within seasons or time period groups).

[0034] Step A3: Calculate the average revenue for different periods in each time unit based on the interval fluctuation data, and construct a power generation revenue change matrix using the average revenue for different periods in each time unit.

[0035] It should be noted that, as Figure 3 As shown, the power generation revenue varies with time (0-24 hours) within a certain time unit (e.g., one day), with the vertical axis representing the power generation revenue data. There are significant fluctuations in power generation revenue at different times: power generation revenue drops to a lower level from noon to afternoon (approximately 10-16:00), while power generation revenue climbs to a peak from evening to night (approximately 16-20:00).

[0036] Specifically, for each interval of fluctuation data obtained, further refinement is performed according to time units and time periods to construct a power generation revenue change matrix. For example, for all days within each quarter, each day is divided into multiple consecutive N-hour time periods, and then the average power generation revenue for all days within each same time period (such as 1-hour periods, 2-hour periods, etc.) is calculated. For example, when N=6, the average power generation revenue for each day in each quarter is calculated for the four time periods: 0-6:00, 6-12:00, 12-18:00, and 18-24:00, thus obtaining an average value matrix reflecting the typical power generation revenue level for each time period in that quarter. The highest power generation revenue is determined from the average value matrix, and the average value matrix is ​​normalized using the highest power generation revenue to obtain the power generation revenue change matrix.

[0037] As an example, within a full year, the fluctuation data of power generation revenue is divided into seasonal variations. portions, usually =4, corresponding to the revenue fluctuations of the four quarters: spring (March-May), summer (June-August), autumn (September-November), and winter (December, January, February). For each quarter, the average revenue per N hours on a complete day is calculated to form an average matrix of power generation revenue within the day. ,in , Determine the highest power generation revenue from the average value matrix. Construct a normalized matrix of power generation revenue changes, i.e., the power generation revenue change matrix. .

[0038] When calculating the average value, abnormal power generation revenue that is significantly outside the reasonable range can be removed first to improve data quality. At the same time, other statistical characteristics of power generation revenue (such as standard deviation, maximum value, and minimum value) can be calculated and included in subsequent analysis.

[0039] In this embodiment of the application, the resource data is processed according to the partitioning rules of the power generation revenue change matrix to obtain multiple resource data items, including the following steps B1-B3: Step B1: Extract the preset time interval from the division rules.

[0040] Specifically, the time dimension structure is parsed from the constructed power generation revenue change matrix, and the pre-defined time intervals used to organize the matrix are extracted. The row dimension of the power generation revenue change matrix typically corresponds to different time intervals (e.g., four quarters), and the column dimension corresponds to different time periods (e.g., every N hours). By reading the row index or related metadata of the matrix, the specific start and end times of these pre-defined time intervals are extracted (e.g., first quarter: March-May, second quarter: June-August, etc.), thereby obtaining a time division rule completely consistent with the power generation revenue change matrix, providing a basis for subsequent synchronous division of wind resource data.

[0041] Step B2: Divide the resource data into multiple interval resource data according to the preset time interval.

[0042] Specifically, the acquired one-year raw wind resource data (including wind speed, wind direction, temperature, air pressure, etc.) is divided into four corresponding interval resource datasets according to preset time intervals (four quarters) extracted from the power generation revenue change matrix. For example, based on the quarterly division rules (spring March-May, summer June-August, autumn September-November, winter December, and the following year January-February), the complete year's wind resource data is categorized into these four time intervals by timestamp, with each interval containing raw wind resource observation data for all periods within that quarter. This division ensures that the temporal structure of the wind resource data is completely consistent with the power generation revenue change matrix, laying the foundation for subsequent generation of resource data items corresponding to each time period.

[0043] Step B3: Extract the time period resource data for each time unit in the interval resource data, and use the time period resource data to generate the corresponding resource data item.

[0044] Specifically, the resource data for each interval is further refined according to time units and time periods. For example, for all days within each quarterly interval, each day is divided into multiple consecutive N-hour time periods. Then, the corresponding wind resource data (including parameters such as wind speed and wind direction) is extracted for each time period, and these time period resource data are used to generate the final corresponding resource data items. For example, when N=6, resource data items for four time periods are generated each day: 0-6:00, 6-12:00, 12-18:00, and 18-24:00. Each resource data item contains typical characteristic values ​​of wind resources within that time period, thus forming multiple resource data items that completely correspond to the power generation revenue change matrix.

[0045] As an example, wind measurement equipment such as wind measurement towers and lidar are used to acquire local wind resource data for wind farms, including key parameters such as wind speed, wind direction, temperature, and air pressure, with a data duration of one full year. Based on the power generation revenue change matrix, the wind resource data for one full year is divided into M parts according to seasonal variations. For the wind resource data of each quarter, the wind resource data for each N hours of the day is calculated, that is, each wind resource data item is divided into 24 / N daily wind resource data items. Through the above processing, the wind resource data for one full year is divided into P resource data items, where... Resource data items express.

[0046] In this embodiment of the application, the effective power generation of the wind farm is calculated based on the power generation revenue change matrix and resource data items, including the following steps C1-C2: Step C1: Calculate the power generation of the wind farm under each resource data item.

[0047] In this embodiment of the application, calculating the power generation of a wind farm under each resource data item includes: obtaining the current wind turbine layout strategy of the wind farm, wherein the current wind turbine layout strategy includes the initial position coordinates and initial configuration parameters of each wind turbine; and calculating the power generation corresponding to each resource data item based on the resource data item, the current wind turbine layout strategy and the preset wake model.

[0048] Specifically, the current wind turbine layout strategy of the wind farm is first obtained, including the initial position coordinates (plane x, y coordinates and altitude) and initial configuration parameters (rotor diameter, hub height, power curve, thrust coefficient curve, etc.) of each turbine. Then, for each resource data item (representing the wind condition characteristics of a specific quarter or a specific N-hour period on a specific day), the total power generation of the wind farm under the specific wind resource conditions is calculated by combining the current wind turbine layout strategy and a preset wake model (such as the Jensen model, Larsen model, and other commonly used engineering models). The specific calculation process includes: based on the wind speed, wind direction, and other parameters in the resource data item, considering the wake effect between turbines, the actual wind acquisition efficiency of each turbine under the incoming wind conditions is calculated iteratively; then, the power generation of each turbine is calculated based on the power curve of the turbine; finally, the total power generation of the entire wind farm under the specific resource data item is obtained.

[0049] Step C2: Construct a power generation matrix using the power generation under each resource data item, and determine the effective power generation of the wind farm based on the power generation revenue change matrix and the power generation matrix.

[0050] In this embodiment of the application, determining the effective power generation of a wind farm based on the power generation revenue change matrix and the power generation matrix includes: calculating the contribution value corresponding to each time unit in different time intervals based on the power generation revenue change matrix and the power generation matrix; summing the contribution values ​​corresponding to each time unit in different time intervals to obtain the contribution sum value; and using the contribution sum value as the effective power generation of the wind farm.

[0051] Specifically, firstly, the calculated power generation under each resource data item is organized according to the same dimensional structure as the power generation revenue change matrix to construct a power generation matrix. The rows of this matrix correspond to different time intervals (quarters), and the columns correspond to different time periods (every N hours). Each element represents the typical power generation of a specific time period in a specific quarter. Then, based on the power generation revenue change matrix (containing the normalized power generation revenue of each time period) and the power generation matrix, the contribution value corresponding to each time unit (day) in different time intervals is calculated. The specific calculation method is to multiply the power generation of each time period by the corresponding power generation revenue (i.e., value weighting). Next, the contribution values ​​of all time periods in all time units of all time intervals are summed to obtain the contribution sum value. Finally, this contribution sum value is taken as the effective power generation of the wind farm. This value reflects the actual value of wind farm power generation in the context of considering the fluctuation of power platform power generation revenue.

[0052] As an example, based on the wind turbine deployment coordinates and turbine parameters, the power generation of the wind farm under each resource data item is calculated using the wake model. The calculation formula is as follows:

[0053] In the formula, For resource data items Electricity generation under certain conditions; This is a function for calculating power generation. For the wake model; The coordinates for the placement of each wind turbine in the wind farm; For configuration parameters; T is the time dimension parameter for the resource data item.

[0054] Given fluctuations in power generation revenue, the revenue corresponding to power generation varies at different times; therefore, effective power generation is defined. This parameter is used to account for the impact of fluctuations in power generation revenue. The effective power generation of a wind farm is calculated using the following formula:

[0055] Where i is the preset time interval. j represents the time period. ; For resource data items Electricity generation under certain conditions; It is an average matrix; To maximize electricity generation revenue; This is the matrix showing the change in power generation revenue.

[0056] In this embodiment of the application, after calculating the effective power generation of the wind farm based on the power generation revenue change matrix and resource data items, the method further includes: Step S201: Detect whether the effective power generation meets the preset optimization conditions.

[0057] In this embodiment, the preset optimization condition can be set to the effective power generation reaching its maximum value or a convergence state. For example, this can be determined by comparing the improvement rate of the current effective power generation with historical iteration values ​​(e.g., an improvement rate less than 1%), or by checking whether the number of iterations exceeds a preset upper limit (e.g., 100 times). Furthermore, the optimization condition can also be based on economic benefit objectives, such as the revenue corresponding to the effective power generation exceeding a certain threshold. Specifically, the system stores the effective power generation value for each iteration and automatically detects it using the termination conditions of optimization algorithms (e.g., gradient descent or genetic algorithms). In implementation, the system stores the effective power generation value for each iteration and automatically detects it using the termination conditions of optimization algorithms (e.g., gradient descent or genetic algorithms).

[0058] In addition, the preset optimization conditions can also be multi-objective optimization conditions (considering both power generation and construction costs), dynamic conditions (adjusted in real time according to power generation revenue), or prediction conditions based on machine learning models (using historical data to train the model to predict the optimal value), thereby enhancing the flexibility and adaptability of optimization.

[0059] In step S202, if the preset optimization conditions are not met, the placement coordinates of the wind turbines in the current wind turbine layout strategy are adjusted to obtain candidate wind turbine layout strategies. The effective power generation calculation and placement coordinate adjustment operations are iteratively executed until the candidate effective power generation corresponding to the candidate wind turbine layout strategy meets the preset optimization conditions. Then, the candidate wind turbine layout strategy is taken as the target wind turbine layout strategy.

[0060] In this embodiment, the system first generates one or more adjustment schemes for the current wind turbine deployment coordinates based on a specific optimization algorithm (such as genetic algorithm, particle swarm optimization, simulated annealing, etc.). This adjustment is not arbitrary, but rather a targeted search driven by the algorithm: the optimization algorithm uses the wind turbine coordinates as decision variables, takes maximizing effective power generation as the objective function, and calculates a new set of coordinate values ​​under constraints such as wind farm boundary conditions and minimum wind turbine spacing, thereby forming a candidate wind turbine layout strategy.

[0061] Next, the candidate strategy is substituted into the previous calculation process for iterative execution. It is indicated that the wake loss and power generation under each resource data item need to be recalculated for the new layout, and finally, the candidate effective power generation corresponding to the candidate layout is obtained by weighted summation with the power generation revenue change matrix. This cycle of calculation, evaluation, and adjustment continues. In each iteration, the optimization algorithm intelligently explores and develops the search space based on the performance of historical candidate schemes (i.e., their effective power generation values), thereby generating a better coordinate adjustment scheme for the next generation. The preset optimization conditions for iteration termination are usually: the increase in candidate effective power generation is less than a certain preset threshold, indicating that the algorithm has difficulty finding a better solution, or has reached the upper limit of the number of iterations, or the candidate effective power generation has reached a preset target value. Once any preset optimization condition is met, the loop terminates, and the currently evaluated optimal candidate wind turbine layout strategy is output as the final target wind turbine layout strategy.

[0062] When adjusting deployment coordinates, gradient descent or other local search algorithms can be used to guide the adjustment direction by calculating the partial derivative of effective power generation with respect to the coordinates. Furthermore, the adjustment operation can be combined with machine learning models, such as using reinforcement learning agents to learn the optimal deployment strategy, reducing the number of iterations.

[0063] Step S203: If the preset optimization conditions are met, the current wind turbine layout strategy of the wind farm is taken as the target wind turbine layout strategy.

[0064] In this embodiment, if the effective power generation corresponding to the current wind turbine layout strategy is detected to meet the preset optimization conditions, the current strategy is directly determined as the final target wind turbine layout strategy. This step is the termination point of the optimization process, and its core is to confirm that the current layout has achieved the expected goal and no further adjustment is needed. In implementation, the wind turbine coordinates and parameters of the current layout are locked as the optimal solution, and the solution is output for wind farm construction. In addition, a real-time monitoring mechanism can be introduced in this state to dynamically verify the current wind turbine layout strategy with real-time power generation revenue fluctuation data to ensure its robustness in different scenarios; or a third-party optimization algorithm library can be integrated to verify the feasibility of the final strategy and eliminate local optima; furthermore, the target strategy that meets the conditions can be automatically entered into the wind farm management system as the benchmark configuration for subsequent expansion or renovation.

[0065] Specifically, such as Figure 4 As shown, the wind farm turbine layout optimization process includes: First, acquiring power generation revenue fluctuation data for a preset time period of the wind farm and constructing a normalized power generation revenue fluctuation matrix; then, according to the partitioning rules of the matrix, acquiring wind resource data for the same time period and dividing it into several resource data items; next, for each resource data item, calculating the wake effect and power generation of the wind farm, and then summing them to obtain the effective power generation of the wind farm; by judging whether the effective power generation meets the preset optimization conditions, if it does, directly determining the target turbine layout strategy of the wind farm; if it does not meet the conditions, adjusting the turbine placement coordinates, and re-calculating the wake effect, power generation, and effective power generation until the effective power generation meets the preset optimization conditions.

[0066] This embodiment also provides a wind farm power calculation device, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0067] This embodiment provides a wind farm power calculation device, such as... Figure 5 As shown, it includes: The acquisition module 51 is used to acquire the power generation revenue change matrix and resource data of the wind farm within a preset time period; Processing module 52 is used to process resource data according to the division rules of the power generation revenue change matrix to obtain multiple resource data items; Calculation module 53 is used to calculate the effective power generation of the wind farm based on the power generation revenue change matrix and resource data items.

[0068] Furthermore, the acquisition module 51 is used to acquire power generation revenue fluctuation data of the wind farm within a preset time period; divide the power generation revenue fluctuation data into multiple interval fluctuation data according to the preset time interval; calculate the average revenue of different periods in each time unit based on the interval fluctuation data, and construct a power generation revenue change matrix using the average revenue of different periods in each time unit.

[0069] Furthermore, the processing module 52 is used to extract the preset time interval in the division rules; divide the resource data into multiple interval resource data according to the preset time interval; extract the time period resource data of each time unit in the interval resource data, and generate the corresponding resource data item using the time period resource data.

[0070] Furthermore, the computing module 53 includes: The calculation submodule is used to calculate the power generation of the wind farm under each resource data item; The construction submodule is used to build a power generation matrix using the power generation under each resource data item, and to determine the effective power generation of the wind farm based on the power generation revenue change matrix and the power generation matrix.

[0071] Furthermore, the calculation submodule is used to obtain the current wind turbine layout strategy of the wind farm, wherein the current wind turbine layout strategy includes the initial position coordinates and initial configuration parameters of each wind turbine; and calculates the power generation corresponding to each resource data item based on the resource data items, the current wind turbine layout strategy and the preset wake model.

[0072] Furthermore, a submodule is constructed to calculate the contribution value corresponding to each time unit in different time intervals based on the power generation revenue change matrix and the power generation matrix; the contribution values ​​corresponding to each time unit in different time intervals are summed to obtain the contribution sum value; and the contribution sum value is used as the effective power generation of the wind farm.

[0073] Furthermore, the device also includes: a detection module, used to detect whether the effective power generation meets the preset optimization conditions; if the preset optimization conditions are not met, the placement coordinates of the wind turbines in the current wind turbine layout strategy are adjusted to obtain a candidate wind turbine layout strategy, and the effective power generation calculation and placement coordinate adjustment operations are iteratively executed until the candidate effective power generation corresponding to the candidate wind turbine layout strategy meets the preset optimization conditions, then the candidate wind turbine layout strategy is used as the target wind turbine layout strategy; or, if the preset optimization conditions are met, the current wind turbine layout strategy of the wind farm is used as the target wind turbine layout strategy.

[0074] Please see Figure 6 , Figure 6 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 6As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system).

[0075] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0076] The memory 20 stores instructions executable by at least one processor 10 to cause at least one processor 10 to perform the method shown in the above embodiments.

[0077] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device as shown by a landing page for an app. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, which can be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0078] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0079] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.

[0080] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0081] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for calculating the power output of a wind farm, characterized in that, The method includes: Obtain the power generation revenue change matrix and resource data of the wind farm within a preset time period; The resource data is processed according to the partitioning rules of the power generation revenue change matrix to obtain multiple resource data items; The effective power generation of the wind farm is calculated based on the power generation revenue change matrix and the resource data items.

2. The method according to claim 1, characterized in that, The process of obtaining the power generation revenue change matrix of a wind farm within a preset time period includes: Obtain the power generation revenue fluctuation data of the wind farm within a preset time period; The power generation revenue fluctuation data is divided into multiple interval fluctuation data according to a preset time interval; The average revenue for different periods within each time unit is calculated based on the aforementioned interval fluctuation data, and a power generation revenue change matrix is ​​constructed using the average revenue for different periods within each time unit.

3. The method according to claim 1, characterized in that, The resource data is processed according to the partitioning rules of the power generation revenue change matrix to obtain multiple resource data items, including: Extract the preset time interval from the division rules; The resource data is divided into multiple interval resource data according to the preset time interval; Extract the time period resource data for each time unit in the interval resource data, and use the time period resource data to generate the corresponding resource data item.

4. The method according to claim 1, characterized in that, The calculation of the effective power generation of the wind farm based on the power generation revenue change matrix and the resource data items includes: Calculate the power generation of the wind farm under each of the resource data items; A power generation matrix is ​​constructed using the power generation under each of the resource data items, and the effective power generation of the wind farm is determined based on the power generation revenue change matrix and the power generation matrix.

5. The method according to claim 4, characterized in that, The calculation of the power generation of the wind farm under each of the resource data items includes: Obtain the current wind turbine layout strategy of the wind farm, wherein the current wind turbine layout strategy includes the initial position coordinates and initial configuration parameters of each wind turbine; The power generation corresponding to each resource data item is calculated based on the resource data item, the current wind turbine layout strategy, and the preset wake model.

6. The method according to claim 4, characterized in that, Determining the effective power generation of the wind farm based on the power generation revenue change matrix and the power generation matrix includes: Based on the power generation revenue change matrix and the power generation matrix, calculate the contribution value corresponding to each time unit in different time intervals; The contribution values ​​corresponding to each time unit in different time intervals are summed to obtain the sum of contributions; The contribution and value are taken as the effective power generation of the wind farm.

7. The method according to claim 5, characterized in that, After calculating the effective power generation of the wind farm based on the power generation revenue change matrix and the resource data items, the method further includes: Detect whether the effective power generation meets the preset optimization conditions; If the preset optimization conditions are not met, the placement coordinates of the wind turbines in the current wind turbine layout strategy are adjusted to obtain a candidate wind turbine layout strategy. The effective power generation calculation and placement coordinate adjustment operations are iteratively executed until the candidate effective power generation corresponding to the candidate wind turbine layout strategy meets the preset optimization conditions. Then, the candidate wind turbine layout strategy is taken as the target wind turbine layout strategy. Alternatively, if preset optimization conditions are met, the current wind turbine layout strategy of the wind farm will be used as the target wind turbine layout strategy.

8. A wind farm power calculation device, characterized in that, The device includes: The acquisition module is used to acquire the power generation revenue change matrix and resource data of the wind farm within a preset time period; The processing module is used to process the resource data according to the partitioning rules of the power generation revenue change matrix to obtain multiple resource data items; The calculation module is used to calculate the effective power generation of the wind farm based on the power generation revenue change matrix and the resource data items.

9. A computer device, characterized in that, include: A memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, the processor executing the computer instructions to perform the method of any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the method of any one of claims 1 to 7.

Images