Wind power station efficiency prediction method based on LightGBM and related device

Abstract

The invention discloses a LightGBM-based wind power plant efficiency prediction method and a related device. The method comprises the steps of obtaining meteorological data and auxiliary features of a current wind power plant; the meteorological data and the auxiliary features of the current wind power plant are input into a trained wind power plant power generation efficiency prediction model, the power generation efficiency of the wind power plant is predicted, and the wind power plant power generation efficiency prediction model is constructed based on LightGBM. The method and the related device can accurately predict the power generation efficiency of the wind power plant.

Description

Technical Field

[0001] The present invention belongs to the technical field of wind power generation, and relates to a wind farm efficiency prediction method based on LightGBM and related devices. Background Art

[0002] The proportion of wind power generation capacity has continued to increase, and the wind power sector has developed rapidly in the past few decades.

[0003] As a clean, renewable energy source, wind power is gaining increasing attention and investment worldwide. Compared to traditional energy sources, wind power offers the advantages of low carbon emissions and environmental friendliness. However, wind power investment is high, particularly during the wind farm construction and equipment deployment phases, which require substantial financial support. Therefore, accurate efficiency predictions are essential before wind farm construction begins. Using wind power prediction models and relevant environmental data, we can rationally assess the power generation capacity of potential wind farms, providing investors with informed decision-making support.

[0004] Currently, wind farm efficiency predictions primarily rely on meteorological data (such as wind speed, temperature, and humidity) and historical power generation data. Traditional wind power generation estimation methods have numerous limitations, such as simple models and insufficient prediction accuracy. In recent years, the development of machine learning technology has opened up new possibilities for wind farm efficiency assessment using data-driven prediction models. Machine learning models can accurately predict wind farm efficiency based on historical data, thereby optimizing wind farm operation strategies. Summary of the Invention

[0005] The purpose of the present invention is to overcome the shortcomings of the above-mentioned prior art and provide a wind farm efficiency prediction method and related devices based on LightGBM, which can accurately predict the power generation efficiency of the wind farm.

[0006] To achieve the above objectives, the present invention discloses a wind farm efficiency prediction method based on LightGBM, comprising:

[0007] Obtain the current meteorological data and auxiliary characteristics of the wind farm;

[0008] The meteorological data and auxiliary features of the current wind farm are input into the trained wind farm station power generation efficiency prediction model to predict the power generation efficiency of the wind farm, wherein the wind farm station power generation efficiency prediction model is constructed based on LightGBM.

[0009] The further improvement of the wind farm efficiency prediction method based on LightGBM described in the present invention is:

[0010] Furthermore, the meteorological data of the wind farm includes wind speed, temperature, humidity and air pressure data, and the auxiliary features include the square of wind speed and the rate of change of air density.

[0011] Furthermore, before inputting the meteorological data and auxiliary features of the current wind farm into the trained wind farm power generation efficiency prediction model, the method further includes:

[0012] Build a dataset;

[0013] Construct a wind farm power generation efficiency prediction model based on LightGBM;

[0014] The wind farm station power generation efficiency prediction model is trained using the data set to obtain a trained wind farm station power generation efficiency prediction model.

[0015] Furthermore, it also includes:

[0016] The SHAP method is used to interpret the wind farm power generation efficiency prediction model and determine the influence of each input parameter on the prediction results of the wind farm power generation efficiency prediction model.

[0017] Furthermore, the Shapley value φ of the i-th input parameter i for:

[0018]

[0019] Where S is the subset of input parameters, excluding input parameter i, f(S) is the model output of predicting the sample using only the features of subset S, and |N| is the total number of features.

[0020] The present invention discloses a wind farm efficiency prediction system based on LightGBM, comprising:

[0021] Acquisition module, used to obtain meteorological data and auxiliary features of the current wind farm;

[0022] A prediction module is used to input the meteorological data and auxiliary features of the current wind farm into the trained wind farm station power generation efficiency prediction model to predict the power generation efficiency of the wind farm, wherein the wind farm station power generation efficiency prediction model is constructed based on LightGBM.

[0023] The further improvement of the wind farm efficiency prediction system based on LightGBM described in the present invention is:

[0024] Furthermore, the meteorological data of the wind farm includes wind speed, temperature, humidity and air pressure data, and the auxiliary features include the square of wind speed and the rate of change of air density.

[0025] Furthermore, it also includes:

[0026] The first building module is used to build a data set;

[0027] The second building module is used to build a wind farm power generation efficiency prediction model based on LightGBM;

[0028] The training module is used to train the wind farm power generation efficiency prediction model using the data set to obtain a trained wind farm power generation efficiency prediction model.

[0029] The present invention discloses a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the wind farm efficiency prediction method based on LightGBM are implemented.

[0030] The present invention discloses a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of the wind farm efficiency prediction method based on LightGBM are implemented.

[0031] The present invention has the following beneficial effects:

[0032] During specific operation, the LightGBM-based wind farm efficiency prediction method and related devices described in the present invention input the meteorological data and auxiliary features of the current wind farm into the trained wind farm power generation efficiency prediction model to predict the power generation efficiency of the wind farm. The wind farm power generation efficiency prediction model is constructed based on LightGBM. The use of LightGBM can capture the nonlinear relationship between multidimensional features, significantly improve the accuracy of wind farm power generation efficiency prediction, and can be applied to wind farms under various climatic and geographical conditions, provide reliable decision support for wind energy investment, and reduce high investment risks.

[0033] Furthermore, the SHAP method is used to reveal the specific impact mechanism of factors such as wind speed, air density, and temperature on wind farm power generation efficiency, enhancing the interpretability and credibility of the model by accurately predicting the efficiency of potential wind farm stations. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The accompanying drawings, which constitute part of the present invention, are intended to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are intended to explain the present invention and do not constitute an undue limitation of the present invention. In the accompanying drawings:

[0035] Figure 1 is a flow chart of the method of the present invention;

[0036] Figure 2Schematic diagram of LightGBM's decision tree growth strategy;

[0037] Figure 3 Schematic diagram of the SHAP method. DETAILED DESCRIPTION

[0038] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0039] In the description of the present invention, it is to be understood that the terms “include” and “comprise” indicate the presence of the described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or collections thereof.

[0040] It should also be understood that the terms used in the present specification are only for the purpose of describing particular embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0041] It should be further understood that the term "and / or" as used in the present specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in the present invention generally indicates that the associated objects are in an "or" relationship.

[0042] It should be understood that although the terms "first," "second," and "third" may be used to describe preset ranges in embodiments of the present invention, these preset ranges should not be limited to these terms. These terms are merely used to distinguish one preset range from another. For example, without departing from the scope of embodiments of the present invention, the first preset range may also be referred to as the second preset range, and similarly, the second preset range may also be referred to as the first preset range.

[0043] The word "if," as used herein, may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to the determination" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)," depending on the context.

[0044] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0045] The accompanying drawings illustrate various schematic diagrams of structures according to embodiments disclosed herein. These figures are not drawn to scale; for clarity, some details are exaggerated and some details may be omitted. The shapes of the various regions and layers shown in the figures, as well as their relative sizes and positional relationships, are merely exemplary and may deviate in practice due to manufacturing tolerances or technical limitations. Those skilled in the art may design regions / layers with different shapes, sizes, and relative positions as needed.

[0046] Example 1

[0047] refer to Figure 1 The wind farm efficiency prediction method based on LightGBM of the present invention includes the following steps:

[0048] 1) Build a dataset;

[0049] The wind farm data includes environmental characteristics such as wind speed, temperature, humidity, and air pressure data of the wind farm in the past year, and real-time monitoring data of wind power within a specified time interval of the wind farm and historical wind power data.

[0050] The collected wind farm data is cleaned and normalized to ensure data quality and consistency. The normalized data is then divided into a training set and a test set in a 7:3 ratio. Typically, a time series partitioning approach is used, with the training set used for model training and parameter tuning, and the test set used to evaluate model performance and generalization. This allows for a more accurate assessment of the model's predictive effectiveness on unknown data, providing reliable results.

[0051] In addition, based on the physical mechanism of wind energy utilization, auxiliary features are generated, such as the square of wind speed and the rate of change of air density. Important features are selected through correlation analysis and L1 regularization, and redundant data are removed to construct the final data set.

[0052] 2) Construct a wind farm power generation efficiency prediction model based on LightGBM;

[0053] It should be noted that the LightGBM (Light Gradient Boosting Machine) is an improved version of the gradient boosting decision tree (GBDT) algorithm, which uses a collection of decision trees for learning. The basic idea of GBDT is to improve the overall performance of the model by iteratively building a series of weak learners (usually decision trees), building a new tree at each step to reduce the error of the previous stage. This cumulative approach continuously reduces the prediction error, ultimately resulting in an accurate prediction model. It has the characteristics of efficient training speed, high accuracy, support for parallel and distributed learning, and automatic processing of categorical features, making it very suitable for training tasks involving large-scale data.

[0054] LightGBM mainly consists of two algorithms: Gradient-based One-Side Sampling (GOSS) and Exclusive Feature Bundling (EFB). The GBDT algorithm that combines GOSS and EFB is LightGBM.

[0055] It should be noted that GOSS is an algorithm that strikes a balance between reducing the amount of data and ensuring accuracy. GOSS reduces the amount of computation by distinguishing instances with different gradients, retaining instances with larger gradients while randomly sampling instances with smaller gradients, thereby improving efficiency.

[0056] The training steps of the GOSS algorithm are:

[0057] Input: training data, number of iterations d, sampling rate a for large gradient data, sampling rate b for small gradient data, loss function, and type of weak learner (usually a decision tree).

[0058] Output: trained strong learner;

[0059] 1a) Sort the sample points in descending order according to their absolute values of gradient;

[0060] 2a) Select the first a*100% of the samples after sorting to generate a subset of large gradient sample points;

[0061] 3a) For the remaining sample set (1-a) 100% of the samples, randomly select b(1-a)*100% sample points to generate a set of small gradient sample points;

[0062] 4a) merging the large gradient sample and the sampled small gradient sample;

[0063] 5a) Multiply the small gradient sample by a weight coefficient;

[0064] 6a) Using the above sampled samples, learn a new weak learner;

[0065] 7a) Repeat steps 1a) to 6a) until a predetermined number of iterations is reached or convergence is achieved.

[0066] When a = 0, the GOSS algorithm degenerates into a random sampling algorithm; when a = 1, the GOSS algorithm becomes an algorithm that uses the entire sample. In many cases, the GOSS algorithm can produce models with higher accuracy than random sampling algorithms. Furthermore, sampling increases the diversity of weak learners, potentially improving the generalization ability of the trained model.

[0067] It should be noted that EFB improves computational efficiency by reducing feature dimensionality through feature bundling. Typically, bundled features are mutually exclusive (one with a zero value and one with a non-zero value), so that bundling two features prevents information loss. If two features are not completely mutually exclusive (in some cases, both have non-zero values), a metric, called the conflict ratio, can be used to measure the degree of mutual non-exclusivity. When this value is low, we can choose to bundle the two non-exclusive features without affecting the final accuracy.

[0068] The implementation process of the EBF algorithm is:

[0069] 1b) Sort the features by the number of non-zero values;

[0070] 2b) calculating the conflict ratio between different features;

[0071] 3b) Iterate over each feature and try to merge features to minimize the conflict ratio.

[0072] Set the objective function in the gradient boosting framework to mean squared error or root mean squared error; use random search and cross-validation to optimize hyperparameters such as learning rate, tree depth, number of leaf nodes, etc.; and select the optimal model architecture and hyperparameter configuration.

[0073] The model is used to predict the test set and evaluate the performance of the model, including R 2 , MAE (mean absolute error) and RMSE, etc.; at the same time, the trained model is used to predict the power generation efficiency of the wind farm and the prediction results are output.

[0074] The SHAP method is used to interpret the LightGBM model and reveal the degree of influence of input features on the prediction results. SHAP (SHapley Additive exPlanations) is a method for explaining prediction results. It is based on the Shapley value theory and provides global and local interpretability for the model by decomposing the prediction results into the influence of each feature. The core idea of SHAP is to distribute the contribution of feature values to different features, calculate the Shapley value of each feature, and multiply it with the feature value to obtain the contribution of the feature to the prediction result. SHAP can be used for machine learning models, including classification and regression models, and can generate graphical and quantitative explanation results to help users explain the decision-making process of the model.

[0075] The calculation formula of Shapley value is:

[0076]

[0077] Among them, φ i is the Shapley value of the i-th feature, S is the feature subset excluding feature i; f(S) is the model output of predicting the sample using only the features of subset S, and |N| is the total number of features.

[0078] Generate SHAP values, analyze the contribution of different environmental parameters to wind farm power generation efficiency, and identify key factors that have the greatest impact on efficiency prediction results, such as wind speed and air density. Visualize SHAP results to provide guidance for the optimized design and operation of wind farms.

[0079] This method captures the nonlinear relationships between multidimensional features, significantly improving the accuracy of wind farm efficiency predictions. It is applicable to wind farms in a variety of climatic and geographical conditions. Furthermore, using the SHAP method, it reveals the specific mechanisms by which factors such as wind speed, air density, and temperature affect wind farm efficiency, enhancing the model's interpretability and reliability. By accurately predicting the efficiency of potential wind farms, this method provides reliable decision support for wind energy investment and reduces the high investment risks.

[0080] Example 2

[0081] The wind farm efficiency prediction system based on LightGBM of the present invention includes:

[0082] Acquisition module, used to obtain meteorological data and auxiliary features of the current wind farm;

[0083] A prediction module is used to input the meteorological data and auxiliary features of the current wind farm into the trained wind farm station power generation efficiency prediction model to predict the power generation efficiency of the wind farm, wherein the wind farm station power generation efficiency prediction model is constructed based on LightGBM.

[0084] In this embodiment, the meteorological data of the wind farm includes wind speed, temperature, humidity and air pressure data, and the auxiliary features include the square of wind speed and the rate of change of air density.

[0085] In this embodiment, it also includes:

[0086] The first building module is used to build a data set;

[0087] The second building module is used to build a wind farm power generation efficiency prediction model based on LightGBM;

[0088] The training module is used to train the wind farm power generation efficiency prediction model using the data set to obtain a trained wind farm power generation efficiency prediction model.

[0089] The division of modules in the embodiments of the present application is illustrative and is merely a logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional modules in the various embodiments of the present application may be integrated into a single processor, or may exist physically separately, or two or more modules may be integrated into a single module. The aforementioned integrated modules may be implemented in the form of hardware or software functional modules.

[0090] Example 3

[0091] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of a LightGBM-based wind farm efficiency prediction method, including, for example: obtaining meteorological data and auxiliary features of the current wind farm; inputting the meteorological data and auxiliary features of the current wind farm into a trained wind farm power generation efficiency prediction model to predict the wind farm's power generation efficiency, wherein the wind farm power generation efficiency prediction model is constructed based on LightGBM. The memory may include internal memory, such as a high-speed random access memory (RAM), or may also include non-volatile memory, such as at least one disk drive. The processor, network interface, and memory are interconnected via an internal bus, which may be an industry standard architecture bus, a peripheral component interconnect standard bus, an extended industry standard architecture bus, etc. The bus may be classified as an address bus, a data bus, a control bus, etc. The memory is used to store programs. Specifically, the programs may include program code, and the program code includes computer operating instructions. The memory may include both internal memory and non-volatile memory, and provides instructions and data to the processor.

[0092] Example 4

[0093] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the wind farm efficiency prediction method based on LightGBM, for example, including: obtaining the meteorological data and auxiliary features of the current wind farm; inputting the meteorological data and auxiliary features of the current wind farm into the trained wind farm power generation efficiency prediction model to predict the power generation efficiency of the wind farm, wherein the wind farm power generation efficiency prediction model is constructed based on LightGBM. Specifically, the computer-readable storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. The volatile memory may include random access memory and / or cache memory, etc. The non-volatile memory may include a read-only memory, a hard disk, a flash memory, an optical disk, a magnetic disk, etc.

[0094] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code.

[0095] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0096] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0097] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0098] Those skilled in the art will readily identify other embodiments of the present invention after considering the specification and disclosure of the invention. This application is intended to cover any variations, uses, or adaptations of the present invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the invention being indicated by the following claims.

[0099] It should be understood that the present invention is not limited to the exact construction described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

[0100] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any way. Any simple modification, change and equivalent structural change made to the above embodiment based on the technical essence of the present invention shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. A wind farm efficiency prediction method based on LightGBM, characterized by: include: Obtain the current meteorological data and auxiliary characteristics of the wind farm; The meteorological data and auxiliary features of the current wind farm are input into the trained wind farm station power generation efficiency prediction model to predict the power generation efficiency of the wind farm, wherein the wind farm station power generation efficiency prediction model is constructed based on LightGBM.

2. The wind farm efficiency prediction method based on LightGBM according to claim 1 is characterized in that: The meteorological data of the wind farm includes wind speed, temperature, humidity and air pressure data, and the auxiliary features include wind speed square and rate of change of air density.

3. The wind farm efficiency prediction method based on LightGBM according to claim 1 is characterized in that: Before inputting the meteorological data and auxiliary features of the current wind farm into the trained wind farm power generation efficiency prediction model, the method further includes: Build a dataset; Construct a wind farm power generation efficiency prediction model based on LightGBM; The wind farm station power generation efficiency prediction model is trained using the data set to obtain a trained wind farm station power generation efficiency prediction model.

4. The wind farm efficiency prediction method based on LightGBM according to claim 1 is characterized in that: Also includes: The SHAP method is used to interpret the wind farm power generation efficiency prediction model and determine the influence of each input parameter on the prediction results of the wind farm power generation efficiency prediction model.

5. The wind farm efficiency prediction method based on LightGBM according to claim 4 is characterized in that: Shapley value φ of the i-th input parameter i for: Where S is the subset of input parameters, excluding input parameter i, f(S) is the model output of predicting the sample using only the features of subset S, and |N| is the total number of features.

6. A wind farm efficiency prediction system based on LightGBM, characterized by: include: Acquisition module, used to obtain meteorological data and auxiliary features of the current wind farm; A prediction module is used to input the meteorological data and auxiliary features of the current wind farm into the trained wind farm station power generation efficiency prediction model to predict the power generation efficiency of the wind farm, wherein the wind farm station power generation efficiency prediction model is constructed based on LightGBM.

7. The wind farm efficiency prediction system based on LightGBM according to claim 6 is characterized in that: The meteorological data of the wind farm includes wind speed, temperature, humidity and air pressure data, and the auxiliary features include wind speed square and rate of change of air density.

8. The wind farm efficiency prediction system based on LightGBM according to claim 6 is characterized in that: Also includes: The first building module is used to build a data set; The second building module is used to build a wind farm power generation efficiency prediction model based on LightGBM; The training module is used to train the wind farm power generation efficiency prediction model using the data set to obtain a trained wind farm power generation efficiency prediction model.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the wind farm efficiency prediction method based on LightGBM as described in any one of claims 1 to 5 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the wind farm efficiency prediction method based on LightGBM as described in any one of claims 1 to 5 are implemented.

Images