Wind power prediction method, device, equipment and medium
By optimizing neural network model and weighted processing technology, the problem of meteorological data uncertainty in wind power power prediction is solved, the prediction accuracy and stability are improved, the ability to capture wind power power trends is enhanced, and the reliability of the power system is improved.
Patent Information
- Application Number
- CN202410905066.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-08
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-07-08
AI Technical Summary
The randomness, volatility and uncertainty of meteorological data in wind power prediction leads to low prediction accuracy, affecting the stability and reliability of the power system.
The optimized neural network model is adopted, combining meteorological data and wind direction information, and the future wind speed and wind power trends are predicted through weighted processing and time series analysis, and the model performance is improved through hyperparameter optimization.
It improves the accuracy and stability of wind power power prediction, enhances the ability to capture wind speed changes and periodicity, reduces the sudden change and fluctuations in the prediction results, and improves the reliability of the power system.
Smart Images

Figure CN118944046A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of wind power prediction, and specifically provides a wind power prediction method, device, equipment and medium. Background Art
[0002] Wind energy is an important renewable energy resource, which is crucial to energy security and environmental safety. Electricity is an important secondary energy source, which is extremely critical to energy conservation, emission reduction and social civilization. Therefore, converting wind and solar energy into electricity to the greatest extent and delivering high-quality electricity to users smoothly and without obstruction has become one of the cores of the energy revolution. However, the fluctuation and intermittent behavior of wind power have strong uncertainty, and its impact on power reliability, power quality, economy and social welfare becomes more and more prominent with the increase of penetration rate. The stability of the power system reflects the ability of the disturbed system to resist system collapse, and the abundance of the power system reflects the ability of the system to meet the power and electricity demand of users. Its risk analysis and control involve uncertainty, bifurcation and chaos theory. The access of large-scale wind power to the grid has greatly increased the impact of uncertain factors. Wind power has gradually become the third largest power source after thermal power and hydropower. The randomness, volatility, uncertainty of wind resources and the weak controllability of wind power output have brought great troubles and challenges to the safe and stable operation of the power system. High-precision wind power prediction technology has become an essential operation technology.
[0003] When using meteorological data to predict wind power, the randomness, volatility and uncertainty of meteorological data pose great challenges to the prediction model. As a powerful tool, neural networks perform well in fitting nonlinear data, so they are widely used in wind power prediction. However, the ratio of valid information to invalid information is different between different meteorological data, which may cause invalid information to cover up valid information, thereby affecting the fitting calculation of the neural network and reducing the prediction accuracy.
[0004] Therefore, a new wind power prediction solution is needed in this field to solve the above problems. Summary of the invention
[0005] In order to overcome the above defects, the present invention is proposed to provide a solution to the problem of low prediction accuracy.
[0006] In a first aspect, the present invention provides a wind power prediction method, comprising: obtaining a real-time wind power trend, a real-time wind power, and a future wind power trend; the future wind power trend is obtained by analyzing the future wind speed predicted based on meteorological data; the real-time wind power trend, the real-time wind power, and the future wind power trend are input into a pre-trained model to obtain the predicted wind power of the wind farm to be tested; the pre-trained model is an optimized neural network model, and the optimization process at least includes: training the neural network model based on a training set, testing the trained model, and judging whether the test result meets a preset condition, and if the preset condition is met, continuing to perform hyperparameter optimization on the neural network model; otherwise, outputting the optimal parameters.
[0007] In a technical solution of the above wind power prediction method, before obtaining the future wind power trend, the method further includes: obtaining the wind direction within a time interval; and dividing the wind direction within the time interval into different wind direction modules.
[0008] In a technical solution of the above-mentioned wind power prediction method, the meteorological data includes at least: air pressure and air density, and obtaining the future wind power trend includes at least: weighting the actual wind speeds corresponding to modules in different directions to obtain weighted results; based on the obtained air pressure of the wind farm to be measured, the future air density, and the weighted results, inputting the trained machine learning model or deep learning model to obtain the predicted future wind speed; subtracting the obtained real-time wind speed from the predicted future wind speed to obtain the predicted future wind speed trend.
[0009] In a technical solution of the above-mentioned wind power prediction method, obtaining the future wind power trend also includes: inputting the weighted result, the future wind speed trend and the obtained real-time wind speed trend into a trained machine learning model or a deep learning model to obtain the predicted wind power of the wind farm to be tested; performing a difference processing between the obtained real-time wind power and the predicted wind power to obtain the future wind power trend of the wind farm to be tested.
[0010] In a technical solution of the above-mentioned wind power prediction method, the preset condition is obtained based on the acquired training error of the neural network model and the preset target error.
[0011] In a technical solution of the above-mentioned wind power prediction method, the process of obtaining the training error of the neural network model includes: inputting the training set into the neural network model for training, inputting the verification set into the trained model to obtain first prediction data; comparing the first prediction data with the test data to obtain the training error.
[0012] In a technical solution of the above-mentioned wind power prediction method, the process of obtaining the future air density includes: obtaining the temperature and humidity of the wind farm to be measured within the time interval; inputting the temperature and humidity into a trained model to obtain the future air density; the model is at least one of the deep extreme learning machine algorithm optimized by the Northern Goshawk algorithm, a time series model, a machine learning model, and a deep learning model.
[0013] In a second aspect, the present invention provides a wind power prediction device, comprising: an acquisition module, used to obtain real-time wind power trend, real-time wind power, and future wind power trend; the future wind power trend is obtained by analyzing the future wind speed based on meteorological data to predict the future wind speed; a prediction module, used to input the real-time wind power trend, real-time wind power, and future wind power trend into a pre-trained model to obtain the predicted wind power of the wind farm to be tested; the pre-trained model is an optimized neural network model, and the optimization process at least includes: training the neural network model based on a training set, testing the trained model, and judging whether the test result meets the preset conditions, if the preset conditions are met, continuing to perform hyperparameter optimization on the neural network model; otherwise, outputting the optimal parameters.
[0014] In a third aspect, an electronic device includes a processor and a storage device, the storage device is suitable for storing multiple program codes, and the program codes are suitable for being loaded and run by the processor to execute a wind power prediction method of any one of the technical solutions of the above-mentioned wind power prediction method.
[0015] In a fourth aspect, the present invention provides a computer-readable storage medium storing a plurality of program codes, wherein the program codes are suitable for being loaded and run by a processor to execute a wind power prediction method of any one of the technical solutions of the above-mentioned wind power prediction method.
[0016] The above one or more technical solutions of the present invention have at least one or more of the following beneficial effects:
[0017] In the technical solution for implementing the present invention, the present invention provides a method for predicting wind power, including: obtaining real-time wind power trend, real-time wind power, and future wind power trend; the future wind power trend is to predict the future wind speed based on meteorological data, and is obtained by analyzing the future wind speed; the real-time wind power trend, real-time wind power, and future wind power trend are input into a pre-trained model to obtain the predicted wind power of the wind farm to be tested; the pre-trained model is an optimized neural network model, and the optimization process at least includes: training the neural network model based on the training set, testing the trained model, and judging whether the test result meets the preset conditions, and if the preset conditions are met, continuing to optimize the hyperparameters of the neural network model; otherwise, outputting the optimal parameters. Compared with the prior art, the beneficial effects of the wind power prediction method provided by the present invention are:
[0018] By predicting future wind speeds based on meteorological data and analyzing future wind speeds, we can more accurately capture the trend changes in future wind power, thereby improving the prediction accuracy.
[0019] Furthermore, the future wind speed is obtained by fitting according to the temperature, humidity, air pressure and weighted wind speed, and the relative trend is obtained by taking the difference between the future wind speed and the current wind speed. The relative wind speed trend obtained is analyzed and further fitted to predict the future wind power. The above method takes full advantage of data information and extracts mutual information of another dimension from meteorological data that is weakly correlated with wind power data, thereby improving the accuracy of predicted wind speed data, that is, making full use of the meteorological training data set and improving the efficiency of the meteorological data prediction model.
[0020] Furthermore, the wind direction is introduced to perform weighted calculation on the actual wind speed, thereby enhancing the time series characteristics of the wind speed, which can more accurately capture the changing trend and periodicity of the wind speed, thereby improving the accuracy of the prediction model. In addition, the wind speed has a certain volatility and randomness, and the enhancement of the time series characteristics can help smooth this volatility, reduce the mutation and fluctuation of the prediction results, and thus improve the stability of the prediction. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] The disclosure of the present invention will become more easily understood with reference to the accompanying drawings. It will be readily understood by those skilled in the art that these drawings are only for illustrative purposes and are not intended to limit the scope of protection of the present invention. In addition, similar numbers in the drawings represent similar components, wherein:
[0022] Figure 1 is a schematic flow chart of main steps of a wind power prediction method according to an embodiment of the present invention;
[0023] Figure 2 is a KOA-LSTM structure diagram according to an embodiment of the present invention;
[0024] Figure 3 1. is a structural diagram of an LSTM neural network according to an embodiment of the present invention;
[0025] Figure 4 This is a comparison chart of the prediction results of the LSTM model without introducing a trend value and the actual analysis data effect according to an embodiment of the present invention;
[0026] Figure 5 This is a graph showing the relative error results of an LSTM model without introducing a trend value according to an embodiment of the present invention;
[0027] Figure 6 This is a comparison chart of the prediction results of the LSTM model with trend value introduced according to an embodiment of the present invention and the actual analysis data effect;
[0028] Figure 7 This is a graph showing the relative error results of an LSTM model with a trend value introduced according to an embodiment of the present invention;
[0029] Figure 8 It is a main structural block diagram of a wind power prediction device according to an embodiment of the present invention. DETAILED DESCRIPTION
[0030] Some embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.
[0031] Embodiment 1
[0032] See attached Figure 1 , Figure 1 FIG. 1 is a schematic flow chart of the main steps of a wind power prediction method according to an embodiment of the present invention. Figure 1 As shown, the wind power prediction method in the embodiment of the present invention mainly includes the following steps S1 to S2.
[0033] Step S1, obtaining real-time wind power trend, real-time wind power, and future wind power trend; the future wind power trend is obtained by analyzing the future wind speed predicted based on meteorological data;
[0034] In this embodiment, the real-time wind power trend refers to the changing trend of the power being generated by the wind farm at the current moment. By monitoring the changes in real-time power data, the power generation situation of the wind farm and possible future power generation trends can be understood. For example, the process of obtaining the real-time wind power trend is: the difference between the wind power at the current moment and the wind power at the previous moment. Real-time wind power indicates the power value actually generated by the wind farm at the current moment. This is an important indicator of the real-time operating status of the wind farm, which can reflect the impact of factors such as wind speed on the power generation. Future wind power trend is to predict the changing trend of the power generation of the wind farm in the future period of time based on meteorological data. By analyzing and predicting meteorological factors such as future wind speed, the future power generation situation of the wind farm can be predicted.
[0035] Specifically, real-time wind power trend and real-time wind power can be achieved through the following methods: monitoring equipment of wind turbines, including anemometers, power meters, data acquisition systems, etc. The data acquisition system obtains meteorological data such as wind speed, wind direction, and wind force in real time, and calculates the real-time wind power in combination with the characteristics of the wind turbine. The real-time data obtained is transmitted to the data center or operation center through the monitoring system or data interface for storage and analysis, and finally forms a real-time wind power trend chart and real-time power value.
[0036] like Figure 2 As shown, step S2, inputting the real-time wind power trend, the real-time wind power, and the future wind power trend into a pre-trained model to obtain the predicted wind power of the wind farm to be tested;
[0037] The pre-trained model is an optimized neural network model, and the optimization process at least includes: training the neural network model based on the training set, testing the trained model, and judging whether the test result meets the preset conditions, if the preset conditions are met, continuing to optimize the hyperparameters of the neural network model; otherwise, outputting the optimal parameters.
[0038] In this embodiment, historical data and actual wind power values can be used as training sets, and the patterns and relationships between the training data can be learned through the neural network algorithm. The trained neural network model is tested using the validation set data to verify the performance of the model on unseen data. Then, it is determined whether the test results meet the preset conditions, such as whether the error range is within an acceptable range. If the test results do not meet the preset conditions, it is necessary to further optimize the hyperparameters of the neural network model, such as the learning rate, network structure, activation function, etc. By adjusting the hyperparameters, the performance of the model is continuously optimized to obtain more accurate prediction results.
[0039] For example, the neural network model can be a Kepler algorithm optimized long short-term memory neural network model (KOA-LSTM), and can also be an autoregressive moving average model, a support vector machine regression, a random forest regression, and a convolutional neural network.
[0040] In one embodiment, the preset condition is obtained based on the acquired training error of the neural network model and a preset target error.
[0041] The process of obtaining the training error of the neural network model includes: inputting the training set into the neural network model for training, inputting the verification set into the trained model to obtain first prediction data; and comparing the first prediction data with the test data to obtain the training error.
[0042] The following is an example of the Kepler algorithm optimized long short-term memory neural network model (KOA-LSTM). The specific process is as follows: First, set the evaluation index of the LSTM model: For example, the root mean square error (RMSE) is selected as the index for evaluating the performance of the LSTM model, which represents the average difference between the model prediction value and the actual value. The smaller the RMSE, the higher the prediction accuracy of the model. Then, the real-time wind power data, wind power trend data, and future wind power trend data are merged with the historical data set, and preprocessing steps such as data cleaning and feature engineering are performed. Using the prepared data set, the data set is divided into a training set and a test set, and then input into the LSTM model for training and prediction. The data predicted by the LSTM model is compared with the test data, the root mean square error (RMSE) is calculated, and it is used as the objective function of the Kepler algorithm (KOA). If the calculated root mean square error exceeds the preset objective function error threshold, the Kepler algorithm (KOA) is used to optimize the initial parameters of the LSTM, and the parameters are updated to continue training and prediction. Repeat the above steps until the root mean square error of the LSTM is less than the set objective function error threshold. The neural network structure of LSTM is as follows Figure 3 As shown, Figure 3 The meanings of the various quantities are as follows:
[0043] Input gate: i t =σ(W i [x t ,h t -1]+b i )
[0044] Forget gate: f t =σ(W f [x t ,h t -1]+b f )
[0045] Output gate: o t =σ(Wo [x t ,h t -1]+b o )
[0046] Candidate cell state: c t ′=tanh(W c [x t ,h t -1]+b c )
[0047] Cell state: c t =f t *c t-1 +i t *c t '
[0048] Hidden state: h t =o t *tanh(c t )
[0049] In one embodiment, before obtaining the future wind power trend, the method further includes: obtaining the wind direction within a time interval; and dividing the wind direction within the time interval into different wind direction modules.
[0050] In this embodiment, an interval window is given, and the window moves with the movement of the time series; the wind direction in the interval is projected into a polar coordinate three-dimensional system with wind speed as the ordinate. This process can associate wind direction and wind speed to form a two-dimensional vector of wind direction-wind speed, while considering the size of wind speed. Then, according to these wind direction-wind speed vectors, cluster analysis can be performed to divide different wind direction modules. In cluster analysis, commonly used methods include K-means clustering, hierarchical clustering, density clustering, etc. Specifically, the wind direction trend is detected in real time. If a new linear change in wind direction is detected, the new wind direction is determined to be the mainstream wind direction; according to the interval of continuous change corresponding to the new change, the window is extended until a nonlinear change occurs, and is divided into the same wind direction module; continue to find different wind direction modules, thereby completing the cluster analysis of wind direction.
[0051] Assume that the wind direction changes at a certain rate over time, and this change can be approximated by a straight line. For example, the wind direction gradually changes from north (N) to northeast (NE) and then to east (E). If there is no drastic fluctuation during this change, it can be approximated as a linear change. Within a given time window, a linear fitting method can be used to detect the changing trend of wind direction. If the fitting results show that the changing trend of wind direction can be better described by a straight line, it can be considered that the change of wind direction during this period is linear. Alternatively, the rate and direction of wind direction change can also be monitored. If the wind direction change rate and direction remain relatively stable over a certain period of time (that is, the change rate is small and the direction changes less), it can be considered that a linear change has occurred.
[0052] In one embodiment, the meteorological data at least includes: air pressure and air density, and obtaining the future wind power trend in step S1 at least includes:
[0053] S11, performing weighted processing on the actual wind speeds corresponding to the modules in different directions to obtain a weighted result;
[0054] In this embodiment, the actual wind speed corresponding to the modules in different directions is weighted in order to more accurately consider the impact of different wind directions on the wind farm. In wind power generation, the impact of wind direction on wind speed is very important, because the blades of the wind turbine will be affected to different degrees according to the wind direction, so the wind speed in different directions has different impacts on the power generation capacity of the wind turbine. Using the above method, the actual wind speed of the entire wind farm can be better reflected, thereby improving the accuracy and reliability of predicted wind power.
[0055] S12, inputting the obtained air pressure of the wind farm to be measured, the future air density, and the weighted result into a trained machine learning model or a deep learning model to obtain a predicted future wind speed;
[0056] In this embodiment, the future air density refers to the air density at a certain time point or time period in the future. The air pressure, future air density, and weighted results of the wind farm to be measured can be input into the gradient boosting machine (LightGBM) to predict the future wind speed of the wind farm in this interval. Other machine model methods can also be used, such as random forest, support vector regression, and one or more of the gated recurrent unit, convolutional neural network, and ensemble learning in the deep learning model, as long as the predicted future wind speed can be obtained.
[0057] S13, performing a difference process between the acquired real-time wind speed and the predicted future wind speed to obtain a predicted future wind speed trend.
[0058] In this embodiment, the wind speed at the current moment may be the real-time wind speed measured by a wind tower.
[0059] Furthermore, the predicted future wind speed is the wind speed after the predicted wind speed is subjected to a step-length hysteresis operation. By appropriately hysteresis processing the predicted wind speed, the inertia and delay effects of wind speed changes can be taken into account, thereby better reflecting the actual situation of future wind speed. This operation helps to improve the accuracy of wind power prediction, making the prediction results more valuable and reliable.
[0060] In one embodiment, obtaining the future wind power trend in step S1 further includes:
[0061] S14, inputting the weighted result, the future wind speed trend and the acquired real-time wind speed trend into a trained machine learning model or a deep learning model to obtain the predicted wind power of the wind farm to be tested;
[0062] S15, performing a difference process between the acquired real-time wind power and the predicted wind power to obtain a future wind power trend of the wind farm to be measured.
[0063] In this embodiment, the machine learning model or deep learning model can adopt a long short-term memory (LSTM) network. In addition, one or more of support vector regression, random forest regression, gradient boosting regression tree or other deep learning models can also be used, as long as the future wind power trend can be obtained.
[0064] Furthermore, the predicted future wind power is obtained after the predicted wind power is subjected to a step-lag operation. The above process can capture the changing trend of power. This can help better understand the historical patterns and trends of power, thereby improving the accuracy of the prediction of future wind power.
[0065] In one embodiment, the process of obtaining the future air density in step S12 includes:
[0066] Step S121, obtaining the temperature and humidity of the wind farm to be measured within the time interval;
[0067] Step S122: input the temperature and humidity into the trained model to obtain the future air density; the model is at least one of a deep extreme learning machine algorithm optimized by a Northern Goshawk algorithm, a time series model, a machine learning model, and a deep learning model.
[0068] In this embodiment, temperature and humidity have a significant impact on the power generation efficiency of the wind farm: temperature and humidity are important factors affecting air density, and air density directly affects the performance of wind turbines. By acquiring and analyzing the temperature and humidity data of the wind farm to be tested within a time interval, the change of air density in the future can be predicted more accurately, helping to optimize the operation and power generation efficiency of the wind farm.
[0069] The historical temperature, humidity, air pressure, hub height wind direction, hub height wind speed, and power generation data of a wind farm in Xinjiang from 0:00 on January 1, 2019 to 24:00 on December 31, 2019 are used as the original data. This prediction task is performed based on the Matlab2023a software platform, and the experimental hardware configuration is Intel(R) Core(TM) i5-8550U CPU / 8GBRAM / NVIDIA GeForce RTX3050.
[0070] The present invention selects the temperature and humidity data of a wind farm in Xinjiang throughout 2019, inputs them into the Northern Goshawk algorithm optimized deep extreme learning machine algorithm (NGO-DELM), predicts the air density data of the wind farm in 2019, and then inputs the air density data, air pressure data, and feature-weighted wind speed data into the gradient boosting machine (LightGBM) to predict the wind speed data of the wind farm in 2019.
[0071] After the future wind speed data is step-lag operated, it is difference processed with the hub height wind speed data to obtain the wind speed trend value from the previous moment to the current moment and the wind speed trend value from the current moment to the next moment of the wind farm. It is then input into the LSTM network together with the hub height wind speed at the current moment to predict the wind power data of the wind farm in 2019.
[0072] The obtained real-time wind speed is subtracted from the predicted future wind speed to obtain the predicted future wind speed trend; the obtained real-time wind power is subtracted from the predicted wind power to obtain the future wind power trend of the wind farm to be tested; the obtained real-time wind power trend, real-time wind power and future wind power trend are input into the Kepler optimization algorithm optimized long short-term memory network (KOA-LSTM) to obtain the final predicted wind power value of the wind farm.
[0073] The present invention selects a wind power prediction experiment that introduces a wind speed trend value and a wind power prediction experiment that does not introduce a trend value, both of which use the LSTM model for prediction, and obtains the wind power prediction value image and the LSTM model relative error image, where the wind power prediction value takes the 5000th to 5200th data, such as Figures 4 to 7 The figure shows a line graph of the wind power prediction image from the 5000th to the 5200th data changing over time. The LSTM model relative error image is the difference between the predicted value and the actual value of all data samples, expressed in the form of a bar graph. It can be seen from the figure that the predicted value with the introduction of trend value is closer to the actual value than the predicted value without the introduction of trend value, and its error is also smaller.
[0074] Embodiment 2
[0075] See attached Figure 8 , Figure 8 FIG. 1 is a main structural block diagram of a wind power prediction device according to an embodiment of the present invention. Figure 8 As shown, the wind power prediction device in the embodiment of the present invention mainly includes an acquisition module 11 and a prediction module 12. In some embodiments, one or more of the acquisition module 11 and the prediction module 12 can be combined into one module. In some embodiments, the acquisition module 11 can be configured to execute the program of step S1. The prediction module 12 can be configured to execute the program of step S2. In one embodiment, the description of the specific implementation function can refer to steps S1-S2.
[0076] The wind power prediction device is used to perform Figure 1 The wind power prediction method embodiment shown in the figure has similar technical principles, technical problems solved and technical effects produced. Technicians in this technical field can clearly understand that for the convenience and conciseness of description, the specific working process and related instructions of the wind power prediction device can refer to the contents described in the embodiment of the wind power prediction method, which will not be repeated here.
[0077] It is understood by those skilled in the art that the present invention implements all or part of the processes in the method of the above embodiment, and can also be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of each of the above method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable storage medium may include: any entity or device, medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory, random access memory, electric carrier signal, telecommunication signal and software distribution medium, etc. that can carry computer program code. It should be noted that the content contained in the computer-readable storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable storage medium does not include electric carrier signals and telecommunication signals.
[0078] Embodiment 3
[0079] The present invention also provides an electronic device. In an embodiment of a device according to the present invention, the device includes a processor and a storage device, the storage device can be configured to store a program for executing the wind power prediction method of the above method embodiment, and the processor can be configured to execute the program in the storage device, which includes but is not limited to the program for executing the wind power prediction method of the above method embodiment. For ease of explanation, only the parts related to the embodiment of the present invention are shown. For specific technical details not disclosed, please refer to the method part of the embodiment of the present invention. The control device can be a control device device formed by various electronic devices.
[0080] Embodiment 4
[0081] The present invention also provides a computer-readable storage medium. In a computer-readable storage medium embodiment according to the present invention, the computer-readable storage medium can be configured to store a program for executing the wind power prediction method of the above method embodiment, and the program can be loaded and run by a processor to implement the above wind power prediction method. For ease of explanation, only the parts related to the embodiment of the present invention are shown. For specific technical details not disclosed, please refer to the method part of the embodiment of the present invention. The computer-readable storage medium can be a storage device formed by various electronic devices. Optionally, the computer-readable storage medium in the embodiment of the present invention is a non-temporary computer-readable storage medium.
[0082] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the original technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.
Claims
1. A wind power prediction method, characterized in that: include: Obtaining real-time wind power trend, real-time wind power, and future wind power trend; the future wind power trend is obtained by analyzing the future wind speed predicted based on meteorological data; Inputting the real-time wind power trend, the real-time wind power, and the future wind power trend into a pre-trained model to obtain the predicted wind power of the wind farm to be tested; The pre-trained model is an optimized neural network model, and the optimization process at least includes: training the neural network model based on the training set, testing the trained model, and judging whether the test result meets the preset conditions, and if the preset conditions are met, continuing to optimize the hyperparameters of the neural network model; Otherwise, output the optimal parameters.
2. The method according to claim 1, characterized in that: Before obtaining the future wind power trend, the method further includes: Get the wind direction within a period of time; The wind direction within the time interval is divided into different wind direction modules.
3. The method according to claim 2, characterized in that The meteorological data at least includes: air pressure and air density, and obtaining the future wind power trend at least includes: Perform weighted processing on the actual wind speeds corresponding to modules in different directions to obtain weighted results; Based on the obtained air pressure of the wind farm to be measured, the future air density, and the weighted result, a trained machine learning model or a deep learning model is input to obtain a predicted future wind speed; The obtained real-time wind speed is subtracted from the predicted future wind speed to obtain the predicted future wind speed trend.
4. The method according to claim 3, characterized in that Obtaining the future wind power trend also includes: Inputting the weighted result, the future wind speed trend and the acquired real-time wind speed trend into a trained machine learning model or a deep learning model to obtain the predicted wind power of the wind farm to be tested; The acquired real-time wind power is subtracted from the predicted wind power to obtain the future wind power trend of the wind farm to be measured.
5. The method according to claim 1, characterized in that The preset condition is obtained based on the acquired training error of the neural network model and the preset target error.
6. The method according to claim 5, characterized in that The process of obtaining the training error of the neural network model includes: The training set is input into the neural network model for training, and the validation set is input into the trained model to obtain the first prediction data; The first predicted data is compared with the test data to obtain a training error.
7. The method according to claim 3, characterized in that The process of obtaining the future air density includes: Acquiring the temperature and humidity of the wind farm to be measured within the time interval; The temperature and humidity are input into a trained model to obtain the future air density; the model is at least one of a deep extreme learning machine algorithm optimized by a Northern Goshawk algorithm, a time series model, a machine learning model, and a deep learning model.
8. A wind power prediction device, characterized in that: include: An acquisition module is used to acquire real-time wind power trend, real-time wind power, and future wind power trend; the future wind power trend is obtained by analyzing the future wind speed predicted based on meteorological data; A prediction module, used for inputting the real-time wind power trend, the real-time wind power, and the future wind power trend into a pre-trained model to obtain the predicted wind power of the wind farm to be tested; The pre-trained model is an optimized neural network model, and the optimization process at least includes: training the neural network model based on the training set, testing the trained model, and judging whether the test result meets the preset conditions, and if the preset conditions are met, continuing to optimize the hyperparameters of the neural network model; Otherwise, output the optimal parameters.
9. An electronic device comprising a processor and a storage device, the storage device being adapted to store a plurality of program codes, characterized in that: The program code is suitable for being loaded and run by a processor to execute the wind power prediction method according to any one of claims 1 to 7.
10. A computer-readable storage medium storing a plurality of program codes, characterized in that: The program code is suitable for being loaded and run by a processor to execute the wind power prediction method according to any one of claims 1 to 7.
Citation Information
Patent Citations
Atmospheric fine particulate matter pollution source identification method and application thereof
CN110610279A
Wind power prediction method and device and electronic equipment
CN114298134A
Wind power segmented short-term power prediction method considering power change trend
CN116187402A
Short-term wind power prediction method and device based on optimized neural base expansion analysis and medium
CN116911430A
Method and system for predicting wind power interval
CN117913822A
