Wind power prediction method, device, equipment and storage medium

Abstract

The present application discloses a wind power prediction method, device, equipment and storage medium, which relates to the field of power prediction technology. The method includes: obtaining multi-source performance evaluation data of an offshore wind farm to be detected, the multi-source performance evaluation data including historical meteorological data, historical wind power data, real-time meteorological data and equipment operation data; determining the meteorological impact coefficient corresponding to the offshore wind farm to be detected based on the historical meteorological data and equipment operation data; outputting a wind power prediction value based on the historical meteorological data and historical wind power data through a preset wind power prediction model; and correcting the wind power prediction value based on the real-time meteorological data and the meteorological impact coefficient to obtain a target wind power prediction value. The application of the above technical solution solves the technical problem in the prior art of low accuracy of offshore wind power prediction due to the complex meteorological environment faced by offshore wind farms.

Description

Technical Field

[0001] The present application relates to the field of power prediction technology, and in particular to a wind power prediction method, device, equipment and storage medium. Background Art

[0002] With the rapid development of offshore wind power projects, particularly the construction of wind farms in near-shore and offshore areas, the scale of offshore wind power has gradually expanded, becoming an important source of renewable energy. However, the stability and reliability of offshore wind power are strongly affected by meteorological conditions. In particular, changes in meteorological factors such as wind speed, direction, temperature, and air pressure have a significant impact on the operation and performance of wind turbines. Therefore, to address the adverse effects of meteorological conditions on wind farms, accurate forecasting of offshore wind power is crucial.

[0003] Currently, traditional wind power forecasting methods typically rely on historical meteorological data and wind power data, using statistical regression models or machine learning models to predict wind power. However, compared to onshore wind farms, offshore wind farms face complex meteorological environments. Variations in sea surface wind speed, direction, and air pressure, as well as extreme weather events (such as lightning strikes, typhoons, and tornadoes), can significantly impact wind farm equipment, leading to damage or increased power output volatility. Consequently, offshore wind power forecasts are not very accurate. Summary of the Invention

[0004] The main purpose of this application is to provide a wind power prediction method, device, equipment and storage medium, aiming to solve the technical problem in the existing technology that the accuracy of offshore wind power prediction is not high due to the complex meteorological environment faced by offshore wind farms.

[0005] To achieve the above objectives, the present application proposes a wind power prediction method, which includes:

[0006] Acquire multi-source performance evaluation data of the offshore wind farm to be inspected, wherein the multi-source performance evaluation data includes historical meteorological data, historical wind power data, real-time meteorological data, and equipment operation data;

[0007] Determining a meteorological impact coefficient corresponding to the offshore wind farm to be detected based on the historical meteorological data and the equipment operation data, wherein the meteorological impact coefficient is used to characterize the degree of influence of the meteorological data on the wind power output by the offshore wind farm to be detected;

[0008] Outputting a wind power prediction value based on the historical meteorological data and the historical wind power data by using a preset wind power prediction model;

[0009] The wind power forecast value is corrected based on the real-time meteorological data and the meteorological influence coefficient to obtain a target wind power forecast value.

[0010] In one embodiment, the step of determining the meteorological impact coefficient corresponding to the offshore wind farm to be detected based on the historical meteorological data and the equipment operation data includes:

[0011] Determine, based on the historical meteorological data, a wind speed duration deviation and a wind speed fluctuation factor corresponding to the environment of the offshore wind farm to be detected during a historical period;

[0012] determining, based on the equipment operation data, a frequency factor of a meteorological damage equipment event corresponding to the offshore wind farm to be detected during the historical time period, wherein the frequency factor of the meteorological damage equipment event is used to characterize the frequency of damage to wind farm equipment in the offshore wind farm to be detected caused by meteorological events;

[0013] Determine, by an objective weighting method, a first weight coefficient corresponding to the wind speed duration deviation, a second weight coefficient corresponding to the wind speed fluctuation factor, and a third weight coefficient corresponding to the meteorological damage equipment event frequency factor;

[0014] The meteorological impact coefficient corresponding to the offshore wind farm to be detected is determined based on the wind speed duration deviation, the wind speed fluctuation factor, the meteorological damage equipment event frequency factor, the first weight coefficient, the second weight coefficient and the third weight coefficient.

[0015] In one embodiment, the step of determining, based on the historical meteorological data, a wind speed duration deviation and a wind speed fluctuation factor corresponding to the environment of the offshore wind farm to be detected during a historical time period, includes:

[0016] Determine the wind speed data and wind speed average corresponding to the environment of the offshore wind farm to be detected in the historical time period according to the historical meteorological data;

[0017] The wind speed duration deviation and the wind speed fluctuation factor corresponding to the historical time period of the offshore wind farm to be detected are determined based on the wind speed data, the wind speed average value and the wind speed allowable deviation range.

[0018] In one embodiment, the step of determining, based on the equipment operation data, a frequency factor of a meteorological equipment damage event corresponding to the offshore wind farm to be detected during the historical time period comprises:

[0019] Acquire equipment damage meteorological events based on the equipment operation data and the historical meteorological data, wherein the equipment damage meteorological events are all meteorological events that cause damage to wind farm equipment in the offshore wind farm to be detected;

[0020] Classifying the equipment damage meteorological event to determine a meteorological event category corresponding to the equipment damage meteorological event;

[0021] Acquire target device operation data corresponding to the meteorological event category from the device operation data and the historical meteorological data;

[0022] Determining, based on the target device operating data, the number of times the device is damaged due to the meteorological event category, and determining, based on the number of times the device is damaged, a probability of the device being damaged due to the meteorological event category;

[0023] The frequency factor of the meteorological equipment damage event corresponding to the offshore wind farm to be detected in the historical time period is determined based on the number of event categories corresponding to the equipment damage meteorological event, the equipment damage probability, the equipment damage frequency, and the number of occurrences corresponding to the meteorological event category.

[0024] In one embodiment, before the step of outputting a wind power prediction value based on the historical meteorological data and the historical wind power data by using a preset wind power prediction model, the step further includes:

[0025] Determine, based on the historical wind power data, a historical wind power forecast value and a historical wind power actual value corresponding to the offshore wind farm to be detected at a target time;

[0026] determining an error term between the historical wind power forecast value and the historical wind power actual value at the target time;

[0027] A preset wind power prediction model is constructed based on the historical wind power prediction value and the error term.

[0028] In one embodiment, after the step of correcting the wind power forecast value based on the real-time meteorological data and the meteorological influence coefficient to obtain a target wind power forecast value, the step further includes:

[0029] Obtaining an actual value of wind power corresponding to the offshore wind farm to be detected;

[0030] Determining a mean absolute percentage error corresponding to the target wind power prediction value based on the target wind power prediction value and the actual wind power value;

[0031] Determining whether the mean absolute percentage error exceeds a preset error tolerance threshold;

[0032] If so, the target wind power forecast value is adjusted.

[0033] In one embodiment, the step of adjusting the target wind power forecast value includes:

[0034] adjusting an initial Kalman gain according to the mean absolute percentage error, the target wind power prediction value, and the actual wind power value to obtain a target Kalman gain;

[0035] Updating a preset Kalman filter dynamic correction algorithm based on the target Kalman gain to obtain an updated Kalman filter dynamic correction algorithm;

[0036] The wind power prediction of the offshore wind farm to be detected is performed using the updated Kalman filter dynamic correction algorithm to adjust the target wind power prediction value.

[0037] In addition, to achieve the above objectives, the present application also proposes a wind power prediction device, the device comprising:

[0038] A data acquisition module is used to acquire multi-source performance evaluation data of the offshore wind farm to be tested, wherein the multi-source performance evaluation data includes historical meteorological data, historical wind power data, real-time meteorological data and equipment operation data;

[0039] an influence coefficient determination module, configured to determine a meteorological influence coefficient corresponding to the offshore wind farm to be detected based on the historical meteorological data and the equipment operation data, wherein the meteorological influence coefficient is used to characterize the degree of influence of the meteorological data on the wind power output by the offshore wind farm to be detected;

[0040] A power prediction module, configured to output a wind power prediction value based on the historical meteorological data and the historical wind power data by using a preset wind power prediction model;

[0041] The prediction value correction module is used to correct the wind power prediction value based on the real-time meteorological data and the meteorological influence coefficient to obtain a target wind power prediction value.

[0042] In addition, to achieve the above-mentioned purpose, the present application also proposes a wind power prediction device, which includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the computer program is configured to implement the steps of the wind power prediction method as described above.

[0043] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium and stores a computer program. When the computer program is executed by a processor, the steps of the wind power prediction method as described above are implemented.

[0044] The present application provides a wind power prediction method, which discloses obtaining multi-source performance evaluation data of an offshore wind farm to be detected, wherein the multi-source performance evaluation data includes historical meteorological data, historical wind power data, real-time meteorological data, and equipment operation data; determining a meteorological influence coefficient corresponding to the offshore wind farm to be detected based on the historical meteorological data and the equipment operation data, wherein the meteorological influence coefficient is used to characterize the degree of influence of meteorological data on the wind power output of the offshore wind farm to be detected; outputting a wind power prediction value based on the historical meteorological data and the historical wind power data through a preset wind power prediction model; and outputting a wind power prediction value based on the real-time meteorological data and the meteorological influence coefficient. The measured value is corrected to obtain the target wind power prediction value; compared with the existing technology that offshore wind farms face complex meteorological environments, which may cause damage to wind farm equipment or increase the volatility of power output, affecting the prediction accuracy of wind power, the present invention can predict the wind power prediction value based on the historical meteorological data of the offshore wind farm and the meteorological influence coefficient determined by the historical wind power data, and correct the wind power prediction value based on the real-time meteorological data and the meteorological influence coefficient to obtain the target wind power prediction value, thereby solving the technical problem in the existing technology that the accuracy of offshore wind power prediction is not high due to the complex meteorological environment faced by offshore wind farms. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0046] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0047] Figure 1 A flow chart of the first embodiment of the wind power prediction method of the present application is provided;

[0048] Figure 2 A flow chart of the second embodiment of the wind power prediction method of this application is provided;

[0049] Figure 3 A schematic diagram of a flow chart provided for the third embodiment of the wind power prediction method of this application;

[0050] Figure 4 This is a schematic diagram of the module structure of the wind power prediction device according to an embodiment of the present application;

[0051] Figure 5 Schematic diagram of the equipment structure of the hardware operating environment involved in the wind power prediction method in the embodiment of the present application.

[0052] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0053] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0054] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0055] The main solution of the embodiment of the present application is: obtaining multi-source performance evaluation data of the offshore wind farm to be tested, the multi-source performance evaluation data including historical meteorological data, historical wind power data, real-time meteorological data and equipment operation data; determining the meteorological impact coefficient corresponding to the offshore wind farm to be tested based on the historical meteorological data and equipment operation data, the meteorological impact coefficient being used to characterize the degree of influence of meteorological data on the wind power output of the offshore wind farm to be tested; outputting a wind power prediction value based on the historical meteorological data and the historical wind power data through a preset wind power prediction model; and correcting the wind power prediction value based on the real-time meteorological data and the meteorological impact coefficient to obtain a target wind power prediction value.

[0056] In the existing technology, when predicting wind power based on historical meteorological data and wind power data, compared with onshore wind farms, offshore wind farms face complex meteorological environments, which will have a greater impact on the equipment of the wind farms, causing equipment damage or increased volatility in power output, thereby affecting the accuracy of wind power prediction and resulting in low accuracy of offshore wind power prediction.

[0057] The present application provides a solution that can predict the wind power forecast value based on the meteorological influence coefficient determined based on the historical meteorological data and historical wind power data of the offshore wind farm, and correct the wind power forecast value based on the real-time meteorological data and the meteorological influence coefficient to obtain the target wind power forecast value, thereby solving the technical problem in the existing technology that the accuracy of offshore wind power forecast is not high due to the complex meteorological environment faced by the offshore wind farm.

[0058] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication, and program execution capabilities, such as a tablet computer, personal computer, or mobile phone, or an electronic device capable of performing the aforementioned functions, a wind power prediction device, or a wind power prediction system including the wind power prediction device. This embodiment and the following embodiments will be described below using a wind power prediction system as an example (hereinafter referred to as the system).

[0059] Based on this, the embodiment of the present application provides a wind power prediction method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the wind power prediction method of the present application.

[0060] In this embodiment, the wind power prediction method includes steps S10 to S40:

[0061] Step S10: Acquire multi-source performance evaluation data of the offshore wind farm to be inspected, wherein the multi-source performance evaluation data includes historical meteorological data, historical wind power data, real-time meteorological data, and equipment operation data.

[0062] It should be understood that the above-mentioned offshore wind farm to be tested can be any offshore wind farm that requires wind power prediction; the above-mentioned multi-source performance evaluation data can be data from multiple sources used to evaluate the performance of offshore wind farms. These data can cover multiple aspects such as meteorology, environment, and wind farm operation, and this embodiment does not impose any restrictions on this.

[0063] In this embodiment, the multi-source performance evaluation data may include historical meteorological data, historical wind power data, real-time meteorological data, and equipment operation data. The historical meteorological data may be meteorological observation data for the area where the offshore wind farm is located over a period of time in the past, including measurement data of meteorological elements such as wind speed, wind direction, temperature, air pressure, humidity, and precipitation. In this embodiment, the historical meteorological data set can be directly obtained from the meteorological department or a professional meteorological data provider. These data sets are usually collated and calibrated, and have high reliability and accuracy. Historical wind power data may be actual wind power data generated by the offshore wind farm over a period of time in the past, which can be directly obtained from the wind farm's operation and maintenance department. Real-time meteorological data may be meteorological observation data for the area where the offshore wind farm is located at the current moment or within a recent period of time. In this embodiment, the meteorological data can be obtained in real time from a meteorological observation station installed near the offshore wind farm, and transmitted to the system's monitoring center via wireless communication or a wired network. The equipment operation data may be the operating status data of wind farm equipment such as wind turbines in an offshore wind farm, for example, the start and stop status of the equipment, fault records, maintenance records, equipment parameters, etc. In this embodiment, the operating status data of the equipment may be obtained through sensors installed on the wind farm equipment (such as vibration sensors, temperature sensors, etc.).

[0064] In practical applications, after acquiring historical meteorological data, historical wind power data, real-time meteorological data, and equipment operation data for an offshore wind farm, these data can be pre-processed, such as by cleaning and standardization, and then integrated to obtain multi-source performance evaluation data. In this embodiment, by fusing historical meteorological data, wind power data, real-time meteorological data, and equipment operation data, wind power prediction can be subsequently performed using this fused multi-source performance evaluation data, which helps improve the accuracy and stability of wind power prediction.

[0065] Step S20: determining a meteorological impact coefficient corresponding to the offshore wind farm to be detected based on the historical meteorological data and the equipment operation data, wherein the meteorological impact coefficient is used to characterize the degree of influence of meteorological data on the wind power output by the offshore wind farm to be detected.

[0066] It should be noted that the aforementioned meteorological impact coefficient can be an indicator that reflects the degree to which meteorological conditions (such as wind speed, wind direction, temperature, and air pressure) affect wind power output. In this embodiment, the system analyzes historical meteorological data and equipment operation data for offshore wind farms to quantify the impact of different meteorological factors on wind power output at the offshore wind farm and generate a corresponding meteorological impact coefficient for the offshore wind farm. In practical applications, because the meteorological impact coefficient comprehensively considers the impact of multiple meteorological factors on wind power output, it can enhance the ability to predict wind power fluctuations under different meteorological conditions, thereby improving the accuracy and stability of wind power forecasts.

[0067] Step S30: outputting a wind power prediction value based on the historical meteorological data and the historical wind power data through a preset wind power prediction model.

[0068] It should be understood that the aforementioned preset wind power prediction model may be a model for predicting the wind power of an offshore wind farm at a future time. In this embodiment, the preset wind power prediction model is a model based on time series analysis. This model can be constructed by learning the relationship between historical meteorological data and historical wind power data, and improves prediction accuracy through time series analysis and a dynamic correction mechanism.

[0069] Furthermore, before the above-mentioned step S30, the method also includes: determining the historical wind power prediction value and the historical wind power actual value corresponding to the offshore wind farm to be detected at the target time based on the historical wind power data; determining the error term between the historical wind power prediction value and the historical wind power actual value at the target time; and constructing a preset wind power prediction model based on the historical wind power prediction value and the error term.

[0070] It should be noted that the above-mentioned historical wind power prediction value can be the predicted value of the wind power of the offshore wind farm to be detected at the target time; the above-mentioned historical wind power actual value can be the actual value of the wind power of the offshore wind farm to be detected at the target time, wherein the target time can be any time within a period of time in the past.

[0071] In the specific implementation, the system can first extract the wind power forecast value at each moment and the historical wind power actual value at the corresponding moment from the historical wind power data, and obtain the model parameters in the database, as well as the error terms between the historical wind power forecast value and the wind power actual value at each moment. Then, these data are preprocessed, and the preprocessed historical meteorological data and historical wind power data are input into the time series model for learning, and finally the preset wind power prediction model is obtained. The specific formula is as follows:

[0072]

[0073] Where, is the wind power forecast value at time t, is the historical wind power forecast value (delay time steps), is the gradient number, , is the total number of gradients, are model parameters, For the moment The error term between the historical wind power forecast value and the actual wind power value.

[0074] In this embodiment, by introducing the error term between the historical wind power forecast value and the actual wind power value into the prediction model, the model's adaptability to uncertain factors can be improved. This noise processing method helps to reduce the interference of external factors on wind power prediction, thereby improving the accuracy and stability of the overall prediction.

[0075] Step S40: Correcting the wind power forecast value based on the real-time meteorological data and the meteorological influence coefficient to obtain a target wind power forecast value.

[0076] It should be noted that the target wind power forecast value may be a revised wind power forecast value. This embodiment utilizes a Kalman filter dynamic correction mechanism to dynamically adjust the wind power value predicted by the preset wind power forecast model based on the wind farm's real-time meteorological data and meteorological impact coefficient. This allows the wind power forecast to flexibly respond to real-time changing meteorological conditions, optimizes the accuracy of the forecast results, and thereby improves the accuracy and stability of wind farm power forecasts.

[0077] In practical applications, the system can first obtain the time The wind power forecast value is calculated based on the real-time meteorological data. The meteorological influence coefficient is then used to correct the wind power forecast value using the Kalman filter dynamic correction formula, where the Kalman filter dynamic correction formula can be:

[0078]

[0079] Where, is the revised wind power forecast value, is the initial Kalman gain, For the moment The wind power forecast value, is the meteorological influence coefficient.

[0080] In this embodiment, the dynamic correction characteristic based on the Kalman filter enables the system to correct the wind power prediction value according to the latest data and change trends, thereby further improving the accuracy of wind farm power prediction.

[0081] The present embodiment provides a wind power prediction method, which discloses obtaining multi-source performance evaluation data of an offshore wind farm to be detected, the multi-source performance evaluation data including historical meteorological data, historical wind power data, real-time meteorological data and equipment operation data; determining a meteorological influence coefficient corresponding to the offshore wind farm to be detected based on the historical meteorological data and the equipment operation data, the meteorological influence coefficient being used to characterize the degree of influence of meteorological data on the wind power output of the offshore wind farm to be detected; outputting a wind power prediction value based on the historical meteorological data and the historical wind power data through a preset wind power prediction model; and outputting a wind power prediction value based on the real-time meteorological data and the meteorological influence coefficient. The measured value is corrected to obtain the target wind power prediction value; compared with the existing technology that offshore wind farms face complex meteorological environments, which may cause damage to wind farm equipment or increase the volatility of power output, affecting the prediction accuracy of wind power, this embodiment can predict the wind power prediction value based on the historical meteorological data of the offshore wind farm and the meteorological influence coefficient determined by the historical wind power data, and correct the wind power prediction value based on the real-time meteorological data and the meteorological influence coefficient to obtain the target wind power prediction value, thereby solving the technical problem in the existing technology that the accuracy of offshore wind power prediction is not high due to the complex meteorological environment faced by offshore wind farms.

[0082] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above embodiment 1 can be referred to the above introduction and will not be described in detail later. Figure 2 , Figure 2 This is a flow chart of the second embodiment of the wind power prediction method of this application.

[0083] In this embodiment, step S20 includes steps S201 to S204:

[0084] Step S201: determining the wind speed duration deviation and wind speed fluctuation factor corresponding to the environment of the offshore wind farm to be detected in a historical time period according to the historical meteorological data.

[0085] It should be understood that the aforementioned wind speed duration deviation can be used as an indicator to measure the duration that the wind speed deviates from its average value over a certain period of time. In practical applications, the wind speed duration deviation can reflect the stability and persistence of wind speed changes. A larger deviation indicates a larger and longer-lasting wind speed change, while a smaller deviation indicates a more stable wind speed.

[0086] It is understood that the aforementioned wind speed fluctuation factor can be an indicator used to measure the intensity of wind speed fluctuations over a certain period of time. In practical applications, the wind speed fluctuation factor can reflect the degree of wind speed fluctuation. Greater volatility indicates greater uncertainty in wind power output. Higher wind speed fluctuation index values ​​require more corrections and dynamic adjustments. High volatility can lead to significant fluctuations in wind power output. Therefore, this embodiment, through real-time tracking of the wind speed fluctuation index, can effectively improve forecast accuracy and avoid errors in wind power forecasts caused by significant meteorological changes.

[0087] Specifically, step S201 includes: determining the wind speed data and the average wind speed corresponding to the environment of the offshore wind farm to be detected in the historical time period based on the historical meteorological data; and determining the wind speed duration deviation and the wind speed fluctuation factor corresponding to the offshore wind farm to be detected in the historical time period based on the wind speed data, the average wind speed and the allowable wind speed deviation range.

[0088] In this embodiment, the system can extract the wind speed data and wind speed average of each moment in the past period of time of the offshore wind farm to be tested from the historical meteorological data, and set a wind speed tolerance range, for example, ±1m / s. Then, the system calculates the deviation between the wind speed data and the wind speed average at each moment, and determines whether the deviation exceeds the tolerance range. If so, the duration of the deviation is recorded. Finally, all durations exceeding the tolerance range are summed to obtain the wind speed duration deviation. The calculation formula for the wind speed duration deviation can be:

[0089]

[0090] Where, is the moment number, , is the total time, For the Wind speed data at the moment, is the average wind speed, The allowable deviation range of wind speed.

[0091] This embodiment quantifies the deviation of the duration of wind speed, thereby being able to evaluate the stability and persistence of wind speed within a certain period of time, and helps to accurately reflect the long-term impact of wind speed on wind power output.

[0092] In this embodiment, the system can extract wind speed data and wind speed average from historical meteorological data, and calculate the wind speed fluctuation index based on the wind speed data and wind speed average using the wind speed fluctuation index calculation formula, wherein the calculation formula of the wind speed fluctuation index can be:

[0093]

[0094] Where, is the moment number, , is the total time, For the Wind speed data at the moment, is the average wind speed.

[0095] Step S202: determining a frequency factor of meteorological equipment damage events corresponding to the offshore wind farm to be detected in the historical time period based on the equipment operation data, wherein the frequency factor of meteorological equipment damage events is used to characterize the frequency of wind farm equipment damage in the offshore wind farm to be detected caused by meteorological events.

[0096] It should be noted that the aforementioned weather-related equipment damage event frequency factor can be used to measure the frequency of equipment damage caused by specific weather events (such as strong winds, lightning strikes, and typhoons). In practical applications, the weather-related equipment damage event frequency factor can reflect the probability of equipment damage under specific weather conditions, thereby helping prediction models more accurately consider the impact of weather factors on wind power output.

[0097] In this embodiment, when equipment in a wind farm suffers meteorological damage, the farm's operations are also affected, thereby impacting wind power forecasts. This embodiment, through in-depth analysis of the impact of meteorological events on equipment damage, enables a more accurate assessment of the potential risk to equipment under different meteorological conditions and incorporates this risk into wind power forecasts. In practical applications, different meteorological events have varying impacts on equipment. Storms or extreme weather conditions can result in a higher probability of damage. For example, if a particular meteorological event (including storms, lightning, extreme temperatures, and precipitation) has a high probability of causing equipment damage, the corresponding value will be larger. Therefore, this embodiment incorporates the frequency factor of meteorological damage to equipment events into the calculation of the meteorological impact coefficient, significantly improving the accuracy and reliability of wind power forecasts.

[0098] Furthermore, the step S202 includes:

[0099] Step S202a: Acquire equipment damage meteorological events based on the equipment operation data and the historical meteorological data, wherein the equipment damage meteorological events are all meteorological events that cause damage to wind farm equipment in the offshore wind farm to be detected.

[0100] Step S202b: classify the equipment damage meteorological event and determine the meteorological event category corresponding to the equipment damage meteorological event.

[0101] It should be understood that the above-mentioned meteorological event categories may be categories corresponding to equipment damage meteorological events. For example, this embodiment may classify meteorological events into categories such as strong winds, lightning strikes, typhoons, and heavy rains.

[0102] Step S202c: Acquire target device operation data corresponding to the meteorological event category from the device operation data and the historical meteorological data.

[0103] Step S202d: Determine the number of times the equipment is damaged due to the meteorological event type according to the target equipment operation data, and determine the probability of equipment damage due to the meteorological event type based on the number of times the equipment is damaged.

[0104] It is understood that the aforementioned number of equipment damages may be the number of equipment damages caused by a particular meteorological event. In this embodiment, the number of equipment damages caused by each meteorological event type can be counted, along with the total number of devices operating in that meteorological event type. The probability of equipment damage caused by that meteorological event type can then be calculated based on the number of equipment damages caused by that meteorological event type and the total number of devices operating in that meteorological event type.

[0105] Step S202e: Determine the frequency factor of the meteorological damage equipment event corresponding to the offshore wind farm to be detected in the historical time period based on the number of event categories corresponding to the equipment damage meteorological event, the equipment damage probability, the equipment damage frequency, and the number of occurrences corresponding to the meteorological event category.

[0106] It should be understood that the number of occurrences corresponding to the above-mentioned meteorological event categories may be the number of occurrences of the meteorological event categories in historical meteorological data. In this embodiment, the calculation formula for the frequency factor of the meteorological damage equipment event may be:

[0107]

[0108] Where, is the meteorological event category number, , is the number of meteorological event categories, For the The probability of equipment damage caused by similar meteorological events, , For the Number of equipment damages caused by similar weather events, For the The total number of devices involved in the operation of this type of meteorological event, For the The number of occurrences of similar meteorological events.

[0109] Step S203: Determine a first weight coefficient corresponding to the wind speed duration deviation, a second weight coefficient corresponding to the wind speed fluctuation factor, and a third weight coefficient corresponding to the meteorological equipment damage event frequency factor through an objective weighting method.

[0110] It should be noted that the objective weighting method described above may be a method for determining the weight coefficients of the impact of different meteorological factors on wind power, such as an entropy weighting method, a principal component analysis method, a factor analysis method, etc., which is not limited in this embodiment. The entropy weighting method may be a method based on the concept of information entropy, which determines the weight by calculating the information entropy of each indicator. The smaller the information entropy, the greater the weight. The principal component analysis method may be a method for determining the weight by extracting the principal components of the data. The greater the variance of the principal components, the greater the weight. The factor analysis method may be a method for determining the weight by analyzing the latent factors of the data. The greater the contribution of the factor, the greater the weight. In this embodiment, the objective weighting method can be used to objectively evaluate the importance of each meteorological factor based on a mathematical model and algorithm, thereby avoiding the bias of subjective judgment.

[0111] It should be understood that the first weight coefficient may be a coefficient used to characterize the impact of the wind speed duration deviation on wind power; the second weight coefficient may be a coefficient used to characterize the impact of the wind speed fluctuation factor on wind power; and the third weight coefficient may be a coefficient used to characterize the impact of the frequency factor of weather-related equipment damage events on wind power. In this embodiment, these weight coefficients can help more accurately assess the impact of different meteorological factors on wind power, thereby improving the accuracy and stability of wind power forecasts.

[0112] Step S204: Determine the meteorological impact coefficient corresponding to the offshore wind farm to be detected based on the wind speed duration deviation, the wind speed fluctuation factor, the meteorological damage equipment event frequency factor, the first weight coefficient, the second weight coefficient and the third weight coefficient.

[0113] In this embodiment, the calculation method of the meteorological influence coefficient integrates multiple meteorological factors, which can ensure that the meteorological influence coefficient formula can flexibly predict the results under different meteorological conditions. The calculation formula of the meteorological influence coefficient can be:

[0114]

[0115] Where, is the meteorological influence coefficient, is the deviation of wind speed duration, is the wind speed fluctuation factor, is the frequency factor of meteorological damage equipment events, 、 、 are the first weight coefficient, the second weight coefficient and the third weight coefficient respectively, is a natural constant.

[0116] In practical applications, multi-dimensional analysis of historical meteorological data and equipment operating data can more accurately assess the specific impact of different meteorological factors on wind power, thereby improving the model's prediction accuracy. Furthermore, this embodiment quantifies and weights the impact of each meteorological factor, helping to further improve the prediction model's adaptability to complex meteorological changes, thereby achieving more efficient wind power forecasting.

[0117] In this embodiment, it is disclosed that the wind speed duration deviation and wind speed fluctuation factor corresponding to the environment of the offshore wind farm to be detected in the historical time period are determined based on historical meteorological data; the meteorological damage equipment event frequency factor corresponding to the offshore wind farm to be detected in the historical time period is determined based on equipment operation data, and the meteorological damage equipment event frequency factor is used to characterize the frequency of wind farm equipment damage in the offshore wind farm to be detected caused by meteorological events; a first weight coefficient corresponding to the wind speed duration deviation, a second weight coefficient corresponding to the wind speed fluctuation factor, and a third weight coefficient corresponding to the meteorological damage equipment event frequency factor are determined by an objective weighting method; the meteorological impact coefficient corresponding to the offshore wind farm to be detected is determined based on the wind speed duration deviation, the wind speed fluctuation factor, the meteorological damage equipment event frequency factor, the first weight coefficient, the second weight coefficient, and the third weight coefficient; because this embodiment can perform multi-dimensional analysis of historical meteorological data and equipment operation data, and quantify and weight the impact of each meteorological factor, it can more accurately evaluate the impact of different meteorological factors on wind power and the model's adaptability to complex meteorological changes, which is conducive to improving the prediction accuracy and efficiency of the model.

[0118] Based on the first embodiment and / or the second embodiment of the present application, in the third embodiment of the present application, the same or similar contents as those in the above embodiments can be referred to the above introduction and will not be described in detail later. Figure 3 , Figure 3 This is a flow chart of the third embodiment of the wind power prediction method of this application.

[0119] In this embodiment, after step S40, the method further includes steps S501 to S504:

[0120] Step S501: obtaining an actual value of wind power corresponding to the offshore wind farm to be detected.

[0121] It is understandable that the above-mentioned actual wind power value may be the wind power value generated by the offshore wind farm at a specific moment, wherein the specific moment is also the moment corresponding to the target wind power prediction value output by the model.

[0122] Step S502: determining a mean absolute percentage error corresponding to the target wind power prediction value based on the target wind power prediction value and the actual wind power value.

[0123] It should be noted that the above-mentioned mean absolute percentage error may be a parameter used to measure the difference between the revised wind power forecast value and the actual power value. In this embodiment, the mean absolute percentage error corresponding to the revised wind power forecast value may be calculated based on the target wind power forecast value and the actual wind power value using the mean absolute percentage error formula, wherein the calculation formula for the mean absolute percentage error may be:

[0124]

[0125] Where, is the mean absolute percentage error, is the moment number, , is the total time, is the revised wind power forecast value, is the actual value of wind power.

[0126] Step S503: Determine whether the mean absolute percentage error exceeds a preset error tolerance threshold.

[0127] It should be understood that the preset error tolerance threshold may be a maximum error value allowed to exist between the wind power prediction value and the wind power actual value.

[0128] Step S504: If yes, adjust the target wind power prediction value.

[0129] In actual applications, the system can compare the average absolute percentage error with the preset error tolerance threshold. If the average absolute percentage error exceeds the preset error tolerance threshold, it means that the error of the revised wind power forecast value is large, and the revised wind power forecast value needs to be adjusted. If the average absolute percentage error does not exceed the preset error tolerance threshold, it means that the error of the revised wind power forecast value is small, and the revised wind power forecast value does not need to be adjusted.

[0130] In this embodiment, by calculating the error between the corrected wind power prediction value and the actual wind power value, the prediction ability of the model can be effectively evaluated. If the error is large, the Kalman gain can be adjusted to ensure high accuracy of the prediction result.

[0131] Furthermore, step S501 includes: adjusting the initial Kalman gain according to the mean absolute percentage error, the target wind power prediction value and the actual wind power value to obtain the target Kalman gain; updating the preset Kalman filter dynamic correction algorithm based on the target Kalman gain to obtain an updated Kalman filter dynamic correction algorithm; and performing wind power prediction on the offshore wind farm to be detected through the updated Kalman filter dynamic correction algorithm to adjust the target wind power prediction value.

[0132] In actual applications, the system can adjust the initial Kalman gain based on the mean absolute percentage error, the actual wind power value, and the revised wind power forecast value to obtain a revised Kalman gain, i.e., the target Kalman gain. Then, the system can replace the initial Kalman gain in the preset Kalman filter dynamic correction formula with the revised Kalman gain to obtain an updated Kalman filter dynamic correction formula, and use the updated Kalman filter dynamic correction formula for the next wind power forecast. This embodiment adjusts the Kalman gain so that the performance of the Kalman filter dynamic correction formula can be further optimized, thereby improving the correction accuracy of each forecast result. This dynamic adjustment mechanism ensures that the wind power forecast can be continuously optimized according to actual conditions, avoiding the problem of model obsolescence or overfitting.

[0133] In this embodiment, the method of obtaining an actual wind power value corresponding to an offshore wind farm to be detected is disclosed; determining a mean absolute percentage error corresponding to a target wind power prediction value based on a target wind power prediction value and an actual wind power value; judging whether the mean absolute percentage error exceeds a preset error allowable threshold; and if so, adjusting the target wind power prediction value. Since this embodiment can dynamically correct the wind power prediction value based on the error between the wind power prediction value and the actual wind power value, the accuracy of the wind power prediction can be further improved.

[0134] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the wind power prediction method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0135] This application also provides a wind power prediction device, please refer to Figure 4 , the wind power prediction device comprises:

[0136] A data acquisition module 10 is used to acquire multi-source performance evaluation data of the offshore wind farm to be tested, wherein the multi-source performance evaluation data includes historical meteorological data, historical wind power data, real-time meteorological data, and equipment operation data;

[0137] An influence coefficient determination module 20 is configured to determine a meteorological influence coefficient corresponding to the offshore wind farm to be detected based on the historical meteorological data and the equipment operation data, wherein the meteorological influence coefficient is used to characterize the degree of influence of the meteorological data on the wind power output by the offshore wind farm to be detected;

[0138] A power prediction module 30 is configured to output a wind power prediction value based on the historical meteorological data and the historical wind power data by using a preset wind power prediction model;

[0139] The prediction value correction module 40 is configured to correct the wind power prediction value based on the real-time meteorological data and the meteorological influence coefficient to obtain a target wind power prediction value.

[0140] The wind power prediction device provided in this application, utilizing the wind power prediction method described in the aforementioned embodiments, can address the technical issue in the prior art of low accuracy in offshore wind power predictions due to the complex meteorological environment faced by offshore wind farms. Compared to the prior art, the wind power prediction device provided in this application offers the same beneficial effects as the wind power prediction method described in the aforementioned embodiments. Other technical features of the wind power prediction device are the same as those disclosed in the aforementioned embodiments and are not further elaborated upon here.

[0141] The present application provides a wind power prediction device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the wind power prediction method in the above-mentioned embodiment 1.

[0142] Reference below Figure 5 , which shows a schematic diagram of the structure of a wind power prediction device suitable for implementing the embodiments of the present application. The wind power prediction device in the embodiments of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 5The wind power prediction device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0143] like Figure 5 As shown, the wind power prediction device may include a processing device 1001 (e.g., a central processing unit, graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in a read-only memory 1002 or programs loaded from a storage device 1003 into a random access memory 1004. The random access memory 1004 also stores various programs and data required for the operation of the wind power prediction device. The processing device 1001, the read-only memory 1002, and the random access memory 1004 are interconnected via a bus 1005. An input / output interface 1006 is also connected to the bus. Typically, the following systems may be connected to the input / output interface 1006: an input device 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; a storage device 1003 including, for example, a magnetic tape or hard disk; and a communication device 1009. Communication device 1009 can allow the wind power prediction device to communicate wirelessly or wired with other devices to exchange data. Although the figure shows a wind power prediction device with various systems, it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems may be implemented or provided instead.

[0144] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a read-only memory 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are performed.

[0145] The wind power prediction device provided in this application, utilizing the wind power prediction method described in the aforementioned embodiment, can address the technical challenges of offshore wind power prediction. Compared to the prior art, the beneficial effects of the wind power prediction device provided in this application are the same as those of the wind power prediction method described in the aforementioned embodiment. Other technical features of the wind power prediction device are the same as those disclosed in the aforementioned embodiment and are not further elaborated upon here.

[0146] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0147] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0148] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, a computer program) stored thereon, wherein the computer-readable program instructions are used to execute the wind power prediction method in the above-mentioned embodiment.

[0149] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0150] The computer-readable storage medium may be included in the wind power prediction device; or may exist independently without being assembled into the wind power prediction device.

[0151] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the wind power prediction device, the wind power prediction device is enabled to: obtain multi-source performance evaluation data of the offshore wind farm to be detected, the multi-source performance evaluation data including historical meteorological data, historical wind power data, real-time meteorological data and equipment operation data; determine the meteorological impact coefficient corresponding to the offshore wind farm to be detected based on the historical meteorological data and the equipment operation data, the meteorological impact coefficient is used to characterize the degree of influence of meteorological data on the wind power output of the offshore wind farm to be detected; output a wind power prediction value based on the historical meteorological data and the historical wind power data through a preset wind power prediction model; correct the wind power prediction value based on the real-time meteorological data and the meteorological impact coefficient to obtain a target wind power prediction value.

[0152] Computer program code for performing the operations of the present application may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0153] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0154] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0155] The computer-readable storage medium provided in this application stores computer-readable program instructions (i.e., a computer program) for executing the aforementioned wind power prediction method. This computer-readable storage medium can address the prior art issue of low accuracy in offshore wind power predictions due to the complex meteorological environment faced by offshore wind farms. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in this application are similar to those of the wind power prediction method provided in the aforementioned embodiments and are not further elaborated here.

[0156] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A wind power prediction method, characterized in that: The method includes: Acquire multi-source performance evaluation data of the offshore wind farm to be inspected, wherein the multi-source performance evaluation data includes historical meteorological data, historical wind power data, real-time meteorological data, and equipment operation data; Determining a meteorological impact coefficient corresponding to the offshore wind farm to be detected based on the historical meteorological data and the equipment operation data, wherein the meteorological impact coefficient is used to characterize the degree of influence of the meteorological data on the wind power output by the offshore wind farm to be detected; Outputting a wind power prediction value based on the historical meteorological data and the historical wind power data by using a preset wind power prediction model; Correcting the wind power forecast value based on the real-time meteorological data and the meteorological influence coefficient to obtain a target wind power forecast value; The step of determining the meteorological impact coefficient corresponding to the offshore wind farm to be detected based on the historical meteorological data and the equipment operation data includes: Determine the wind speed data and wind speed average corresponding to the environment of the offshore wind farm to be detected in the historical time period according to the historical meteorological data; Determining, based on the wind speed data, the wind speed average value, and the wind speed allowable deviation range, a wind speed duration deviation and a wind speed fluctuation factor corresponding to the offshore wind farm to be detected in the historical time period; determining, based on the equipment operation data, a frequency factor of a meteorological damage equipment event corresponding to the offshore wind farm to be detected during the historical time period, wherein the frequency factor of the meteorological damage equipment event is used to characterize the frequency of damage to wind farm equipment in the offshore wind farm to be detected caused by meteorological events; Determine, by an objective weighting method, a first weight coefficient corresponding to the wind speed duration deviation, a second weight coefficient corresponding to the wind speed fluctuation factor, and a third weight coefficient corresponding to the meteorological damage equipment event frequency factor; The meteorological impact coefficient corresponding to the offshore wind farm to be detected is determined based on the wind speed duration deviation, the wind speed fluctuation factor, the meteorological damage equipment event frequency factor, the first weight coefficient, the second weight coefficient and the third weight coefficient.

2. The method according to claim 1, wherein The step of determining the frequency factor of the meteorological equipment damage event corresponding to the offshore wind farm to be detected in the historical time period based on the equipment operation data includes: Acquire equipment damage meteorological events based on the equipment operation data and the historical meteorological data, wherein the equipment damage meteorological events are all meteorological events that cause damage to wind farm equipment in the offshore wind farm to be detected; Classifying the equipment damage meteorological event to determine a meteorological event category corresponding to the equipment damage meteorological event; Acquire target device operation data corresponding to the meteorological event category from the device operation data and the historical meteorological data; Determining, based on the target device operating data, the number of times the device is damaged due to the meteorological event category, and determining, based on the number of times the device is damaged, a probability of the device being damaged due to the meteorological event category; The frequency factor of the meteorological equipment damage event corresponding to the offshore wind farm to be detected in the historical time period is determined based on the number of event categories corresponding to the equipment damage meteorological event, the equipment damage probability, the equipment damage frequency, and the number of occurrences corresponding to the meteorological event category.

3. The method according to any one of claims 1 to 2, characterized in that Before the step of outputting a wind power prediction value based on the historical meteorological data and the historical wind power data by using a preset wind power prediction model, the method further includes: Determine, based on the historical wind power data, a historical wind power forecast value and a historical wind power actual value corresponding to the offshore wind farm to be detected at a target time; determining an error term between the historical wind power forecast value and the historical wind power actual value at the target time; A preset wind power prediction model is constructed based on the historical wind power prediction value and the error term.

4. The method according to any one of claims 1 to 2, characterized in that After the step of correcting the wind power forecast value based on the real-time meteorological data and the meteorological influence coefficient to obtain a target wind power forecast value, the method further includes: Obtaining an actual value of wind power corresponding to the offshore wind farm to be detected; Determining a mean absolute percentage error corresponding to the target wind power prediction value based on the target wind power prediction value and the actual wind power value; Determining whether the mean absolute percentage error exceeds a preset error tolerance threshold; If so, the target wind power forecast value is adjusted.

5. The method according to claim 4, wherein The step of adjusting the target wind power forecast value includes: adjusting an initial Kalman gain according to the mean absolute percentage error, the target wind power prediction value, and the actual wind power value to obtain a target Kalman gain; Updating a preset Kalman filter dynamic correction algorithm based on the target Kalman gain to obtain an updated Kalman filter dynamic correction algorithm; The wind power prediction of the offshore wind farm to be detected is performed using the updated Kalman filter dynamic correction algorithm to adjust the target wind power prediction value.

6. A wind power prediction device, characterized in that: The device comprises: A data acquisition module is used to acquire multi-source performance evaluation data of the offshore wind farm to be tested, wherein the multi-source performance evaluation data includes historical meteorological data, historical wind power data, real-time meteorological data and equipment operation data; an influence coefficient determination module, configured to determine a meteorological influence coefficient corresponding to the offshore wind farm to be detected based on the historical meteorological data and the equipment operation data, wherein the meteorological influence coefficient is used to characterize the degree of influence of the meteorological data on the wind power output by the offshore wind farm to be detected; A power prediction module, configured to output a wind power prediction value based on the historical meteorological data and the historical wind power data by using a preset wind power prediction model; A prediction value correction module, configured to correct the wind power prediction value based on the real-time meteorological data and the meteorological influence coefficient to obtain a target wind power prediction value; The impact coefficient determination module is also used to determine the wind speed data and wind speed average corresponding to the environment of the offshore wind farm to be detected in the historical time period based on the historical meteorological data; determine the wind speed duration deviation and wind speed fluctuation factor corresponding to the offshore wind farm to be detected in the historical time period based on the wind speed data, the wind speed average and the wind speed allowable deviation range; determine the meteorological damage equipment event frequency factor corresponding to the offshore wind farm to be detected in the historical time period based on the equipment operation data, and the meteorological damage equipment event frequency factor is used to characterize the frequency of wind farm equipment damage in the offshore wind farm to be detected caused by meteorological events; determine the first weight coefficient corresponding to the wind speed duration deviation, the second weight coefficient corresponding to the wind speed fluctuation factor and the third weight coefficient corresponding to the meteorological damage equipment event frequency factor through an objective weighting method; determine the meteorological impact coefficient corresponding to the offshore wind farm to be detected based on the wind speed duration deviation, the wind speed fluctuation factor, the meteorological damage equipment event frequency factor, the first weight coefficient, the second weight coefficient and the third weight coefficient.

7. A wind power prediction device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the wind power prediction method according to any one of claims 1 to 5.

8. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the wind power prediction method according to any one of claims 1 to 5 are implemented.

Images