Meteorological data intelligent analysis method for new energy

Abstract

The invention belongs to the technical field of new energy meteorological monitoring, and discloses a new energy-oriented meteorological data intelligent analysis method. Comprising the following steps: fusing and extracting meteorological element data of a target region based on a global reanalysis data set and a regional high-resolution observation data set, and constructing a new energy meteorological analysis large model; performing meteorological data prediction by using a new energy meteorological analysis large model according to the current meteorological element data; collecting multi-dimensional feature information of each monitoring area, generating preset power generation feasibility evaluation results corresponding to each wind field monitoring area, each water field monitoring area and each light field monitoring area in combination with meteorological prediction data of each monitoring area, and performing power generation feasibility judgment; and further identifying an abnormal power generation new energy type direction and a key power generation new energy type direction. The prediction accuracy and timeliness are remarkably improved, the power generation feasibility can be comprehensively and accurately evaluated, potential risks can be perceived in advance, and the power generation stability and the equipment safety are effectively guaranteed.

Description

Technical Field

[0001] The invention belongs to the technical field of new energy meteorological monitoring, and relates to an intelligent analysis method of meteorological data for new energy. Background Art

[0002] The production process of renewable energy power is highly dependent on meteorological data forecasts, which can provide information on key meteorological parameters such as wind speed, wind direction, sunshine time, cloud thickness, etc. These parameters are essential for accurate prediction of renewable energy production management. Due to the complexity and variability of meteorological conditions, how to obtain refined and high-resolution meteorological data, especially accurate prediction in the short term, is one of the main challenges facing renewable energy power generation processing and prediction. Therefore, research based on intelligent analysis of meteorological data for renewable energy is of great significance.

[0003] There are also technical solutions for new energy meteorological monitoring in the prior art. For example, a Chinese invention patent application with publication number CN118332937B is for a new energy meteorological big model construction method, device and power prediction method, which includes: constructing a new energy meteorological big model training data set based on ERA5 data; constructing a graph neural network big model with wind and solar node attention and dynamic graph structure; inputting the constructed input data set and output data set into the graph neural network big model, and obtaining the new energy meteorological big model through training; obtaining the site new energy meteorological element prediction data through the new energy meteorological big model, and inputting the meteorological-power correction model to obtain the predicted power.

[0004] In addition, a Chinese invention patent application for a new energy long-term electricity forecasting method and system for intelligent migration of power meteorological data with publication number CN116227249B includes: obtaining historical power generation data of a target power station, and determining a first power generation forecast result of the target power station in a forecast time period based on the historical power generation data of the target power station; matching similar power stations of the target power station in a power station set based on target meteorological characteristics corresponding to the target power station; obtaining historical power generation data of similar power stations, and determining a second power generation forecast result of the target power station in a forecast time period based on the historical power generation data of similar power stations; and determining a target power generation forecast result of the target power station based on the first power generation forecast result and the second power generation forecast result.

[0005] Although the above two schemes have proposed some solutions for new energy meteorological monitoring, they still have certain limitations: on the one hand, the existing technical solutions usually use a single data set obtained from the study of the mechanism of conventional general meteorological factors for meteorological forecasting and analysis. For example, the Chinese invention patent application for the above-mentioned new energy meteorological large model construction method, device and power prediction method constructs a new energy meteorological large model training data set based on ERA5 data. The data source is single, which is quite different from the new energy meteorological forecast requirements, reducing the accuracy of meteorological data analysis and prediction.

[0006] On the other hand, prior art solutions usually do not conduct a comprehensive analysis of meteorological forecast conditions, weather influencing factors and terrain influencing factors when further processing meteorological data. For example, in the above-mentioned two invention patent applications, the site new energy meteorological element forecast data and the target power generation forecast results are all simple meteorological data forecast results. This analysis method will lead to a lack of comprehensiveness in the meteorological data processing process and an inability to accurately reflect the actual meteorological environment.

[0007] On the other hand, the predicted power and target power generation prediction result analysis described in the above-mentioned two invention patent applications are not based on the data processing results to further conduct substantive analysis of power production risk management and control, but directly obtain the new energy related operating parameters. There is a lack of quantitative analysis and processing of the degree of power generation risk, which makes the risk assessment results lack usability and practicality, reducing the effectiveness of system use. Summary of the invention

[0008] In view of this, in order to solve the problems raised in the above background technology, a new energy-oriented meteorological data intelligent analysis method is proposed.

[0009] The purpose of the present invention can be achieved through the following technical solutions: A method for intelligent analysis of meteorological data for new energy, comprising: S1, extracting the two-dimensional distribution information of the target area to divide the monitoring area into several monitoring areas, and generating a unique code, each monitoring area corresponds to a different new energy type, including wind field, water field and light field.

[0010] S2. Based on the fusion of the global reanalysis dataset and the regional high-resolution observation dataset, the meteorological element data of the target area are extracted, and then a large model for new energy meteorological analysis is constructed. At the same time, the current meteorological element data of each monitoring area are collected.

[0011] S3. According to the current meteorological element data, a new energy meteorological analysis model is used to predict meteorological data to obtain meteorological forecast data for each monitoring area within a preset forecast period.

[0012] S4. Collect multi-dimensional feature information of each monitoring area, and then combine the meteorological forecast data of each monitoring area to generate power generation feasibility evaluation results corresponding to each wind field monitoring area, water field monitoring area and light field monitoring area within a preset forecast period.

[0013] S5. According to the power generation feasibility evaluation results, the power generation feasibility of each monitoring area within the preset prediction period is judged, and the specific abnormal power generation new energy type and key power generation new energy type are further identified.

[0014] Compared with the prior art, the present invention has the following beneficial effects: (1) The present invention extracts meteorological element data of the target area by fusing the global reanalysis dataset with the regional high-resolution observation dataset, making the data richer and more complete, effectively reducing the error and uncertainty of a single data source, and enhancing data reliability.

[0015] (2) The present invention constructs a large-scale new energy meteorological analysis model by fusing the global reanalysis dataset with the regional high-resolution observation dataset to extract the meteorological element data of the target area, and performs meteorological forecasting based on the model, which significantly improves the accuracy and timeliness of the forecast, taking into account both large-scale meteorological trends and regional subtle meteorological changes.

[0016] (3) The present invention comprehensively considers the impact of meteorological forecast results, environmental factors and abnormal meteorological indicators when generating the power generation feasibility evaluation results. It can comprehensively and accurately evaluate the feasibility of power generation, detect potential risks in advance, and ensure power generation stability and equipment safety.

[0017] (4) The present invention determines the feasibility of power generation in each monitoring area within a preset forecast period based on the power generation feasibility evaluation results, and can provide energy companies with a clear prediction of the power generation conditions in each area in the future period in advance, helping them to reasonably plan production plans; by accurately locating high-feasibility areas, resources can be concentrated to improve power generation efficiency and reduce operating costs; for low-feasibility areas, early warnings can be issued and response strategies can be formulated to enhance power generation stability and safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0019] Figure 1 It is a schematic diagram of the implementation steps of the method of the present invention.

[0020] Figure 2 A flow chart for determining the feasibility of wind farm power generation provided by the present invention.

[0021] Figure 3 A flow chart for judging the feasibility of water field power generation provided by the present invention.

[0022] Figure 4 A flow chart for determining the feasibility of light field power generation provided by the present invention.

[0023] Figure 5 is a block diagram of a computer system for implementing some embodiments of the present invention.

[0024] Reference numerals: 100 —computer system, 110 —memory, 120 —processor, 130 —bus, 140 —input and output interface, 150 —network interface, 160 —storage interface. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] See also Figure 1 As shown, the present invention provides an intelligent analysis method of meteorological data for new energy, including: S1, extracting two-dimensional distribution information of the target area to divide the monitoring area into several monitoring areas, and generating a unique code, each monitoring area corresponds to a different new energy type, including wind field, water field and light field.

[0027] It should be noted that the two-dimensional distribution information of the target area is extracted based on the design or drawings of the target area.

[0028] It should be added that the specific method of dividing the monitoring area is: based on the two-dimensional distribution information of the target area, the target area is divided according to the new energy type to obtain the wind field distribution area, water field distribution area and light field distribution area, and then further based on the equal area grid division method, a secondary area division is performed to obtain a number of wind field monitoring areas, water field monitoring areas and light field monitoring areas. It should be noted that in practice, the target area may only have one or two of the wind field, water field and light field. Considering the versatility of the method technology, the target area in the present invention includes a wind field, a water field and a light field, and the wind field, water field and light field are divided into a number of wind field monitoring areas, water field monitoring areas and light field monitoring areas.

[0029] It should be noted that the wind farm refers to a place where wind power is used for power generation, which may be a photovoltaic power plant. The water farm refers to a place where hydropower is used for power generation, which may be a hydroelectric dam. The wind farm refers to a place where wind power is used for power generation, which may be a wind power plant.

[0030] S2. Based on the fusion of the global reanalysis dataset and the regional high-resolution observation dataset, the meteorological element data of the target area are extracted, and then a large model for new energy meteorological analysis is constructed. At the same time, the current meteorological element data of each monitoring area are collected.

[0031] It should be explained that the global reanalysis dataset refers to a globally consistent meteorological and climate dataset generated by combining historical observation data with numerical weather forecast models using data assimilation technology. It provides long-term, high-temporal and spatial resolution global meteorological variables and is widely used in climate research, weather forecasting, environmental monitoring and other fields. The global reanalysis dataset in the present invention refers to ERA5.

[0032] It should be explained that the regional high-resolution observation data set refers to the meteorological, environmental or geographical data with high temporal and spatial resolution obtained for a specific geographical area through a high-density observation network or high-precision remote sensing technology. It is usually obtained through comprehensive collection of ground observation stations, satellite remote sensing and radar observation technology. The regional high-resolution observation data set in the present invention refers to the China regional high-resolution data set.

[0033] It should be noted that the reason for extracting meteorological element data of the target area based on the fusion of the global reanalysis dataset and the regional high-resolution observation dataset is: on the one hand, the global reanalysis dataset provides meteorological data with extensive temporal and spatial coverage, and the regional high-resolution observation dataset focuses on regional details. The combination of the two can make up for the limitations of a single dataset, making the extracted data more comprehensive and accurate, and fully presenting the characteristics of meteorological elements. On the other hand, the fused data provides richer information for building a large model for new energy meteorological analysis, which helps the model learn complex meteorological laws and improve the accuracy of meteorological data prediction, thereby more reliably evaluating the feasibility of new energy power generation and providing strong support for the development of the new energy industry.

[0034] In a preferred embodiment of the present invention, the specific method of constructing the new energy meteorological analysis large model is as follows: extract the key meteorological element data in the target power generation area after the fusion of the global reanalysis data set and the regional high-resolution observation data set, and use the neural network to simulate the evolution process of the meteorological element data with time and space to obtain the new energy meteorological analysis large model.

[0035] It should be noted that the reason for constructing a large model for meteorological analysis of new energy is that the construction of a large model for meteorological analysis of new energy can accurately evaluate the power generation status of new energy. The power generation efficiency of new energy is greatly affected by meteorological conditions. Wind farm power generation depends on wind speed and direction, water field depends on rainfall, and light field is related to solar irradiance. By fusing the global reanalysis data set with the regional high-resolution observation data set to extract meteorological element data and then construct a large model, the spatiotemporal evolution of meteorological elements can be simulated. This can predict the meteorological data of each monitoring area, combine multi-dimensional feature information to evaluate the feasibility of power generation, identify abnormal and key power generation areas, help new energy companies to rationally plan power generation plans, improve power generation efficiency, reduce risks caused by meteorological factors, and promote the stable development of the new energy industry.

[0036] It should be noted that the present invention extracts meteorological element data of the target area based on the fusion of the global reanalysis dataset and the regional high-resolution observation dataset, making the data richer and more complete, effectively reducing the error and uncertainty of a single data source, and enhancing data reliability.

[0037] S3. According to the current meteorological element data, a new energy meteorological analysis model is used to predict meteorological data to obtain meteorological forecast data for each monitoring area within a preset forecast period.

[0038] In a preferred embodiment of the present invention, the specific contents of the meteorological forecast data of each monitoring area are as follows: the monitoring areas can be divided into wind field monitoring areas, water field monitoring areas and light field monitoring areas according to the type of new energy, among which the meteorological forecast data of the wind field monitoring area is wind speed and wind direction, the meteorological forecast data of the water field monitoring area is rainfall, and the meteorological forecast data of the light field monitoring area is solar irradiance.

[0039] It should be noted that the current meteorological element data collected in each monitoring area is input into the constructed new energy meteorological analysis model. The model calculates according to the previously learned evolution law of meteorological elements and outputs the meteorological forecast data of each monitoring area within the preset forecast period, among which the wind field monitoring area obtains wind speed data, the water field monitoring area obtains rainfall data, and the light field monitoring area obtains solar irradiance data.

[0040] It should be further explained that the present invention constructs a large model for new energy meteorological analysis by extracting meteorological element data of the target area based on the fusion of the global reanalysis dataset and the regional high-resolution observation dataset, and performs meteorological forecasting based on the model, which significantly improves the accuracy and timeliness of the forecast, and takes into account both large-scale meteorological trends and regional subtle meteorological changes.

[0041] S4. Collect multi-dimensional feature information of each monitoring area, and then combine the meteorological forecast data of each monitoring area to generate power generation feasibility evaluation results corresponding to each wind field monitoring area, water field monitoring area and light field monitoring area within a preset forecast period.

[0042] In a preferred embodiment of the present invention, the specific method of collecting multi-dimensional feature information of each monitoring area is as follows: using a high-definition camera to obtain a distribution image of the target area, locating the position of each obstacle in each wind farm monitoring area based on the distribution image, numbering each obstacle, and using image processing software to obtain the height of each obstacle, the distance between each obstacle and each wind turbine, and the height of each wind turbine hub.

[0043] It should be noted that the obstacles may be natural obstacles and non-natural obstacles, wherein natural obstacles may be mountains and tall trees, and non-natural obstacles may be buildings and communication towers.

[0044] Extract and obtain the distribution image of the target area using a high-definition camera, obtain the flow direction of water in each water field monitoring area, and obtain the monitoring areas through which each water flow passes as the water volume convergence influence area of ​​each water field monitoring area, and obtain the influence distance of each water volume convergence influence area relative to each water field monitoring area.

[0045] It should be supplemented that the influence distance of each water volume convergence influence area relative to each water field monitoring area specifically refers to the horizontal distance between the center point of each water volume convergence influence area and the center point of each water field monitoring area.

[0046] The meteorological forecast results obtained by predicting the meteorological data using the new energy meteorological analysis model based on the current meteorological element data are extracted, and the preset prediction period is divided into several monitoring periods based on equal intervals. The duration of each monitoring period remains consistent, and each monitoring period is numbered. The rainfall in each monitoring period of each water field monitoring area within the preset prediction period and the rainfall in each monitoring period of each corresponding water volume aggregation impact area are statistically obtained.

[0047] It should be noted that the interval duration is set based on: first, the changing characteristics of meteorological data. If meteorological elements such as rainfall change frequently, a shorter interval duration needs to be set to accurately capture the changes; second, the accuracy requirements for power generation feasibility evaluation. If a more detailed assessment of the feasibility of hydropower generation is expected, a shorter interval can provide more detailed rainfall data; third, data processing cost and efficiency. Although too long an interval can reduce the amount of data processing, it will lose information, and too short an interval will increase the processing burden. It is necessary to weigh the two to determine the appropriate duration. Exemplary, the interval duration is 20 minutes. Correspondingly, the preset forecast period is 6 hours.

[0048] The cloud thickness of each light field monitoring area within the preset prediction period is obtained according to the meteorological forecast result, and then the cloud thickness is quantified based on a preset cloud thickness quantification relationship to obtain the cloud influence coefficient of each light field monitoring area.

[0049] It should be added that the quantitative relationship of the cloud thickness is shown in Table 1.

[0050] Table 1 Quantitative relationship table of cloud thickness

[0051]

[0052] In a preferred embodiment of the present invention, the specific analysis method for generating the power generation feasibility evaluation results corresponding to each wind farm monitoring area, water field monitoring area and light field monitoring area within a preset prediction period is as follows: Specifically, the power generation feasibility evaluation results corresponding to the wind field, water field and light field need to construct a power generation feasibility evaluation index for each wind farm monitoring area, a power generation feasibility evaluation index for each water field monitoring area and a power generation feasibility evaluation index for each light field monitoring area.

[0053] The specific analysis method of the power generation feasibility evaluation index of each wind farm monitoring area is as follows: extract the wind speed of each wind farm monitoring area, recorded as ,in Indicates the number of the wind farm monitoring area. , Indicates the number of wind farm monitoring areas.

[0054] The height of each obstacle corresponding to each wind farm monitoring area, the distance between each obstacle and each wind turbine, and the height of each wind turbine hub are extracted and recorded as , , ,in Indicates the number of the obstacle. , represents the number of obstacles, Indicates the fan number. , Indicates the number of fans.

[0055] Using the formula The power generation feasibility evaluation index of each wind farm monitoring area is obtained by analysis ,in Indicates the preset suitable working wind speed. It represents the average horizontal distance between obstacles and wind turbines in each wind farm monitoring area. Calculate the mean value, It represents the average obstacle height of each wind farm monitoring area, which is calculated by Calculate the mean value, It represents the average hub height of each wind turbine in the monitoring area of ​​each wind farm, which is calculated by Calculate the mean value, It represents the standard deviation of wind speed in each wind farm monitoring area, which is obtained by calculating the wind speed in each wind farm monitoring area. It indicates the weight factor calibrated by comprehensively considering various influencing factors in advance.

[0056] It should be noted that the construction ideas of the analysis formulas for the power generation feasibility evaluation index of the above wind farm monitoring areas are as follows: 1. Wind speed consideration: In the formula This part reflects the impact of wind speed on the feasibility of power generation. This formula can reflect the impact of the difference between actual wind speed and suitable wind speed on the feasibility of power generation. The closer the wind speed is to the suitable wind speed, the larger the value of this part is, and the higher the power generation feasibility evaluation index may be.

[0057] 2. Impact of obstacles: This reflects the impact of obstacles. When the obstacle is far away from the wind turbine ( Large), low obstacle height ( Small), high fan hub height ( This part has a great effect on improving the power generation feasibility evaluation index when the obstacle shielding coefficient is large, which is consistent with the principle that it is beneficial to power generation when the obstacle shielding coefficient is low. It reflects the influence of the relative position relationship between the obstacle and the wind turbine on the feasibility of power generation.

[0058] 3. Turbulence intensity considerations: The stability of wind speed is taken into account, which is specifically reflected in the influence of turbulence intensity. Wind speed standard deviation The smaller the turbulence intensity The smaller it is, the more stable the wind speed is. The larger it is, the smaller the negative impact on the power generation feasibility evaluation index is, which reflects the role of wind speed stability on power generation feasibility.

[0059] 4. and It is a weight factor calibrated by comprehensively considering various influencing factors in advance. It is used to weigh the influence of factors such as obstacles and wind speed stability on the power generation feasibility evaluation index, so as to comprehensively consider multiple factors and construct a more comprehensive calculation model for the power generation feasibility evaluation index.

[0060] It should be further explained that and The specific calibration method is: collect a large amount of historical data of wind farms, including wind speed, obstacle height and distance, power generation and other data. Use principal component analysis PCA to reduce the dimension of the data, find out the main components that affect the feasibility of power generation, and determine the weight factor according to the contribution rate of the main components. If the analysis finds that the contribution rate of the main component corresponding to the obstacle-related factors is 40%, and the contribution rate of the main component corresponding to the wind speed stability factor is 60%, then Set to 0.4, Set to 0.6.

[0061] In one possible embodiment, assuming , , , , and then perform data simulation calculation based on the power generation feasibility evaluation index analysis formula of the wind farm monitoring area to obtain the corresponding simulation calculation results. Some simulation results can be referred to Table 2.

[0062] Table 2 Power generation feasibility based on some wind farm monitoring areas

[0063] Evaluation index analysis formula corresponding to data simulation results

[0064]

[0065] It is necessary to further explain the above data simulation results: 1. The power generation feasibility evaluation index is obtained by comprehensively considering factors such as wind speed, obstacle conditions and wind speed stability. The higher the index, the better the feasibility of power generation in the wind farm monitoring area.

[0066] 2. The power generation feasibility evaluation index of wind farm monitoring area 2 is the highest (33.93). The reason is that its wind speed (9m / s) is close to the suitable working wind speed (8m / s), and the average obstacle height is low (8m). The combination of the average horizontal distance between obstacles and wind turbines and the average wind turbine hub height is also more favorable, which makes the combined calculation results in the formula higher.

[0067] 3. The index of wind farm monitoring area 1 is the second highest (18.84). Its wind speed is slightly lower than the suitable working wind speed, and the obstacle-related parameters are not as ideal as those in area 2, but it still has certain feasibility for power generation.

[0068] 4. The power generation feasibility evaluation index of wind farm monitoring area 3 is the lowest (10.35), mainly because its wind speed (6m / s) is far from the suitable working wind speed, and the average obstacle height is high (12m). These factors combined lead to its relatively poor power generation feasibility.

[0069] In a preferred embodiment of the present invention, the specific analysis method of the power generation feasibility evaluation index of each water field monitoring area is as follows: extract the rainfall and rainfall duration of each water field monitoring area, recorded as ,in Indicates the number of the water field monitoring area. , Represents the number of water field monitoring areas. Based on historical data records, the water flow rate of each water field monitoring area at the current monitoring time is obtained, which is recorded as .

[0070] It should be noted that the specific method for obtaining the water flow rate of each water field monitoring area at the current monitoring time based on historical data records is: extracting historical data records, and then using the water flow rate of each water field monitoring area at the reference time corresponding to the current monitoring period as the water flow rate of each water field monitoring area at the current monitoring time. The reference time refers to the time corresponding to the preset reference time length before the current reference time.

[0071] Extract the rainfall in each monitoring period of each water field monitoring area and the corresponding rainfall in each monitoring period of each water volume aggregation impact area, and record them as , ,in Indicates the number of the monitoring period, , represents the number of monitoring periods, The number indicating the area affected by the water flow. , Indicates the number of areas affected by water collection.

[0072] Extract the influence distance of each water volume gathering influence area relative to each water field monitoring area, recorded as .

[0073] Using the formula The feasibility evaluation index of power generation in each water field monitoring area is obtained through analysis. ,in Indicates the preset appropriate water flow rate. It represents the average rainfall in each monitoring period in each water field monitoring area. Calculate the mean value, It represents the preset water volume collection impact correction factor, which is calculated as follows: ,in Indicates the preset reference rainfall warning value. Indicates the preset reference aggregation influence distance, It represents the average influence distance of each water volume gathering influence area relative to each water field monitoring area, which is calculated by the influence distance of each water volume gathering influence area relative to each water field monitoring area. Calculate the mean value, It represents the average rainfall in each monitoring period of each water field monitoring area corresponding to each water volume gathering impact area.

[0074] It should be noted that the construction ideas of the analysis formulas for the power generation feasibility evaluation index of the above-mentioned water field monitoring areas are as follows: 1. Suitable water flow rate factor: This part reflects the impact of water flow rate on the feasibility of power generation. It is the pre-set appropriate water flow rate. is the actual water flow velocity. This formula reflects the impact of the difference between the actual water flow velocity and the appropriate flow velocity on the feasibility of power generation. When the actual flow velocity is closer to the appropriate flow velocity, the value of this part is larger, and the power generation feasibility evaluation index may be higher, highlighting the importance of water flow velocity as a key factor to water field power generation.

[0075] 2. Rainfall factors: This part takes into account the rainfall factor. is the average rainfall in each monitoring area of ​​each water field during each monitoring period. is the rainfall in each monitoring period. The role of average rainfall is emphasized. The average rainfall and the fluctuation of rainfall in different periods are taken into consideration. This part aims to measure the impact of rainfall and its stability on the feasibility of power generation. The greater the average rainfall and the smaller the fluctuation, the more favorable it is to the feasibility of power generation, and the value of this part will increase accordingly.

[0076] 3. Water volume collection correction factors: In is the pre-set water volume aggregation correction factor, which is calculated as follows: .in is the reference rainfall warning value, is the reference aggregation influence distance, It is the average rainfall of each monitoring period in each water volume gathering impact area in each water field monitoring area. It is the average influence distance of each water collection area relative to each water field monitoring area. This factor takes into account the impact of factors such as rainfall in the water collection area and its distance from the water field monitoring area on the feasibility of power generation, and is used to correct the evaluation index to make the evaluation more in line with the actual situation.

[0077] In one possible embodiment, assuming , , , , , , based on the power generation feasibility evaluation index analysis formula of the water field monitoring area, data simulation calculation is performed to obtain the corresponding simulation calculation results. Some simulation results can be referred to Table 3.

[0078] Table 3 Power generation feasibility based on some water field monitoring areas

[0079] Evaluation index analysis formula corresponding to data simulation results

[0080]

[0081] What needs further explanation is that the above data simulation results are: 1. The power generation feasibility evaluation index comprehensively considers factors such as water flow rate, rainfall and water collection to measure the power generation feasibility of the water field monitoring area. The higher the index, the better the power generation feasibility.

[0082] 2. The power generation feasibility evaluation index of area 2 is the highest (7.29), because its actual water flow rate (6m / s) is close to the appropriate water flow rate (5m / s), the average rainfall (15mm) is large and the rainfall fluctuation is relatively small, and the water volume convergence correction factor is positive and large. These factors combined make its power generation feasibility high.

[0083] 3. The index of region 1 is second (4.60), with moderate average rainfall (10 mm), but the water flow rate is slightly lower than the appropriate value, and the correction factor of water concentration is also positive. The overall feasibility of power generation is at a medium level.

[0084] 4. The power generation feasibility evaluation index of area 3 is the lowest (2.75), mainly because the actual water flow velocity (3m / s) is far from the appropriate flow velocity, and the average rainfall (7mm) is small. Although the correction factor of water volume convergence is negative, which reduces the impact to a certain extent, the overall power generation feasibility is poor.

[0085] In a preferred embodiment of the present invention, the specific analysis method of the power generation feasibility evaluation index of each light field monitoring area is as follows: extract the solar irradiance of each light field monitoring area, recorded as ,in Indicates the number of the light field monitoring area, , Indicates the number of light field monitoring areas.

[0086] Extract the cloud influence coefficient of each light field monitoring area and record it as .

[0087] Using the formula The power generation feasibility evaluation index of each light field monitoring area is obtained by analysis ,in Indicates the preset reference solar irradiance threshold.

[0088] It should be noted that the construction ideas of the above-mentioned power generation feasibility evaluation index analysis formulas for each light field monitoring area are as follows: 1. Solar irradiance factor: This part reflects the impact of solar irradiance on the feasibility of power generation. is the solar irradiance of each light field monitoring area, is the preset reference solar irradiance threshold. This formula reflects the relative relationship between the actual solar irradiance and the reference threshold. The higher the actual solar irradiance, The larger the value of , the higher the power generation feasibility evaluation index may be when other conditions remain unchanged, which highlights the importance of solar irradiance as a key factor to solar field power generation. This is because solar irradiance directly determines the amount of energy that a solar field can obtain, which in turn affects the feasibility and efficiency of power generation.

[0089] 2. Cloud influence factors: Introducing cloud influence coefficient This is to take into account the effects of clouds on solar radiation shielding and scattering. The presence of clouds will change the solar irradiance reaching the light field monitoring area, and different cloud conditions (such as thickness, density, etc.) will have different effects. It comprehensively reflects the weakening or enhancement of solar radiation by clouds (when clouds have a certain reflection and scattering effect to enhance local irradiance, it may be greater than 1; in general, clouds mainly play a weakening role. is less than 1). By multiplying , the actual changes in solar irradiance caused by cloud factors can be corrected, making the power generation feasibility evaluation index more consistent with the actual situation of solar field power generation.

[0090] In one possible embodiment, assuming , ,Based on the analysis formula of the power generation feasibility evaluation index of the light field monitoring area, data simulation calculation is performed to obtain the corresponding simulation calculation results. Some simulation results can be referred to Table 4.

[0091] Table 4 Power generation feasibility based on some light field monitoring areas

[0092] Evaluation index analysis formula corresponding to data simulation results

[0093]

[0094] What needs further explanation is that the simulation results of the above data are as follows: 1. The power generation feasibility evaluation index combines the solar irradiance and cloud influence coefficient to measure the power generation feasibility of the light field monitoring area. The higher the index, the better the power generation feasibility.

[0095] 2. The power generation feasibility evaluation index of area 2 is the highest (1.0125) because its solar irradiance (900W / m 2 ) is higher than the reference solar irradiance threshold (800 ), and the cloud influence coefficient (0.9) is relatively high, which means that the clouds have a small weakening effect on solar radiation. These two factors combined make it more feasible to generate electricity.

[0096] 3. The index of region 4 is the second highest (0.7), and its solar irradiance (700 ) is lower than the reference threshold. Although the cloud influence coefficient is 0.8, the overall power generation feasibility is at a medium level.

[0097] 4. The power generation feasibility evaluation index of area 3 is the lowest (0.525), mainly because of its solar irradiance (600W / m 2 ) is relatively low, and the cloud influence coefficient (0.7) is also small. The clouds have a greater effect on weakening solar radiation, resulting in poor overall power generation feasibility.

[0098] It should be noted that the present invention comprehensively considers the influence of meteorological forecast results, environmental factors and abnormal meteorological indicators when generating the power generation feasibility evaluation results. It can comprehensively and accurately evaluate the feasibility of power generation, detect potential risks in advance, and ensure power generation stability and equipment safety.

[0099] S5. According to the power generation feasibility evaluation results, the power generation feasibility of each monitoring area within the preset prediction period is judged, and the specific abnormal power generation new energy type and key power generation new energy type are further identified.

[0100] In a preferred embodiment of the present invention, the specific method of judging the feasibility of power generation in each monitoring area within a preset prediction period is as follows: extract the power generation feasibility evaluation results corresponding to each wind farm monitoring area, water field monitoring area and light field monitoring area, and then perform comparative analysis based on the pre-set wind farm power generation feasibility evaluation threshold, water field power generation feasibility evaluation threshold and light field power generation feasibility evaluation threshold, to obtain the result of whether each monitoring area within the preset prediction period is allowed to carry out power generation operations.

[0101] Furthermore, the power generation feasibility evaluation index of each wind farm monitoring area, the power generation feasibility evaluation index of the water field monitoring area and the power generation feasibility evaluation index of the light field monitoring area are respectively compared with the pre-set wind farm power generation feasibility evaluation threshold, the water field power generation feasibility evaluation threshold and the light field power generation feasibility evaluation threshold.

[0102] See also Figure 2 As shown, if the power generation feasibility evaluation index of a wind farm monitoring area is greater than or equal to the wind farm power generation feasibility evaluation threshold, it is determined that the wind farm monitoring area is allowed to perform power generation operations.

[0103] See also Figure 3 As shown, if the power generation feasibility evaluation index of a water field monitoring area is greater than or equal to the water field power generation feasibility evaluation threshold, it is determined that the water field monitoring area is allowed to perform power generation operations.

[0104] See also Figure 4 As shown, if the power generation feasibility evaluation index of a certain light field monitoring area is greater than or equal to the light field power generation feasibility evaluation threshold, it is determined that the light field monitoring area is allowed to perform power generation operations.

[0105] It should be noted that the setting basis of the feasibility evaluation threshold of wind farm power generation, the feasibility evaluation threshold of water field power generation and the feasibility evaluation threshold of solar field power generation is: first, historical data and experience, referring to the actual operation data of wind, water and solar field power generation in the past, summarizing the feasibility of power generation under different conditions, and determining the threshold value in combination with industry experience; second, equipment performance, considering the normal operation of wind, water and solar power generation equipment and the minimum environmental conditions required to achieve a certain power generation efficiency, such as the suitable wind speed range of wind turbines, the water flow conditions required for turbines, the light intensity required for photovoltaic panels, etc.; third, economic factors, comprehensively considering the cost and benefits of power generation, ensuring that power generation above the threshold is economically feasible, and balancing resource utilization and economic benefits. Exemplarily, the feasibility evaluation threshold of wind farm power generation is 20, the feasibility evaluation threshold of water field power generation is 4, and the feasibility evaluation threshold of solar field power generation is 0.7.

[0106] In a preferred embodiment of the present invention, the specific identification process of the abnormal power generation new energy type is as follows: extract the judgment results of whether each monitoring area is allowed to perform power generation operations, record the monitoring areas where it is judged that power generation operations are allowed as normal monitoring areas, and record the monitoring areas where it is judged that power generation operations are not allowed as risk monitoring areas, count the number of wind field monitoring areas, water field monitoring areas and light field monitoring areas corresponding to the risk monitoring areas, and then perform comparative analysis to obtain the abnormal power generation new energy type.

[0107] Specifically, the number of wind farm monitoring areas, water field monitoring areas and light field monitoring areas corresponding to the risk monitoring areas are compared, and the largest number is selected as the indicator of abnormal power generation new energy type.

[0108] In a preferred embodiment of the present invention, the specific identification process of the key power generation new energy type is as follows: count the number of wind field monitoring areas, water field monitoring areas and light field monitoring areas corresponding to the normal monitoring area, and then conduct comparative analysis to obtain the key power generation new energy type.

[0109] Specifically, the number of wind field monitoring areas, water field monitoring areas and light field monitoring areas corresponding to the normal monitoring areas are compared, and the area with the largest number is selected as the key type of new energy for power generation.

[0110] It should be noted that the present invention determines the feasibility of power generation in each monitoring area within a preset forecast period based on the power generation feasibility evaluation results, and can provide energy companies with a clear prediction of the power generation conditions of each area in the future period in advance, helping them to reasonably plan production plans; by accurately locating high-feasibility areas, resources can be concentrated to improve power generation efficiency and reduce operating costs; for low-feasibility areas, early warnings can be issued and response strategies can be formulated to enhance power generation stability and safety.

[0111] See also Figure 51 is a block diagram of a computer system for implementing some embodiments of the present disclosure. The computer system 100 may be in the form of a general-purpose computing device. The computer system 100 includes a memory 110, a processor 120, and a bus 130 that connects different system components.

[0112] The memory 110 may include, for example, a system memory, a non-volatile storage medium, etc. The system memory may store, for example, an operating system, an application program, a boot loader (BootLoader), and other programs. The system memory may include a volatile storage medium, such as a random access memory (RAM) and / or a cache memory. The non-volatile storage medium may store, for example, instructions for executing at least one of the corresponding embodiments of the method for improving the torsional stiffness of the vehicle body. The non-volatile storage medium includes, but is not limited to, a disk memory, an optical memory, a flash memory, etc.

[0113] The processor 120 can be implemented by a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistors and other discrete hardware components. Accordingly, such as the construction of a large model for new energy meteorological analysis, meteorological data forecasting, generation of power generation feasibility evaluation results and power generation feasibility judgment can be implemented by the instructions of the central processing unit (CPU) running the memory to execute the corresponding steps, or by a dedicated circuit to execute the corresponding steps.

[0114] The bus 930 may use any of a variety of bus architectures, including, but not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MCA) bus, and a Peripheral Component Interconnect (PCI) bus.

[0115] The computer system 100 may also include an input / output interface 140, a network interface 150, a storage interface 160, etc. These interfaces 140, 150, 160, the memory 110, and the processor 120 may be connected via a bus 130. The input / output interface 140 may provide a connection interface for input / output devices such as a display, a mouse, and a keyboard. The network interface 150 may provide a connection interface for various networked devices. The storage interface 160 may provide a connection interface for external storage devices such as a floppy disk, a USB flash drive, and an SD card.

[0116] The flowchart or block diagram of the method according to the embodiment of the present invention describes various aspects of the present invention. It should be understood that each frame of the flowchart or block diagram and the combination of frames can be implemented by computer-readable program instructions.

[0117] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they shall all fall within the protection scope of the present invention.

Claims

1. A meteorological data intelligent analysis method for new energy, characterized in that: include: S1. Extract the two-dimensional distribution information of the target area to divide the monitoring area into several monitoring areas and generate unique codes. Each monitoring area corresponds to a different type of new energy, including wind farms, water farms and light farms. S2, extract meteorological element data of the target area based on the fusion of global reanalysis dataset and regional high-resolution observation dataset, and then build a large model for new energy meteorological analysis, and collect current meteorological element data of each monitoring area at the same time; S3, using the new energy meteorological analysis model to predict meteorological data based on the current meteorological element data, and obtaining meteorological forecast data for each monitoring area within a preset forecast period; S4, collecting multi-dimensional feature information of each monitoring area, and then combining the meteorological forecast data of each monitoring area to generate power generation feasibility evaluation results corresponding to each wind field monitoring area, water field monitoring area and light field monitoring area within a preset forecast period; S5. According to the power generation feasibility evaluation results, the power generation feasibility of each monitoring area within the preset prediction period is judged, and the specific abnormal power generation new energy type and key power generation new energy type are further identified.

2. The method for intelligent analysis of meteorological data for new energy sources as claimed in claim 1, characterized in that: The specific method of constructing the new energy meteorological analysis model is as follows: The key meteorological element data in the target power generation area are extracted by fusing the global reanalysis dataset and the regional high-resolution observation dataset. The neural network is used to simulate the evolution of the meteorological element data over time and space to obtain a large model for new energy meteorological analysis.

3. The method for intelligent analysis of meteorological data for new energy sources as claimed in claim 1, characterized in that: The specific contents of the meteorological forecast data for each monitoring area are as follows: The monitoring areas can be divided into wind field monitoring areas, water field monitoring areas and light field monitoring areas according to the type of new energy. The meteorological forecast data for the wind field monitoring area is wind speed and wind direction, the meteorological forecast data for the water field monitoring area is rainfall, and the meteorological forecast data for the light field monitoring area is solar irradiance.

4. The method for intelligent analysis of meteorological data for new energy sources as claimed in claim 3, characterized in that: The specific method of collecting the multi-dimensional feature information of each monitoring area is as follows: Use a high-definition camera to obtain the distribution image of the target area, locate the position of each obstacle in each wind farm monitoring area based on the distribution image, number each obstacle, and use image processing software to obtain the height of each obstacle, the distance between each obstacle and each wind turbine, and the height of each wind turbine hub; Extract the distribution image of the target area obtained by using a high-definition camera, obtain the flow direction of the water body in each water field monitoring area, and obtain the monitoring areas through which each water body flows as the water volume convergence influence area of ​​each water field monitoring area, and obtain the influence distance of each water volume convergence influence area relative to each water field monitoring area; Extract the meteorological forecast results obtained by forecasting meteorological data using the new energy meteorological analysis large model based on the current meteorological element data, divide the preset forecast period into several monitoring periods based on equal intervals, keep the duration of each monitoring period consistent, number each monitoring period, and statistically obtain the rainfall in each monitoring period of each water field monitoring area within the preset forecast period and the rainfall in each monitoring period of each corresponding water volume aggregation impact area; The cloud thickness of each light field monitoring area within the preset prediction period is obtained according to the meteorological forecast result, and then the cloud thickness is quantified based on a preset cloud thickness quantification relationship to obtain the cloud influence coefficient of each light field monitoring area.

5. The method for intelligent analysis of meteorological data for new energy sources as claimed in claim 4, characterized in that: The specific analysis method for generating the power generation feasibility evaluation results corresponding to each wind farm monitoring area, water farm monitoring area and light farm monitoring area within the preset prediction period is as follows: Specifically, the power generation feasibility evaluation results corresponding to the wind farm, water farm and light farm need to construct the power generation feasibility evaluation index of each wind farm monitoring area, the power generation feasibility evaluation index of each water farm monitoring area and the power generation feasibility evaluation index of each light field monitoring area, wherein the specific analysis method of the power generation feasibility evaluation index of each wind farm monitoring area is as follows: Extract the wind speed in each wind farm monitoring area and record it as ,in Indicates the number of the wind farm monitoring area. , Indicates the number of wind farm monitoring areas; The height of each obstacle corresponding to each wind farm monitoring area, the distance between each obstacle and each wind turbine, and the height of each wind turbine hub are extracted and recorded as , , ,in Indicates the number of the obstacle. , represents the number of obstacles, Indicates the fan number. , Indicates the number of fans; Using the formula The power generation feasibility evaluation index of each wind farm monitoring area is obtained by analysis ,in Indicates the preset suitable working wind speed. It represents the average horizontal distance between obstacles and wind turbines in each wind farm monitoring area. Calculate the mean value, It represents the average obstacle height of each wind farm monitoring area, which is calculated by Calculate the mean value, It represents the average hub height of each wind turbine in the monitoring area of ​​each wind farm, which is calculated by Calculate the mean value, It represents the standard deviation of wind speed in each wind farm monitoring area, which is obtained by calculating the wind speed in each wind farm monitoring area. It indicates the weight factor calibrated by comprehensively considering various influencing factors in advance.

6. The method for intelligent analysis of meteorological data for new energy sources as claimed in claim 5, characterized in that: The specific analysis method of the power generation feasibility evaluation index of each water field monitoring area is as follows: Extract the rainfall and rainfall duration in each water field monitoring area and record it as ,in Indicates the number of the water field monitoring area. , Represents the number of water field monitoring areas. Based on historical data records, the water flow rate of each water field monitoring area at the current monitoring time is obtained, which is recorded as ; Extract the rainfall in each monitoring period of each water field monitoring area and the corresponding rainfall in each monitoring period of each water volume aggregation impact area, and record them as , ,in Indicates the number of the monitoring period, , represents the number of monitoring periods, The number indicating the area affected by the water flow. , Indicates the number of areas affected by water accumulation; Extract the influence distance of each water volume gathering influence area relative to each water field monitoring area, recorded as ; Using the formula The feasibility evaluation index of power generation in each water field monitoring area is obtained through analysis. ,in Indicates the preset appropriate water flow rate. It represents the average rainfall in each monitoring period in each water field monitoring area. Calculate the mean value, It represents the preset water volume collection impact correction factor, which is calculated as follows: ,in Indicates the preset reference rainfall warning value. Indicates the preset reference aggregation influence distance, It represents the average influence distance of each water volume gathering influence area relative to each water field monitoring area, which is calculated by the influence distance of each water volume gathering influence area relative to each water field monitoring area. Calculate the mean value, It represents the average rainfall in each monitoring period of each water field monitoring area corresponding to each water volume gathering impact area.

7. The method for intelligent analysis of meteorological data for new energy sources as claimed in claim 6, characterized in that: The specific analysis method of the power generation feasibility evaluation index of each light field monitoring area is as follows: Extract the solar irradiance of each light field monitoring area and record it as ,in Indicates the number of the light field monitoring area, , Indicates the number of light field monitoring areas; Extract the cloud influence coefficient of each light field monitoring area and record it as ; Using the formula The power generation feasibility evaluation index of each light field monitoring area is obtained by analysis ,in Indicates the preset reference solar irradiance threshold.

8. The method for intelligent analysis of meteorological data for new energy sources as claimed in claim 1, characterized in that: The specific method for determining the feasibility of power generation in each monitoring area within the preset prediction period is as follows: The power generation feasibility evaluation results corresponding to each wind farm monitoring area, water field monitoring area and light field monitoring area are extracted, and then a comparative analysis is performed based on the pre-set wind farm power generation feasibility evaluation threshold, water field power generation feasibility evaluation threshold and light field power generation feasibility evaluation threshold to obtain the result of whether power generation operations are allowed in each monitoring area within the preset prediction period.

9. The method for intelligent analysis of meteorological data for new energy sources as claimed in claim 8, characterized in that: The specific identification process of the abnormal power generation new energy type is as follows: The judgment results of whether power generation operations are allowed in each monitoring area are extracted, and the monitoring areas where power generation operations are allowed are recorded as normal monitoring areas, and the monitoring areas where power generation operations are not allowed are recorded as risk monitoring areas. The number of wind farm monitoring areas, water farm monitoring areas and light field monitoring areas corresponding to the risk monitoring areas is counted, and then a comparative analysis is performed to obtain the type of abnormal power generation new energy.

10. The method for intelligent analysis of meteorological data for new energy sources as claimed in claim 9, characterized in that: The specific identification process of the key power generation new energy type is as follows: The number of wind field monitoring areas, water field monitoring areas and light field monitoring areas corresponding to the normal monitoring areas is counted, and then a comparative analysis is conducted to obtain the focus on the types of new energy sources for power generation.

Images