Wind turbine generator set ad hoc network cluster system based on meteorological networking

Abstract

The invention discloses a wind turbine generator set ad hoc network cluster system based on meteorological networking. The wind turbine generator set ad hoc network cluster system comprises a wind turbine generator set data measurement module, a communication module, a visualization module and a central control module, wherein the central control module comprises a data receiving module, a weather forecast module, a data analysis module and a decision module, the data receiving module and the weather forecast module are responsible for acquiring real-time and future weather data and inputting the weather data into the data analysis module, and the decision module is used for making a decision according to an analysis result output by the data analysis module. And the decision module decides the power generation state of each wind turbine generator based on big data analysis and according to the analysis result output by the data analysis module. According to the method, the wind turbine generators are networked, mutual cooperation and autonomous decision making are achieved, the power generation efficiency and the system stability can be improved, the operation and maintenance cost can be effectively reduced, the safety is improved, and more environment-friendly and user-friendly services are provided.

Description

Technical Field

[0001] The present invention relates to the technical field of wind turbine control, and in particular to a wind turbine self-organizing network cluster system based on meteorological networking. Background Art

[0002] Existing wind turbine clusters are often not connected to weather forecast systems, presenting significant deficiencies and potential hazards. For example, without real-time weather forecasts, wind turbines may fail to shut down in time when strong winds arrive, potentially damaging blades or towers. Alternatively, during freezing winter weather, wind turbines may be unable to adjust their operating status in a timely manner, potentially leading to blade icing, additional load, and even equipment downtime.

[0003] In summary, if wind turbines are not connected to the weather forecast system, they will lead to low power generation efficiency, increased risk of equipment damage, higher maintenance costs, energy waste, and poor user experience. Therefore, connecting wind turbines to the weather forecast system is crucial to improving the overall performance and economic benefits of wind farms. Summary of the Invention

[0004] The purpose of the present invention is to overcome the shortcomings of the existing technology and propose a wind turbine self-organizing network cluster system based on meteorological networking. By connecting wind turbines to the network and realizing mutual collaboration and autonomous decision-making, it can not only improve the power generation efficiency and system stability, but also effectively reduce operation and maintenance costs, improve safety, and provide more environmentally friendly and user-friendly services.

[0005] The purpose of the present invention is achieved through the following technical solution: a wind turbine self-organizing network cluster system based on meteorological networking, comprising:

[0006] Data measurement module, used to measure wind speed, wind direction, temperature, humidity and precipitation data of the environment where the wind turbine is located;

[0007] Communication module, used for data transmission between each wind turbine and each module;

[0008] The visualization module is used to visualize the predicted wind speed, actual wind speed and power generation recommendation data output by the central control module;

[0009] The central control module receives data from all wind turbines and analyzes and makes decisions based on weather forecast information, including:

[0010] The data receiving module is used to receive the wind speed, wind direction, temperature and humidity data output by the data measurement module, as well as precipitation data related to wind turbine power generation;

[0011] A weather forecast module is used to obtain real-time and predicted weather information, including future wind speed forecast data and future wind direction forecast data;

[0012] A data analysis module is used to analyze the collected data and determine whether current and future weather conditions are suitable for power generation based on machine learning;

[0013] The decision module determines the power generation status of each wind turbine based on big data analysis and the analysis results output by the data analysis module.

[0014] Furthermore, the data analysis module performs the following operations:

[0015] a. Receive data from the data receiving module and weather forecast module, and preprocess the data by filling in missing values, normalizing, and dividing the data into time series. First, use interpolation or statistical methods to fill in missing data, then standardize all data to the same range, and finally divide the data into short-term, medium-term, and long-term time series for analysis;

[0016] b. For the pre-processed wind speed data, a power generation strategy is selected according to the value of the wind speed data; if the wind speed data is in the low wind speed range, which is 0-3m / s, the wind turbine is considered unsuitable for power generation under this wind speed data; if the wind speed data is in the medium wind speed range, which is 4-10m / s, the wind turbine is considered suitable for power generation under this wind speed data, and the power generation efficiency is on an upward trend; if the wind speed data is in the high wind speed range, which is 11-25m / s, the wind turbine is considered suitable for power generation under this wind speed data, but the generator needs to be adjusted to ensure the safety of the equipment, that is, it should be used with caution; if the wind speed data is in the extremely high wind speed range, which is not less than 26m / s, the wind turbine is considered to have too high a risk of power generation under this wind speed data, and power generation needs to be stopped to protect the equipment;

[0017] c. For the pre-processed wind direction data, ensure that the wind direction data is consistent with the design direction of the wind turbine. Calculate the angle between the wind turbine and the optimal wind direction based on trigonometric functions. If the angle exceeds a preset threshold, reduce the wind turbine's power generation.

[0018] d. Use a machine learning model to predict wind speeds for the next few days. The pre-trained machine learning model is fed with historical wind speeds, temperatures, and air pressures, and outputs the expected future wind speeds. The machine learning model also incorporates a feedback mechanism. If the output of the expected future wind speed deviates from the actual power generation results, the model parameters are adjusted or the model is retrained.

[0019] e. Set a benchmark threshold value and compare the expected value of future wind speed with the benchmark threshold value to determine the power generation status of the wind turbine. If the expected value of future wind speed is higher than the benchmark threshold value, the wind turbine is considered suitable for power generation at this time. If the expected value of future wind speed is equal to the benchmark threshold value, it is considered that the accuracy of the expected value of future wind speed needs to be evaluated at this time. If the expected value of future wind speed is lower than the benchmark threshold value, the wind turbine is considered unsuitable for power generation at this time.

[0020] Furthermore, the decision module performs the following operations:

[0021] Combine current weather conditions with future forecasts from data analysis modules to generate power generation recommendations;

[0022] If the current weather is judged to be suitable for power generation and the expected value of future wind speed is higher than the reference threshold, the power generation suggestion = +1 is displayed;

[0023] If the current weather is judged to require caution and the expected value of future wind speed is equal to the benchmark threshold, the power generation suggestion = 0 is displayed;

[0024] If it is determined that the current weather is not suitable for power generation and the expected value of the future wind speed is lower than the reference threshold, the power generation suggestion = -1 is displayed.

[0025] Furthermore, the decision module includes:

[0026] Startup conditions: When the wind speed reaches the preset threshold and the wind speed obtained by the weather forecast module remains stable within the preset time period in the future, the wind turbine is started;

[0027] Stop conditions: When the wind speed is lower than the preset threshold or the wind speed is expected to drop significantly within the preset time period in the future as obtained by the weather forecast module, the wind turbine will be stopped; when the real-time weather information indicates snowfall, the wind turbine will be stopped; when the real-time weather information indicates hailfall, the wind turbine will be stopped; when the real-time weather information indicates that the precipitation exceeds the threshold precipitation, the wind turbine will be stopped;

[0028] Adjustment conditions: According to the changes in wind speed and wind direction, the blade angle of the wind turbine is dynamically adjusted based on machine learning; if the wind speed data is in the low wind speed range, which is 0-3m / s, the wind turbine blade angle is adjusted close to the wind direction, and the wind turbine is stopped from generating electricity; if the wind speed data is in the medium wind speed range, which is 4-10m / s, the wind turbine blade angle is dynamically increased and adjusted according to the real-time wind speed to optimize aerodynamic efficiency; if the wind speed data is in the high wind speed range, which is 11-25m / s, the wind turbine blade angle is adjusted to the limit angle to prevent the wind turbine from being damaged due to excessive wind speed; if the wind speed data is in the extremely high wind speed range, which is not less than 26m / s, the wind turbine blade angle is adjusted to the parking position, that is, the angle between the blade and the wind direction is maximized, and the wind turbine is stopped from generating electricity.

[0029] Furthermore, the wind turbine is integrated with a wind speed sensor, a wind direction sensor, a temperature sensor, a humidity sensor and a local controller, and the wind speed sensor, wind direction sensor, temperature sensor and humidity sensor are respectively communicated with the local controller for preliminary data processing, and the local controller is communicated with the data measurement module.

[0030] Furthermore, the central control module is respectively connected to multiple wind turbines through the communication modules to form a self-organizing network cluster of wind turbines, and the communication module and the central control module are redundant. The communication module is integrated with the MQTT or HTTP standard communication protocol, and the data measurement module, communication module, visualization module and central control module are connected in communication.

[0031] Furthermore, the data analysis module, weather forecast module, data analysis module and decision-making module are communicatively connected in sequence, the weather forecast module is communicatively connected to a weather forecast system, and the weather forecast system is integrated with a weather forecast service API.

[0032] A wind turbine self-organizing network clustering method based on meteorological networking is implemented by a processor calling a data measurement module, a communication module and a central control module in the above-mentioned wind turbine self-organizing network clustering system based on meteorological networking.

[0033] A non-transitory computer-readable medium storing instructions, when the instructions are executed by a processor, performs the steps of the above-mentioned wind turbine self-organizing network clustering method based on meteorological networking.

[0034] A computing device includes a processor and a memory for storing a program executable by the processor. When the processor executes the program stored in the memory, the above-mentioned wind turbine self-organizing network clustering method based on meteorological networking is implemented.

[0035] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0036] 1. Improve power generation efficiency. Using real-time weather forecast information and on-site data, the central control module more accurately schedules the operating status of each wind turbine, avoiding unnecessary downtime or inefficient operation. Based on changes in wind speed and direction, it dynamically adjusts wind turbine operating parameters to maximize power generation efficiency.

[0037] 2. Enhanced system stability. This provides a better redundancy mechanism. When a wind turbine fails, other wind turbines can promptly fill in, ensuring overall power generation capacity is not affected. Real-time monitoring and data analysis can quickly detect and locate faulty wind turbines, reducing downtime and improving system availability.

[0038] 3. Reduced Operation and Maintenance Costs. Remote Monitoring: The central control module monitors the status of all wind turbines in real time, reducing the need for manual inspections and lowering operation and maintenance costs. Data analysis enables early identification of potential failures, enabling preventive maintenance and avoiding downtime and repair costs caused by unexpected failures.

[0039] 4. Improve safety. Before severe weather arrives, the system can issue an early warning and automatically adjust the status of wind turbines or shut them down, reducing the risk of equipment damage. In the event of an emergency, the system can respond quickly to protect equipment safety.

[0040] 5. Data-driven decision-making. Collecting and analyzing large amounts of real-time data can reveal wind turbine operating patterns and potential problems, providing a basis for subsequent optimization. Leveraging machine learning and artificial intelligence technologies, we can continuously optimize wind turbine operating strategies, further improving power generation efficiency and system performance.

[0041] 6. Environmentally friendly. Through precise scheduling and optimization, ineffective operation time is reduced, energy consumption and carbon emissions are lowered. This improves system stability and reliability, extends the service life of wind turbines, reduces replacement and maintenance frequency, and minimizes environmental impact. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 This is the architecture diagram of the wind turbine self-organizing network cluster system based on meteorological networking.

[0043] Figure 2 This is the workflow diagram of the wind turbine self-organizing network cluster system based on meteorological networking. DETAILED DESCRIPTION

[0044] The present invention will be further described below with reference to specific embodiments.

[0045] Example 1

[0046] See also Figure 1 As shown in FIG, a wind turbine self-organizing network cluster system based on meteorological networking provided by this embodiment is provided. The wind turbine is integrated with a wind speed sensor, a wind direction sensor, a temperature sensor, a humidity sensor and a local controller. The wind speed sensor, wind direction sensor, temperature sensor and humidity sensor are respectively connected to the local controller for preliminary data processing, including:

[0047] 1) A data measurement module is used to measure wind speed, wind direction, temperature, humidity and precipitation data of the environment in which the wind turbine is located; the local controller is in communication with the data measurement module.

[0048] 2) Communication module, used for data transmission between each wind turbine and each module, the communication module is integrated with MQTT or HTTP standard communication protocol.

[0049] 3) Visualization module, which is used to visualize the predicted wind speed, actual wind speed and power generation recommendation data output by the central control module.

[0050] 4) A central control module, which is used to receive data from all wind turbines and analyze and make decisions based on weather forecast information. The central control module is connected to multiple wind turbines through communication modules to form a wind turbine self-organizing network cluster. The communication modules and central control modules have redundancy and include:

[0051] 4.1) Data receiving module, used to receive wind speed, wind direction, temperature and humidity data output by the data measurement module, as well as precipitation data related to wind turbine power generation;

[0052] 4.2) A weather forecast module, used to obtain real-time and predicted weather information; the weather forecast module is communicatively connected to a weather forecast system, and the weather forecast system is integrated with a weather forecast service API.

[0053] 4.3) Data analysis module, used to analyze the collected data and determine whether the current and future weather conditions are suitable for power generation, and perform the following operations:

[0054] a. Receive data from the data receiving module and weather forecast module, and preprocess the data by filling in missing values, normalizing, and time series partitioning. First, use interpolation or statistical methods to fill in missing data, then standardize all data to the same range, and finally divide the data into hourly, daily, and weekly time series for analysis;

[0055] b. For the pre-processed wind speed data, a power generation strategy is selected according to the value of the wind speed data; if the wind speed data is in the low wind speed range, which is 0-3m / s, the wind turbine is considered unsuitable for power generation under this wind speed data; if the wind speed data is in the medium wind speed range, which is 4-10m / s, the wind turbine is considered suitable for power generation under this wind speed data, and the power generation efficiency is on an upward trend; if the wind speed data is in the high wind speed range, which is 11-25m / s, the wind turbine is considered suitable for power generation under this wind speed data, but the generator needs to be adjusted to ensure the safety of the equipment, that is, it should be used with caution; if the wind speed data is in the extremely high wind speed range, which is not less than 26m / s, the wind turbine is considered to have too high a risk of power generation under this wind speed data, and power generation needs to be stopped to protect the equipment;

[0056] c. For the pre-processed wind direction data, ensure that the wind direction data is consistent with the design direction of the wind turbine. Calculate the angle between the wind turbine and the optimal wind direction based on trigonometric functions. If the angle exceeds the preset threshold of 30°, the wind turbine power generation needs to be reduced.

[0057] d. Use a machine learning model to predict wind speeds for the next few days. The pre-trained machine learning model is fed with historical wind speeds, temperatures, and air pressures, and outputs the expected future wind speed. The machine learning model also incorporates a feedback mechanism. If the output of the expected future wind speed deviates from the actual power generation results, the model parameters are adjusted or the model is retrained. Machine learning models include regression analysis, random forest, or LSTM time series models.

[0058] e. Set the benchmark threshold to 6 m / s, compare the expected value of future wind speed with the benchmark threshold, and judge the power generation situation of the wind turbine; if the expected value of future wind speed is higher than the benchmark threshold of 6 m / s, the wind turbine is considered suitable for power generation at this time; if the expected value of future wind speed is equal to the benchmark threshold of 6 m / s, it is considered that the accuracy of the expected value of future wind speed needs to be evaluated at this time; if the expected value of future wind speed is lower than the benchmark threshold of 6 m / s, the wind turbine is considered unsuitable for power generation at this time.

[0059] 4.4) The decision module determines the power generation status of each wind turbine based on big data analysis and the analysis results output by the data analysis module, including:

[0060] Startup conditions: When the wind speed reaches the preset threshold and the wind speed obtained by the weather forecast module remains stable within the preset time period in the future, the wind turbine is started;

[0061] Stop conditions: When the wind speed is lower than the preset threshold or the wind speed is expected to drop significantly within the preset time period in the future as obtained by the weather forecast module, the wind turbine will be stopped; when the real-time weather information indicates snowfall, the wind turbine will be stopped; when the real-time weather information indicates hailfall, the wind turbine will be stopped; when the real-time weather information indicates that the precipitation exceeds the threshold precipitation, the wind turbine will be stopped;

[0062] Adjustment conditions: According to the changes in wind speed and wind direction, the blade angle of the wind turbine is dynamically adjusted based on machine learning; if the wind speed data is in the low wind speed range, which is 0-3m / s, the wind turbine blade angle is adjusted close to the wind direction, and the wind turbine is stopped from generating electricity; if the wind speed data is in the medium wind speed range, which is 4-10m / s, the wind turbine blade angle is dynamically increased and adjusted according to the real-time wind speed to optimize aerodynamic efficiency; if the wind speed data is in the high wind speed range, which is 11-25m / s, the wind turbine blade angle is adjusted to the limit angle to prevent the wind turbine from being damaged due to excessive wind speed; if the wind speed data is in the extremely high wind speed range, which is not less than 26m / s, the wind turbine blade angle is adjusted to the parking position, that is, the angle between the blade and the wind direction is maximized, and the wind turbine is stopped from generating electricity.

[0063] Finally, a comprehensive analysis combining current weather and future forecasts from the data analysis module generates power generation recommendations;

[0064] If the current weather is judged to be suitable for power generation and the expected future wind speed is higher than the baseline threshold, the power generation suggestion is displayed as +1; if the current wind speed is 7m / s and the future predicted wind speed is 8m / s, the comprehensive power generation suggestion is +1, which means it is suitable to continue power generation;

[0065] If the current weather is judged to require caution and the expected value of future wind speed is equal to the benchmark threshold, the power generation suggestion = 0 is displayed;

[0066] If the current weather is judged to be unsuitable for power generation and the expected future wind speed is lower than the benchmark threshold, the power generation suggestion is displayed as -1. If the current wind speed is 2m / s and the future predicted wind speed is 5m / s, the comprehensive power generation suggestion is -1, which means it is not suitable for power generation.

[0067] The installation and debugging process of the wind turbine self-organizing network cluster system based on meteorological networking is as follows:

[0068] S1. Hardware deployment:

[0069] Install sensors and communication modules on each wind turbine.

[0070] Deploy the central control system server and configure the communication interface.

[0071] S2. Software Development:

[0072] Develop data collection and transmission programs to ensure that sensor data can be uploaded in real time.

[0073] Develop data analysis and decision-making modules for central control systems.

[0074] Integrate third-party weather forecast service API to obtain real-time and predicted weather information.

[0075] S3, testing and debugging:

[0076] Conduct system integration testing to ensure that various modules work together.

[0077] Debug decision-making logic to ensure that wind turbines can make autonomous decisions based on weather forecast information.

[0078] S4, online operation:

[0079] Deploy the system to the production environment and start formal operation.

[0080] Regularly monitor system performance and perform optimization and maintenance.

[0081] Example 2

[0082] See also Figure 2As shown, this embodiment discloses a method for clustering wind turbine self-organizing networks based on meteorological networking. The method is implemented by a processor calling the data measurement module, the communication module, and the central control module in the above-mentioned wind turbine self-organizing network cluster system based on meteorological networking, and includes the following steps:

[0083] S1, Internet weather data collection;

[0084] S2, data preprocessing;

[0085] S3, data analysis and judgment;

[0086] S4. Future weather forecast;

[0087] S5, comprehensive decision generation;

[0088] S6. The fan performs the action.

[0089] Example 3

[0090] This embodiment discloses a non-transitory computer-readable medium storing instructions. When the instructions are executed by a processor, the steps of the wind turbine self-organizing network clustering method based on meteorological networking according to embodiment 2 are performed.

[0091] The non-transitory computer-readable medium in this embodiment can be a disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), a USB flash drive, a mobile hard disk, or other media.

[0092] Example 4

[0093] This embodiment discloses a computing device, including a processor and a memory for storing a program executable by the processor. When the processor executes the program stored in the memory, the wind turbine self-organizing network clustering method based on meteorological networking described in Example 2 is implemented.

[0094] The computing device described in this embodiment may be a desktop computer, a laptop computer, a smart phone, a PDA handheld terminal, a tablet computer, a programmable logic controller (PLC), or other terminal devices with a processor function.

[0095] The embodiments described above are only preferred embodiments of the present invention and are not intended to limit the scope of implementation of the present invention. Therefore, any changes made based on the shape and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A wind turbine self-organizing network cluster system based on meteorological networking, characterized in that: include: Data measurement module, used to measure wind speed, wind direction, temperature, humidity and precipitation data of the environment where the wind turbine is located; Communication module, used for data transmission between each wind turbine and each module; The visualization module is used to visualize the predicted wind speed, actual wind speed and power generation recommendation data output by the central control module; The central control module receives data from all wind turbines and analyzes and makes decisions based on weather forecast information, including: The data receiving module is used to receive the wind speed, wind direction, temperature and humidity data output by the data measurement module, as well as precipitation data related to wind turbine power generation; A weather forecast module is used to obtain real-time and predicted weather information, including future wind speed forecast data and future wind direction forecast data; A data analysis module is used to analyze the collected data and determine whether current and future weather conditions are suitable for power generation based on machine learning; The decision module determines the power generation status of each wind turbine based on big data analysis and the analysis results output by the data analysis module.

2. The wind turbine self-organizing network cluster system based on meteorological networking according to claim 1, characterized in that: The data analysis module performs the following operations: a. Receive data from the data receiving module and weather forecast module, and preprocess the data by filling in missing values, normalizing, and dividing the data into time series. First, use interpolation or statistical methods to fill in missing data, then standardize all data to the same range, and finally divide the data into short-term, medium-term, and long-term time series for analysis; b. For the pre-processed wind speed data, a power generation strategy is selected according to the value of the wind speed data; if the wind speed data is in the low wind speed range, which is 0-3m / s, the wind turbine is considered unsuitable for power generation under this wind speed data; if the wind speed data is in the medium wind speed range, which is 4-10m / s, the wind turbine is considered suitable for power generation under this wind speed data, and the power generation efficiency is on an upward trend; if the wind speed data is in the high wind speed range, which is 11-25m / s, the wind turbine is considered suitable for power generation under this wind speed data, but the generator needs to be adjusted to ensure the safety of the equipment, that is, it should be used with caution; if the wind speed data is in the extremely high wind speed range, which is not less than 26m / s, the wind turbine is considered to have too high a risk of power generation under this wind speed data, and power generation needs to be stopped to protect the equipment; c. For the pre-processed wind direction data, ensure that the wind direction data is consistent with the design direction of the wind turbine. Calculate the angle between the wind turbine and the optimal wind direction based on trigonometric functions. If the angle exceeds a preset threshold, reduce the wind turbine's power generation. d. Use a machine learning model to predict wind speeds for the next few days. The pre-trained machine learning model is fed with historical wind speeds, temperatures, and air pressures, and outputs the expected future wind speeds. The machine learning model also incorporates a feedback mechanism. If the output of the expected future wind speed deviates from the actual power generation results, the model parameters are adjusted or the model is retrained. e. Set a benchmark threshold value and compare the expected value of future wind speed with the benchmark threshold value to determine the power generation status of the wind turbine. If the expected value of future wind speed is higher than the benchmark threshold value, the wind turbine is considered suitable for power generation at this time. If the expected value of future wind speed is equal to the benchmark threshold value, it is considered that the accuracy of the expected value of future wind speed needs to be evaluated at this time. If the expected value of future wind speed is lower than the benchmark threshold value, the wind turbine is considered unsuitable for power generation at this time.

3. The wind turbine self-organizing network cluster system based on meteorological networking according to claim 1, characterized in that: The decision module performs the following operations: Combine current weather conditions with future forecasts from data analysis modules to generate power generation recommendations; If the current weather is judged to be suitable for power generation and the expected value of future wind speed is higher than the reference threshold, the power generation suggestion = +1 is displayed; If the current weather is judged to require caution and the expected value of future wind speed is equal to the benchmark threshold, the power generation suggestion = 0 is displayed; If it is determined that the current weather is not suitable for power generation and the expected value of the future wind speed is lower than the reference threshold, the power generation suggestion = -1 is displayed.

4. The wind turbine self-organizing network cluster system based on meteorological networking according to claim 1, characterized in that: The decision module includes: Startup conditions: When the wind speed reaches the preset threshold and the wind speed obtained by the weather forecast module remains stable within the preset time period in the future, the wind turbine is started; Stop conditions: When the wind speed is lower than the preset threshold or the wind speed is expected to drop significantly within the preset time period in the future as obtained by the weather forecast module, the wind turbine will be stopped; when the real-time weather information indicates snowfall, the wind turbine will be stopped; when the real-time weather information indicates hailfall, the wind turbine will be stopped; when the real-time weather information indicates that the precipitation exceeds the threshold precipitation, the wind turbine will be stopped; Adjustment conditions: According to the changes in wind speed and wind direction, the blade angle of the wind turbine is dynamically adjusted based on machine learning; if the wind speed data is in the low wind speed range, which is 0-3m / s, the wind turbine blade angle is adjusted close to the wind direction, and the wind turbine is stopped from generating electricity; if the wind speed data is in the medium wind speed range, which is 4-10m / s, the wind turbine blade angle is dynamically increased and adjusted according to the real-time wind speed to optimize aerodynamic efficiency; if the wind speed data is in the high wind speed range, which is 11-25m / s, the wind turbine blade angle is adjusted to the limit angle to prevent the wind turbine from being damaged due to excessive wind speed; if the wind speed data is in the extremely high wind speed range, which is not less than 26m / s, the wind turbine blade angle is adjusted to the parking position, that is, the angle between the blade and the wind direction is maximized, and the wind turbine is stopped from generating electricity.

5. The wind turbine self-organizing network cluster system based on meteorological networking according to claim 1, characterized in that: The wind turbine is integrated with a wind speed sensor, a wind direction sensor, a temperature sensor, a humidity sensor and a local controller, and the wind speed sensor, wind direction sensor, temperature sensor and humidity sensor are respectively connected to the local controller for preliminary data processing, and the local controller is connected to the data measurement module.

6. The wind turbine self-organizing network cluster system based on meteorological networking according to claim 1, characterized in that: The central control module is connected to multiple wind turbines through communication modules to form a self-organizing network cluster of wind turbines, and the communication module and the central control module are redundant. The communication module is integrated with the MQTT or HTTP standard communication protocol, and the data measurement module, communication module, visualization module and central control module are connected in communication.

7. The wind turbine self-organizing network cluster system based on meteorological networking according to claim 1, characterized in that: The data analysis module, weather forecast module, data analysis module and decision-making module are communicatively connected in sequence. The weather forecast module is communicatively connected to a weather forecast system, and the weather forecast system is integrated with a weather forecast service API.

8. A wind turbine self-organizing network clustering method based on meteorological networking, characterized in that: The method is implemented by a processor calling the data measurement module, communication module, visualization module and central control module in the wind turbine self-organizing network cluster system based on meteorological networking according to any one of claims 1 to 7.

9. A non-transitory computer-readable medium storing instructions, characterized in that: When the instruction is executed by the processor, the steps of the wind turbine self-organizing network clustering method based on meteorological networking according to claim 8 are executed.

10. A computing device comprising a processor and a memory for storing a program executable by the processor, characterized in that When the processor executes the program stored in the memory, the wind turbine self-organizing network clustering method based on meteorological networking as claimed in claim 8 is implemented.

Images