Rapid wind power plant power optimization method and system based on graph neural network

Abstract

The invention provides a rapid wind power plant power optimization method and system based on a graph neural network. The method comprises the following steps of a, constructing a graph neural network model, b, performing rapid power calculation, c, optimizing a yaw angle by combining a genetic algorithm, d, optimizing power output of a fan, and e, performing real-time data updating and model adaptability. The system comprises a data input module (1), a graph neural network model (2), a genetic algorithm optimization module (3), a control system (4) and a feedback module (5). The method is applied to the technical field of wind power.

Description

Technical Field

[0001] The present invention relates to the field of wind power technology, and in particular to a method and system for rapid wind farm power optimization based on graph neural network. Background Art

[0002] The field-level control method of wind farms has become a research hotspot in recent years. With the expansion of wind farm scale and the increase in the number of wind turbines, how to effectively coordinate the operation of multiple wind turbines to optimize the overall power generation efficiency and reduce the wake effect between wind turbines has become a core challenge. Traditional control methods mostly rely on centralized or distributed control strategies, mainly based on physical models or local measurement data to achieve coordinated control of wind turbines. However, due to the complex and changeable factors such as wind speed, wind direction, and terrain within the wind farm, these traditional methods have limitations in the optimization of large-scale wind farms.

[0003] In the existing technology, there is a wind farm control method based on physical models. In this method, the current mainstream technology is to use the wake model and the wind turbine performance curve to optimize the overall performance of the wind farm by adjusting the power output and unit angle of the wind turbine. For example, tools such as FLORIS are used to simulate the flow field changes in the wind farm, and control adjustments are made in combination with traditional optimization algorithms. These methods work well in small-scale wind farms, but as the scale of wind farms expands, the computational complexity increases significantly and the accuracy decreases.

[0004] There are also control strategies based on machine learning. In this way, some studies have begun to try to apply machine learning technology to wind farm control, especially using reinforcement learning to optimize the control strategy of wind turbines. Although these methods can show good optimization effects under specific wind farm conditions, they usually rely on a large amount of historical data for training and have limited ability to model the complex fluid dynamics inside the wind farm and the interaction between wind turbines.

[0005] From the above analysis, it can be seen that the method based on physical models relies on detailed wake and flow field simulation, and has high computational complexity. Especially in large-scale wind farms, the response speed is slow when applied in real time, and it is difficult to cope with complex dynamic environments. Traditional control strategies based on physical models or machine learning have limited performance in dealing with nonlinear interactions between wind turbines, especially the wake effects between different wind turbines in a wind farm are difficult to accurately model, resulting in poor overall performance optimization. Existing technologies mostly use single machines or local areas as optimization targets, lacking attention to the global optimality of the entire wind farm, resulting in failure to maximize overall efficiency. Summary of the invention

[0006] The technical problem to be solved by the present invention is to overcome the shortcomings of the prior art and provide a method and system for rapid wind farm power optimization based on graph neural networks, aiming to solve the problems of computational complexity, poor real-time performance, and insufficient global optimization capabilities in the prior art in dealing with field-level optimization of wind farms; by introducing the advanced modeling and optimization capabilities of graph neural networks, the overall power generation efficiency of wind farms can be significantly improved, and the impact of wake between wind turbines can be reduced.

[0007] The technical solution adopted by the rapid wind farm power optimization method based on graph neural network described in the present invention is a rapid wind farm power optimization method based on graph neural network alone, which includes the following steps: Step a, constructing a graph neural network model: using a graph neural network to model the relationship between wind turbines in a wind farm, where nodes represent wind turbines and their states, edges represent interactions between wind turbines, and historical data of wind turbine coordinates, wind speed, wind direction, and yaw angles are input into the graph neural network model. The graph neural network model is trained by inputting historical data to obtain a graph neural network model of wind farm power; Step b, fast power calculation: obtaining real-time data of coordinates, wind speed, wind direction and yaw angle of each wind turbine and inputting them into the graph neural network model, the graph neural network model captures the dynamic influence between wind turbines and outputs the power prediction value of each wind turbine; Step c, optimizing the yaw angle by combining genetic algorithm: using genetic algorithm under the conditions of fixed coordinates and wind speed, through multiple iterations, taking the power prediction value output by the graph neural network model as the fitness function of the genetic algorithm, and solving the optimal yaw angle under the conditions of fixed wind speed and wind direction through selection, crossover and mutation operations; Step d, optimizing the power output of the wind turbine: adjusting the yaw angle of the corresponding wind turbine according to the optimal yaw angle obtained by the genetic algorithm, and realizing precise control of the wind turbine through the electric control system of the wind turbine to achieve the optimal operating state; Step e: Real-time data update and model adaptability: Feedback the real-time measured information to the graph neural network model to promote online learning and model update and maintain the adaptability of the model.

[0008] The system of the present invention for realizing the above-mentioned rapid wind farm power optimization method based on graph neural network includes: A data input module for receiving data input; A graph neural network model for processing input data from the data input module, establishing mutual influence relationships between wind turbines, and predicting power output of each wind turbine; A genetic algorithm optimization module for iteratively optimizing the power data output by the graph neural network model using a genetic algorithm to solve the optimal yaw angle under fixed wind speed and wind direction conditions; A control system for receiving the optimal yaw angle output by the genetic algorithm optimization module, adjusting the yaw setting of the wind turbine, and realizing precise control of the wind turbine through the electric control device of the wind turbine to ensure the optimal operating state; and A feedback module is used to feed back the real-time data received by the data input module to the graph neural network model, promote online learning and model updating of the graph neural network model, and maintain the adaptability of the model.

[0009] The data input module is a sensor or a meteorological data interface.

[0010] The architecture of the graph neural network model is: Input layer: used to accept data input of wind turbine coordinates, wind speed, wind direction and yaw angle; Hidden layers: Several graph convolutional layers to capture the relationships between wind turbines; and Output layer: used to output the power prediction results of each wind turbine.

[0011] The working process of the genetic algorithm optimization module is as follows: Ⅰ. Initialize the population: randomly generate yaw angle combinations; II. Fitness evaluation: using the power data predicted by the graph neural network model as the fitness function, evaluate the performance of each combination in step I and obtain the fitness value of each combination; III. Selection, crossover and mutation operations: Genetic operations are performed based on the fitness value. After multiple iterative updates, the optimal yaw angle is finally obtained.

[0012] The beneficial effects of the present invention are as follows: in the present invention, due to the use of a graph neural network power model, the input data from the data input module is processed, the mutual influence relationship between wind turbines is established, the power output of each wind turbine is predicted, and the genetic algorithm is used under the conditions of fixed coordinates and wind speed. Through multiple iterations, the power prediction value output by the graph neural network model is used as the fitness function of the genetic algorithm, and the optimal yaw angle under the conditions of fixed wind speed and wind direction is solved through selection, crossover, and mutation operations; according to the optimal yaw angle obtained by the genetic algorithm, the yaw angle of the corresponding wind turbine is adjusted, and the wind turbine is accurately controlled through the wind turbine's electrical control system to achieve the optimal operating state; this significantly reduces the cost of the calculation. The calculation time can be reduced, and real-time power prediction can be achieved; this advantage enables wind farms to respond quickly to environmental changes and optimize operational efficiency; the interaction between wind turbines is modeled by graph neural network, which improves the accuracy of power prediction; at the same time, by feeding back the real-time measured information to the graph neural network model, it promotes online learning and model updating, maintains the adaptability of the model, and enables the model to have real-time data update capabilities, quickly adapt to changes in wind speed and wind direction, and ensure long-term operational stability; combined with the optimization scheme of the genetic algorithm, it realizes the rapid solution of the optimal yaw angle under specific conditions; compared with traditional methods, this scheme is more flexible and adaptable, and can improve the energy output of the overall wind farm. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 It is a simplified structural block diagram of the system of the present invention; Figure 2 It is a simplified architecture diagram of the graph neural network model; Figure 3 It is a simple flow chart of the method of the present invention. DETAILED DESCRIPTION

[0014] In the present invention, the modeling, iterative calculation and other processes involved are all implemented on a computer. The graph neural network model and genetic algorithm are mature mathematical calculation models. The present invention uses a wind farm power model trained by a graph neural network to replace the traditional wake model, thereby improving the wind farm power optimization rate.

[0015] like Figures 1 to 3 As shown, a rapid wind farm power optimization method based on graph neural network includes the following steps: Step a, constructing a graph neural network model: using a graph neural network to model the relationship between wind turbines in a wind farm, where nodes represent wind turbines and their states, edges represent interactions between wind turbines, and historical data of wind turbine coordinates, wind speed, wind direction, and yaw angles are input into the graph neural network model. The graph neural network model is trained by inputting historical data to obtain a graph neural network model of wind farm power; Step b, fast power calculation: obtaining real-time data of coordinates, wind speed, wind direction and yaw angle of each wind turbine and inputting them into the graph neural network model, the graph neural network model captures the dynamic influence between wind turbines and outputs the power prediction value of each wind turbine; Step c, optimizing the yaw angle by combining genetic algorithm: using genetic algorithm under the conditions of fixed coordinates and wind speed, through multiple iterations, taking the power prediction value output by the graph neural network model as the fitness function of the genetic algorithm, and solving the optimal yaw angle under the conditions of fixed wind speed and wind direction through selection, crossover and mutation operations; Step d, optimizing the power output of the wind turbine: adjusting the yaw angle of the corresponding wind turbine according to the optimal yaw angle obtained by the genetic algorithm, and realizing precise control of the wind turbine through the electric control system of the wind turbine to achieve the optimal operating state; Step e: Real-time data update and model adaptability: Feedback the real-time measured information to the graph neural network model to promote online learning and model update and maintain the adaptability of the model.

[0016] The above method is implemented by a rapid wind farm power optimization system based on a graph neural network, which includes a data input module 1 for receiving data input; A graph neural network model 2 for processing input data from the data input module 1, establishing a mutual influence relationship between wind turbines, and predicting the power output of each wind turbine; A genetic algorithm optimization module 3 for iteratively optimizing the power data output by the graph neural network model 2 using a genetic algorithm to solve the optimal yaw angle under fixed wind speed and wind direction conditions; A control system 4 for receiving the optimal yaw angle output by the genetic algorithm optimization module 3, adjusting the yaw setting of the wind turbine, and realizing precise control of the wind turbine through the electric control device of the wind turbine to ensure the optimal operating state; and A feedback module 5 is used to feed back the real-time data received by the data input module 1 to the graph neural network model 2, promote online learning and model updating of the graph neural network model 2, and maintain the adaptability of the model.

[0017] Specifically, the data input module 1 is a sensor or a meteorological data interface. Here, the sensor includes various sensors, such as wind speed sensor, temperature sensor, humidity sensor, angle sensor, direction sensor, etc., which respectively detect the wind speed, temperature and humidity, yaw angle of the fan blades, etc. of the environment where the fan is located.

[0018] The architecture of the graph neural network model 2 is: Input layer 21: used to accept data input of wind turbine coordinates, wind speed, wind direction and yaw angle; Hidden layer 22: having several graph convolutional layers for capturing the relationship between wind turbines; and Output layer 23: Used to output the power prediction results of each fan.

[0019] The working process of the genetic algorithm optimization module 3 is as follows: Ⅰ. Initialize the population: Randomly generate yaw angle combinations; Ⅱ. Fitness evaluation: Use the power data predicted by the graph neural network model 2 as the fitness function to evaluate the performance of each combination in step Ⅰ and obtain the fitness value of each combination; Ⅲ. Selection, crossover, and mutation operations: Perform genetic operations based on the fitness value. After multiple iterations of update, finally obtain the optimal yaw angle.

[0020] The technical solution of the present invention is applicable to the intelligent control system of large-scale wind farms. The following are specific examples of the best implementation methods: 1. Implementation environment: A certain large-scale offshore wind farm with multiple fans, where the wind speed and direction change frequently; 2. Data input: Use a weather station and a wind speed sensor to obtain the wind speed (12 m / s) and wind direction (45°) in real time, and obtain the fan coordinate data through the GPS system; 3. Operation of the trained graph neural network model 2: Input the data into the graph neural network model 2 to predict the power of each fan. The predicted power of fan A is 1.5 MW, and that of fan B is 1.2 MW; 4. Optimization process of the genetic algorithm optimization module 3: Use the genetic algorithm optimization module to optimize the yaw angle. After several generations of iteration, finally obtain the optimal yaw angle (the optimal yaw angle of fan A is 30°, and that of fan B is 25°); 5. Control system adjustment: The control system receives the optimal yaw angle instruction and adjusts the yaw settings of the fans; 6. Real-time feedback and model update: The system feeds the new wind speed and wind direction data back to the graph neural network model 2 for online learning to ensure that the model adapts to future changes.

[0021] Through this technical solution, the present invention can significantly improve the power output and operation efficiency of the wind farm, adapt to complex meteorological conditions, and provide technical support for the efficient utilization of renewable energy.

[0022] Finally, it should be emphasized that the above-mentioned are only the preferred embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A fast wind farm power optimization method based on graph neural network, characterized in that: The method comprises the following steps: Step a, constructing a graph neural network model: using a graph neural network to model the relationship between wind turbines in a wind farm, where nodes represent wind turbines and their states, edges represent interactions between wind turbines, and historical data of wind turbine coordinates, wind speed, wind direction, and yaw angles are input into the graph neural network model. The graph neural network model is trained by inputting historical data to obtain a graph neural network model of wind farm power; Step b, fast power calculation: obtaining real-time data of coordinates, wind speed, wind direction and yaw angle of each wind turbine and inputting them into the graph neural network model, the graph neural network model captures the dynamic influence between wind turbines and outputs the power prediction value of each wind turbine; Step c, optimizing the yaw angle by combining genetic algorithm: using genetic algorithm under the conditions of fixed coordinates and wind speed, through multiple iterations, taking the power prediction value output by the graph neural network model as the fitness function of the genetic algorithm, and solving the optimal yaw angle under the conditions of fixed wind speed and wind direction through selection, crossover and mutation operations; Step d, optimizing the power output of the wind turbine: adjusting the yaw angle of the corresponding wind turbine according to the optimal yaw angle obtained by the genetic algorithm, and realizing precise control of the wind turbine through the electric control system of the wind turbine to achieve the optimal operating state; Step e: Real-time data update and model adaptability: Feedback the real-time measured information to the graph neural network model to promote online learning and model update and maintain the adaptability of the model.

2. A system for implementing the method for rapid wind farm power optimization based on graph neural network as claimed in claim 1, characterized in that: The system includes A data input module (1) for receiving data input; A graph neural network model (2) for processing input data from the data input module (1), establishing a mutual influence relationship between wind turbines, and predicting the power output of each wind turbine; A genetic algorithm optimization module (3) for iteratively optimizing the power data output by the graph neural network model (2) using a genetic algorithm to solve the optimal yaw angle under fixed wind speed and wind direction conditions; A control system (4) for receiving the optimal yaw angle output by the genetic algorithm optimization module (3), adjusting the yaw setting of the wind turbine, and realizing precise control of the wind turbine through the electric control device of the wind turbine to ensure the optimal operating state; as well as A feedback module (5) is used to feed back the real-time data received by the data input module (1) to the graph neural network model (2), promote online learning and model updating of the graph neural network model (2), and maintain the adaptability of the model.

3. The rapid wind farm power optimization system based on graph neural network according to claim 2 is characterized in that: The data input module (1) is a sensor or a meteorological data interface.

4. The rapid wind farm power optimization system based on graph neural network according to claim 2 is characterized in that: The architecture of the graph neural network model (2) is: Input layer (21): used to receive data input of wind turbine coordinates, wind speed, wind direction and yaw angle; Hidden layer (22): has several graph convolutional layers to capture the relationship between wind turbines; and Output layer (23): used to output the power prediction results of each wind turbine.

5. The rapid wind farm power optimization system based on graph neural network according to claim 2 is characterized in that: The working process of the genetic algorithm optimization module (3) is as follows: Ⅰ. Initialize the population: randomly generate yaw angle combinations; II. Fitness evaluation: using the power data predicted by the graph neural network model (2) as the fitness function, evaluate the performance of each combination in step I and obtain the fitness value of each combination; III. Selection, crossover and mutation operations: Genetic operations are performed based on the fitness value. After multiple iterative updates, the optimal yaw angle is finally obtained.

Images