Intelligent coordination control method based on offshore wind power direct current delivery grid-connected system

Abstract

The invention discloses an intelligent coordination control method based on an offshore wind power direct current delivery grid-connected system, and relates to the technical field of offshore wind power direct current transmission and power grid control. According to the method, key data of an offshore wind plant, a direct-current power transmission system and a power grid are collected in real time, and a comprehensive control model including the offshore wind plant, the direct-current power transmission system and the power grid is established. And the output power of the offshore wind plant and the load demand of the power grid are predicted in real time by using time sequence analysis and a neural network. And designing an intelligent coordination control strategy based on the prediction result, and realizing stable operation of the system by adjusting the output power of the wind power plant and the voltage and current of the direct-current power transmission system. A self-adaptive control mechanism is further introduced, control parameters are adjusted in real time according to the actual condition of system operation, and a control strategy is optimized. By analyzing the operation data of the system, potential fault risks can be identified, and corresponding prevention measures are taken to ensure the safe operation of the system.

Description

Technical Field

[0001] The present invention belongs to the technical field of offshore wind power direct current transmission and power grid control, and in particular relates to an intelligent coordinated control method based on an offshore wind power direct current transmission grid-connected system. Background Art

[0002] The offshore wind power DC transmission grid-connected system is a key link in transmitting the electricity generated by offshore wind farms into the power grid through DC transmission technology. However, due to the remote geographical location of offshore wind farms, harsh environmental conditions and high requirements of the power grid for power quality, the control of the offshore wind power DC transmission grid-connected system faces many challenges. Most of the existing control methods are based on traditional PID control or fixed control strategies, which are difficult to adapt to the volatility of offshore wind farm output power and the diversity of power grid loads. This leads to poor system control effect, reduced power quality, and may even cause power grid failures. Summary of the invention

[0003] In order to overcome the shortcomings and deficiencies of the above-mentioned prior art, the present invention adopts the following technical solutions:

[0004] The intelligent coordinated control method based on the offshore wind power DC transmission grid-connected system has the following steps:

[0005] Step 1: Install sensors in offshore wind farms, DC transmission systems and power grids to collect data such as wind speed, output power, voltage, current and load demand in real time;

[0006] Step 2: Clean and preprocess the collected data;

[0007] Step 3: Based on the collected data, establish a comprehensive control model including the offshore wind farm, DC transmission system and power grid;

[0008] Step 4: Use time series analysis and neural network methods to predict wind farm output power and grid load demand in the future;

[0009] Step 5: Based on the prediction results, design a strategy to adjust the output power of the wind farm and the voltage and current of the DC transmission system;

[0010] Step 6: According to the actual situation of system operation, the control parameters are adjusted in real time through the adaptive learning algorithm;

[0011] Step 7: Identify potential failure risks by analyzing system operation data and take corresponding preventive measures.

[0012] Preferably, step three is as follows:

[0013] S31. Establish an offshore wind farm model: Use the power curve of the wind turbine to establish a relationship model between wind speed and output power; describe the control logic of the wind turbine through the MPPT control algorithm; use time series analysis to establish a dynamic response model of the wind farm;

[0014] S32. Establish a DC transmission system model: Based on physical equations, establish a voltage and current dynamic model of the DC transmission system, describe the control strategy of the VSC, such as closed-loop control of voltage and current; use simulation software to verify and optimize the model;

[0015] S33. Establish a power grid model: Based on historical load data, establish a load demand model for the power grid; describe the frequency and voltage dynamic characteristics of the power grid, and consider the stability and reliability requirements of the power grid; use simulation tools to verify and optimize the model.

[0016] Preferably, step 4 is as follows:

[0017] S41. Model selection: For wind farm output power forecasting, select the LSTM model to capture temporal dependencies; for grid load demand forecasting, select the ARIMA model to process periodically changing data;

[0018] S42, model training: divide the data into training set and test set, use the training set data to train the LSTM model and ARIMA model; adjust the model parameters to optimize the prediction performance;

[0019] S43, Model Validation: Use the test set data to verify the generalization ability of the model; calculate the prediction error and evaluate the accuracy of the model;

[0020] S44. Forecast results: Use the trained model to predict the wind farm output power and grid load demand for the next week; analyze the forecast results and evaluate the performance of the model.

[0021] Preferably, step five is as follows:

[0022] S51, output power smoothing adjustment: according to the predicted wind farm output power, adjust the pitch angle and speed of the wind turbine to make the wind turbine always work near the maximum power point; use a smoothing filter to smooth the change of output power to reduce the impact on the power grid;

[0023] S52, voltage and current stability control: according to the predicted grid load demand, adjust the converter trigger angle of the DC transmission system, control the voltage of the DC line, and ensure that the voltage is within a safe range; adjust the modulation ratio of the DC transmission system, control the current of the DC line, and ensure that the current is within a safe range;

[0024] S53, real-time adjustment of control parameters: using adaptive learning algorithm, real-time adjustment of control parameters and optimization of control strategy according to the actual situation of system operation; through feedback control mechanism, adjustment of control parameters according to actual deviation to ensure stable operation of the system;

[0025] S54. Execution of control strategy: Through the automated control system, the control strategy is executed in real time to adjust the output power of the wind farm and the voltage and current of the DC transmission system; it also includes manually adjusting the control parameters according to the actual operation of the system to ensure the safe operation of the system.

[0026] Preferably, step six is ​​as follows:

[0027] S61. Monitor system status and evaluate system performance: define performance indicators, including voltage stability, frequency stability, power balance and energy utilization; monitor voltage fluctuations of the DC transmission system to ensure that the voltage is within a safe range; monitor frequency fluctuations of the power grid to ensure that the frequency is within the standard range; monitor the output power of the wind farm and the load demand of the power grid to ensure the balance between supply and demand;

[0028] S62, adjust control parameters: adjust the control law in real time, including the parameters of the PID controller, by estimating system parameters online; use reinforcement learning or deep learning algorithms to automatically adjust control parameters and optimize control strategies based on historical data and current status;

[0029] S63. Monitor the operating status of the system in real time and use feedback control mechanisms to adjust control parameters based on actual deviations. Optimize control strategies through adaptive learning algorithms. During system operation, continuously collect data, update model parameters, and optimize control strategies. Regularly analyze historical data, optimize model parameters, and improve control strategies.

[0030] Preferably, step seven is as follows:

[0031] S71. Use threshold analysis to issue an alarm when a parameter exceeds a set threshold; use trend analysis to identify abnormal changes by analyzing data trends; use machine learning algorithms to identify potential failure risks;

[0032] S72. Preventive measures: When a potential failure risk is detected, an alarm is immediately sounded to notify the operation and maintenance personnel; the system's operating status is checked in real time through the remote monitoring system to promptly detect and handle problems; regular inspection and maintenance of related equipment is performed based on the fault diagnosis results; repairs are performed in advance before a failure occurs; system operating parameters are adjusted based on the fault diagnosis results; the burden on individual equipment is reduced by adjusting the load distribution of the power grid.

[0033] Preferably, in step three, establishing the offshore wind farm model further comprises using wind speed and wind direction data in combination with weather forecasts to predict future wind speed changes, thereby optimizing the output power prediction of the wind farm.

[0034] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0035] The intelligent coordinated control method of the present invention realizes smooth regulation of output power and stable control of voltage and current through real-time prediction, intelligent coordinated control and adaptive learning. At the same time, the fault diagnosis and prediction method can detect potential fault risks of the system in advance, provide decision support for operation and maintenance personnel, reduce operation and maintenance costs and safety risks, and improve the control effect and power quality of the offshore wind power DC transmission grid-connected system. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 The flowchart of the intelligent coordinated control method of the offshore wind power DC transmission grid-connected system according to the present invention is shown. DETAILED DESCRIPTION

[0038] 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.

[0039] In addition, the described features, structures or characteristics may be combined in one or more example embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the example embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or other methods, components, steps, etc. may be adopted. In other cases, well-known structures, methods, implementations or operations are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0040] Embodiment 1:

[0041] See also Figure 1As shown, the intelligent coordinated control method based on the offshore wind power DC transmission grid-connected system of this embodiment comprises the following steps:

[0042] Step 1: Data collection: Install sensors in offshore wind farms, DC transmission systems and power grids to collect data such as wind speed, output power, voltage, current and load demand in real time.

[0043] Step 2: Data preprocessing: Clean and preprocess the collected data to remove noise and outliers.

[0044] Step 3: Based on the collected data, establish a comprehensive control model of the offshore wind farm, DC transmission system and power grid.

[0045] S31. Establish an offshore wind farm model.

[0046] Using the power curve of the wind turbine, a relationship model between wind speed and output power is established; the control logic of the wind turbine is described through the MPPT control algorithm. Using time series analysis, a dynamic response model of the wind farm is established.

[0047] S32. Establish a DC transmission system model.

[0048] Based on the physical equations, the voltage and current dynamic model of the DC transmission system is established to describe the control strategy of the VSC, such as the closed-loop control of voltage and current. The model is verified and optimized using simulation software.

[0049] S33. Establish a power grid model.

[0050] Based on historical load data, the load demand model of the power grid is established. The frequency and voltage dynamic characteristics of the power grid are described, and the stability and reliability requirements of the power grid are considered. Simulation tools are used to verify and optimize the model.

[0051] Through the above steps, a comprehensive control model is established, which provides a solid foundation for intelligent coordinated control.

[0052] Step 4: Use time series analysis and neural network methods to predict the wind farm output power and grid load demand in the future.

[0053] S41. Model selection: For wind farm output power forecasting, select the LSTM model because it can capture temporal dependencies. For grid load demand forecasting, select the ARIMA model because it is suitable for processing periodically changing data.

[0054] S42. Model training: Divide the data into training set and test set, and use the training set data to train the LSTM model and ARIMA model. Adjust the model parameters to optimize the prediction performance.

[0055] S43. Model validation: Use the test set data to verify the generalization ability of the model. Calculate the prediction error and evaluate the accuracy of the model.

[0056] S44. Prediction results: Use the trained model to predict the wind farm output power and grid load demand in the next week.

[0057] Analyze the prediction results and evaluate the performance of the model.

[0058] Step 5: Based on the prediction results, an intelligent coordinated control strategy is designed to achieve stable operation of the system by adjusting the output power of the wind farm and the voltage and current of the DC transmission system.

[0059] S51, output power smoothing adjustment: According to the predicted wind farm output power, adjust the pitch angle and speed of the wind turbine to make the wind turbine always work near the maximum power point. Use a smoothing filter to smooth the change of output power and reduce the impact on the power grid.

[0060] S52, voltage and current stability control: according to the predicted grid load demand, adjust the DC transmission system converter trigger angle, control the DC line voltage, and ensure that the voltage is within a safe range. Adjust the DC transmission system modulation ratio, control the DC line current, and ensure that the current is within a safe range.

[0061] S53, real-time adjustment of control parameters: using adaptive learning algorithms, real-time adjustment of control parameters and optimization of control strategies according to the actual situation of system operation. Through feedback control mechanisms, control parameters are adjusted according to actual deviations to ensure stable operation of the system.

[0062] S54, Execution of control strategy: Through the automated control system, the control strategy is executed in real time to adjust the output power of the wind farm and the voltage and current of the DC transmission system. When necessary, the operator can manually adjust the control parameters according to the actual situation of the system operation to ensure the safe operation of the system.

[0063] Step 6: According to the actual situation of system operation, adjust the control parameters in real time and optimize the control strategy through adaptive learning algorithm.

[0064] S61. Monitor system status and evaluate system performance.

[0065] Performance indicators: define a series of performance indicators, including but not limited to voltage stability, frequency stability, power balance, and energy utilization.

[0066] Voltage stability: Monitor voltage fluctuations in the DC transmission system to ensure that the voltage is within a safe range.

[0067] Frequency stability: Monitors frequency fluctuations in the power grid to ensure that the frequency is within the standard range.

[0068] Power balance: Monitor the output power of wind farms and the load demand of the power grid to ensure the balance between supply and demand.

[0069] S62. Adjust control parameters.

[0070] By estimating system parameters online, the control law can be adjusted in real time, such as the parameters of the PID controller (proportional coefficient, integral coefficient, differential coefficient).

[0071] Use reinforcement learning or deep learning algorithms to automatically adjust control parameters and optimize control strategies based on historical data and current status.

[0072] S63. By real-time monitoring of the system's operating status and using a feedback control mechanism, control parameters are adjusted according to actual deviations to ensure stable operation of the system.

[0073] Adaptive learning: Through adaptive learning algorithms, the control strategy is continuously optimized to improve the adaptability and robustness of the system.

[0074] Online learning: During system operation, continuously collect data, update model parameters, and optimize control strategies.

[0075] Offline optimization: Regularly analyze historical data, optimize model parameters, and improve control strategies.

[0076] Step 7: Identify potential failure risks by analyzing system operation data and take corresponding preventive measures.

[0077] S71. Use threshold analysis to issue an alarm when a parameter exceeds the threshold.

[0078] Use trend analysis to identify unusual changes by analyzing trends in data.

[0079] Use machine learning algorithms, such as Support Vector Machines (SVM) or Random Forest, to identify potential failure risks.

[0080] S72. Preventive measures.

[0081] When a potential failure risk is detected, an alarm is immediately issued to notify the operation and maintenance personnel. Through the remote monitoring system, the operating status of the system can be viewed in real time to detect and handle problems in a timely manner.

[0082] Based on the fault diagnosis results, it is recommended to regularly inspect and maintain the relevant equipment.

[0083] Before a failure occurs, repairs can be performed in advance to avoid the occurrence of failures.

[0084] According to the fault diagnosis results, adjust the system operating parameters to reduce the risk of failure.

[0085] By adjusting the load distribution of the power grid, the burden on individual equipment can be reduced and the risk of failure can be lowered.

[0086] The beneficial effects of this embodiment are as follows: Based on the intelligent coordinated control method of the offshore wind power DC transmission grid-connected system, by establishing a comprehensive control model, using advanced prediction algorithms and data analysis technology, designing intelligent coordinated control strategies, introducing adaptive control mechanisms, and proposing fault diagnosis and prediction methods, the system is fully, intelligently, and efficiently controlled and managed. This method not only improves the operating efficiency and stability of the system, but also reduces the risk of failure, providing a strong guarantee for the efficient and safe operation of offshore wind power.

[0087] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

[0088] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. An intelligent coordinated control method based on an offshore wind power DC transmission grid-connected system, characterized in that: The method comprises the following steps: Step 1: Install sensors in offshore wind farms, DC transmission systems and power grids to collect real-time data on wind speed, output power, voltage, current and load demand; Step 2: Clean and preprocess the collected data; Step 3: Based on the collected data, establish a comprehensive control model including the offshore wind farm, DC transmission system and power grid; Step 4: Use time series analysis and neural network methods to predict wind farm output power and grid load demand in the future; Step 5: Based on the prediction results, design a strategy to adjust the output power of the wind farm and the voltage and current of the DC transmission system; Step 6: According to the actual situation of system operation, the control parameters are adjusted in real time through the adaptive learning algorithm; Step 7: Identify potential failure risks by analyzing system operation data and take corresponding preventive measures.

2. The intelligent coordination control method based on the offshore wind power DC transmission grid-connected system according to claim 1 is characterized in that: The step three is as follows: S31. Establish an offshore wind farm model: Use the power curve of the wind turbine to establish a relationship model between wind speed and output power; describe the control logic of the wind turbine through the MPPT control algorithm; use time series analysis to establish a dynamic response model of the wind farm; S32. Establish a DC transmission system model: Based on physical equations, establish a voltage and current dynamic model of the DC transmission system, describe the control strategy of the VSC, such as closed-loop control of voltage and current; use simulation software to verify and optimize the model; S33. Establish a power grid model: Based on historical load data, establish a load demand model for the power grid; describe the frequency and voltage dynamic characteristics of the power grid, and consider the stability and reliability requirements of the power grid; use simulation tools to verify and optimize the model.

3. The intelligent coordination control method based on the offshore wind power DC transmission grid-connected system according to claim 1 is characterized in that: The step 4 is as follows: S41. Model selection: For wind farm output power forecasting, select the LSTM model to capture temporal dependencies; for grid load demand forecasting, select the ARIMA model to process periodically changing data; S42, model training: divide the data into training set and test set, use the training set data to train the LSTM model and ARIMA model; adjust the model parameters to optimize the prediction performance; S43, Model Validation: Use the test set data to verify the generalization ability of the model; calculate the prediction error and evaluate the accuracy of the model; S44. Forecast results: Use the trained model to predict the wind farm output power and grid load demand for the next week; analyze the forecast results and evaluate the performance of the model.

4. The intelligent coordination control method based on the offshore wind power DC transmission grid-connected system according to claim 1 is characterized in that: The step five is as follows: S51, output power smoothing adjustment: according to the predicted wind farm output power, adjust the pitch angle and speed of the wind turbine to make the wind turbine always work near the maximum power point; use a smoothing filter to smooth the change of output power to reduce the impact on the power grid; S52, voltage and current stability control: according to the predicted grid load demand, adjust the converter trigger angle of the DC transmission system, control the voltage of the DC line, and ensure that the voltage is within a safe range; adjust the modulation ratio of the DC transmission system, control the current of the DC line, and ensure that the current is within a safe range; S53, real-time adjustment of control parameters: using adaptive learning algorithm, real-time adjustment of control parameters and optimization of control strategy according to the actual situation of system operation; through feedback control mechanism, adjustment of control parameters according to actual deviation to ensure stable operation of the system; S54. Execution of control strategy: Through the automated control system, the control strategy is executed in real time to adjust the output power of the wind farm and the voltage and current of the DC transmission system; it also includes manually adjusting the control parameters according to the actual operation of the system to ensure the safe operation of the system.

5. The intelligent coordination control method based on the offshore wind power DC transmission grid-connected system according to claim 1 is characterized in that: The step six is ​​as follows: S61. Monitor system status and evaluate system performance: define performance indicators, including voltage stability, frequency stability, power balance and energy utilization; monitor voltage fluctuations of the DC transmission system to ensure that the voltage is within a safe range; monitor frequency fluctuations of the power grid to ensure that the frequency is within the standard range; monitor the output power of the wind farm and the load demand of the power grid to ensure the balance between supply and demand; S62, adjust control parameters: adjust the control law in real time, including the parameters of the PID controller, by estimating system parameters online; use reinforcement learning or deep learning algorithms to automatically adjust control parameters and optimize control strategies based on historical data and current status; S63, by real-time monitoring of the system's operating status, using feedback control mechanisms, adjusting control parameters according to actual deviations; optimizing control strategies through adaptive learning algorithms; During system operation, data is continuously collected, model parameters are updated, and control strategies are optimized; historical data is regularly analyzed, model parameters are optimized, and control strategies are improved.

6. The intelligent coordination control method based on the offshore wind power DC transmission grid-connected system according to claim 1 is characterized in that: The step seven is as follows: S71. Use threshold analysis to issue an alarm when a parameter exceeds a set threshold; use trend analysis to identify abnormal changes by analyzing data trends; use machine learning algorithms to identify potential failure risks; S72. Preventive measures: When a potential failure risk is detected, an alarm is immediately issued to notify the operation and maintenance personnel; through the remote monitoring system, the operating status of the system can be viewed in real time to detect and handle problems in a timely manner; According to the fault diagnosis results, regularly inspect and maintain related equipment; carry out repairs in advance before a fault occurs; adjust the system's operating parameters according to the fault diagnosis results; and reduce the burden on individual equipment by adjusting the load distribution of the power grid.

7. The intelligent coordination control method based on the offshore wind power DC transmission grid-connected system according to claim 1 is characterized in that: In the step three, establishing the offshore wind farm model also includes using wind speed and wind direction data in combination with weather forecasts to predict future wind speed changes, thereby optimizing the output power prediction of the wind farm.

Images