Wind Turbine Performance Modeling

Real-time collaborative yaw control of wind farms that maximizes power generation by coordinating wind turbine yaw angles in response to changing wind conditions. The method involves predicting short-term wind variations using wavelet decomposition and machine learning models. This allows rapid and accurate prediction of wind direction and speed variations that can be used for real-time coordinated yaw control to mitigate wake effects between turbines.

Source

Intelligent control method and system for wind turbines that optimizes power generation efficiency by using digital twin modeling, data monitoring, and strategy matching to mitigate the effects of variable wind conditions. The method involves: monitoring wind speed with synchronized sensors, generating predicted wind speed, fitting turbine efficiency using digital twin models, matching optimization results with calibrated wind speeds, and stable optimization using averaged wind speeds.

Source

Optimizing wind turbine yield by adaptive curtailment to mitigate wake effects from nearby obstacles. The method involves using weather forecasts to estimate wind conditions and wake lengths. If forecasts indicate weaker wake impacts, turbine curtailment is reduced. This balances yield vs load protection. The curtailment is also adjusted based on terrain (flat vs mountainous) to account for flow dynamics. The turbine uses a local weather model trained on historical data to adapt curtailment to site-specific conditions. By leveraging forecasts and terrain, curtailment is tailored to reduce wake loads without excessive yield loss.

Source

Optimizing wind turbine performance using reinforcement learning to adjust blade angles and yaw based on predicted wind changes. The system analyzes environmental, equipment, and production factors to evaluate wind energy utilization. It predicts wind direction and speed changes and optimizes turbine adjustments to capture wind energy before actual changes. This improves power generation efficiency and reduces losses compared to just reacting to wind changes. The optimization is verified by comparing wind energy utilization before and after implementing the optimized control.

Source

Wind farm optimization method that quickly adjusts wind turbine parameters to maximize total power output. The method involves determining the dominant wind direction, key turbines in that direction, and correcting non-critical turbine data using a wake model based on the keys. It then optimizes the critical turbine parameters while monitoring total power sensitivity.

Source

Intelligent control of wind turbines using cloud-edge collaboration to improve power generation efficiency and reliability. The method involves real-time collection of wind data and turbine parameters at the edge using sensors and data collectors. It trains a short-term prediction channel using historical data to forecast wind energy accurately. If the forecast accuracy exceeds a threshold, it uses the forecast for intelligent control of the turbine. This leverages local edge processing for real-time monitoring and cloud-based training for accurate wind forecasting.

Source

A system to optimize power output of a wind turbine when operating at yaw misalignment. The system has a control device that calculates target pitch and torque setpoints based on the turbine's yaw misalignment to compensate for reduced efficiency. This allows operating turbines at yaw angles for wake steering without degrading performance. A farm-wide control can also adjust turbine yaw angles to optimize overall power.

Source

Wind farm power optimization by considering wake effects between wind turbines. The method involves a central controller that communicates with local controllers in each wind turbine. The central controller adjusts pitch angles to track the global optimum of total farm power by hill climbing. It calculates gradients based on wind farm power and uses them to guide pitch adjustments. This coordinated pitch optimization mitigates local optima caused by wake effects.

Source

Wind farm power control system that optimizes power allocation considering individual turbine output status to improve reliability and reduce fatigue. The system involves a wind power prediction module, a wind farm power distribution module, a database, SCADA, and turbine control systems. The power distribution module combines power prediction with turbine output analysis to optimize allocation of power commands to turbines based on their current output levels. This better tracks power commands and reduces fatigue compared to uniform or proportional allocation.

Source

Automatic identification of parameters for wind turbine generators to improve control performance, safety and reduce maintenance costs. The method involves controlling the generator to no-load start and shut down by adjusting blade pitch. During this transient, voltages and flux linkage can be measured to determine generator parameters like rotor angle, pole pairs, and flux linkage. Closing the circuit breaker at shutdown allows measuring stator resistance and inductance. This avoids manual parameter entry errors and reduces software versions compared to static tables.

Source

Optimizing wind farm active power regulation during grid frequency fluctuations using model predictive control to accurately allocate adjustment amounts to each wind turbine. This involves quantifying the active support capability of wind turbines using simulation when they only use rotor kinetic energy for short-term regulation. The turbine's maximum up and down power adjustments are calculated under different wind speeds. Then during frequency deviations, the total farm adjustment is computed and allocated per turbine via MPC to avoid exceeding their support limits and prevent rotor speed issues.

Source

Improving the adaptability and robustness of wind farm power generation control against changes in the environment or other factors. The method involves using a multi-agent system where each wind turbine has an independent intelligent agent. Communication connections are deployed between the agents. The inter-turbine wake impact relationship matrix is calculated for each wind turbine. Depth is determined for each turbine based on the matrix to decide if interaction is needed. Then, the yaw decision-making sequence is determined based on turbine depth to optimize efficiency and avoid redundant information.

Source

Wake steering optimization for wind farms that balances turbine efficiency and health. The method involves using a model to analyze factors like turbine waking, offline status, underperformance, and derating. This balances efficiency from wake steering against operational constraints. It generates recommended yaw controls for turbines based on both efficiency and health considerations. The method also uses a probabilistic network to determine turbine operational state. This allows selecting turbines that are feasible for wake steering based on their probability of being waked vs offline vs underperforming vs derated.

Source

Neural network based control of wind turbines to optimize power extraction and robustness. The control uses a trained neural network to estimate the optimal rotor speed and maximum power for a wind turbine given the wind speed. This is done by feeding wind speed and tip speed ratio into the network and outputting the optimal rotor speed and maximum power. The wind turbine is then operated at the estimated optimal speed determined by the neural network for any wind condition. This allows the turbine to track maximum power and efficiently adjust rotor speed in response to wind changes.

Source

Intelligent wind power prediction and dispatching method and system using deep learning and reinforcement learning to improve wind farm output and grid stability. The method involves using a ConvLSTM model to accurately predict wind speed and direction from historical data and meteorological inputs. This is followed by intelligent wind turbine control using reinforcement learning to maximize power and life. Finally, wind farm dispatching using reinforcement learning to balance output with grid needs, reducing impact and losses.

Source

Method to reduce misoperation of wind farm units by using short-term wind speed prediction. The method involves predicting wind speeds at each wind turbine in a wind farm for the next few dozen minutes or hours. This prediction is then used to optimize blade pitch and start/stop decisions to mitigate issues like frequent starts/stops and stall control at high wind speeds. By incorporating short-term wind forecasts into control algorithms, misoperation of wind farm units can be reduced compared to relying solely on real-time wind measurements.

Source

A wind farm control strategy that maximizes overall power generation by using a trained model to predict optimal operating conditions for a wind farm based on real-time wind data and current turbine conditions. The model takes incoming wind data, turbine restrictions, and current turbine settings to forecast the best settings for maximum power. This allows the wind farm to operate at the highest possible output by dynamically adjusting turbine settings in real-time based on the predicted optimal conditions.

Source

Power optimization method for wind farms to reduce wake losses and improve overall power generation by coordinated yaw control. The method involves using a wake model fitted from measured data, particle swarm optimization, and a wind farm power model to determine optimal yaw angles for each turbine. This reduces wake losses compared to individual turbine yawing.

Source

Optimizing power output of multi-rotor wind turbines by accurately determining the optimal yaw angle for the turbines. The method involves measuring wind power parameters over a range of relative wind directions for each rotor nacelle assembly. The maximum power points are determined for each nacelle. The average of these maximum points is used as the control wind direction for the common yaw system. This aligns the rotors with the wind for maximum power.

Source

Optimizing wind turbine power generation by predicting meteorological parameters and using machine learning to find the optimal operating parameters for maximum power. The method involves training a meteorological parameter prediction model and a wind turbine power generation model using support vector machines. It then solves for the optimal operating parameters in real time by combining predicted meteorological parameters and turbine parameters using an adaptive evolution strategy. This allows faster, more accurate wind turbine power optimization compared to using real-time meteorological data.

Source