Enhanced hybrid residual learning framework for robust wind turbine power prediction using machine learning
TL;DR
This research work captures the variation in wind resource variability by implementing advanced machine learning models for short-term power forecasting using SCADA data using a fresh framework to focus on parameters such as aerodynamic behavior, temporal patterns, and overall regime.
Abstract
Wind turbine power generation for any nation is always a priority since its impact on power grids and imbalance the sustainability parameters. This research work captures the variation in wind resource variability by implementing advanced machine learning models for short-term power forecasting using SCADA data. Here, a fresh framework was developed to focus on parameters such as aerodynamic behavior, temporal patterns, and overall regime. This information was fed to the model to analyze actual and theoretical power output. With the strong literature study few models were shortlisted such as Extreme Gradient Boosting (XGBoost), Deep Neural Networks (DNN), and a novel hybrid stacking ensemble to fulfill the criteria. From the generated data hybrid model was the top choice as its value for RMSE came down to 0.0103, while it moves as high as 0.9992 in case of R². With the need to optimize the present work, multiple algorithms were selected and merged to get the desired output so that accuracy can be maintained without compromising on the grid stability and performance. The models were so selected that the outcome can give lower reliance on carbon-intensive power. This work shows a better data driven based farmwork which only addresses energy forecasting parameters by relating to renewable penetration and sustainable energy systems.