Noise-intensification data augmented machine learning for day-ahead wind power forecast

The day-ahead wind power forecast is essential for the designation of dispatch schedules grid and rational arrangement production planning by generation companies. This paper specifically investigates effect adding noise to original data forecasting models. Linear regression, artificial neural networks, adaptive boosting predictive models based on data-intensification white uniform are evaluated in detail their superiority over data-based compared. results demonstrate that solely injecting into dataset can statistically boost performance all with learning algorithms. findings this study suggest a fresh perspective developing prediction carry certain energy engineering merits.