A SIREN-Based Multi-Horizon Wind-Speed Forecasting Approach for Onshore and Offshore Wind Farms

The importance of accurate and fast forecasting of wind speed is critical for guiding investment decisions, grid integration of wind power plants, and dispatch management. However, due to surface smoothness and the effects of thermal processes, wind-speed time series obtained from onshore and offshore sites have very statistically and dynamically distinct characteristics in terms of volatility, non-stationarity, autocorrelation, and noise components. This study proposes a Sinusoidal Representation Network (SIREN)-based framework to provide accurate, fast, and direct multi-horizon wind-speed forecasting for both onshore and offshore wind farms. Two datasets of onshore and offshore wind speeds, which have long durations and data continuity, are used to assess the performance of the suggested approach from very-short-term to long-term forecasting horizons. Both of the datasets use Savitzky–Golay filters and moving medians to reduce short-term noise and sudden spikes and winsorization and Hampel filters to limit the effect of outliers. Additionally, robust scaling is done to ensure stability of the scales of the variables, while log transformation is applied to counteract the problem of skewness and variation in the data distribution. The SIREN model is trained, validated, and tested independently for each forecast horizon, corresponding to times ranging from 5 min to 30 days. Ablation and sensitivity analyses are conducted to evaluate the effect of the parameters used in the model on forecast performance. In addition, comparative analyses incorporating traditional time series, and ML and DL techniques are conducted to more comprehensively evaluate the model’s performance. The obtained graphical and numerical results have revealed that the proposed SIREN approach is a highly accurate and computationally convenient alternative wind-speed forecasting method that can be flexibly adapted to different time resolutions and forecast horizons in both onshore and offshore systems.