In the dynamic landscape of renewable energy, the primary goal continues to be the enhancement of competitiveness through the implementation of cutting-edge technologies. This requires a strategic focus on reducing energy costs and maximizing system performance. Within this framework, the continuous online monitoring of assets is essential for efficient operations, by conducting measurements that describe the condition of various components. However, the execution of these measurements can present technical and economic obstacles. To overcome these challenges, the implementation of indirect measurement techniques emerges as a viable solution. By leveraging measurements obtained in easily accessible areas, these methods enable the estimation of quantities in regions that would otherwise be inaccessible. This approach improves the monitoring process’s efficiency and provides previously unattainable information. Adopting indirect measurement techniques is also cost-effective, allowing the replacement of expensive sensors with existing infrastructure, which cuts down on installation costs and labor. This paper offers a detailed state-of-the-art review by providing an in-depth examination and classification of indirect measurement techniques and virtual sensing methods applied in the field of renewable energies. It also identifies and discusses the existing challenges and limitations within this topic and explores potential future developments.

This study introduces a classification-based prognostic framework to anticipate temperature threshold exceedance events that lead to automatic shutdowns in wind turbines. The framework assesses whether an observed temperature anomaly is likely to evolve into such an event and relies exclusively on Supervisory Control and Data Acquisition data combined with Deep Learning and Conformal Prediction for uncertainty quantification. To characterize the temporal evolution of the exceedance tendency, we propose a novel metric, the Instantaneous Event Intensity, derived from confidence intervals produced by Conformal Prediction. By aggregating Instantaneous Event Intensity values over time, we define the Cumulative Event Intensity, which integrates the event magnitude. The Cumulative Event Intensity is then compared with a predefined event threshold to support binary decision-making on whether the component will experience a temperature threshold exceedance event. The proposed approach is validated on 207 wind turbines from 20 wind farms, covering three manufacturers and three distinct components, detecting 87.25% of temperature threshold exceedance events 15 days in advance, with a false positive rate below 21%. Notably, several events can be anticipated up to three months earlier, highlighting the robustness of the early-warning capability.

This study introduces a SCADA-based framework for predicting the remaining useful life of wind turbine components, enabling the anticipation of gradual, overheating-related degradation processes observable at SCADA resolution. To ensure physical consistency and interpretability, a health indicator is derived from temperature-rise signals using a cumulative-maximum filtering strategy that enforces monotonic behavior over time. On this basis, several artificial intelligence models are evaluated to learn the relationship between SCADA variables and remaining useful life, among which a gated recurrent unit emerges as the most effective architecture. Predictive uncertainty is subsequently quantified using conformalized quantile regression, providing calibrated confidence intervals without reliance on distributional assumptions. The proposed framework is validated on operational data from 28 main bearings spanning multiple wind farms and manufacturers. The results show an average RMSE of 26.54 days and an R2 of 88.43 %, while maintaining robust uncertainty calibration for prediction horizons exceeding three months, thereby demonstrating the practical viability of SCADA-only prognostics for fleet-scale deployment.