Agentic Workflow Using RBA$_\theta$ for Event Prediction

TL;DR

This paper introduces a novel event-first, frequency-aware wind power forecasting framework that directly predicts ramp events using advanced machine learning models, enabling better transferability and operational utility across different wind farms.

Contribution

It develops an integrated, multi-scale deep learning architecture for direct ramp event prediction, improving robustness and transferability over traditional methods.

Findings

Accurate reconstruction of wind power trajectories from sparse event forecasts

Distinct mid-frequency bands govern ramp magnitude and duration

Zero-shot transfer to unseen wind farms achieved

Abstract

Wind power ramp events are difficult to forecast due to strong variability, multi-scale dynamics, and site-specific meteorological effects. This paper proposes an event-first, frequency-aware forecasting paradigm that directly predicts ramp events and reconstructs the power trajectory thereafter, rather than inferring events from dense forecasts. The framework is built on an enhanced Ramping Behaviour Analysis (RBA$_\theta$) method's event representation and progressively integrates statistical, machine-learning, and deep-learning models. Traditional forecasting models with post-hoc event extraction provides a strong interpretable baseline but exhibits limited generalisation across sites. Direct event prediction using Random Forests improves robustness over survival-based formulations, motivating fully event-aware modelling. To capture the multi-scale nature of wind ramps, we introduce an event-first deep architecture that integrates wavelet-based frequency decomposition, temporal excitation features, and adaptive feature selection. The resulting sequence models enable stable long-horizon event prediction, physically consistent trajectory reconstruction, and zero-shot transfer to previously unseen wind farms. Empirical analysis shows that ramp magnitude and duration are governed by distinct mid-frequency bands, allowing accurate signal reconstruction from sparse event forecasts. An agentic forecasting layer is proposed, in which specialised workflows are selected dynamically based on operational context. Together, the framework demonstrates that event-first, frequency-aware forecasting provides a transferable and operationally aligned alternative to trajectory-first wind-power prediction.