Enhancing Wind Power Forecasting with GRU-Dynamic Context-Aware Power Forecasting Hybrid Model

Accurate forecasts of wind energy for the next day can deliver a consistent basis and guarantee for the operation and distribution of the grid. This paper addresses the contextual prediction accuracy from the inability of existing methods to analyze temporal information deeply. It introduces a novel Transformer-based Dynamic context-aware power forecasting model that combines the Gate Recurrent Unit (GRU) to enhance contextual wind power prediction. The model identifies significant factors influencing wind power generation and integrates various conditions affecting wind power output into a unified embedding. To improve the forecast accuracy, the model adopts a two-layer architecture. The first layer uses GRU's gated units to extract essential temporal features from the data stream. The subsequent layer utilizes the Dynamic context-aware model's hierarchical multi-head self-attention mechanism to discern global information and contextual interrelations within the temporal data and identify essential features for the current period. This process refines the sequence data, and increases the representational capacity of the model, resulting in accurate contextual predictions of seasonal performance. Empirical validation using actual measurement data validates that the GRU-Dynamic context-aware model outperforms existing methods in prediction accuracy.