WaveHiTS: Wavelet-Enhanced Hierarchical Time Series Modeling for Wind Direction Nowcasting in Eastern Inner Mongolia

2025-04-09

AI Summary

To address the challenges of directional cyclicity, multi-step error accumulation, and complex meteorological coupling in short-term wind direction forecasting over eastern Inner Mongolia, this paper proposes a waveform-enhanced hierarchical time-series modeling framework. The method innovatively integrates wavelet transform with the Neural Hierarchical Interpolation Time-Series (NHITS) architecture, coupled with U-V wind component decomposition, to jointly suppress error propagation across dual pathways: multi-scale frequency domains and multi-granularity temporal dependencies. Evaluated on real-world meteorological data, the model achieves a 60-minute wind direction prediction RMSE of 19.2°–19.4°—a substantial reduction from baseline values of 56°–64°—along with a vector correlation coefficient (VCC) of 0.985–0.987 and wind direction hit rates of 88.5%–90.1%. These improvements significantly enhance yaw control accuracy for wind turbines.

Technology Category

• Machine Learning: Ensemble Methods
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Wind direction forecasting plays a crucial role in optimizing wind energy production, but faces significant challenges due to the circular nature of directional data, error accumulation in multi-step forecasting, and complex meteorological interactions. This paper presents a novel model, WaveHiTS, which integrates wavelet transform with Neural Hierarchical Interpolation for Time Series to address these challenges. Our approach decomposes wind direction into U-V components, applies wavelet transform to capture multi-scale frequency patterns, and utilizes a hierarchical structure to model temporal dependencies at multiple scales, effectively mitigating error propagation. Experiments conducted on real-world meteorological data from Inner Mongolia, China demonstrate that WaveHiTS significantly outperforms deep learning models (RNN, LSTM, GRU), transformer-based approaches (TFT, Informer, iTransformer), and hybrid models (EMD-LSTM). The proposed model achieves RMSE values of approximately 19.2{deg}-19.4{deg} compared to 56{deg}-64{deg} for deep learning recurrent models, maintaining consistent accuracy across all forecasting steps up to 60 minutes ahead. Moreover, WaveHiTS demonstrates superior robustness with vector correlation coefficients (VCC) of 0.985-0.987 and hit rates of 88.5%-90.1%, substantially outperforming baseline models. Ablation studies confirm that each component-wavelet transform, hierarchical structure, and U-V decomposition-contributes meaningfully to overall performance. These improvements in wind direction nowcasting have significant implications for enhancing wind turbine yaw control efficiency and grid integration of wind energy.

Problem

• Addresses circular wind direction data forecasting challenges
• Mitigates error propagation in multi-step time series prediction
• Improves wind energy optimization via accurate nowcasting

Innovation

• Wavelet transform captures multi-scale frequency patterns
• Hierarchical structure models temporal dependencies effectively
• U-V decomposition mitigates circular data challenges