An Adaptive Approach for Probabilistic Wind Power Forecasting Based on Meta-Learning
This addresses the need for accurate and adaptable wind power forecasting for energy grid operators, though it appears incremental as it builds on existing meta-learning and incremental learning techniques.
The paper tackles probabilistic wind power forecasting by developing an adaptive meta-learning approach with offline and online stages, showing improved adaptability in temporal and spatial forecasting scenarios through numerical tests on real-world data.
This paper studies an adaptive approach for probabilistic wind power forecasting (WPF) including offline and online learning procedures. In the offline learning stage, a base forecast model is trained via inner and outer loop updates of meta-learning, which endows the base forecast model with excellent adaptability to different forecast tasks, i.e., probabilistic WPF with different lead times or locations. In the online learning stage, the base forecast model is applied to online forecasting combined with incremental learning techniques. On this basis, the online forecast takes full advantage of recent information and the adaptability of the base forecast model. Two applications are developed based on our proposed approach concerning forecasting with different lead times (temporal adaptation) and forecasting for newly established wind farms (spatial adaptation), respectively. Numerical tests were conducted on real-world wind power data sets. Simulation results validate the advantages in adaptivity of the proposed methods compared with existing alternatives.