New ensemble method improves photovoltaic power forecasting accuracy

Researchers have developed a novel hierarchical ensemble method for short-term photovoltaic power forecasting. This approach combines various models, including temporal neural networks, historical analogs, climatology, and gradient-boosted trees, to account for both regular solar cycles and weather-driven fluctuations. The system uses horizon-specific convex weights to integrate predictions from these diverse models, with a calibration step to correct for recent biases. Evaluations on public PVDAQ and GEFCom2014 datasets demonstrated that this ensemble method achieves improved accuracy compared to strong individual models like LightGBM and Chronos-2, particularly at shorter forecast horizons. AI

IMPACT This research introduces a novel ensemble technique that could enhance the accuracy of renewable energy forecasting systems.

RANK_REASON The cluster contains a research paper detailing a new methodology for photovoltaic power forecasting. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• alphaXiv
• arXiv
• CatalyzeX
• Chronos-2 Forecasting Model
• DagsHub
• GEFCom2014
• Gotit.pub
• Hugging Face
• LightGBM
• PVDAQ
• ScienceCast

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →