Researchers propose new models for heat pump load forecasting in energy communities
- Admin
- May 29, 2024
- 1 min read
An international research group investigated the impact of heat pumps on energy community load forecasting. They found that transformer models improve forecasting quality. The researchers used machine learning techniques and evaluated the novel neural network architecture of transformers. They proposed additional features for forecasting and utilized the Bayesian optimization model to identify relevant features. The group also applied the CEEMDAN method to each forecasting technique. The study was conducted in Germany's Hamelin energy community using a dataset of household loads with water-to-water heat pumps. The best-performing forecasting methods were transformer-based models, especially after the installation of heat pumps.
Source:
Want to read more?
Subscribe to vitaliydaviy.wixsite.com to keep reading this exclusive post.
