TUCKER-CLUS: Multi-aspect renewable energy forecasting

A new method based on the Tucker tensor decomposition, capable of extracting a new feature space for the multi-plant energy forecasting task.

For evaluation purposes, we have investigated the performance of predictive clustering trees with the new feature space, compared to the original feature space, in three renewable energy datasets. The results are favorable for the proposed method, also when compared with state-of-the-art algorithms.

The performance of the method has been tested on the 24-hour ahead multi-plant energy forecasting task. Additional details can be found on the research paper referenced below.

Publications:

R. Corizzo, M. Ceci, H. Fanaee-T, J. Gama: Multi-aspect renewable energy forecasting, Information Sciences (DOI: 10.1016/j.ins.2020.08.003), https://www.sciencedirect.com/science/article/pii/S0020025520307611

Citation:

@article{corizzo2021multi,
  title={Multi-aspect renewable energy forecasting},
  author={Corizzo, Roberto and Ceci, Michelangelo and Fanaee-T, Hadi and Gama, Joao},
  journal={Information Sciences},
  volume={546},
  pages={701--722},
  year={2021},
  publisher={Elsevier}
}