In this paper, a new deep learning-based two-stage dataset-clustering/temporal-clustering method is proposed for time aggregation in renewable energy-integrated power systems. In this way, for the first time, the representative period, including one or more representative days, is obtained using a GAN-based model in which the LSTM Network is embedded in both generator and discriminator models.
Highlights
-
- We propose a generative time aggregation method for selecting representative periods.
- The proposed approach contains the LSTM in both generator and discriminator parts.
- We propose a clustering specific loss term to enhance the clustering performance.
- Multiple power time series with spatio-temporal correlations among them are used.
- Extensive results on both the data-based and model-based evaluations are presented.
Authors: Razieh Rastgoo, Nima Amjady, Hamidreza Zareipour
Read the full paper on ScienceDIrect
