Abstract
This paper presents a novel deep learning architecture for short-term load forecasting of building energy loads. The architecture is based on a simple base learner and multiple boosting systems that are modelled as a single deep neural network. The architecture transforms the original multivariate time series into multiple cascading univariate time series. Together with sparse interactions, parameter sharing and equivariant representations, this approach makes it possible to combat against overfitting while still achieving good presentation power with a deep network architecture. The architecture is evaluated in several short-term load forecasting tasks with energy data from an office building in Finland. The proposed architecture outperforms state-of-the-art load forecasting model in all the tasks.
Original language | English |
---|---|
Article number | 2370 |
Journal | Energies |
Volume | 13 |
Issue number | 9 |
DOIs | |
Publication status | Published - 9 May 2020 |
MoE publication type | A1 Journal article-refereed |
Funding
This work has been funded by VTT Technical Research Centre of Finland and Business Finland.
Keywords
- deep neural networks
- short-term load forecasting