Back to Search
Start Over
Multivariate Prediction of Energy Time Series by Autoencoded LSTM Networks
- Source :
- 2021 IEEE International Conference on Environment and Electrical Engineering and 2021 IEEE Industrial and Commercial Power Systems Europe (EEEIC / I&CPS Europe).
- Publication Year :
- 2021
- Publisher :
- IEEE, 2021.
-
Abstract
- In this paper, a novel approach for the multivariate prediction of energy time series is presented. It is based on the Long Short-Term Memory deep neural network. The latter is made up of two stacked recurrent layers and it is used in two different training configurations. First, an encoder-decoder structure is implemented in order to extract meaningful representative features from the time series. Then, this embedded data are used to improve the actual prediction. To prove the goodness of our approach, its performance is compared with two different benchmarks. The numerical results show that the proposed model outperforms the aforementioned benchmarks.
- Subjects :
- Artificial neural network
Series (mathematics)
Computer science
Feature extraction
Structure (category theory)
Renewable Energy Sources
multivariate time series forecasting
data embedding
autoencoder learning
Long Short-Term Memory
Multivariate prediction
Measurement uncertainty
Time series
Algorithm
Energy (signal processing)
Subjects
Details
- Database :
- OpenAIRE
- Journal :
- 2021 IEEE International Conference on Environment and Electrical Engineering and 2021 IEEE Industrial and Commercial Power Systems Europe (EEEIC / I&CPS Europe)
- Accession number :
- edsair.doi.dedup.....e0acedf25b022fd17f56cdcb9cfaf374