Online learning of windmill time series using Long Short-term Cognitive Networks
Morales-Hernández,Alejandro Nápoles,Gonzalo Jastrzebska,Agnieszka Salgueiro,Yamisleydi Vanhoof,Koen
Morales-Hernández,Alejandro
Nápoles,Gonzalo
Jastrzebska,Agnieszka
Salgueiro,Yamisleydi
Vanhoof,Koen
Abstract
Forecasting windmill time series is often the basis of other processes such as anomaly detection, health monitoring, or maintenance scheduling. The amount of data generated by windmill farms makes online learning the most viable strategy to follow. Such settings require retraining the model each time a new batch of data is available. However, updating the model with new information is often very expensive when using traditional Recurrent Neural Networks (RNNs). In this paper, we use Long Short-term Cognitive Networks (LSTCNs) to forecast windmill time series in online settings. These recently introduced neural systems consist of chained Short-term Cognitive Network blocks, each processing a temporal data chunk. The learning algorithm of these blocks is based on a very fast, deterministic learning rule that makes LSTCNs suitable for online learning tasks. The numerical simulations using a case study involving four windmills showed that our approach reported the lowest forecasting errors with respect to a simple RNN, a Long Short-term Memory, a Gated Recurrent Unit, and a Hidden Markov Model. What is perhaps more important is that the LSTCN approach is significantly faster than these state-of-the-art models.
Description
Funding Information: Alejandro Morales and Koen Vanhoof from Hasselt University would like to thank the support received by the Flanders AI Research Program , as well as other partners involved in this project. Agnieszka Jastrzebska’s contribution was founded by the National Science Centre , grant No. 2019/35/D/HS4/01594 , decision no. DEC-2019/35/D/HS4/01594. Y. Salgueiro would like to acknowledge the support provided by the National Center for Artificial Intelligence CENIA FB210017 , Basal ANID and the super-computing infrastructure of the NLHPC (ECM-02). The authors would like to thank Isel Grau from the Eindhoven University of Technology for revising the paper. Publisher Copyright: © 2022 The Author(s)
Date
2022-11-01
Journal Title
Journal ISSN
Volume Title
Publisher
Research Projects
Organizational Units
Journal Issue
Keywords
Forecasting, Long Short-term Cognitive Network, Multivariate time series, Recurrent Neural Network, Energy, Neural-network, Integration, Challenges, Hidden Markov-Models
Citation
Morales-Hernández, A, Nápoles, G, Jastrzebska, A, Salgueiro, Y & Vanhoof, K 2022, 'Online learning of windmill time series using Long Short-term Cognitive Networks', Expert Systems with Applications, vol. 205, 117721, pp. 1-9. https://doi.org/10.1016/j.eswa.2022.117721