Abstract
In this paper, we present SpringNet, a novel deep learning approach for time series forecasting, and demonstrate its performance in a case study for solar power forecasting. SpringNet is based on the Transformer architecture but uses a Spring DTW attention layer to consider the local context of the time series data. Firstly, it captures the local shape of the time series with Spring DTW attention layers, dealing with data fluctuations. Secondly, it uses a batch version of the Spring DTW algorithm for efficient computation on GPU, to facilitate applications to big time series data. We comprehensively evaluate the performance of SpringNet on two large solar power data sets, showing that SpringNet is an effective method, outperforming the state-of-the-art DeepAR and LogSparse Transformer methods.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Li, S., et al.: Enhancing the locality and breaking the memory bottleneck of Transformer on time series forecasting. In: Conference on Neural Information Processing Systems (NeurIPS) (2019)
Salinas, D., Flunkert, V., Gasthaus, J., Januschowski, T.: DeepAR: probabilistic forecasting with autoregressive recurrent networks. Int. J. Forecast. 36, 1181–1191 (2020)
Vaswani, A., et al.: Attention is all you need. In: Conference on Neural Information Processing Systems (NeurIPS) (2017)
Sakoe, H., Chiba, S.: Dynamic programming algorithm optimization for spoken word recognition. IEEE Trans. Acoust. Speech Signal Process. 26, 43–49 (1978)
Cuturi, M., Blondel, M.: Soft-DTW: a differentiable loss function for time-series. In: International Conference on Machine Learning (ICML) (2017)
Guen, V.L., Thome, N.: Shape and time distortion loss for training deep time series forecasting models. In: Conference on Neural Information Processing Systems (NeurIPS) (2019)
Cai, X., Xu, T., Yi, J., Huang, J., Rajasekaran, S.: DTWNet: a dynamic time warping network. In: Conference on Neural Information Processing Systems (NeurIPS) (2019)
Sakurai, Y., Faloutsos, C., Yamamuro, M.: Stream monitoring under the time war-ping distance. In: International Conference on Data Engineering (ICDE) (2007)
Pedro, H.T., Coimbra, C.F.: Assessment of forecasting techniques for solar power production with no exogenous inputs. Solar Energy 86, 2017–2028 (2012)
Lin, Y., Koprinska, I., Rana, M., Troncoso, A.: Pattern sequence neural network for solar power forecasting. In: International Conference on Neural Information Processing (ICONIP) (2019)
Rana, M., Koprinska, I., Agelidis, V.G.: 2D-interval forecasts for solar power production. Solar Energy 122, 191–203 (2015)
Azur, M., Stuart, E., Frangakis, C., Leaf, P.: Multiple imputation by chained equations: what is it and how does it work? Int. J. Methods Psychiatr. Res. 20, 40–49 (2011)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Lin, Y., Koprinska, I., Rana, M. (2020). SpringNet: Transformer and Spring DTW for Time Series Forecasting. In: Yang, H., Pasupa, K., Leung, A.CS., Kwok, J.T., Chan, J.H., King, I. (eds) Neural Information Processing. ICONIP 2020. Lecture Notes in Computer Science(), vol 12534. Springer, Cham. https://doi.org/10.1007/978-3-030-63836-8_51
Download citation
DOI: https://doi.org/10.1007/978-3-030-63836-8_51
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-63835-1
Online ISBN: 978-3-030-63836-8
eBook Packages: Computer ScienceComputer Science (R0)