Temporal Convolutional Networks Applied to Energy-Related Time Series Forecasting
Source abstract
Abstract
Modern energy systems collect high volumes of data that can provide valuable information about energy consumption. Electric companies can now use historical data to make informed decisions on energy production by forecasting the expected demand. Many deep learning models have been proposed to deal with these types of time series forecasting problems. Deep neural networks, such as recurrent or convolutional, can automatically capture complex patterns in time series data and provide accurate predictions. In particular, Temporal Convolutional Networks (TCN) are a specialised architecture that has advantages over recurrent networks for forecasting tasks. TCNs are able to extract long-term patterns using dilated causal convolutions and residual blocks, and can also be more efficient in terms of computation time. In this work, we propose a TCN-based deep learning model to improve the predictive performance in energy demand forecasting. Two energy-related time series with data from Spain have been studied: the national electric demand and the power demand at charging stations for electric vehicles. An extensive experimental study has been conducted, involving more than 1900 models with different architectures and parametrisations. The TCN proposal outperforms the forecasting accuracy of Long Short-Term Memory (LSTM) recurrent networks, which are considered the state-of-the-art in the field.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Energy Load and Power Forecasting · Stock Market Forecasting Methods · Time Series Analysis and Forecasting
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Division of Computer Science, University of Sevilla, ES-41012 Seville, Spain
Funding
Ministerio de Economía y Competitividad · Junta de Andalucía
References (43)
Show source-provided references
1. ARIMA models to predict next-day electricity prices10.1109/TPWRS.2002.804943 ↗
2. Electricity price forecasting by a hybrid model, combining wavelet transform, ARMA and kernel-based extreme learning machine methods10.1016/j.apenergy.2016.12.130 ↗
3. Day-ahead electricity price forecasting via the application of artificial neural network based models10.1016/j.apenergy.2016.03.089 ↗
4. A new hybrid Modified Firefly Algorithm and Support Vector Regression model for accurate Short Term Load Forecasting10.1016/j.eswa.2014.03.053 ↗
5. A regional hybrid GOA-SVM model based on similar day approach for short-term load forecasting in Assam, India10.1016/j.energy.2017.12.156 ↗
6. Development of prediction models for next-day building energy consumption and peak power demand using data mining techniques10.1016/j.apenergy.2014.04.016 ↗
7. Torres, J., Troncoso, A., Koprinska, I., Wang, Z., and Martínez-Álvarez, F. (2018, January 6–8). Deep Learning for Big Data Time Series Forecasting Applied to Solar Power. Proceedings of the 13th International Conference on Soft Computing Models in Industrial and Environmental Applications, San Sebastian, Spain.10.1007/978-3-319-94120-2_12 ↗
8. Ray, P., Mishra, D., and Lenka, R. (2016, January 1–3). Short term load forecasting by artificial neural network. Proceedings of the 2016 International Conference on Next Generation Intelligent Systems (ICNGIS), Kottayam, India.10.1109/ICNGIS.2016.7854003 ↗
9. Schäfer, A.M., and Zimmermann, H.G. (2006, January 10–14). Recurrent Neural Networks Are Universal Approximators. Proceedings of the 16th International Conference on Artificial Neural Networks ICANN’06, Athens, Greece.
10. Wang, Y., Liu, M., Bao, Z., and Zhang, S. (2018). Short-Term Load Forecasting with Multi-Source Data Using Gated Recurrent Unit Neural Networks. Energies, 11.10.3390/en11051138 ↗
11. Zheng, J., Xu, C., Zhang, Z., and Li, X. (2017, January 22–24). Electric load forecasting in smart grids using Long-Short-Term-Memory based Recurrent Neural Network. Proceedings of the 2017 51st Annual Conference on Information Sciences and Systems (CISS), Baltimore, MD, USA.
12. Long Short-term Memory10.1162/neco.1997.9.8.1735 ↗
13. Long short-term memory neural network for traffic speed prediction using remote microwave sensor data10.1016/j.trc.2015.03.014 ↗
14. Gensler, A., Henze, J., Sick, B., and Raabe, N. (2016, January 9–12). Deep Learning for solar power forecasting—An approach using AutoEncoder and LSTM Neural Networks. Proceedings of the 2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Budapest, Hungary.10.1109/SMC.2016.7844673 ↗
15. Deep learning with long short-term memory networks for financial market predictions10.1016/j.ejor.2017.11.054 ↗
16. Effective long short-term memory with differential evolution algorithm for electricity price prediction10.1016/j.energy.2018.05.052 ↗
17. Amarasinghe, K., Marino, D., and Manic, M. (2017, January 19–21). Deep neural networks for energy load forecasting. Proceedings of the 2017 IEEE 26th International Symposium on Industrial Electronics (ISIE), Edinburgh, UK.10.1109/ISIE.2017.8001465 ↗
18. Almalaq, A., and Edwards, G. (2017, January 18–21). A review of deep learning methods applied on load forecasting. Proceedings of the 2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA), Cancun, Mexico.10.1109/ICMLA.2017.0-110 ↗
19. Kuo, P.H., and Huang, C.J. (2018). A High Precision Artificial Neural Networks Model for Short-Term Energy Load Forecasting. Energies, 11.10.3390/en11010213 ↗
20. Koprinska, I., Wu, D., and Wang, Z. (2018, January 8–13). Convolutional Neural Networks for Energy Time Series Forecasting. Proceedings of the 2018 International Joint Conference on Neural Networks (IJCNN), Rio de Janeiro, Brazil.10.1109/IJCNN.2018.8489399 ↗
21. Cirstea, R.G., Micu, D.V., Muresan, G.M., Guo, C., and Yang, B. Correlated Time Series Forecasting Using Multi-Task Deep Neural Networks. Proceedings of the 27th ACM International Conference on Information and Knowledge Management.
22. Tian, C., Ma, J., Zhang, C., and Zhan, P. (2018). A Deep Neural Network Model for Short-Term Load Forecast Based on Long Short-Term Memory Network and Convolutional Neural Network. Energies, 11.10.3390/en11123493 ↗
23. Shen, Z., Zhang, Y., Lu, J., Xu, J., and Xiao, G. (2019). A novel time series forecasting model with deep learning. Neurocomputing.10.1016/j.neucom.2018.12.084 ↗
24. Bai, S., Kolter, J.Z., and Koltun, V. (2018). An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling. arXiv.
25. Dilated convolutional neural networks for time series forecasting
26. Chen, Y., Kang, Y., Chen, Y., and Wang, Z. (2020). Probabilistic Forecasting with Temporal Convolutional Neural Network. Neurocomputing.10.1016/j.neucom.2020.03.011 ↗
27. Wan, R., Mei, S., Wang, J., Liu, M., and Yang, F. (2019). Multivariate temporal convolutional network: A deep neural networks approach for multivariate time series forecasting. Electronics, 8.10.3390/electronics8080876 ↗
28. (2020, February 25). Spanish Public Grid (Red eléctrica de España). Available online: https://www.ree.es/es/datos/.
29. Rojas, I., Joya, G., and Catala, A. (2017). Scalable Forecasting Techniques Applied to Big Electricity Time Series. Advances in Computational Intelligence, Springer International Publishing.
30. (2020, February 25). Cecovel: Centro de control de vehículo eléctrico (Monitoring Centre of Electric Vehicles). Available online: https://www.ree.es/es/red21/vehiculo-electrico/cecovel.
31. A Novel Ensemble Method for Electric Vehicle Power Consumption Forecasting: Application to the Spanish System10.1109/ACCESS.2019.2936478 ↗
32. A review and comparison of strategies for multi-step ahead time series forecasting based on the NN5 forecasting competition10.1016/j.eswa.2012.01.039 ↗
33. Forecasting across time series databases using recurrent neural networks on groups of similar series: A clustering approach10.1016/j.eswa.2019.112896 ↗
34. Multi-output bus travel time prediction with convolutional LSTM neural network10.1016/j.eswa.2018.11.028 ↗
35. Yu, F., and Koltun, V. (2016, January 2–4). Multi-Scale Context Aggregation by Dilated Convolutions. Proceedings of the 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico.
36. Lara-Benítez, P., Carranza-García, M., García-Gutiérrez, J., and Riquelme, J. (2020). Asynchronous dual-pipeline deep learning framework for online data stream classification. Integr. Comput.-Aided Eng., 1–19.10.3233/ICA-200617 ↗
37. Nair, V., and Hinton, G. (2010, January 21–24). Rectified linear units improve Restricted Boltzmann machines. Proceedings of the ICML 2010—27th International Conference on Machine Learning, Haifa, Israel.
38. Van den Oord, A., Dieleman, S., Zen, H., Simonyan, K., Vinyals, O., Graves, A., Kalchbrenner, N., Senior, A.W., and Kavukcuoglu, K. (2016). WaveNet: A Generative Model for Raw Audio. arXiv.
39. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
40. Pascanu, R., Mikolov, T., and Bengio, Y. (2012). On the difficulty of training Recurrent Neural Networks. arXiv.
41. Kingma, D.P., and Ba, J. (2014). Adam: A Method for Stochastic Optimization. arXiv.
42. Lara-Benítez, P., and Carranza-García, M. (2020, March 01). Electric Demand Forecasting with Temporal Convolutional Networks. Available online: https://github.com/pedrolarben/ElectricDemandForecasting-DL.
43. Keskar, N.S., Mudigere, D., Nocedal, J., Smelyanskiy, M., and Tang, P.T.P. (2016). On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima. arXiv.