DEAP LEARNING MODELS FOR TIME SERIES FORECASTING
DOI:
https://doi.org/10.26906/SUNZ.2024.1.082Keywords:
time series forecasting, machine learning, artificial neural network, deep learning models, convolutional networks, long short-term memoryAbstract
Topicality. Time series forecasting is one of the important tools for various spheres of human activity, as it allows analyzing past trends, understanding the dynamics of events, and making substantiated decisions based on previously collected historical data. In recent years, deep learning artificial neural network models have demonstrated significant potential in the field of time series forecasting. The goal of this work is to analyze the use of deep learning models for short-term forecasting of time series of various origins and with possible presence of distortions. The object of research is the process of time series forecasting. The subject of research is the use of models based on CNN, RNN, TCNN and LSTM architectures for time series forecasting. Results. Experimental research has shown that forecasts of non-stationary time series using an artificial neural network based on LSTM architecture are closer to real data, compared to other deep learning models. Conclusions. The obtained results in most cases confirm the advantage of using models based on LSTM over other considered deep learning models for time series forecasting.Downloads
References
Chatfield C. (2000), “Time-Series Forecasting”, Chapman and Hall, P. 280.
Lin Y., Korsinska Y., Rana M. (2021), “Temporal Convolutional Attention Neural Networks for Time Series Forecasting”, International Joint Conference on Neural Networks, pp. 236-238.
Pedro H., Coimbra C. (2012), “Assessment of forecasting techniques for solar power production with no exogenous inputs”, Solar Energy, № 86(7), pp. 2017-2028.
Amin Salih Mohammed, Ivashchenko H., Filimonchuk T., Ivanisenko I., Barkovska O. (2020) “Green Hybrid Models Based on Clonal Selection and Case-based Reasoning for Short-term Time Series Forecasting”, Journal of Green Engineering, vol. 10, issue 5, pp. 2139-2154.
Shahin A. (2021), “Deep Learning BiLSTM Encoding-Decoding Model for COVID-19 Pandemic Spread Forecasting”, Fractal and Fractional, №4. pp. 175-176.
Marzouka M. (2021), “Deep learning model for forecasting COVID-19 outbreak in Egypt”, Process Safety and Environmental Protection, № 153, pp. 363-375.
Rangapuram S., Seeger M., Gasthaus D., Stella L., Wang Y, Januschowski T. (2018), “Deep state space models for time series forecasting”, Proceedings of the Conference on Neural Information Processing Systems (NeurIPS), P. 10.
Vaswani A., Shazeer N., Parmar N., Uszkoreit J., Jones L., Gomez A., Kaiser Ł., Polosukhin I. (2017), “Attention is all you need”, Proceedings of the Conference on Neural Information Processing Systems (NeurIPS), P. 11.
Derbentsev V., Matviychuk A., Datsenko N., Bezkorovainyi V., Azaryan A. (2020), “Machine learning approaches for financial time series forecasting”, Proceedings of the Selected Papers of the Special Edition of International Conference on Monitoring, Modeling & Management of Emergent Economy, № 2713, Odessa, Ukraine, pp. 434-450.
Hemmati A., Abdoos M., Akbar A. (2015), “Short term load forecasting using a hybrid intelligent method”, Knowledge-Based System, № 76, pp. 139-147.
Voyant C., Nivet M., Paoli C., Muselli M., Notton G. (2014), “Meteorological time series forecasting based on MLP modelling using heterogeneous transfer functions”, Journal of Physics: Conference Series, № 574, Madrid, Spain, pp. 28-31
Khan S., Rahmani H., Ali Shakh S. A., Bennamoun M (2018), “Guide to Convolutional Neural Networks for Computer Vision”, Morgan & Claypool Publishers, P. 207.
Goodfellow I., Bengio Y., Courville A (2016), “Deep Learning (Adaptive Computation and Machine Learning series)”, The MIT Press, P. 775.
Greff, K., Srivastava, R., Koutnik, J., Steunebrink, B., Schmidhuber, J. (2017), “LSTM: A Search Space Odyssey”, IEEE Transactions on Neural Networks and Learning Systems, № 28, pp. 2222-2232.
Breiman L. (2001), “Random forests”, Machine learning, № 45(1), pp. 5-32.
