Robust Interval Time Series Forecasting

A.A. Chervyakov, E.V. Nikulchev

Abstract


Time series forecasting is used in many practical problems and occupies a prominent place in scientific research in various fields. The article considers a robust approach to forecasting time series in the form of intervals. The analysis of existing approaches is carried out. It is shown that classical methods, such as autoregressive or stochastic models, use not only point estimates, but also confidence intervals. However, the result of a classical prediction is points, while in interval prediction the solution is ranges of values. An important distinguishing feature of the interval forecast from confidence probabilities is the assessment of the quality of solutions. In the approach under consideration, the size of the interval is controlled not by the level of significance, but by specially introduced criteria. The main types of criteria for evaluating interval solutions and the features of their use are considered. The use of forecast in the form of intervals provides a decrease in the degree of uncertainty in the data and the robustness of the model in terms of output, but at the same time, the accuracy of the forecast is blurred. The paper considers a technique for the series portfolio management strategy based on a robust interval forecast using standard models. The results obtained testify to the effectiveness and prospects of the development of the theory of interval time forecasting and the practice of its application for various applications.

Full Text:

PDF (Russian)

References


Z. Liu, J. Liu, “A robust time series prediction method based on empirical mode decomposition and high-order fuzzy cognitive maps,” Knowledge-Based Systems, vol. 203, p. 106105, 2020.

G. Box, G. Jenkins, G. Reinsel, “Time series analysis: forecasting and control. Forecasting and control series,” Prentice Hall, 1994.

R. Hyndman, A. Koehler, K. Ord, R.D. Snyder, “Forecasting with exponential smoothing. The state space approach,” Springer Berlin Heidelberg, 2008.

R.J. Hyndman, “A brief history of forecasting competitions,” International Journal of Forecasting, vol. 36, no. 1, p. 7–14, 2020.

L.G. Marín, N. Cruz, D. Sáez, M. Sumner, A. Núñez, “Prediction interval methodology based on fuzzy numbers and its extension to fuzzy systems and neural networks,” Expert Systems with Applications, vol. 119, p. 128–141, 2019.

H. Hewamalage, C. Bergmeir, K. Bandara, “Recurrent neural networks for time series forecasting: Current status and future directions,” International Journal of Forecasting, vol. 37. no. 1. p. 388–427, 2021.

Bazhenov A.N., Zhilin S.I., Kumkov S.I., Shary S.P. Processing and analysis of data with interval uncertainty: https://cdn.website-editor.net/cef40558e07d4eef8c29b78a5945738a/files/uploaded/Metodika-26.III.2021.pdf. 2021.

E.V. Nikulchev, A.A. Chervyakov, “Construction of robust interval models for predicting the dynamics of a structural complex system,” Trudy NNSTU im. R.E. Alekseev, no. 1, p. 33–41, 2023.

M.H. Park, J.S. Lee, I.C. Doo, “A Study of the Demand Forecasting Model for Publishing Business using Business Analysis,” International Journal of Computing and Digital Systems, vol. 9, no. 5, p. 1–12, 2020.

M. Zhou, B. Wang, S. Guo, J. Watada, “Multi-objective prediction intervals for wind power forecast based on deep neural networks,” Information Sciences, vol. 550, p. 207–220, 2021.

Z. Zhang, L. Ye, et al., “Wind speed prediction method using shared weight long short-term memory network and Gaussian process regression,” Applied energy, vol. 247, p. 270–284, 2019.

S. Ghimire, R.C. Deo, H. Wang, M.S. Al-Musaylh, D. Casillas-Pérez, S. Salcedo-Sanz, “Stacked LSTM sequence-to-sequence autoencoder with feature selection for daily solar radiation prediction: a review and new modeling results,” Energies, vol. 15, no. 3, p. 1061, 2022.

Y. Guan, D. Li, S. Xue, Y. Xi, “Feature-fusion-kernel-based Gaussian process model for probabilistic long-term load forecasting,” Neurocomputing, vol. 426, p. 174-184, 2021.

E.V. Nikulchev, V.N. Petrushin, E.O. Malygin, A.A. Trubochkin, I.A. Chertikhina, “Probabilistic-interval approach to data analysis,” Vestnik RGRTU, no. 38, p. 112–115, 2011.

V.N., Petrushin E.V., Nikulchev I.A. Chertikhina, “Empirical evaluation of interval solutions,” Izvestiya vuzov. Problems of printing and publishing, no. 6, p. 051-063, 2011.

A. Khosravi, S. Nahavandi, D. Creighton, A.F. Atiya, “Lower upper bound estimation method for construction of neural network-based prediction intervals,” IEEE Transactions on Neural Networks and Learning Systems, vol. 22, no. 3, p. 337–346, 2011.

H. Quan., D. Srinivasan, A. Khosravi, “Short-term load and wind power forecasting using neural network-based prediction intervals,” IEEE Transactions on Neural Networks and Learning Systems, vol. 25. no. 2. p. 303–315, 2014.

G. Zhang, Y. Wu, K.P. Wong, Z. Xu, Z.Y. Dong, H.H.C. Iu, “An advanced approach for construction of optimal wind power prediction intervals,” IEEE Transactions on Power Systems, vol. 30, no. 5, p. 2706–2715, 2014.

R. Taormina, K.W. Chau, “ANN-based interval forecasting of streamflow discharges using the LUBE method and MOFIPS,” Engineering Applications of Artificial Intelligence, vol. 45, p. 429– 440, 2015.

C. Zhang, H. Wei, L. Xie, Y. Shen, K. Zhang, “Direct interval forecasting of wind speed using radial basis function neural networks in a multi-objective optimization framework,” Neurocomputing, vol. 205, p. 53–63, 2016.

P. Arora, S.M.J. Jalali, S. Ahmadian, B.K. Panigrahi, P. Suganthan, A. Khosravi, “Probabilistic wind power forecasting using optimised deep auto-regressive recurrent neural networks,” IEEE Transactions on Automation Science and Engineering, vol. 20, p. 271–284, 2023.

Nikulchev E.V. Geometric approach to the modeling of nonlinear systems from experimental data. M., 2007.

Nikulchev E.V. Identification of dynamical systems based on the symmetries of the reconstructed attractors. M., 2010.


Refbacks

  • There are currently no refbacks.


Abava  Кибербезопасность IT Congress 2024

ISSN: 2307-8162