Reference for citation: Martynchuk I. G. Forecasting multi-seasonal load processes in elastic computing systems. Journal of Instrument Engineering. 2023. Vol. 66, N 11. P. 907—916 (in Russian). DOI: 10.17586/0021-3454-2023-66-11-907-916.

Abstract. The correctness of using the multi-seasonal season-trend decomposition method based on locally weighted scattergram smoothing for the problems of forecasting multi-seasonal load processes in elastic systems is assessed. A comparative analysis of the performance and accuracy of the above method and the seasonal integrated autoregressive moving average (SARIMA) model is performed. Results of experiments are presented that confirm the difficulty of constructing the SARIMA model based on data with a high degree of discretization and period values exceeding classical seasonality, such as 7, 12, 52. When creating the SARIMA model, time restrictions are imposed on the selection of parameters due to high memory consumption, which lead to a decrease in forecast accuracy and limited the ability to build a model based on higher seasonality indicators. The multi-seasonal season-trend decomposition method demonstrates an advantage over the SARIMA model in terms of forecast execution time and memory consumption, however, with a small set of initial data, the SARIMA model shows higher accuracy.

Keywords: elastic systems, multi-seasonal workload, time series forecasting, SARIMA, MSTL

References:

1. Aliev T.I., Rebezova M.I., Russ A.A. Automatic Control and Computer Sciences, 2015, no. 6(49), pp. 321–327.
2. Bogatyrev V.A., Bogatyrev S.V., Bogatyrev A.V. 2022 International Conference on Information, Control, and Communication Technologies (ICCT), 2022, рр. 1–5.
3. Bogatyrev V.A., Bogatyrev S.V. Journal of Instrument Engineering, 2016, no. 9(59), pp. 735–740. (in Russ.)
4. Portnoy M. Virtualization essentials, John Wiley & Sons, 2012, 336 p.
5. Roy N., Dubey A., Gokhale A. 2011 IEEE 4th International Conference on Cloud Computing, 2011, рр. 500–507.
6. Tirado J.M. et al. 11th IEEE/ACM Intern. Symp. on Cluster, Cloud and Grid Computing, 2011, рр. 285–294.
7. Liao S. et al. 5th Intern. Conf. on advanced cloud and big data (CBD), 2017, рр. 33–38.
8. Melhem S. B. et al. IEEE Access, 2017, vol. 6, рр. 7190–7205.
9. Yazdanian P., Sharifian S. 2018 4th Iranian Conf. on Signal Processing and Intelligent Systems (ICSPIS), 2018, рр. 83–87.
10. Vagropoulos S.I. et al. 2016 IEEE Intern. Energy Conf. (ENERGYCON), 2016, рр. 1–6.
11. Naim I., Mahara T., Idrisi A.R. Procedia Computer Science, 2018, vol. 132, рр. 1832–1841.
12. Xie T., Ding J. 2020 IEEE Intern. Conf. on Big Data (Big Data), 2020, рр. 240–245.
13. Bandara K., Hyndman R.J., Bergmeir C. arXiv preprint arXiv:2107.13462, 2021.
14. Fryzlewicz P., Van Bellegem S., Von Sachs R. Annals of the Institute of Statistical Mathematics, 2003, no. 4(55), pp. 737–764.
15. Antoni J., Randall R.B. Mechanical Systems and Signal Processing, 2004, no. 1(18), pp. 89–101.