HYBRID MACHINE LEARNING METHODS FOR DECISION SUPPORT IN AUTOMATED INFORMATION SYSTEMS
DOI:
https://doi.org/10.28925/2663-4023.2025.29.880Keywords:
time series forecasting, hybrid machine learning, LSTM, ARIMA, attention mechanism, cloud computing, AWS, decision support systemsAbstract
This article is dedicated to the development and research of an advanced hybrid machine learning method for time series forecasting in decision support systems (DSS). The relevance of the work is driven by the rapid growth of data volumes in modern information systems, particularly in cloud infrastructures, and the need for accurate forecasting tools for effective resource management. The objective of the study is to increase the accuracy of computing resource load forecasting by developing a hybrid model that combines the advantages of statistical methods and deep learning architectures. A novel hybrid architecture is proposed, integrating the Autoregressive Integrated Moving Average (ARIMA) model for modeling linear components of a time series, and a Long Short-Term Memory (LSTM) recurrent neural network with a built-in Attention Mechanism for analyzing non-linear residuals. The ARIMA model is used to capture stationary dependencies and seasonality, while the LSTM network with an attention mechanism effectively models complex, non-linear, and long-term patterns in the data remaining after ARIMA processing. An experimental study was conducted on a real dataset of CPU utilization monitoring from virtual machines in the AWS (Amazon Web Services) cloud environment. The proposed hybrid ARIMA-LSTM model with an attention mechanism demonstrated a significant improvement in forecasting accuracy compared to baseline models: pure ARIMA, pure LSTM, and a standard hybrid ARIMA-LSTM model. The Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE) metrics for the developed model were 12-18% lower than those of the best-performing baseline model. Scientific novelty lies in the enhancement of existing hybrid approaches by integrating an attention mechanism into the LSTM architecture for analyzing time series residuals. Practical significance of the work consists in the potential for implementing the developed method in automated DSS for optimizing resource allocation, auto-scaling, preventing overloads, and reducing operational costs of cloud infrastructure.
Downloads
References
Box, G. E. P., Jenkins, G. M., Reinsel, G. C., & Ljung, G. M. (2015). Time Series Analysis: Forecasting and Control. John Wiley & Sons.
Hyndman, R. J., & Athanasopoulos, G. (2018). Forecasting: principles and practice. OTexts.
Dinda, P. A. (2006). A case for prediction-based resource management in enterprise and cloud computing. ACM SIGMETRICS Performance Evaluation Review, 34(3), 1-8.
Gong, L., Lu, Y., Li, S., & Li, T. (2020). Workload forecasting for cloud computing based on support vector regression. Journal of Network and Computer Applications, 165, 102693.
Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735-1780.
Wang, J., Zhang, Q., & Zhou, A. (2019). LSTM-based traffic prediction for data center networks. IEEE Communications Letters, 23(10), 1731-1735.
Kong, W., Dong, Z. Y., Jia, Y., Hill, D. J., Xu, Y., & Zhang, Y. (2019). Short-term residential load forecasting based on LSTM recurrent neural network. IEEE Transactions on Smart Grid, 10(1), 841-851.
Lipton, Z. C., Berkowitz, J., & Elkan, C. (2015). A critical review of recurrent neural networks for sequence learning. arXiv preprint arXiv:1506.00019.
Zhang, P. G. (2003). Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing, 50, 159-175.
Babu, C. N., & Reddy, B. E. (2014). A moving-average filter based hybrid ARIMA–ANN model for forecasting time series data. Applied Soft Computing, 23, 27-38.
Kim, H. Y., & Won, C. H. (2018). A hybrid model of ARIMA and feed-forward neural networks for forecasting the KOSPI index. Journal of the Korean Statistical Society, 47(1), 81-90.
Al-Hasan, A. A., Al-Dahidi, S., & Ayasrah, A. (2022). A Hybrid ARIMA-LSTM Model for Solar Irradiance Forecasting. Energies, 15(19), 7051.
Bahdanau, D., Cho, K., & Bengio, Y. (2014). Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473.
Qin, Y., Song, D., Chen, H., Cheng, W., Jiang, G., & Cottrell, G. (2017). A dual-stage attention-based recurrent neural network for time series prediction. arXiv preprint arXiv:1704.02971.
Liang, Y., Ke, S., Zhang, J., Yi, X., & Zheng, Y. (2018). GeoMAN: Multi-level attention networks for geo-sensory time series prediction. In Proceedings of the 27th International Joint Conference on Artificial Intelligence (pp. 3428-3434).
De Gooijer, J. G., & Hyndman, R. J. (2006). 25 years of time series forecasting. International journal of forecasting, 22(3), 443-473.
Calheiros, R. N., Ranjan, R., Beloglazov, A., De Rose, C. A., & Buyya, R. (2011). CloudSim: a toolkit for modeling and simulation of cloud computing environments and evaluation of resource provisioning algorithms. Software: Practice and experience, 41(1), 23-50.
Kumar, G., & Jain, S. (2021). A survey on hybrid models for time series forecasting. Journal of King Saud University-Computer and Information Sciences, 33(9), 1059-1072.
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., ... & Polosukhin, I. (2017). Attention is all you need. In Advances in neural information processing systems (pp. 5998-6008).
Kuremoto, T., Kimura, S., Kobayashi, K., & Obayashi, M. (2014). Time series forecasting using a deep belief network with restricted Boltzmann machines. Neurocomputing, 137, 47-56.
National Agency for Higher Education Quality Assurance (NAQA). (2021). Requirements for scientific articles for the award of scientific degrees. Retrieved from [official NAQA website link].
Amazon Web Services. (2024). Amazon EC2 Auto Scaling. Retrieved from [official AWS documentation link].
Guresen, E., Kayakutlu, G., & Daim, T. U. (2011). Using artificial neural network (ANN) for stock market index prediction. Expert systems with applications, 38(8), 10842-10849.
Graves, A. (2013). Generating sequences with recurrent neural networks. arXiv preprint arXiv:1308.0850.
Smyl, S. (2020). A hybrid method of exponential smoothing and recurrent neural networks for time series forecasting. International Journal of Forecasting, 36(1), 75-85.
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Павло Кудринський, Олександр Звенігородський
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
