Integrated Neural Network and Wavelet-Based Model for Web Server Load Forecasting
DOI:
https://doi.org/10.31861/sisiot2024.2.02006Keywords:
web server, load forecasting, time series, web traffic, probability theoryAbstract
This paper presents an integrated model for predicting the load on a web server by combining historical server logs, traffic data, and environmental factors to forecast load variations accurately. Key components include time series analysis for trend and seasonality detection, discrete wavelet transforms for noise reduction and feature extraction and neural networks for predictive modeling. Experimental results demonstrate that the integrated model achieves 15–25% higher forecasting accuracy compared to traditional methods, such as ARIMA. The proposed solution is scalable, adaptable, and provides a foundation for proactive load balancing and resource allocation strategies, ensuring robust server performance even during peak demand. The integrated model accounts for both short-term and long-term load variations, which is crucial for predicting peak loads and planning server resources. Future research may focus on optimizing algorithms and expanding the applications of this model to other systems, including cloud computing and distributed systems. The increasing demand for reliable and efficient web services necessitates accurate load prediction models to ensure optimal server performance and user experience. The modularity of the proposed model makes it scalable and adaptable, providing a foundation for active load balancing and resource allocation strategies to maintain server reliability even during peak load periods. A notable feature of the model is its ability to consider a wide range of variables, making it versatile for various types of data through the combination of classical statistical methods and modern machine learning algorithms. In addition to forecasting web server load, the proposed integrated model can be utilized for user behavior analysis, optimizing energy consumption, monitoring and predicting in data centers.
Downloads
References
T. Shelatkar, S. Tondale, S. Yadav, and S. Ahir, "Web traffic time series forecasting using ARIMA and LSTM RNN," ITM Web Conf., vol. 32, p. 03017, 2020.
V. Tambe, A. Golait, S. Pardeshi, R. Javheri, and P. G. Arsalwad, “Web traffic time series forecasting using ARIMA model,” Int. J. Res. Appl. Sci. Eng. Technol., vol. 10, no. 5, pp. 2447–2453, 2022.
I. Lohrasbinasab, A. Shahraki, A. Taherkordi, and A. Delia Jurcut, "From statistical‐ to machine learning‐based network traffic prediction," Trans. Emerg. Telecommun. Technol., vol. 33, no. 4, 2022.
I. Mahmood, S. Ameen, H. Yasin, N. Omar, S. Kak, Z. Najat, A. Salih, N. O. M. Salim, and D. Ahmed, "Web Server Performance Improvement Using Dynamic Load Balancing Techniques: A Review," Asian Journal of Research in Computer Science, vol. 10, pp. 47–62, 2021. DOI: 10.9734/AJRCOS/2021/v10i130234.
H.-K. Wang, X. Zhang, H. Long, S. Yao, and P. Zhu, "W-FENet: Wavelet-based Fourier-Enhanced Network Model Decomposition for Multivariate Long-Term Time-Series Forecasting," Neural Processing Lett., vol. 56, pp. 1–18, 2024. DOI: 10.1007/s11063-024-11478-3.
Z. Tian, "Network traffic prediction method based on wavelet transform and multiple models fusion," Int. J. Commun. Syst., vol. 33, e4415, 2020. DOI: 10.1002/dac.4415.
Z. Hu, I. Tereikovskyi, L. Tereikovska, M. Tsiutsiura, and K. Radchenko, "Applying wavelet transforms for web server load forecasting," in Advances in Computer Science for Engineering and Education II, Z. Hu, S. Petoukhov, I. Dychka, and M. He, Eds., vol. 938, Advances in Intelligent Systems and Computing. Cham: Springer, 2020, pp. 13-22. doi: 10.1007/978-3-030-16621-2_2.
K.O. Radchenko, "Application of discrete wavelet transformations for forecasting the level of load on the web server of general purpose computer networks," Computer-integrated technologies: education, science, production, no. 45, pp. 90–96, 2021. DOI: 10.36910/6775-2524-0560-2021-45-13.
K.O. Radchenko, "Peculiarities of predicting the level of web traffic in general purpose computer networks," Problems of informatization and management, no. 3(71), pp. 41–50, 2022. DOI: 10.18372/2073-4751.71.17002.
S. Prajam, C. Wechtaisong, and A. A. Khan, “Applying machine learning approaches for network traffic forecasting,” Indian J. Comput. Sci. Eng., vol. 13, no. 2, pp. 324–335, 2022.
K. Irie, C. Glynn, and T. Aktekin, “Sequential modeling, monitoring, and forecasting of streaming web traffic data,” Ann. Appl. Stat., vol. 16, no. 1, pp.300-325, 2022.
D. A. Tedjopurnomo, Z. Bao, B. Zheng, F. Choudhury, and A. K. Qin, “A survey on modern deep neural network for traffic prediction: Trends, methods and challenges,” IEEE Trans. Knowl. Data Eng., pp. 1–1, 2020.
A. Mamun, Md S. Sohel, Md N. Sami, Md S. Sunny, D. Roy, and E. Hossain, "A Comprehensive Review of the Load Forecasting Techniques Using Single and Hybrid Predictive Models," IEEE Access, vol. PP, pp. 1–1, 2020. DOI: 10.1109/ACCESS.2020.3010702.
D. Saxena, J. Kumar, A. Singh, and S. Schmid, "Performance Analysis of Machine Learning Centered Workload Prediction Models for Cloud," IEEE Transactions on Parallel and Distributed Systems, vol. PP, pp. 1–18, 2023. DOI: 10.1109/TPDS.2023.3240567.
Published
Issue
Section
License
Copyright (c) 2024 Security of Infocommunication Systems and Internet of Things
This work is licensed under a Creative Commons Attribution 4.0 International License.
