Abstract
The study focuses on increasing the effectiveness of web server load forecasting systems, which are utilized for technical state diagnostics and ensuring data security of distributed computer systems and networks. The analysis of applied research papers has shown that a promising way of web server load forecasting systems development is improving their mathematical background by using modern frequency-time signal analysis methods based on the wavelet transformation theory. It has been established that the challenges of using the wavelet transformation theory are primarily related to the choice of basis wavelet type, parameters of which shall be adapted to the application conditions in a particular forecasting system. A new basis wavelet type selection method, which is most effective for web server load parameters forecasting, has been proposed. This method is based on a series of conditions and criteria to achieve significant effectiveness for the given forecasting task by choosing a basis wavelet type. Also, simulation modelling based on the web server request statistics collected by the authors in a Ukrainian university has shown that the method allows selecting the basis wavelet type, which ensures the approximation error level similar to that of the modern web server load forecasting systems. The possibility to avoid long-term simulation modelling typically used for basis wavelet type selection is a significant advantage of the proposed method for wavelet model development. Prospects for further research are related to the refinement of the effectiveness criteria calculation process and improvement of the proposed method by developing a basis wavelet parameters calculation procedure.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Bapiyev, I.M., Aitchanov, B.H., Tereikovskyi, I.A., Tereikovska, L.A., Korchenko, A.A.: Deep neural networks in cyber attack detection systems. Int. J. Civil Eng. Technol. (IJCIET) 8(11), 1086–1092 (2017)
Chen, Q.-S., Zhang, X., Xiong, S.-H., Chen, X.-W.: Short-term power load forecasting with least squares support vector machines and wavelet transform. In: International Conference on Machine Learning and Cybernetics, vol. 3, pp. 1425–1429 (2008)
Dychka, I., Tereikovskyi, I., Tereikovska, L., Pogorelov, V., Mussiraliyeva, S.: Deobfuscation of computer virus malware code with value state dependence graph. In: Advances in Intelligent Systems and Computing, pp. 370–379 (2018). https://doi.org/10.1007/978-3-319-91008-6
Hu, Z., Tereykovskiy, I.A., Tereykovska, L.O., Pogorelov, V.V.: Determination of structural parameters of multilayer perceptron designed to estimate parameters of technical systems. Int. J. Intell. Syst. Appl. (IJISA) 9(10), 57–62 (2017). https://doi.org/10.5815/ijisa.2017.10.07
Kavitha, K.J., Shan, B.P.: Reversible joint watermarking for medical images and videos. Int. J. Eng. Manuf. (IJEM) 8(5), 10–21 (2018). https://doi.org/10.5815/ijem.2018.05.02
Pereberin, A.V.: On the classification of wavelet transforms. Vyich. met. programmirovanie 2(3), 15–40 (2001). (in Russian)
Quadry, K.M., Govardhan, A., Misbahuddin, M.: A novel approach of kurtosis based watermarking by using wavelet transformation. Int. J. Image Graph. Sig. Process. (IJIGSP) 10(7), 42–50 (2018). https://doi.org/10.5815/ijigsp.2018.07.05
Savakar, D.G., Pujar, S.: Digital image watermarking using DWT and FWHT. Int. J. Image Graph. Sig. Process. (IJIGSP) 10(6), 50–67 (2018). https://doi.org/10.5815/ijigsp.2018.06.06
Starck, J.-L., Murtagh, F., Bijaoui, A.: Image and Data Analysis: The Multiscale Approach. Cambridge University Press, Great Britain, 307 p. (1998)
Steinbuch, M., van de Molengraft, M.J.G.: Wavelet Theory and Applications: A Literature Study. Eindhoven University of Technology, Netherlands, 39 p. (2005)
Takore, T.T., Kumar, P.R., Devi, G.L.: A new robust and imperceptible image watermarking scheme based on hybrid transform and PSO. Int. J. Intell. Syst. Appl. (IJISA) 10(11), 50–63 (2018). https://doi.org/10.5815/ijisa.2018.11.06
Tereykovska, L., Tereykovskiy, I., Aytkhozhaeva, E., Tynymbayev, S., Imanbayev, A.: Encoding of neural network model exit signal, that is devoted for distinction of graphical images in biometric authenticate systems. News Natl. Acad. Sci. Repub. Kaz. Ser. Geol. Tech. Sci. 6(426), 217–224 (2017)
Yakuben, M.B.: Detection of cyber attacks by searching for anomalies based on probabilistic and verification modelling. Shtuchnyj intelekt 3, 679–687 (2005). (in Russian)
Yang, Z.: Research on server load prediction based on wavelet packet theory. In: First IEEE International Symposium on Information Technologies and Applications in Education, pp. 610–613 (2007). https://doi.org/10.1109/isitae.2007.4409360
Yao, S., Hu, C., Peng, W.: Server load prediction based on wavelet packet and support vector regression. In: International Conference on Computational Intelligence and Security, vol. 2, pp. 1016–1019 (2006)
Yao, S., Hu, C., Sun, M.: Prediction of web traffic based on wavelet and neural network. In: 6th World Congress on Intelligent Control and Automation, vol. 1, pp. 4026–4028 (2006)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Hu, Z., Tereikovskyi, I., Tereikovska, L., Tsiutsiura, M., Radchenko, K. (2020). Applying Wavelet Transforms for Web Server Load Forecasting. In: Hu, Z., Petoukhov, S., Dychka, I., He, M. (eds) Advances in Computer Science for Engineering and Education II. ICCSEEA 2019. Advances in Intelligent Systems and Computing, vol 938. Springer, Cham. https://doi.org/10.1007/978-3-030-16621-2_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-16621-2_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-16620-5
Online ISBN: 978-3-030-16621-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)