Yu.M. Iskanderov1, A.A. Butsanets2, S.V. Smolentsev3, E.B. Mazakov4, K.V. Matrokhina5, V.Ya. Trofimets6

1 St. Petersburg Federal Research Center of the Russian Academy of Sciences (St. Petersburg, Russia)

2,3 Admiral Makarov State University of Maritime and Inland Shipping (St. Petersburg, Russia)

4–6 St. Petersburg Mining University (St. Petersburg, Russia)

1 iskanderov_y_m@mail.ru, 2 butsanetsaa@gumrf.ru, 3 SmolencevSV@gumrf.ru, 4 mazakov_eb@pers.spmi.ru 5 k.matrokhina@mail.ru, 6 zemifort@inbox.ru

The article presents an information traffic control algorithm in telecommunication networks, built using the fuzzy logic apparatus. As the base of fuzzy control algorithm, the Mamdani algorithm was chosen. Corresponding operations of fuzzy inference have been determined, allowing to give the control algorithm “flexibility” based on taking into account the accumulated practical experience of staff in the process of operating a telecommunication network. Initial dataset has been generated based on the technical characteristics of the network, as well as on the basis of expert data obtained during its operation. The required linguistic variables used to control the network were specified, for these variables the necessary membership functions of three types are constructed. The base of fuzzy inference rules is formed, on the basis of which the value of the output linguistic variable is found. The results obtained allowed to identify the most effective model of the membership function, which must be used for adequate fuzzy control. On a real example, the possibilities of using the proposed fuzzy control algorithm were demonstrated. The results of information traffic control modeling in the telecommunication network of a transport and energy company based on queuing theory and fuzzy logic are presented. The main characteristics of this network were calculated using and without using the proposed fuzzy controller, and their comparative analysis was carried out. To assess and justify the reliability of the obtained results of the problem under consideration, the main characteristics of the corresponding queuing system were calculated and the necessary dependencies were plotted. It is established that, with the use of the fuzzy control algorithm, the probability of failure and queuing in the telecommunication network is reduced, and the absolute throughput is increased. It is shown that for input and output variables it is advisable to use triangular membership functions, since their application allows to provide the user with the highest throughput.

Iskanderov Yu.M., Butsanets A.A., Smolentsev S.V., Mazakov E.B., Matrokhina K.V., Trofimets V.Ya. The effectiveness of the principles of adaptive layout in the development of user interfaces. Electromagnetic waves and electronic systems. 2024. V. 29. № 1. P. 41−55. DOI: https://doi.org/10.18127/j15604128-202401-04 (in Russian)

1. Bouillard A., Boyer M., Le Corronc E. Deterministic Network Calculus: From Theory to Practical Implementation. New York: Wiley-ISTE. 2018. 334 p. ISBN 9781119440284.
2. Logothetis M., Moscholios I.D. Efficient MultirateTeletraffic Loss Models Beyond Erlang. New York: Wiley-IEEE Press. 2019. 556 p. ISBN 978-1-119-42688-2.
3. Zukerman M. Introduction to Queueing Theory and Stochastic Teletraffic Models. ArXiv. 2013. DOI 10.48550/arXiv.1307.2968.
4. Tavalinsky D.A., Ratushin A.P., Timofeev D.I., Chikin R.V. Features of the Use of Deduplication Procedures for Signal Formation in Telecommunication Systems. Electromagnetic waves and electronic systems. 2020. V. 25. № 6. P. 75–82. DOI 10.18127/j15604128-2006-09. (in Russian)
5. Bogatin E. Signal and Power Integrity. Simplified. 2nd ed. Pearson Education. 2010. 902 p. ISBN-13 978-0-13-234979-6.
6. Levy B.C. Random Processes with Applications to Circuits and Communications. Springer. 2019. 466 p. ISBN 3030222969.
7. Simakov D.V. Traffic Engineering for Networks with High Dynamics of Routing Metrics. Online journal of Science Studies. 2016. V. 8. №1(32). P. 55. DOI 10.15862/60TVN116. (in Russian)
8. Tavalinskiy D.A., Krasikov D.A. Graphic dynamic modelling of information telecommunication network in interests of a rational distribution of resources. Dynamics of complex systems. 2022. V. 16. № 3. P. 40−46. DOI 10.18127/j19997493-202203-04. (in Russian)
9. Potapchuk I.A., Bagryantseva A.V. The routing method in a wireless self-organizing network based on a fuzzy logic apparatus. High voltage engineering and electronics. 2016. № 14. P. 82–88. (in Ukrainian)
10. Sorokin A.A., Chang Kuok T. Adaptive Fuzzy Control for Buffer Loading Regulation of Network Node. Scientific and technical bulletin of St. Petersburg State Polytechnic University. Computer science. Telecommunications. Management. 2018. V. 11. № 4. P. 36–48. DOI 10.18721/JCSTCS.11403. (in Russian)
11. Altaş I.H. Fuzzy Logic Control in Energy Systems with Design Applications in MatLab/Simulink. London: The Institution of Engineering and Technology. 2017. 506 p.
12. Melin P., Castillo O., Kacprzyk J., Reformat M., Melek W. Fuzzy Logic in Intelligent System Design. Theory and Applications. Springer. 2018. 416 p.
13. Park K.I. Fundamentals of Probability and Stochastic Processes with Applications to Communications. New York: Springer. 2018. 273 p. ISBN 978-3-319-68074-3.
14. Deepshikha B., Sonali V. Pervasive Computing: A Networking Perspective and Future Directions. Springer. 2019. 163 р. ISBN 978-981-13-3462-7.
15. Bouchon-Meunier B., Yager R.R., Zadeh L.A. Fuzzy Logic and Soft Computing. World Scientific. 1995. 509 p.
16. Bobyr M.V. Design of neural and fuzzy models in the field of computer engineering and control systems: Textbook. M.: Agramak-Media. 2018. 110 p. (in Russian)
17. Lukinsky V.S., Iskanderov Yu.M., Sokolov B.V., Nekrasov A.G. Problems and prospects of using intelligent information technologies in logistics systems. Materials of the conference "Information technologies in management". St. Petersburg: Central Research Institute "Electropribor". 2018. P. 80–89. (in Russian)
18. Iskanderov Yu.M., Doroshenko V.I. Organization of transport and technological processes based on integrated information systems. Collection of articles of the International Scientific and Practical Conference "New Economy" and the main directions of its formation. St. Petersburg: Peter the Great St. Petersburg Polytechnic University. 2016. P. 53–62. (in Russian)
19. Iskanderov Yu.M., Gaskarov V.D., Smolentsev S.V. Development of Transport and Technological Processes Based on Integrated Information Systems. Transport business of Russia. 2019. № 5. P. 114–117. (in Russian)
20. Asadullaev R.G. Fuzzy logic and neural networks: Textbook. Stipend. Belgorod: BelSU. 2017. 309 p. (in Russian)
21. Shtovba S.D. Introduction to the theory of fuzzy sets and fuzzy logic. [Electronic resource] – Access mode: https://studylib.ru/ doc/6257364/shtovba-s.d.-vvedenie-v-teoriyu-nechetkih-mnozhestv-i-nechetku ..., date of application 10.10.2023. (in Russian)
22. Bauer P. Introduction to fuzzy logic and fuzzy control systems. [Electronic resource] – Access mode: http://www.gotai.net/docu-ments/doc-l-fl-001.aspx, date of application 10.10.2023. (in Russian)
23. Paklin N. Fuzzy logic – mathematical foundations. [Electronic resource] – Access mode: https://loginom.ru/blog/fuzzy-logic, date of application 10.10.2023. (in Russian)
24. Yemelyanov S.G., Titov V.S., Bobyr M.V. Adaptive fuzzy logic control systems. M.: Argamak-Media. 2013. 184 p. ISBN 978-5-00024-005-2. (in Russian)
25. Matrokhina K.V. Application of the Apparatus of Fuzzy Logic to Solving Management Problems in Telecommunication Companies. Modern science: actual problems of theory and practice. Series: Natural and Technical Sciences. 2020. № 11. P. 91–96. DOI 10.37882/ 2223-2966.2020.11.24. (in Russian)
26. Khizhnyakov Yu.N. Algorithms of fuzzy, neural and fuzzy neural control in real-time systems: Textbook. Perm: Perm National Research Polytechnic University. 2013. 156 p. (in Russian)