Analysis of the Architecture of Distributed Systems for the Reduction of Loading High-Load Networks

  • Yurii KryvenchukEmail author
  • Pavlo Mykalov
  • Yurii Novytskyi
  • Maryana Zakharchuk
  • Yuriy Malynovskyy
  • Michal Řepka
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1080)


In high-capacity networks, there is always a problem of delaying the receipt of packets between a client and a server. The load distribution should be made automatically based on the analysis of the distributed system state, since in the processing of Large Data it is necessary to analyze flows in a distributed, open dynamic system with a variable structure in real time. A distributed system for the task of reducing the load in high-capacity networks has been developed. An architectural scheme of “entering the remainder” is applied by introducing the new essence of the “last message”. This allows us to write the following message in the field of correspondence in the field. Therefore, we will be able to receive the latest message of any correspondence, but now, after each message arrives, it will be necessary to record it in two places. The cascade time synchronization scheme is proposed. The accuracy of time is important in distributed systems and allows you to synchronize the process. To do this, the Marzullo algorithm was used. This made it possible to establish a logarithmic relationship between the efficiency indicator and the number of machines. In this regard, it is important not to use too many computers with an algorithm that cannot provide efficient computer management. Improved messaging scheme. This allows you to define the entities used in this approach and to find references to each other. Query distribution managers send requests not only to each machine in sequence, but in real time recognize the one that is least downloaded and select it to handle the most demanding queries. This allows you to polynomically reduce the computation time.


High-load systems Distributed system Architecture Thread queue Multithreading Marzullo algorithm 


  1. 1.
    Brin, S., Page, L.: The anatomy of a large-scale hypertextual web search engine. Comput. Netw. ISDN Syst. 107–117 (1998).
  2. 2.
    Kryvenchuk, Y., Shakhovska, N., Shvorob, I., Montenegro, S., Nechepurenko, M.: The smart house based system for the collection and analysis of medical data. In: CEUR, vol. 2255, pp. 215–228 (2018)Google Scholar
  3. 3.
    Melnykova, N., Marikutsa, U., Kryvenchuk U.: The new approaches of heterogeneous data consolidation. In: XIIIth International Conference on Scientific and Technical Conference Computer Sciences and Information Technologies (CSIT), pp. 408–411 (2018).
  4. 4.
    Boyko, N.: A look trough methods of intellectual data analysis and their applying in informational systems. In: XIth International Scientific and Technical Conference on Computer Sciences and Information Technologies (CSIT), pp. 183–185 (2016).
  5. 5.
    Intanagonwiwat, C., Govindan, R., Estrin, D., Heidemann, J., Silva, F.: Directed diffusion for wireless sensor networking. Trans. Netw. 2–16 (2003).
  6. 6.
    Levis, P., Lee, N., Welsh, M., Culler, D.: TOSSIM: accurate and scalable simulation of entire TinyOS applications. In: Proceedings of the 1st International Conference on Embedded Networked Sensor Systems, pp. 126–137 (2003).
  7. 7.
    Goh, K.I., Oh, E., Kahng, B., Kim, D.: Betweenness centrality correlation in social networks. Phys. Rev. E 67(1), 017101 (2003)CrossRefGoogle Scholar
  8. 8.
    Vito, L., Massimo, M.: A measure of centrality based on the network efficiency. New J. Phys. 9, 1–29 (2007). Scholar
  9. 9.
    Jianwei, W., Tianzhu, G.: A new measure of node importance in complex networks with tunable parameters. In: WiCOM, Beijing (2008).
  10. 10.
    Zheng, C., Dong, J.: Sliding window calculating method of time synchronization based on information fusion. In: Tan, H. (ed.) Knowledge Discovery and Data Mining, vol. 135, pp. 687–691. Springer, Heidelberg (2012). Scholar
  11. 11.
    Olexa, R.: Implementing 802.11, 802.16, and 802.20 Wireless Networks: Planning, Troubleshooting, and Operations. Elsevier (2004)Google Scholar
  12. 12.
    Kryvenchuk, Y., Shakhovska, N., Melnykova, N., Holoshchuk, R.: Smart integrated robotics system for SMEs controlled by Internet of Things based on dynamic manufacturing processes. In: Conference on Computer Science and Information Technologies, pp. 535–549 (2018).
  13. 13.
    Peleshko, D., Ivanov, Y., Sharov, B., Izonin, I., Borzov, Y.: Design and implementation of visitors queue density analysis and registration method for retail videosurveillance purposes. In: First International Conference on Data Stream Mining and Processing, pp. 159–162 (2016).
  14. 14.
    Melnykova, N., Melnykov, V., Vasilevskis, E.: The personalized approach to the processing and analysis of patients’ medical data. In: IDDM, pp. 103–112 (2018)Google Scholar
  15. 15.
    Khavalko, V., Khudyy, A.: Application of neural network technologies for information protection in real time. In: First International Conference on System Analysis and Intelligent Computing, pp. 173–177 (2018)Google Scholar
  16. 16.
    Khavalko, V., Tsmots, I.: Image classification and recognition on the base of autoassociative neural network usage. In: 2nd Ukraine Conference on Electrical and Computer Engineering, pp. 1118–1121 (2019)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Lviv Polytechnic National UniversityLvivUkraine
  2. 2.Institute of Technology and Businesses in České BudějoviceCeske BudejoviceCzech Republic

Personalised recommendations