Method of Dynamic Optimal Distribution of the Applications Flow in Multi-Server Interactive Systems

Authors

DOI:

https://doi.org/10.31649/1997-9266-2026-186-3-6-16

Keywords:

load balancing, interactive system, multiserver architecture, optimal distribution method, dynamic redistribution, token bucket algorithm

Abstract

The paper presents a dynamic optimal method of request flows distribution in multi-server interactive systems aimed at achieving adaptive load balancing under conditions of non-stationary and unpredictable traffic. The proposed approach ensures real-time adjustment of the request flow among parallel servers based on the current load coefficients, thereby maintaining system stability and minimizing the probability of overloads. A structural-functional model of the proposed method is developed, consisting of modules for traffic smoothing, dynamic demultiplexing, and load equalization across the server line.

A modified version of the “token bucket” algorithm is introduced to convert a non-stationary and pulsating incoming flow into quasi-stationary traffic segments that can be processed by discrete control mechanisms. The model continuously measures instantaneous load parameters for each server and performs iterative redistribution of queued requests between overloaded and underloaded nodes. In case of critical congestion, additional servers can be automatically activated, while in periods of low intensity, redundant servers are temporarily deactivated to optimize resource utilization.

The proposed method can be applied to the design of real-time systems, cloud data centers, VoIP and IoT platforms, and 5G core networks, where maintaining stable performance under variable loads is a critical requirement. The approach enhances system scalability, reduces latency and request loss probability, and provides a foundation for implementing intelligent software-based controllers for adaptive load balancing. The proposed software implementation confirmed the efficiency of the developed method for dynamic optimal distribution of the requests flow in multi-server interactive systems. The algorithm provides adaptive load balancing, reduces the probability of overloads and loss of requests, and can also be integrated into real-time systems, SDN platforms, VoIP servers or data centers.

Author Biographies

V. O. Gnatyuk, State University «Kyiv Aviation Institute»

Cand. Sc. (Eng.), Associate Professor, Head of the Chair of Telecommunications and Radioelectronic Systems

K. Yu. Zander, State University “Kyiv Aviation Institute”

Post-Graduate Student of the Chair of Telecommunications and Radioelectronic Systems

References

N. Olifer, V. Olifer, “Computer Networks: Principles,” Technologies and Protocols for Network Design, NJ: Wiley, 2005. 1008 с. [Electronic resource]. Available: https://link.springer.com/book/10.1007/978-3-031-17601-2 .

F. Miguelez, J. Doncel, and B. J. Prabhu, “Load-balancing for multi-skilled servers with Bernoulli routing,” Ann Oper Res, no. 312, pp. 949-971, 2022. https://doi.org/10.1007/s10479-022-04532-7 .

Kaur Shubhinder, and Kaur Gurpreet, “A Review of Load Balancing Strategies for Distributed Systems,” International Journal of Computer Applications, no. 121, pp. 45-47, 18, July 2015. https://doi.org/10.5120/21644-4985 .

J. Zhou, U. K. Lilhore, et al. “Comparative analysis of metaheuristic load balancing algorithms for efficient load balancing in cloud computing,” J Cloud Comp. no. 12, 85, 2023. https://doi.org/10.1186/s13677-023-00453-3 .

K. A. Vani, and K. N. RamaMohanBabu, “An Intelligent Server load balancing based on Multi-criteria decision-making in SDN”, IJECES, vol. 14, no. 4, pp. 433-442, Apr. 2023. [Electronic resource]. Available: https://ijeces.ferit.hr/index.php/ijeces/article/view/1946 .

Downloads

Abstract views: 13

Published

2026-07-06

How to Cite

[1]
V. O. Gnatyuk and K. Y. Zander, “Method of Dynamic Optimal Distribution of the Applications Flow in Multi-Server Interactive Systems”, Вісник ВПІ, no. 3, pp. 6–16, Jul. 2026.

Issue

No. 3 (2026)

Section

COMPUTER ENGINEERING, INFORMATION SYSTEMS AND TECHNOLOGIES

Metrics

Downloads

Download data is not yet available.

License

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Authors who publish with this journal agree to the following terms:

  • Authors retain copyright and grant the journal right of first publication.
  • Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
  • Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).