Improving the Efficiency of Data Processing and Traffic Allocation in Distributed Telecommunication Systems Based on NSGA-III and RVEA
DOI:
https://doi.org/10.31861/sisiot2026.1.01008Keywords:
distributed telecommunication systems, NSGA-III, RVEA, multi-objective optimization, data flow distributionAbstract
The article presents the development and experimental validation of modified evolutionary multi-objective optimization algorithms for improving data processing and flow distribution efficiency in distributed telecommunication systems.
The purpose of the study is to enhance system performance under dynamic operating conditions characterized by variable workload, interference, and limited computational resources. The scientific problem addressed lies in achieving efficient and stable multi-objective optimization of data flow distribution and processing, taking into account conflicting criteria such as processing delay, resource utilization, load balancing, and system stability. The proposed approach is based on modifications to the NSGA-III and RVEA algorithms, incorporating adaptive mechanisms, including workload prediction, hybrid constraint handling, dynamic adjustment of search directions, and adaptive mutation strategies. These enhancements enable improved adaptability of the algorithms to dynamic and uncertain operating environments. The architecture of the proposed solution integrates evolutionary optimization mechanisms into distributed data processing pipelines, allowing coordinated resource allocation and adaptive control of computational processes across network nodes. Experimental verification was conducted in two scenarios: traffic distribution in distributed telecommunication systems and object recognition in video streams under interference conditions. The results demonstrate that the modified NSGA-III algorithm provides the greatest improvement in performance, reducing processing time by up to 2.8% and increasing recognition accuracy by up to 1.4%. The modified RVEA algorithm ensures stable performance reducing processing time by approximately 2.3%, increasing accuracy by 1.1%, and reducing GPU usage by up to 2.0%. Statistical validation using the Student’s t-test confirmed the significance of improvements in processing time, accuracy, and GPU utilization (p < 0.05), while changes in CPU, RAM, and VRAM usage were not statistically significant, indicating the absence of additional computational overhead. The obtained results confirm that the proposed modifications of evolutionary algorithms are effective for adaptive optimization of data processing and flow distribution in distributed telecommunication environments, ensuring improved efficiency, stability, and robustness under dynamic conditions.
Downloads
References
I. Syvolovskyi and O. Komar, “A method of multicriteria data stream distribution in telecommunication networks based on an evolutionary approach,” Computer-Integrated Technologies: Education, Science, Production, no. 59, pp. 230–239, 2025, https://doi.org/10.36910/6775-2524-0560-2025-59-41.
B. Sadovnykov and O. Zhuchenko, “Mathematical model for object detection and recognition in video streams using inter-frame difference analysis,” National Aviation University. Science-intensive Technologies. Series: Electronics, Telecommunications and Radio Engineering, no. 66, pp. 182–189, 2025, https://doi.org/10.18372/2310-5461.66.20281.
P. Bieliaiev, V. Pastushenko, K. Trubchaninova, and O. Komar, “Method SYNERGY of distributed optimization and coordinated control in Fog/Edge telecommunication environments,” SISIOT, vol. 3, no. 2, p. 02018, Dec. 2025, https://doi.org/10.31861/sisiot2025.2.02018.
M. Klymash, A. Senyk, Y. Pyrih, and V. Mrak, “Investigation of a context-sensitive cybersecurity monitoring algorithm based on recurrent neural networks,” Infocommunication Technologies and Electronic Engineering, vol. 4, no. 1, pp. 1–9, 2024, https://doi.org/10.23939/ictee2024.01.001.
H. Qian, Y. Wu, R. Qin, X. An, Y. Chen, and A. Zhou, “Provable space discretization based evolutionary search for scalable multi-objective security games,” Swarm and Evolutionary Computation, p. 101770, 2025, https://doi.org/10.1016/j.swevo.2024.101770.
H. Seada and K. Deb, “A unified evolutionary optimization procedure for single, multiple, and many objectives,” IEEE Trans. Evol. Comput., vol. 20, no. 3, pp. 358–369, Jun. 2016, https://doi.org/10.1109/TEVC.2015.2459718.
S. Swarnakar, N. Kumar, A. Kumar, and C. Banerjee, “Modified genetic based algorithm for load balancing in cloud computing,” in Proc. IEEE Int. Conf. Convergence in Engineering (ICCE), Kolkata, India, 2020, pp. 255–259, https://doi.org/10.1109/ICCE50343.2020.9290563.
A. Sharaf and M. Pillai, “Genetic algorithm based clustering techniques in wireless sensor networks: A comprehensive study,” in Proc. Int. Conf. Innovations in Information and Communication Technology (ICIICT), Chennai, India, 2019, pp. 1–5, https://doi.org/10.1109/ICIICT1.2019.8741485.
G. Tel, Introduction to Distributed Algorithms. Cambridge, U.K.: Cambridge Univ. Press, 2000, https://doi.org/10.1017/CBO9781139168724.
O. Yunak, O. Shpur, B. Strykhaliuk, and M. Klymash, “Algorithm forming randomized system of iterative functions based on Cantor structure,” Infocommunication Technologies and Electronic Engineering, vol. 1, no. 2, pp. 71–80, 2021, https://doi.org/10.23939/ictee2021.02.071.
Y. Vesikar, K. Deb, and J. Blank, “Reference point based NSGA-III for preferred solutions,” in Proc. IEEE Symp. Series on Computational Intelligence (SSCI), 2018, pp. 1587–1594, https://doi.org/10.1109/SSCI.2018.8628819.
R. Zitar, “A review of the genetic algorithm and JAYA algorithm applications,” in Proc. Int. Congress on Image and Signal Processing (CISP-BMEI), Beijing, China, 2022, pp. 1–7, https://doi.org/10.1109/CISPBMEI56279.2022.9980332.
Y. Pyrih, “Computational complexity evaluation of a genetic algorithm,” Infocommunication Technologies and Electronic Engineering, vol. 4, no. 1, pp. 52–60, 2024, https://doi.org/10.23939/ictee2024.01.052.
W. Abdallah and T. Val, “Genetic-Voronoi algorithm for coverage of IoT data collection networks,” in Proc. Int. Conf. Computer Theory and Applications (ICCTA), Alexandria, Egypt, 2020, pp. 16–22, https://doi.org/10.48550/arXiv.2202.13735.
Y. Pyrih, M. Klymash, Y. Pyrih, and O. Lavriv, “Genetic algorithm as a tool for solving optimization problems,” Infocommunication Technologies and Electronic Engineering, no. 3, pp. 95–107, 2023, https://doi.org/10.23939/ictee2023.02.095.
B. I. Sadovnykov and O. S. Zhuchenko, “Method for object detection and recognition in video streams using interframe delta computation,” Control, Navigation and Communication Systems, vol. 2, no. 80, pp. 249–254, 2025, https://doi.org/10.26906/SUNZ.2025.2.249.
Published
Issue
Section
License
Copyright (c) 2026 Security of Infocommunication Systems and Internet of Things
This work is licensed under a Creative Commons Attribution 4.0 International License.
