Method for Multi-Objective Optimization of Complex Signal Ensembles Based on the Evolutionary Algorithm E-LPT-MOEA/D
DOI:
https://doi.org/10.31861/sisiot2025.2.02014Keywords:
telecommunication systems, optimization, evolutionary approach, complex signal ensembles, SNRAbstract
The article proposes a method of multi-objective optimization of complex signal ensembles based on the evolutionary algorithm E-LPT-MOEA/D, which combines logarithmic time-segment permutations (LPT) with the task decomposition principle in a multi-objective evolutionary optimization framework. Unlike existing approaches, the method introduces adaptive interaction between the working population and the external Pareto archive, ensuring consistent updating of the solution set and convergence stability under stochastic perturbations. A modified genetic algorithm has been developed that incorporates entropy-weighted adjustment of weighting coefficients, flexible task delegation, and dynamic mutation control. This integration maintains a balance between exploration and exploitation, prevents premature convergence, and preserves the diversity of signal ensembles. The mathematical model includes objective functions representing the mean cross-correlation coefficient, integrated side-lobe level, variance of signal energy, and structural uniformity index. The optimization quality was evaluated using hypervolume (IH), inverted generational distance (IGD), and correlation deviation (Δρ) indicators. Experimental simulations were conducted in both normalized and absolute modes for various signal-to-noise ratios (10 – 25 dB) and time-segmentation parameters (τ = 0.3 – 1.0). The obtained results confirm the advantages of the proposed method, including a 20 – 30 % improvement in convergence speed, a 15 – 25 % increase in stability, and a 30 – 40 % reduction in the amplitude of hypervolume difference (ΔH) oscillations between the archive and the population. It has been proven that integrating the external archive mechanism with internal time-domain signal permutation ensures more uniform Pareto front coverage and enhances the structural balance of signal ensembles. As a result, the E-LPT-MOEA/D algorithm provides rapid adaptation to changing optimization conditions, resistance to interference, and scalability with increasing problem dimensionality. The proposed method can be effectively applied to the optimization of signal formation and processing processes in cognitive telecommunication environments, particularly in the development of dynamic spectrum monitoring systems, distributed communication networks, and energy-efficient data transmission protocols.
Downloads
References
І. Syvolovskyi and Komar О., “A method of multicriteria data stream distribution in telecommunication networks based on an evolutionary approach,” Computer-integrated technologies: education, science, production, Lutsk National Technical University, Lutsk, 2025, no. 59, pp. 230–239, 2025. https://doi.org/10.36910/6775-2524-0560-2025-59-41.
X. Cai, Q. Zhang, and Z. Fan, “An External Archive Guided Multiobjective Evolutionary Algorithm Based on Decomposition,” IEEE Transactions on Evolutionary Computation, vol. 19, no. 6, pp. 717–731, 2015, DOI:10.1109/TEVC.2014.2350995.
H. Song, Y. Liu, J. Chen, J. Wang, and L. Shen, “Evolutionary Ensemble Learning for Multivariate Time-Series,” IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 51, no. 12, pp. 7373–7385, 2021. https://arxiv.org/pdf/2108.09659.
O. Veklych and O. Drobyk, “Justification of the Efficiency of Time Segment Permutation in a Multilevel Optimization Method for Signal Ensembles,” Computer-Integrated Technologies and Automation, no. 4(52), pp. 88–95, 2025. https://doi.org/10.36910/6775-2524-0560-2025-59-38.
V. P. Lysechko, D. O. Kulagin, S. V. Indyk, O. S. Zhuchenko, and I. V. Kovtun, “The study of the cross-correlation properties of complex signals ensembles obtained by filtered frequency elements permutations,” Radio Electronics, Computer Science, Control, no. 2, p. 15, 2022. https://doi.org/10.15588/1607-3274-2022-2-2.
H. Azami, S. Sanei, K. Mohammadi, and H. Hassanpour, “A hybrid evolutionary approach tosegmentation of non-stationary signals,” Digital Signal Processing, vol. 23, no. 4, pp. 1103–1114, July 2013. https://doi.org/10.1016/j.dsp.2013.02.019.
L. Miao, Z. Sun, and Z. Jie, “The Parallel Algorithm Based on Genetic Algorithm for Improving the Performance of Cognitive Radio,” Wireless Communications and Mobile Computing, vol. 2, 2018. https://doi.org/10.1155/2018/5986482.
S. V. Indyk and V. P. Lysechko, “Study of ensemble properties of complex signals obtained by frequency filtering of pseudorandom sequences with low interaction in the time domain,” Collection of scientific works, Kharkiv: HUPS named after I. Kozheduba, issue 4 (66), pp. 46–50, 2020. DOI:10.30748/zhups.2020.66.06.
H. Wang, D. Li, Z. Liu, and J. Zhao, “Harmonic Detection Method Based on Permutation Entropy,” Review of Scientific Instruments, vol. 92, no. 2, 025118, 2021. https://doi.org/10.1063/1.5141923.
Q. Zhang and H. Li, “MOEA/D: A Multiobjective Evolutionary Algorithm Based on Decomposition,” IEEE Transactions on Evolutionary Computation, vol. 11, no. 6, pp. 712–731, 2007. 10.1109/TEVC.2007.892759.
X. Ma, F. Liu, Y. Qi, et al., “A Decomposition-Based Evolutionary Algorithm with Neighborhood Region Domination (MOEA/D-NRD),” Algorithms, vol. 10, no. 1, p. 19, 2025. https://doi.org/10.3390/biomimetics10010019.
Z. Fan, X. Ma, F. Liu, and Y. Qi, “MOEA/D with Angle-based Constrained Dominance Principle (ACDP) for Constrained Multi-objective Optimization Problems,” Information Sciences, vol. 465, pp. 1–22, 2019. https://doi.org/10.1016/j.asoc.2018.10.027.
J. Li, S. Xu, J. Zheng, G. Jiang, and W. Ding, “Research on Multi-Objective Evolutionary Algorithms Based on Large-Scale Decision Variable Analysis,” Applied Sciences, vol. 14, no. 22, p. 10309, 2024. https://doi.org/10.3390/app142210309.
T. Liu, Y. Chen, and X. Wang, “Domain Knowledge-Assisted Multi-Objective Evolutionary Algorithm for EEG-Channel Selection in Brain-Computer Interfaces,” Frontiers in Neuroscience, vol. 17, 1251968, 2023. https://doi.org/10.3389/fnins.2023.1251968.
YA. Baysal, S. Ketenci, I. H. Altas, and T. Kayikcioglu, “Multi-objective symbiotic organism search algorithm for optimal feature selection in brain computer interfaces,” Expert Syst. Appl., vol. 165, 113907, 2021. https://doi.org/10.1016/j.eswa.2020.113907.
Published
Issue
Section
License
Copyright (c) 2025 Security of Infocommunication Systems and Internet of Things
This work is licensed under a Creative Commons Attribution 4.0 International License.
