A Fundamental Multilevel Optimization Decision Model for Complex Systems Based on an AI-Optimization Fusion Framework
DOI:
https://doi.org/10.35335/cit.Vol17.2025.1388.pp136-147Keywords:
Multilevel Optimization, AI-Optimization Fusion Framework, Hierarchical Decision-Making, Hybrid Intelligent Algorithms, Complex Systems ModelingAbstract
Complex systems in modern domains such as transportation, energy, supply chains, and autonomous multi-agent networks require decision-making frameworks capable of handling hierarchical structures, dynamic environments, and high levels of uncertainty. Traditional multilevel optimization models offer a structured approach but often struggle with computational complexity, nonlinear interactions, and incomplete information. This research proposes a fundamental multilevel optimization decision model based on an AI-Optimization Fusion Framework designed to overcome these limitations. The model integrates bilevel and trilevel hierarchical structures with artificial intelligence learning paradigms, including supervised learning, deep learning, and reinforcement learning, to form a unified architecture that adapts to evolving system behaviors. A hybrid algorithmic formulation is developed to merge optimization procedures with learning-based approximations, enabling faster convergence, improved robustness, and enhanced decision quality. The experimental and simulation results demonstrate that the proposed framework outperforms traditional optimization approaches in accuracy, computational efficiency, scalability, and resilience under uncertainty. The model’s hierarchical decision mechanisms allow for dynamic coordination across decision levels, while AI-driven components provide predictive and adaptive capabilities that mitigate complexity in high-dimensional environments. The research contributes a novel integrated architecture, theoretical enhancements in multilevel decision modeling, and algorithmic innovations for hybrid AI–optimization systems. Limitations related to data availability, computational resources, and structural assumptions are acknowledged, offering directions for future exploration. Overall, this study establishes a new foundation for intelligent, scalable, and robust decision-making in complex systems, positioning AI–optimization integration as a key enabler for next-generation autonomous and adaptive decision frameworks.
Downloads
References
F. G. Filip, “Decision support and control for large-scale complex systems,” Annu. Rev. Control, vol. 32, no. 1, pp. 61–70, 2008.
N. V Sahinidis, “Optimization under uncertainty: state-of-the-art and opportunities,” Comput. Chem. Eng., vol. 28, no. 6–7, pp. 971–983, 2004.
Y. Tang, J. Kurths, W. Lin, E. Ott, and L. Kocarev, “Introduction to focus issue: When machine learning meets complex systems: Networks, chaos, and nonlinear dynamics,” Chaos An Interdiscip. J. Nonlinear Sci., vol. 30, no. 6, 2020.
A. Papageorgiou, M. Tarkian, K. Amadori, and J. Ölvander, “Multidisciplinary design optimization of aerial vehicles: A review of recent advancements,” Int. J. Aerosp. Eng., vol. 2018, no. 1, p. 4258020, 2018.
P. Das, J. Mathur, R. Bhakar, and A. Kanudia, “Implications of short-term renewable energy resource intermittency in long-term power system planning,” Energy Strateg. Rev., vol. 22, pp. 1–15, 2018.
G. N. Yannakakis and J. Togelius, Artificial intelligence and games, vol. 2. Springer, 2018.
K. Abraham, “Deep Reinforcement Learning Based Approach for Multi-Agent Control of Residential Electric Water Heaters for Distribution Load Management.” University of Waterloo, 2021.
R. K. Tripathy and I. Bilionis, “Deep UQ: Learning deep neural network surrogate models for high dimensional uncertainty quantification,” J. Comput. Phys., vol. 375, pp. 565–588, 2018.
J. B. Maguire, D. Grattarola, V. K. Mulligan, E. Klyshko, and H. Melo, “XENet: Using a new graph convolution to accelerate the timeline for protein design on quantum computers,” PLoS Comput. Biol., vol. 17, no. 9, p. e1009037, 2021.
M. Majumder, “Multi criteria decision making,” in Impact of urbanization on water shortage in face of climatic aberrations, Springer, 2015, pp. 35–47.
G. Zhang, J. Lu, and Y. Gao, “Multi-level decision making,” Model. Methods Appl., 2015.
S. M. Zahraee, M. K. Assadi, and R. Saidur, “Application of artificial intelligence methods for hybrid energy system optimization,” Renew. Sustain. energy Rev., vol. 66, pp. 617–630, 2016.
G. Biswas et al., “Multilevel learner modeling in training environments for complex decision making,” IEEE Trans. Learn. Technol., vol. 13, no. 1, pp. 172–185, 2019.
S. Twaha and M. A. M. Ramli, “A review of optimization approaches for hybrid distributed energy generation systems: Off-grid and grid-connected systems,” Sustain. Cities Soc., vol. 41, pp. 320–331, 2018.
R. M. Lewis and S. G. Nash, “Model problems for the multigrid optimization of systems governed by differential equations,” SIAM J. Sci. Comput., vol. 26, no. 6, pp. 1811–1837, 2005.
C. Yang, Q. Huang, Z. Li, K. Liu, and F. Hu, “Big Data and cloud computing: innovation opportunities and challenges,” Int. J. Digit. Earth, vol. 10, no. 1, pp. 13–53, 2017.
A. Lavin et al., “Simulation intelligence: Towards a new generation of scientific methods,” arXiv Prepr. arXiv2112.03235, 2021.
H. Harun, “AI-Based Optimization of Resource Utilization in Edge and Cloud Environments,” Am. Int. J. Comput. Sci. Technol., vol. 1, no. 6, pp. 1–10, 2019.
F. Pardo, A. Tavakoli, V. Levdik, and P. Kormushev, “Time limits in reinforcement learning,” in International Conference on Machine Learning, PMLR, 2018, pp. 4045–4054.
H. H. Rashidi, N. K. Tran, E. V. Betts, L. P. Howell, and R. Green, “Artificial intelligence and machine learning in pathology: the present landscape of supervised methods,” Acad. Pathol., vol. 6, p. 2374289519873088, 2019.
A. Gachet and P. Brézillon, “A multi-level model,” J. Decis. Syst., vol. 14, no. 1–2, pp. 9–37, 2005.
E. C. Lupu and M. Sloman, “Conflicts in policy-based distributed systems management,” IEEE Trans. Softw. Eng., vol. 25, no. 6, pp. 852–869, 2002.
V. De Buck, P. Nimmegeers, I. Hashem, C. A. Muñoz López, and J. Van Impe, “Exploiting trade-off criteria to improve the efficiency of genetic multi-objective optimisation algorithms,” Front. Chem. Eng., vol. 3, p. 582123, 2021.
M. S. H. Lipu et al., “Artificial intelligence based hybrid forecasting approaches for wind power generation: Progress, challenges and prospects,” IEEE Access, vol. 9, pp. 102460–102489, 2021.
L. G. Pee, S. L. Pan, J. Wang, and J. Wu, “Designing for the future in the age of pandemics: a future-ready design research (FRDR) process,” Eur. J. Inf. Syst., vol. 30, no. 2, pp. 157–175, 2021.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Hengki Tamando Sihotang, Roma Sinta Simbolon
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
