A Hybrid Analytic-Numeric Framework For Optimization In Constrained Multivariate Systems
DOI:
https://doi.org/10.64137/XXXXXXXX/IJMAR-V1I1P101Keywords:
Hybrid optimization, Constrained multivariate systems, Bayesian optimization, Interior-point methods, Gaussian process regression, Global-local synergyAbstract
This paper explains a method that uses both calculation and analysis to handle optimization problems in restricted multi-variable systems. By combining global stochastic methods with local algorithms, the framework takes advantage of the benefits of Bayesian optimization for global searching and interior-point algorithms for smooth convergence. Gaussian process regression is used to form surrogate models, which allows for exploring the design space probabilistically, while IPOPT is applied to refine candidate solutions that look promising. Making use of both global and local approaches helps resolve the obstacles of each (such as large costs for global and limited success for local approaches). Through case studies on both constrained Ackley functions and industrial energy systems, it is shown that the proposed framework performs exceptionally well, as it is 40% faster than traditional strategies. Penalty terms are used to process nonlinear constraints, and the method also uses nesting to reduce dimensions, allowing for fast processing of big data. These results support the view that Q-learning succeeds in managing how it learns new behaviors versus how it takes advantage of learned strategies in domains with both nonconvex goals and traces of boundaries
References
[1] Parvathareddy, S., Yahya, A., Amuhaya, L., Samikannu, R., & Suglo, R. S. (2025). A Hybrid Machine Learning and Optimization Framework for Energy Forecasting and Management. Results in Engineering, 105425.
[2] Medina, E. A. (1999). Incorporating Hybrid Models into a Framework for Designing Multistage Materials Processes.
[3] Ahmad, I., Wan, Z., Ahmad, A., & Ullah, S. S. (2024). A hybrid optimization model for efficient detection and classification of Malware in the internet of things. Mathematics, 12(10), 1437.
[4] Zhou, H., Cheng, H. Y., Wei, Z. L., Zhao, X., Tang, A. D., & Xie, L. (2021). A hybrid butterfly optimization algorithm for numerical optimization problems. Computational Intelligence and Neuroscience, 2021(1), 7981670.
[5] Barton, P. I., Lee, C. K., & Yunt, M. (2006). Optimization of hybrid systems. Computers & chemical engineering, 30(10-12), 1576-1589.
[6] Kaiqiang Sun, X. W., Yang, S., Wang, H., Xu, Y., Zhang, Y., & Mao, S. (2024). A hybrid FEM-NN optimization method to learn the physics-constrained constitutive relations from full-field data. arXiv e-prints, arXiv-2406.
[7] Cuate, O., Uribe, L., Lara, A., & Schütze, O. (2020). Dataset on a benchmark for equality constrained multiobjective optimization. Data in brief, 29, 105130.
[8] Liu, L., Khishe, M., Mohammadi, M., & Mohammed, A. H. (2022). Optimization of constraint engineering problems using robust universal learning chimp optimization. Advanced Engineering Informatics, 53, 101636.
[9] Nan, Y., Ishibuchi, H., Shu, T., & Shang, K. (2024, July). Analysis of real-world constrained multiobjective problems and performance comparison of multiobjective algorithms. In Proceedings of the Genetic and Evolutionary Computation Conference (pp. 576-584).
[10] Rahimi, I., Gandomi, A. H., Nikoo, M. R., Mousavi, M., & Chen, F. (2024). Efficient implicit constraint handling approaches for constrained optimization problems. Scientific Reports, 14(1), 4816.
[11] Duan, S., Jiang, S., Dai, H., Wang, L., & He, Z. (2023). The applications of hybrid approach combining exact method and evolutionary algorithm in combinatorial optimization. Journal of Computational Design and Engineering, 10(3), 934-946.
[12] Yıldız, B. S., Kumar, S., Panagant, N., Mehta, P., Sait, S. M., Yildiz, A. R., ... & Mirjalili, S. (2023). A novel hybrid arithmetic optimization algorithm for solving constrained optimization problems. Knowledge-Based Systems, 271, 110554.
[13] Dehghani, M., & Trojovský, P. (2022). Hybrid leader based optimization: a new stochastic optimization algorithm for solving optimization applications. Scientific Reports, 12(1), 5549.
[14] Noyan, N., & Rudolf, G. (2013). Optimization with multivariate conditional value-at-risk constraints. Operations research, 61(4), 990-1013.
[15] Liang, J., Ban, X., Yu, K., Qu, B., Qiao, K., Yue, C., ... & Tan, K. C. (2022). A survey on evolutionary constrained multiobjective optimization. IEEE Transactions on Evolutionary Computation, 27(2), 201-221.
[16] Barigidad S. Edge-Optimized Facial Emotion Recognition: A High-Performance Hybrid Mobilenetv2-Vit Model. IJAIBDCMS [Internet]. 2025 Apr. 3 [cited 2025 May 21];6(2):1-10. Available from: https://ijaibdcms.org/index.php/ijaibdcms/article/view/113
[17] Agarwal S. “Multi-Modal Deep Learning for Unified Search-Recommendation Systems in Hybrid Content Platforms”. IJAIBDCMS [International Journal of AI, BigData, Computational and Management Studies]. 2025 May 30 [cited 2025 Jun. 4]; 4(3):30-39. Available from: https://ijaibdcms.org/index.php/ijaibdcms/article/view/154
[18] Lakshmikanthan, G. (2022). EdgeChain Health: A Secure Distributed Framework for Next-Generation Telemedicine. International Journal of AI, BigData, Computational and Management Studies, 3(1), 32-36.
[19] Sudheer Panyaram, (2023), AI-Powered Framework for Operational Risk Management in the Digital Transformation of Smart Enterprises.
[20] Susmith Barigidad. “Edge-Optimized Facial Emotion Recognition: A High-Performance Hybrid Mobilenetv2-Vit Model". IJAIBDCMS [International JournalofAI,BigData,ComputationalandManagement Studies]. 2025 Apr. 3 [cited 2025 Jun. 4]; 6(2):PP. 1-10.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
