![[2602.13746] Data-driven Bi-level Optimization of Thermal Power Systems with embedded Artificial Neural Networks](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2602.13746] Data-driven Bi-level Optimization of Thermal Power Systems with embedded Artificial Neural Networks
Summary
This paper presents a machine learning-based bi-level optimization framework for industrial thermal power systems, enhancing efficiency and scalability in operations.
Why It Matters
The integration of artificial neural networks in optimizing thermal power systems addresses significant computational challenges, paving the way for more efficient energy production. This research contributes to the advancement of Industry 5.0 by offering scalable solutions that can adapt to real-world complexities and uncertainties in energy generation.
Key Takeaways
- Introduces a bi-level optimization framework using ANN for thermal power systems.
- Achieves significant computational efficiency with quick solution times (0.22 to 0.88 seconds).
- Demonstrates comparable performance to traditional bi-level optimization methods.
- Provides a robust operating envelope that accounts for uncertainties in operational variables.
- Contributes to energy-efficient operations in large-scale engineering systems.
Computer Science > Machine Learning arXiv:2602.13746 (cs) [Submitted on 14 Feb 2026] Title:Data-driven Bi-level Optimization of Thermal Power Systems with embedded Artificial Neural Networks Authors:Talha Ansar, Muhammad Mujtaba Abbas, Ramit Debnath, Vivek Dua, Waqar Muhammad Ashraf View a PDF of the paper titled Data-driven Bi-level Optimization of Thermal Power Systems with embedded Artificial Neural Networks, by Talha Ansar and 4 other authors View PDF HTML (experimental) Abstract:Industrial thermal power systems have coupled performance variables with hierarchical order of importance, making their simultaneous optimization computationally challenging or infeasible. This barrier limits the integrated and computationally scaleable operation optimization of industrial thermal power systems. To address this issue for large-scale engineering systems, we present a fully machine learning-powered bi-level optimization framework for data-driven optimization of industrial thermal power systems. The objective functions of upper and lower levels are approximated by artificial neural network (ANN) models and the lower-level problem is analytically embedded through Karush-Kuhn-Tucker (KKT) optimality conditions. The reformulated single level optimization framework integrating ANN models and KKT constraints (ANN-KKT) is validated on benchmark problems and on real-world power generation operation of 660 MW coal power plant and 395 MW gas turbine system. The results reveal a comparable...
