ANN-driven optimization and dynamic performance assessment of a hybrid energy system with enhanced SOFC and compressed air energy storage

Chengbiao Dong and Milana Gennadyevna Gunina

Energy, 2025, vol. 328, issue C

Abstract: The present research introduces a new hybrid power cycle for higher renewable penetration while shaving electricity demands through efficient storage technologies. The research explores the critical question of how to optimize such a system for enhanced thermodynamic efficiency, economic feasibility, and environmental sustainability under varying operational and environmental conditions. A key novelty involves using flame-assisted solid oxide fuel cell technology, which increases hydrogen concentration in the combustion chamber, thus improving efficiency. Moreover, compressed air energy storage enhances the air pressure supplied to the fuel cell, thereby optimizing oxygen availability and reaction kinetics. The system's performance is comprehensively assessed, and multi-objective optimization through the Non-dominated Sorting Genetic Algorithm is employed. An Artificial Neural Network is utilized as a surrogate model to mitigate computational burden, trained on a dataset of simulation results to forecast performance indicators based on design variables. The surrogate model is incorporated into the NSGA-II optimization to enhance convergence while maintaining accuracy. The system has an exergy efficiency of 79.9 %, a levelized cost of power (LCOP) of 198 USD/MWh, and a CO2 emission index of 210.9 kg/MWh at TOPSIs point. Optimization significantly improves system performance, achieving a 10.8 % increase in exergy efficiency and reducing LCOP and CO2 emissions by 143.4 USD/MWh and 60.7 kg/MWh, respectively. Seasonal variations in wind speed and temperature significantly affect system performance under optimal conditions, with monthly LCOP values fluctuating between 191.59 USD/MWh in October and 273.27 USD/MWh in March, alongside a sustainability index ranging from 7.8 to 9.2. Hourly analyses indicate that high wind availability improves sustainability metrics, whereas low wind conditions lead to greater dependence on combustion-driven operations, thereby diminishing efficiency and sustainability.

Keywords: Compressed air energy storage (CAES); Techno-economic analysis; Environmental analysis; Flame-assisted fuel cells; Genetic algorithm optimization (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544225020900
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:328:y:2025:i:c:s0360544225020900

DOI: 10.1016/j.energy.2025.136448

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().