Deep neural network optimization of a continuous solar-geothermal-driven plant with integrated thermal and mechanical energy storage: Incorporating bypass mechanism

Ali Ranjbar Hasan Barogh and Mahdi Moghimi

Energy, 2024, vol. 303, issue C

Abstract: In this current investigation, optimizing the cost and technological aspects of a novel integrated dual energy storage system embedded in a solar-geothermal-driven plant is proposed to assist in generating inexpensive and continuous power, fresh water, and hydrogen. the devised compressed air energy storage unit, aims to store a portion of the compressed air in the storage tank to use later for low-priced electricity production in peak demand times, and via a Bypass, the rest of the compressed air is used to run the downward sub-cycles even during the charging phase of the compressed air energy storage tank. The novel introduction of a Bypass in the compressed air energy storage unit, accelerates the synergy of the system by enabling the compressed air energy storage unit to continuously provide pressurized air to the system, instead of only supplying pressurized air for a limited time. Therefore, this will largely contribute to an increase in the production of the system. The introduction of the Bypass in the CAES unit has resulted in a significant 20.36 % increase in its round-trip efficiency, with only a negligible 2.8482 % rise in the overall cost rate, and a major 44.05 % increase in the rate of hydrogen production. The heated compressed air by the heliostat field is stored in the phase change material tank to supply the gas turbine with a constant heat load. Additionally, geothermal energy as an auxiliary energy source helps to generate desired products. A parametric study investigates how design parameters affect system performance. Through deep learning optimization which involves artificial neural networks and genetic algorithms, reduces the time used in optimization as it helps in finding the best solution fast and efficient. Based on multi-objective optimization, the system achieves a round-trip efficiency of 46 %, produces 6.956 kg/day of hydrogen, and has a total cost rate of 1.46 $/s.

Keywords: Deep neural networks; Phase change material; Compressed air energy storage; Multi-objective optimization; Thermodynamic analysis (search for similar items in EconPapers)
Date: 2024
References: View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S036054422401658X
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:303:y:2024:i:c:s036054422401658x

DOI: 10.1016/j.energy.2024.131885

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 ().