Machine learning-based optimization of a waste-to-energy power plant with CAES for peak load management: Feasibility and a case study in Tehran

Adel Balali, Mohammad Javad Raji Asadabadi, Amirhosein Lotfollahi and Mahdi Moghimi

Energy, 2025, vol. 335, issue C

Abstract: This study presents a novel multi-generation system that integrates municipal solid waste (MSW) gasification with compressed air energy storage (CAES), aiming to enhance grid stability and achieve efficient waste-to-energy conversion. Furthermore, the proposed design enables the simultaneous production of electricity, freshwater, and hydrogen through a multi-heat recovery approach. A unique feature of this research is the integration of a supercritical CO2 cycle with a transcritical CO2 cycle to optimize waste heat recovery, improve efficiency, and reduce environmental impact. The results show that integrating these two units into the standalone gasifier/GT leads to a 58.24 % improvement in electricity production and a 36.8 % reduction in CO2 emission index (EMI). Additionally, the system harnesses high-temperature flue gas to reheat compressed air during CAES discharge, thereby eliminating the need for supplementary fuel consumption and minimizing greenhouse gas emissions. Integrating the CAES/PEME unit into the base system yields improved financial performance, with a 5.2 % increase in net present value. Parametric and sensitivity analysis from the 4E perspective (energy, exergy, economic, and environmental), implemented in MATLAB, identifies gasification temperature and biomass moisture content as the dominant factors affecting power generation, ERTE, and total cost. By applying a novel optimization method that integrates an artificial neural network with the gray wolf algorithm, the computational costs and runtime are significantly reduced compared to conventional methods. The proposed system achieves an ERTE of 33.52 %, EMI of 0.22 kg/kWh, and a payback period (PP) of 5.79 years under optimal conditions, representing an 8.27 % improvement in ERTE, a 4.35 % reduction in EMI, and a 9.67 % reduction in PP compared to the baseline scenario. Then, a case study assessed the potential of this system to utilize Tehran's MSW, predicting that it could supply electricity and freshwater to approximately 330,000 and 165,000 households, respectively. These findings underscore the system's considerable potential as a sustainable and cost-effective solution for addressing energy, waste, and emission challenges, while highlighting the need for future research on gasification efficiency, hybrid storage, and life-cycle assessment.

Keywords: Biomass gasification; Multi-heat recovery; Energy storage; 4E analysis; Machine learning (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544225036461
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:335:y:2025:i:c:s0360544225036461

DOI: 10.1016/j.energy.2025.138004

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 ().