Optimal expansion for a clean power sector transition in Mexico based on predicted electricity demand using deep learning scheme

Tania Itzel Serrano-Arévalo, Francisco Javier López-Flores, Alma Yunuen Raya-Tapia, César Ramírez-Márquez and José María Ponce-Ortega

Applied Energy, 2023, vol. 348, issue C, No S0306261923009613

Abstract: This study presents a mathematical programming approach for the strategic planning of electrical energy production. The proposed approach seeks the optimal selection of conventional and clean technologies and their production capacity in a given period. In addition, it aims to assess the amount of emissions generated and water consumption, without neglecting economic aspects. The planning considered in this study extends from 2020 to 2040, where the approach considers the implementation of deep learning models to forecast the future electricity demand of each year through historical data; thus obtaining a more precise energy configuration. Fossil fuels and biofuels are used as primary energy in the operation of different technologies. Therefore, both economic and environmental objectives are considered. The economic objective function determines the minimum total discounted cost, which encompasses energy production, operation, maintenance, primary energy, and investment costs. While the environmental objective focuses on reducing water consumption and emissions. Through Pareto curves, using the ɛ-constraint method, the proposed model determines the trade-offs between the total discounted cost and the CO2eq emissions generated. The Mexican electrical system is presented as a specific case study with real production data and available resources. The results show that it is possible to reduce the total discounted cost by up to 11.02%, while in environmental aspects, up to 28.27% in emissions and up to 20.23% in water consumption, achieving that the power produced by renewable energies increases progressively until reaching 70% of the energy demand in 2040, where the system is committed to implementing clean technologies and replaces a percentage of fossil fuels with biofuels in conventional technologies. The results highlight that by increasing the investment cost with clean technologies, the system is balanced with a lower total future cost in the planning presented, thus reducing the environmental burden, and determining trade-offs between cost and environmental aspects.

Keywords: Power sector transition; Deep learning; Optimal planning; Renewable energy; Emissions reduction (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0306261923009613
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:appene:v:348:y:2023:i:c:s0306261923009613

Ordering information: This journal article can be ordered from
http://www.elsevier.com/wps/find/journaldescription.cws_home/405891/bibliographic
http://www.elsevier. ... 405891/bibliographic

DOI: 10.1016/j.apenergy.2023.121597

Access Statistics for this article

Applied Energy is currently edited by J. Yan

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