Work

Machine learning-driven design of a hybrid photovoltaic–thermoelectric and earth-coupled ventilation system for energy-efficient buildings

Year: 2026

Type: article

Abstract: The growing demand for sustainable and low-energy buildings has accelerated research into renewable systems that can simultaneously provide heating, cooling, and electricity. This study introduces a novel hybrid energy system that combines photovoltaic and thermoelectric modules with an earth-coupled ventilation duct. The system is designed for dual-mode operation preheating in winter and precooling in summer and aims to enhance building energy efficiency while maintaining thermal comfort. The proposed configuration integrates a photovoltaic panel for solar electricity generation, a thermoelectric generator for converting waste heat into additional electricity, and an underground earth air duct that passively conditions incoming air using the stable subsurface temperature. Together, these components form a thermodynamically coupled system capable of providing multi-functional energy services. A machine learning framework is developed to predict key performance indicators thermal power, electrical output, outlet air temperature, and exergy efficiency across various environmental and design conditions.

Source: Ain Shams Engineering Journal

DOI: 10.1016/j.asej.2026.104320

Authors: Wenfang Li, Suqi Wang, Rou Wang, Min Yang, Xiaoquan Zhou

Institutions: Jiangxi University of Software Professional Technology, Huai'an University, Yuzhang Normal University

Language: English

Topic: Building Energy and Comfort Optimization

Subfield: Building and Construction

Field: Engineering

Domain: Physical Sciences

SDGs: Affordable and clean energy, Climate action, Industry, innovation and infrastructure, Sustainable cities and communities

Open Access status: gold

Estimated APC paid: $1,200