Forecasting Performance Indicators of a Single-Channel Solar Chimney Using Artificial Neural Networks

Abstract

Solar chimneys are renewable energy systems designed to enhance natural ventilation, improving thermal comfort in buildings. As passive systems, solar chimneys contribute to energy efficiency in a sustainable and environmentally friendly way. The effectiveness of a solar chimney depends on its design and orientation relative to the cardinal directions, both of which are critical for optimal performance. This article presents a supervised learning approach using artificial neural networks to forecast the performance indicators of solar chimneys. The dataset includes information from 2784 solar chimney configurations, which encompasses various factors such as chimney height, channel thickness, glass thickness, paint, wall material, measurement date, and orientation. The case study examines the four cardinal orientations and weather data from Mexico City, covering the period from 01 January to 31 December 2024. The main results indicate that the proposed artificial neural network models achieved higher coefficient of determination values (0.905-0.990) than the baseline method across performance indicators of the solar chimney system, demonstrating greater accuracy and improved generalization. The proposed approach highlights the potential of using artificial neural networks as a decision-making tool in the design stage of solar chimneys in sustainable architecture.