Can machine learning predict large-scale solar irradiation and energy generation on building surfaces?

Therefore, this study presents a novel method for predicting large-scale solar irradiation and energy generation on building surfaces using urban morphological indicators through machine learning models.

Can machine learning predict solar potential for building façade PV systems?

Using an Australian city as a case study, a hierarchical two-level machine learning model is developed to predict the solar potential for building façade PV systems. The model incorporates 13 urban morphological predictors to determine average shading height and unshaded solar irradiance.

How can AI improve solar power?

Digital twins and algorithms for AI provide a robust basis for the early detection of system malfunctions. Integrating PV technology into building envelopes, vehicles and roads, as well as over agricultural fields and floating on water surfaces, capitalizes on surface areas with a tremendous potential for generating solar power.

Can machine learning predict solar energy potential?

The process of using machine learning to predict the solar potential for building PV at an urban scale is presented in Fig. 3, which presents a hierarchical, two-tiered predictive model to assess the relationship between urban morphology and solar energy potential.

How do PV systems affect the outdoor environment?

PV systems also affect the outdoor environment. The studies pointed out that the integration of PV systems, especially in facades, can increase the air temperature and accentuate the UHI effect during hot periods with higher solar radiation.

Are wind flow effects a derating factor in solar power modeling?

The novelty of this work lies in incorporating wind flow effects as a derating factor in solar power modeling, an aspect often ignored in similar studies. The proposed model offers a unique contribution by providing more accurate and practical information into the deployment of photovoltaic systems in wind-sensitive regions.