Sustainable energies and machine learning: An organized review of recent applications and challenges

In alignment with the rapid development of artificial intelligence in the era of data management, the application domains for machine learning have expanded to all engineering fields. Noting the importance of using sustainable energies to run the world for the rest of this century, much research has focused on applying machine learning techniques to renewable and sustainable energies, and a comprehensive, well-organized, reader -oriented review of that research is needed. This review organizes the essential basics, major applications, and remaining challenges of machine learning in sustainable energies into two parts to accommodate the background knowledge and interests of both artificial intelligence and sustainable energy experts. First, the major applications of machine learning are divided into prediction, clustering, and optimization. For each category, the literature is categorized from new viewpoints, and research trends are highlighted to focus future research. In the second part, three primary machine learning???driven sustainability areas are introduced with respect to their abundance in the literature: multi-carrier energy systems, spatiotemporal analytics, and circular integration. For each engineering area, the contemporary progress is investigated in terms of a specific future research path. It is anticipated that the rapid application of machine learning tools will speed the development of sustainable energies during the next decade.

Automated summary

In alignment with the rapid development of artificial intelligence, machine learning is being widely applied in various engineering fields. This review emphasizes the importance of using machine learning techniques in renewable and sustainable energies, and provides a comprehensive overview of the major applications and remaining challenges. It is anticipated that the rapid application of machine learning tools will speed up the development of sustainable energies in the next decade.