Machine Learning in Smart Grids

A Systematic Review, Novel Taxonomy, and Comparative Performance Evaluation

Absztrakt

This article presents a state of the art review on machine learning (ML) methods and applications used in smart grids to predict and optimize energy management. The article discusses the challenges faced by smart grids and how ML can help, using a new taxonomy to categorize ML models by method and domain. It explains different ML techniques used in smart grids. It examines various smart grid use cases, including demand response, energy forecasting, fault detection, and grid optimization, and how ML can improve these cases. The article proposes a new taxonomy to categorize ML models and evaluates their performance based on accuracy, interpretability, and computational efficiency. Finally, it discusses limitations, challenges and future trends of using ML in smart grid applications. Overall, the article highlights how ML can enable efficient and reliable smart grid systems.