Evolution of Machine Learning in Smart Grids

Abstract

The objective of this work is to investigate the evolution of the application of ma-chine learning (ML) in the area of smart grids. It presents an overview of research that used ML in the area of smart grids, through the quantitative descriptive analysis of periodical articles and newspapers, registered in the IEEE Xplore Library database, in the period between the years 2010 and 2019. A total of 108 research publications were identified that address the application of machine learning in the area of smart grids. The study also present the incidence of each topic related to smart grids as well as the types of machine learning used in each document. As a result, it was concluded that the number of surveys has increased in the previous 3 years, meaning this is between 2017 and 2019, with the main research topics related to smart grids being safety and reliability of the electrical network and energy management / forecasting. Also, was indicated that the main-ly two techineques of machine learning that have been used in smart grid area was Neural networks and Support Vector Machine (SVM).