Machine learning driven smart electric power systems

2022

Full text Open access: Gold Metadata (CSL-JSON)
DOI 10.32523/2616-7263-2022-141-4-30-37
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

The rapid growth of the population and economy leads to an increase in demand for electricity. Existing energy systems are intensively switching to active, flexible, and smart analogs of the smart grid, which creates big problems in many areas, such as the integration of renewable energy sources, cyberspace security, demand management, planning, and decision-making about the use of the system. Today, in the conditions of digitalization, automation, and intellectualization, traditional energy is changing, and new technologies are emerging, for example, «machine learning». This article discusses the possibilities of machine learning in electric power systems. The article describes the interrelation and interaction of elements of the smart network, the Internet of Things, and machine learning. The article presents methods of machine learning and their differences in solving technical problems of an intelligent network.