Data analysis and predictive models in Smart Grid

Abstract

With the increasing penetration of smart elements into the electric power industry, the problem of processing, analyzing, and using data is becoming increasingly important. The presence of a large number of measuring devices allows you to collect hundreds of gigabytes of data, and every year the number of such devices will increase, allowing power companies to build more accurate predictive models using machine learning. These models can be used for a more accurate forecast of cross-border flows, improvement of control systems for energy storage systems, and improvement of work on the electricity trade market. This article explores several predictive models on the available data.