Autonomous life support using intelligent analysis in Kazakhstan

Abstract

The Republic of Kazakhstan has chosen a fundamentally new path for the development of society with the adoption by of the “Strategy “Kazakhstan 2050” and the Concept of transition to a “green” economy. One of the central points in the gradual transition to a green economy is energy efficiency. The use of modern neural network technologies in this area is a promising and relevant area of research. In this paper, we propose a model consisting of two similar perceptrons, one of which is applicable for predicting the hourly load profile of a working day, the other for a weekend or holiday. It was developed the software "Smart House Energy Management System". The software product includes four main blocks: Measurement data; Power indicators; Generation and consumption of electricity; and predictive model. The demo example predicted the current drawn by the load for two connected devices. It is possible to play different scenarios, disconnect and connect devices. We can adjust the work of alternative energy sources (we have solar panels) depending on the forecast.