Browse

The paper analyzes the existing data mining methods to predict heat consumption in buildings of public sector facilities. The highest accuracy in solving the regression problem was obtained using the ensembles of artificial neural network models of the MLP architecture, gradient boosting models on decision-making trees and linear regression models. The ensembles of the studied methods were used in the development of the analytical subsystem in the energy resource management system of the Belgorod Region. Approbati...

The article is devoted to the implementation of predictive data analysis in energy resource management systems. An analytical review of modern methods used to verify information about the energy and resource consumption of distributed objects and the construction of mathematical models for its forecasting has been performed. It is reflected the positive and negative aspects of the use of predictive analytics as a source of data for planning the activities of organizations. The need for implementation is justified ...