ELECTRICAL ENERGY CONSUMPTION PREDICTION OF THE FEDERAL DISTRICT OF RUSSIA ON THE BASED OF THE RECCURENT NEURAL NETWORK

Abstract

The paper considers the prediction of electrical energy consumption using the recurrent neural network. Neural network is built on the base of the energy consumption data of the major Russian federal districts over the past 13 years. When developing the model, the following dominant factors were taken into account: data on energy consumption over the forecast period; meteorological factors (air temperature, cloudiness, amount of precipitation, wind speed, length of daylight, etc.); date (day, month); data of production calendars (information on the day of the week: weekday / weekend / holiday / shortened); specificity of the industry in the district under consideration (combining statistical information on major centers of federal districts). The factor were selected on the basis of test runs through the neural network of fixed configuration. The relevance of the study is explained by the practical importance of searching for the most accurate methods for predicting the main parameters of the energy market conducted by scientists in most developed countries of the world. The constructed recurrent neural network has yielded more accurate prediction results than the widely used mathematical prediction models based on regression dependencies. The obtained scientific result will help to reduce costs and increase the energy efficiency of the electro-energy subjects in the wholesale electric energy and capacity in Russia.