POWER CONSUMPTION FORECASTING BASED ON FULLY CONNECTED FEED-FORWARD NEURAL NETWORKS

Abstract

The relevance The relevance of electricity consumption forecasting on the basis of fully connected feed-forward neural networks (FNN) to improve the validity of applications for electricity is considered. Aim of research Synthesis of predictive model of electricity consumption in the form of four-layer fully connected feed-forward neural network, linking the volume of production and the predicted electricity consumption is performed. Research methods The algorithm of the predictive model development includes: formation and initial statistical processing of initial data; determination of FNN structure hyperparameters — total number of layers, number of neurons in layers, activation function, training rate coefficient; selection of optimization method; training, checking model adequacy. Results The analytical expression for the description of the forecast model based on FNN is given. The synthesized forecast model makes it possible to increase the validity of electric power applications of enterprises.