The study of the quality of multi-step time series forecasting

Abstract

The work is devoted to the study of the quality of multistep forecasting of time series using the electricity consumption data for forecasting. Five models of multistep forecasting have been implemented, with their subsequent training and evaluation of the results obtained. The dataset is an upgraded minute-by-minute measurement of four years of electricity consumption. The dataset has been divided into training, validation, and test samples for training and testing models. The implementation is simplified by using the Tensor Flow machine learning library, which allows us to conveniently process and present data; build and train neural networks. The Tensor Flow functionality also provides standard metrics used to assess the accuracy of time series forecasting, which made it possible to evaluate the obtained models for forecasting the time series of electricity consumption and highlight the best of those considered according to the given indicators. The models are built in such a way that they can be used in studies of the quality of time series forecasting in various areas of human life. The problem of multistep forecasting for twenty four hours ahead, considered in the paper, has not yet been solved for estimating electricity consumption. The obtained forecasting accuracy is comparable to recently published methods for estimating electricity consumption used in other conditions. At the same time, the forecasting accuracy of the constructed models has been improved in comparison with other methods.