Electricity Consumption Forecast Based on Neural Networks
Uakhitova A.B.
October 2022Pleiades Publishing
Mathematical Models and Computer Simulations
2022#14Issue 5863 - 874 pp.
Abstract: Load forecasting is an important tool for the operation of power systems. Quality planning of energy consumption leads to lower costs for energy retail companies. In this paper to improve electricity consumption forecasting accuracy, a new model based on an artificial neural network is proposed. A machine-learning-based load prediction model has been developed, implemented on the basis of Matlab simulation modelling. For short-term forecasting, hourly energy consumption data of the city of Nur-Sultan for the period 2018–2019 were used. In the work, the analysis of modern methods for forecasting electricity consumption, the choice of the configuration of the neural network, the determination of the input set of variables were carried out. Testing showed that the best results on the accuracy of the load forecast are achieved by a network with nonlinear autoregression and the Bayesian training principle. As a training algorithm for artificial neural networks, training algorithms for direct distribution networks were used, since they accounted for the greatest spread in forecasting loads. The simulation results illustrated that the proposed model performs well in power consumption forecasting and showed a high accuracy of the forecast.
artificial neural networks , Electricity consumption , load forecasting , Matlab
Text of the article Перейти на текст статьи
Department of Electric Power Supply, S.Seifullin Kazakh Agrotechnical University, Nur-Sultan, 010011, Kazakhstan
Department of Electric Power Supply
10 лет помогаем публиковать статьи Международный издатель
Книга Публикация научной статьи Волощук 2026 Book Publication of a scientific article 2026