Abstract
The paper considers the problem of forecasting the peak load hours for an upcoming month using artificial neural networks. To forecast the peak load hours, an indirect method is used based on forecasting the total energy consumption in a region for the next month. The region's total energy consumption has been forecasted using the popular Keras deep learning library. The paper presents the results of numerical experiments on forecasting the total energy consumption and peak load hours for a month to come. The paper also shows a way to improve the reliability of the forecasts using data obtained from the analysis of peak load hours for previous years. The possibility to forecast peak load hours may have a great practical effect in reducing energy costs when taking measures to decrease energy consumption during peak load hours.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call