Using deep learning for short-term load forecasting
- PDF / 1,301,169 Bytes
- 13 Pages / 595.276 x 790.866 pts Page_size
- 47 Downloads / 204 Views
(0123456789().,-volV)(0123456789(). ,- volV)
ORIGINAL ARTICLE
Using deep learning for short-term load forecasting Nadjib Mohamed Mehdi Bendaoud1 • Nadir Farah1 Received: 13 May 2019 / Accepted: 14 March 2020 Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract Electricity is the most important source of energy that is exploited nowadays; it is essential for the economic development and the social stability, and this implies the need to model systems that keeps a perfect balance between supply and demand. This task depends heavily on identifying the factors that affect power consumption and improving the precision of the forecasted model. This paper presents a novel convolutional neural network (CNN) for short-term load forecasting (STLF); studies have been conducted to identify the different factors that affect the power consumption in Algeria (North Africa), and these studies helped to determine the inputs to the model. The proposed CNN uses a two-dimensional input unlike the conventional one-dimensional input used for STLF, and the results given by the CNN were compared to other artificial intelligence methods and demonstrated good results for both: one-quarter-ahead and 24-h-ahead forecast. Keywords Short-term load forecasting Convolutional Neural Network Deep learning Artificial intelligence
1 Introduction With the current industrial and commercial development that the world is witnessing, electric energy is the one factor that keeps the world on developing and advancing. The need for controlling and monitoring this energy is a fundamental task. Due to the high demand for the electric energy and the fact that it cannot be stocked in nature, many efforts have been made to forecast its future values to make a reliable production workflow and avoid any overproduction or subproduction. Several works have been conducted on a load forecast; some of them focus on long-term forecasts (above 3 years), while others on a medium-term range (from 2 weeks to 3 years). These two find their meaning in the scheduling of future power demand which helps to maintain and upgrade the electric grid [1]. However, there is a more precise type of electric power prediction, which is known as short-term load forecasting
& Nadjib Mohamed Mehdi Bendaoud [email protected] Nadir Farah [email protected] 1
Labged Laboratory, Department of Computer Sciences, University of Badji Mokhtar Annaba, Annaba, Algeria
(STLF). This prediction type focuses on relatively short periods of time (1 h to 1 week); an accurate STLF prediction model can improve the energy market in terms of reliability, by regulating the production and avoiding overproduction or underproduction, and also decreasing production costs, and this will help to control the production and the supply chain and simplify the dynamic management of electric power. Several methods have been used in the literature in order to develop accurate STLF systems; these methods can be categorized into two classes: statistical methods and artificial intelligence (AI) ones, a
Data Loading...
