2026-04-17T02:50:22Zhttps://recercat.cat/oai/request

oai:recercat.cat:2117/4494642026-03-20T06:57:16Zcom_2072_1033col_2072_452950

Forecasting energy demand in quicklime manufacturing: a data-driven approach Leon-Medina, Jersson X. Fonseca Gonzalez, John Erick Callejas Rodriguez, Nataly Yohana González Niño, Mario Eduardo Hernandez Moreno, Saul Andres Pineda Muñoz, Wilman Alonso Siachoque Celys, Claudia Patricia Umbarila Suarez, Bernardo Pozo Montero, Francesc Àrees temàtiques de la UPC::Enginyeria civil::Aspectes econòmics Energy consumption prediction Recurrent neural network Deep learning Long Short-Term Memory (LSTM) Gated Recurrent Unit (GRU) Time series forecasting This study presents a deep learning-based framework for forecasting energy demand in a quicklime production company, aiming to enhance operational efficiency and enable data-driven decision-making for industrial scalability. Using one year of real electricity consumption data, the methodology integrates temporal and operational variables—such as load profile, active power, shift indicators, and production-related proxies—to capture the dynamics of energy usage throughout the manufacturing process. Several neural network architectures, including Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Conv1D models, were trained and compared to predict short-term power demand with 10-min resolution. Among these, the GRU model achieved the highest predictive accuracy, with a best performance of RMSE = 2.18 kW, MAE = 0.49 kW, and SMAPE = 3.64% on the test set. The resulting forecasts support cost-efficient scheduling under time-of-use tariffs and provide valuable insights for infrastructure planning, capacity management, and sustainability optimization in energy-intensive industries. Colombian Ministry of Science Innovation and Technology (MINISTERIO DE CIENCIA, TECNOLOGÌA E INNOVACIÓN-Minciencias) with its grant 934 “Convocatoria de estancias posdoctorales orientadas por misiones”. This research is also funded by FONDO FRANCISCO JOSÉ DE CALDAS. Peer Reviewed Postprint (published version) 2025-12-16 Article https://www.mdpi.com/1424-8220/25/24/7632 http://creativecommons.org/licenses/by/4.0/ Open Access Attribution 4.0 International Multidisciplinary Digital Publishing Institute (MDPI)