Forecasting Residential Energy Consumption with the Use of Long Short-Term Memory Recurrent Neural Networks
Metadatos
Mostrar el registro completo del ítemAutor
Severiche Maury, Zurisaddai; Uc-Ríos, Carlos Eduardo; Arrubla Hoyos, Wilson; Cama-Pinto, Dora; Holgado Terriza, Juan Antonio; Damas Hermoso, Miguel; Cama Pinto, AlejandroEditorial
MDPI
Materia
HEMS Energy consumption prediction Deep learning LSTM Networks
Fecha
2025-03-04Referencia bibliográfica
Severiche-Maury, Z.; Uc-Rios, C.E.; Arrubla-Hoyos, W.; Cama-Pinto, D.; Holgado-Terriza, J.A.; Damas-Hermoso, M.; Cama-Pinto, A. Forecasting Residential Energy Consumption with the Use of Long Short-Term Memory Recurrent Neural Networks. Energies 2025, 18, 1247. https://doi.org/10.3390/en18051247
Patrocinador
University of Sucre; University of Granada; MICIU/AEI/10.13039/501100011033/PID2022-136779OB-C33 (PLEISAR); FEDER, EU.Resumen
In the quest to improve energy efficiency in residential environments, home energy management systems (HEMSs) have emerged as an effective solution, leveraging artificial intelligence (AI) technologies to improve energy efficiency. This study proposes a deep learning-based approach employing Long Short-Term Memory (LSTM) neural networks to predict household energy usage based on power consumption data from common appliances, such as lamps, fans, air conditioners, televisions, and computers. The model comprises two interrelated submodels: one predicts the individual energy consumption and usage time of each device, while the other estimates the total energy consumption of connected appliances. This dual structure enhances accuracy by capturing both device-specific consumption patterns and overall household energy use, facilitating informed decision-making at multiple levels. Following a systematic methodology that includes model building, training, and evaluation, the LSTM model achieved a low test set loss and mean squared error (MSE), with values of 0.0163 for individual consumption and usage time and 0.0237 for total consumption. Additionally, the predictive performance was strong, with MSE values of 1.0464 × 10−6 for usage time, 0.0163 for individual consumption, and 0.0168 for total consumption. The analysis of scatter plots and residuals revealed a high degree of correspondence between predicted and actual values, validating the model’s accuracy and reliability in energy forecasting. This study represents a significant advancement in intelligent home energy management, contributing to improved efficiency and promoting sustainable consumption practices.