TY - GEN
T1 - A Novel Hybrid Machine Learning Model for Short-Term Load Forecasting
T2 - 28th International Conference on Mechatronics Technology, ICMT 2025
AU - Mohammed, Fareeduddin
AU - Boumaiza, Ameni
AU - Sanfilippo, Antonio
AU - Qarnain, Syed
N1 - Publisher Copyright:
© 2025 IEEE.
PY - 2025/11/15
Y1 - 2025/11/15
N2 - In energy management, short-term load forecasting (STLF) is vital for maintaining the balance between demand and supply and ensuring operational efficiency in smart grids. We propose a hybrid model combining Multi-Linear Regression (MLR), Long Short-Term Memory (LSTM), and Feedforward Neural Networks (FFNN) to enhance forecast accuracy while maintaining computational efficiency. The model was validated on real datasets from Qatar and Panama City across 5-minute, 15-minute, 30-minute, and 1-hour resolutions. Compared to traditional hybrid models, it achieves significant improvements, including a 29% reduction in RMSE and 59% faster training times. These results demonstrate the model's applicability for real-time STLF in dynamic power grids, with direct implications for energy-efficient mechatronic systems.
AB - In energy management, short-term load forecasting (STLF) is vital for maintaining the balance between demand and supply and ensuring operational efficiency in smart grids. We propose a hybrid model combining Multi-Linear Regression (MLR), Long Short-Term Memory (LSTM), and Feedforward Neural Networks (FFNN) to enhance forecast accuracy while maintaining computational efficiency. The model was validated on real datasets from Qatar and Panama City across 5-minute, 15-minute, 30-minute, and 1-hour resolutions. Compared to traditional hybrid models, it achieves significant improvements, including a 29% reduction in RMSE and 59% faster training times. These results demonstrate the model's applicability for real-time STLF in dynamic power grids, with direct implications for energy-efficient mechatronic systems.
KW - Feedforward neural network (FFNN)
KW - Long short-term memory (LSTM)
KW - Multi-linear regression (MLR)
KW - Short-term load forecasting (STLF)
KW - Smart grids
UR - https://www.scopus.com/pages/publications/105032067968
U2 - 10.1109/ICMT67823.2025.11298922
DO - 10.1109/ICMT67823.2025.11298922
M3 - Conference contribution
AN - SCOPUS:105032067968
T3 - Proceedings of 2025 28th International Conference on Mechatronics Technology, ICMT 2025
SP - 259
EP - 264
BT - Proceedings of 2025 28th International Conference on Mechatronics Technology, ICMT 2025
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 12 November 2025 through 15 November 2025
ER -