The analysis and forecasting of customer electricity consumption remain among the primary challenges in the power generation industry. Over the past decades, extensive research has been conducted to enhance the accuracy and efficiency of analysis and forecasting methodologies in this domain. With the rapid progress in computer science and artificial intelligence, machine learning algorithms have emerged as robust tools for predicting customer electricity consumption, attracting significant attention from researchers. This paper proposes a hybrid method based on Harris Hawks Optimization (HHO) algorithm and Long Short-Term Memory (LSTM) neural network for load forecasting using time series data. The HHO algorithm is employed to optimize the hyperparameters of the LSTM network, including the number of LSTM units, learning rate, and number of layers. The dataset consists of electricity consumption records, weather conditions, and temporal variables from Panama for the period spanning 2015 to 2020. The evaluation, conducted using RMSE, MAPE, MAE, and MSE metrics, indicates that the proposed HHO-LSTM model outperforms conventional methods such as Support Vector Machines (SVM), linear regression, and basic neural networks. The model achieves a MAPE of 0.08% and an RMSE of 27.36. This approach offers a promising solution for optimizing energy production and distribution planning within smart power systems.
Elahi,H. , Pourhashem Kallehbasti,M. M. and Pirgazi,J. (2026). Enhanced Electricity Load Forecasting Using HHO-Optimized LSTM Networks. Advances in Sustainable Energies and Environment, 01(01), 18-28. doi: 10.22034/a-see.2025.2055995.1002
MLA
Elahi,H. , , Pourhashem Kallehbasti,M. M. , and Pirgazi,J. . "Enhanced Electricity Load Forecasting Using HHO-Optimized LSTM Networks", Advances in Sustainable Energies and Environment, 01, 01, 2026, 18-28. doi: 10.22034/a-see.2025.2055995.1002
HARVARD
Elahi H., Pourhashem Kallehbasti M. M., Pirgazi J. (2026). 'Enhanced Electricity Load Forecasting Using HHO-Optimized LSTM Networks', Advances in Sustainable Energies and Environment, 01(01), pp. 18-28. doi: 10.22034/a-see.2025.2055995.1002
CHICAGO
H. Elahi, M. M. Pourhashem Kallehbasti and J. Pirgazi, "Enhanced Electricity Load Forecasting Using HHO-Optimized LSTM Networks," Advances in Sustainable Energies and Environment, 01 01 (2026): 18-28, doi: 10.22034/a-see.2025.2055995.1002
VANCOUVER
Elahi H., Pourhashem Kallehbasti M. M., Pirgazi J. Enhanced Electricity Load Forecasting Using HHO-Optimized LSTM Networks. A-SEE, 2026; 01(01): 18-28. doi: 10.22034/a-see.2025.2055995.1002
