Short-term electric load forecasting in the presence of solar renewable resources using adaptive neural fuzzy network (ANFIS) optimized with the fire hawk optimizer (FHO) algorithm
1
Department of Economics, Ar.C., Islamic Azad University, Arak, Iran.
2
Department of Computer, Ar.C., Islamic Azad University, Arak, Iran.
10.61882/jgeri.2026.2088470.1111
Abstract
Short-term load forecasting (STLF) plays a key role in the efficient management of smart grids, generation planning, and demand response. In this study, a novel hybrid model based on Adaptive Neural Network Fuzzy (ANFIS) is proposed, trained with the Fire Hawk Optimizer (FHO) algorithm. The model inputs include n previous time samples (lagged features) and statistical features extracted from past data (such as moving average, variance, maximum, minimum, and slope of the time series). This combination allows for accurate modeling of nonlinear relationships and management of uncertainties in load data. The proposed model was evaluated on real data of the power substation of Markazi Province (Arak region) during the years 2015 to 2019. In this work, the effects of the presence of renewable solar resources on household consumption for some households in the region have been included in the estimation of energy consumption. Comparative results with standard ARIMA, LSTM and ANFIS methods indicate the significant superiority of the proposed model. The MAPE and MSE values of the ANFIS-FHO model are on average less than 0.04 and 12, respectively, which shows a significant improvement over the baseline methods. The simplicity of implementation, reasonable computational speed and high accuracy make this model suitable for practical applications in smart grids.
Akbari,M , sharifnezhad,M , sharifnezhad,M and Haji,G . (2026). Short-term electric load forecasting in the presence of solar renewable resources using adaptive neural fuzzy network (ANFIS) optimized with the fire hawk optimizer (FHO) algorithm. (e737043). Journal of Green Energy Research and Innovation, (), e737043 doi: 10.61882/jgeri.2026.2088470.1111
MLA
Akbari,M , , sharifnezhad,M , , sharifnezhad,M , and Haji,G . "Short-term electric load forecasting in the presence of solar renewable resources using adaptive neural fuzzy network (ANFIS) optimized with the fire hawk optimizer (FHO) algorithm" .e737043 , Journal of Green Energy Research and Innovation, , , 2026, e737043. doi: 10.61882/jgeri.2026.2088470.1111
HARVARD
Akbari M, sharifnezhad M, sharifnezhad M, Haji G. (2026). 'Short-term electric load forecasting in the presence of solar renewable resources using adaptive neural fuzzy network (ANFIS) optimized with the fire hawk optimizer (FHO) algorithm', Journal of Green Energy Research and Innovation, (), e737043. doi: 10.61882/jgeri.2026.2088470.1111
CHICAGO
M Akbari, M sharifnezhad, M sharifnezhad and G Haji, "Short-term electric load forecasting in the presence of solar renewable resources using adaptive neural fuzzy network (ANFIS) optimized with the fire hawk optimizer (FHO) algorithm," Journal of Green Energy Research and Innovation, (2026): e737043, doi: 10.61882/jgeri.2026.2088470.1111
VANCOUVER
Akbari M, sharifnezhad M, sharifnezhad M, Haji G. Short-term electric load forecasting in the presence of solar renewable resources using adaptive neural fuzzy network (ANFIS) optimized with the fire hawk optimizer (FHO) algorithm. JGERI. 2026;():e737043. doi: 10.61882/jgeri.2026.2088470.1111
