An Investigation on the Soft Computing Method Performance of the Optimizing Energy Consumption Cost

During peak demand hours, hydroelectric energy is one of the most significant sources of energy. Power sector restructuring has increased competition among the country’s electricity providers. Estimating the future price of energy is critical for producers in order to enhance investment profit and make better use of resources. One of the most significant technologies of artificial intelligence, Artificial Neural Networks (ANN), has various applications in estimating and forecasting phenomena. Combining artificial intelligence models with optimization models (e.g. Artificial Bee Colonoy [ABC]) has recently become quite popular for improving the performance of artificial intelligence models. The goal of this study is to look at the effectiveness of ANN and ABC-ANN models in forecasting the dispersed and sinusoidal data of Angola’s daily peak power price. The findings reveal that in this case study, the employment of the ABC-ANN model is not superior to the ANN model and has not resulted in enhanced performance and forecasting of power market data. As a result, the R2 of the ANN and ABC-ANN models is 0.88 and 0.85, respectively.