Forecasting electricity consumption in Algeria using artificial neural networks

Abstract EN

This paper applied the artificial neural network (ANN) to forecast electricity consumption in Algeria.

two independent variables, GDP (gross domestic product) per capita and population, are used to forecast electricity consumption.

the models' performance is evaluated using the coefficient of determination (R2) and the mean absolute percentage error (MAPE).

the results show that the ANN model that models electricity consumption as a function of economic indicators outperforms the ANN time input model.

in addition, the results indicate that Algeria’s projected electricity consumption will be 76.06 and 94.66 billion kwh in 2020 and 2025, respectively.

as a result, improved electricity forecasting is critical for policymakers when constructing future energy plants.