Optimum estimation and forecasting of renewable energy consumption by artificial neural networks

Abstract

Increasing energy consumption has led to release of pollutants such as greenhouse gases that affects on human health, agriculture, natural ecosystems, and earth temperature. Accurate estimation and forecasting of renewable energy is vital for policy and decision-making process in energy sector. This paper presents an Artificial Neural Network (ANN) approach for optimum estimation and forecasting of renewable energy consumption by considering environmental and economical factors. The ANN trains and tests data with Multi Layer Perceptron (MLP) approach which has the lowest mean absolute percentage error (MAPE). The proposed approach is particularly useful for locations where there are no available measurement equipments. To show the applicability and superiority of the proposed ANN approach, monthly available data were collected for 11 years (1996–2006) in Iran. Complete sensitivity analysis is conducted to choose the best model for prediction of renewable energy consumption. The acquired results have shown high accuracy of about 99.9%. The results of the proposed model have been compared with conventional and fuzzy regression models to show its advantages and superiority. The outcome of this paper provides policymakers with an efficient tool for optimum prediction of renewable energy consumption. This study bypasses previous studies with respect to several distinct features.