Ethanol Fuel Demand Forecasting in Brazil Using a LSTM Recurrent Neural Network Approach

Autor(es)

Puentes, J. A. ^[1] ; Ribeiro, C. O. ^[2] ; Ruelas, E. A. ^[3] ; Figueroa, V. ^[1]

Afiliação do(s) autor(es)

^[1] Tecnol Nacl Mexico Celaya, Guanajuato - Mexico

^[2] Univ Sao Paulo, Sao Paulo, SP - Brazil

^[3] Inst Tecnol Super Irapuato, Guanajuato - Mexico

• Tipo de documento: Artigo Científico
• Fonte: IEEE Latin America Transactions; v. 19, n. 4, p. 551-558, APR 2021.
• Citações Web of Science: 0

Resumo

Ethanol is a biofuel widely consumed in Brazil, which functions as a substitute for gasoline since the late 1970s. Due to several fluctuations in the characteristics of the Brazilian vehicle fleet and the political-economic conditions of the country, forecasting ethanol consumption has become a difficult task to perform. Under this scenario, the aim of this paper was to forecast ethanol consumption in Brazil using an approach of Long-Short Term Memory (LSTM) Recurrent Neural Networks (RNN) and Autoregressive Integrated Moving Average (ARIMA) models. The above, taking into consideration univariate and multivariate models for each case. Likewise, single-layer and multi-layer topologies of LSTM RNN were explored in this study. The results show that LSTM models overperformed ARIMA models even working with a relatively small training dataset of just 180 instances. This, for both univariate and multivariate models. A novel approach for searching suitable LSTM Neural Network topologies is proposed in this paper. (AU)

• Processo FAPESP: 15/50684-9 - Sustainable gas pathways for Brazil: from microcosm to macrocosm
• Beneficiário: Reinaldo Giudici
• Modalidade de apoio: Auxílio à Pesquisa - Temático
• Processo FAPESP: 14/50279-4 - Brasil Research Centre for Gas Innovation
• Beneficiário: Julio Romano Meneghini
• Modalidade de apoio: Auxílio à Pesquisa - Programa Centros de Pesquisa em Engenharia