Análise da demanda de acumuladores de energia utilizando séries temporais

The use of statistical methods for forecasting demand helps managers in decision making, especially when it is necessary to carry out production planning. Therefore, it is extremely important to know the demand for a particular product, especially when it comes to lines of jobbing production systems...

Descripción completa

Detalles Bibliográficos
Autores: Cavalcante, Thiago Sales, Feitosa, Matheus, Orrego, Tulio Fidel, Gomes, Susane de Farias
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2022
País:Brasil
Institución:Universidade Estadual de Alagoas (UNEAL)
Repositorio:Diversitas Journal
Idioma:portugués
OAI Identifier:oai:ojs.diversitasjournal.com.br:article/2360
Acceso en línea:https://diversitasjournal.com.br/diversitas_journal/article/view/2360
Access Level:acceso abierto
Palabra clave:Previsão da demanda
Métodos de previsão
séries temporais
acumuladores de energia
Demand forecasting
forecasting methods
temporal series
energy accumulators
Descripción
Sumario:The use of statistical methods for forecasting demand helps managers in decision making, especially when it is necessary to carry out production planning. Therefore, it is extremely important to know the demand for a particular product, especially when it comes to lines of jobbing production systems in which transforming resources are shared between products. Following this idea, the manufacturing time of the products plays a relevant role both for the production programming to avoid incurring higher costs incurred in storage, obsolescence, among others. In order to overcome these difficulties by providing information on future sales of the product to the decision maker, this work uses time series of demand that were provided by the manufacturer of energy accumulators to forecast the demand for batteries. The study was aided by forecasting methods. Among these methods, the autoregressive integrated time series method – ARIMA – stands out, which was used and evaluated the accuracy of its forecasts. However, it was found that the additive Holt-Winters method presented the best fit for the data of this research. With the application of this methodology, it is expected to contribute to the efficiency of the programming of manufacturing processes.