Bayesian forecasting technique for energy demand in Colombia
The daily energy demand forecast is very important for energy regulators in Colombia. Innovative techniques becomes increasingly necessary to forecast such variables. This paper presents a Bayesian approach to a forecast, based on a technique that enables elicitation of expert information and their integration into a single probability distribution, measuring the mean absolute percentage error indicator (MAPE) on the forecasts presented. We found that the use of the method could be enriching to innovate against the way to forecast energy and achieve appropriate levels of condence, without any historical data.
Main Authors: | , , |
---|---|
Format: | Digital revista |
Language: | spa |
Published: |
Universidad Nacional de Colombia - Sede Medellín - Facultad de Ciencias
2014
|
Online Access: | https://revistas.unal.edu.co/index.php/rfc/article/view/49272 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|