Abstract
Traditional forecasting models have been widely used for decision-making in production, finance and energy. Such is the case of the ARIMA models, developed in the 1970s by George Box and Gwilym Jenkins [1], which incorporate characteristics of the past models of the same series, according to their autocorrelation. This work compares advanced statistical methods for determining the demand for electricity in Colombia, including the SARIMA, econometric and Bayesian methods.
Highlights
There are several studies on the habitual behavior of energy in Colombia [1]; shortcomings have been found in some of them, such as: lack of success, lack of integration with exogenous variables, lack of data to estimate models, among others.In Colombia, the National Dispatch Center (NDC), department of XM Compañía de Expertos en Mercados S.A.E.S.P, a subsidiary of ISA, is in charge of the operation and administration of the entire National Interconnected System of Colombia (SIN) [2]
This paper presents a characterization, analysis and comparison of the following models: SARIMA, econometric [6], and a Bayesian technique named Gaussian regression with Monte Carlo simulation by Markov Chains (MCMC) [7], which allow, after the estimation of tests, the validation and measurement of the average absolute percentage error indicator (MAPE) with adjustment and prognosis data for each one, and determine the best one to make the prediction of the demand for the Colombian state
The estimates of the statistical models used are presented with the respective characterization of Colombia's daily energy consumption, using the validation tests and comparison criteria necessary for an adequate analysis and selection of the one that allows optimizing in a more integral way, the forecast by showing a lower level of relative absolute error
Summary
The CND must make a maneuver plan for the generating companies, indicating the amount of power they must produce daily. For this reason, the forecast of energy demand is one of the most important tools in this process. That is why an effective prediction is really necessary, guaranteeing quality, security and reliability in the service for the users. In this regard, [3] states: "The prediction of demand is a problem of great importance for the electricity sector, since, based on its results, the agents of the energy market make the most appropriate decisions for their work". ESP, the electricity distribution and marketing company in Colombia, has prepared forecasts based on linear regression, exponential smoothing and moving average [4], comparing them using the ASM criterion [5]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
