Electricity Distributor Load Forecasting with ARMA Models

The present work attempts to evaluate the advantages inherent to the use of exogenous variables highly correlated to the electric load, for the forecast of future demand. Here we utilize time series models of the auto-regressive moving average types incorporating seasonal treatment and exogenous variables. The details relevant to good modeling are presented and various different models are adjusted, including different combinations of load against the exogenous regressors IBC-Br and temperature. Considerations regarding non-stationary data such as different data generating processes (DGP) using trend or difference integration alternatives are investigated. In the end we demonstrate that predictions made using ARMA type models do not benefit from further sophistication in the form of exogenous variables due to the error inherent to the method itself, when applied to long term forecasts