A MEDIUM-TERM PROBABILISTIC MODEL FOR FORECASTING LOADS WITH A SMALL PROPORTION OF AIR-CONDITIONERS

In this paper, a medium-term load forecasting model is proposed, inten ded to be used for the extrapolation of loads containing a small propo rtion of air conditioners. The main feature of the proposed model is t he decomposition of weekly load observations into two independent comp onents: trend line and seasonal variations. The trend line is describe d by the combination of the polynomial regression and the first-order autoregressive model. The parameters of this model are estimated with the aid of the generalized least-squares method. The seasonal componen t is modeled via a discrete model, where the weather sensitive cycle i s separated from the weather insensitive one. A linear regression mode l is further proposed in order to associate weather sensitive variatio ns with the exogenous weather variable (temperature). This procedure e nabled a simple and efficient convolution of all load components into a single forecasting model. The whole methodology is verified on a rea l-life example of the peak-load consumption within the power system of former Yugoslavia.