Applications of noniterative least absolute value estimation for forecasting annual peak electric power demand

A noniterative least absolute value (LAV) technique for estimating the para meters of a selected electric load forecasting model is utilized. The selec ted forecasting model with the estimated parameters is employed in forecast ing the demand of a given data set. The main feature of the LAV technique i s its capability of rejecting any bad data in the parameters estimation pro cess without any previous knowledge of their location. To illustrate the ef ficiency of the LAV technique in electric load forecasting, two types of ap plications are considered. In the first application. the adequacy of the LA V technique for estimating reliable electric load forecasting model paramet ers is illustrated. Results have shown that models with parameters estimate d using the LAV technique generate better forecasting results than those us ing least-squares-technique-estimated parameters. In the second application , the efficiency of the LAV technique in estimating good forecasting model parameters for given bad data is demonstrated. The results have shown that the model with parameters estimated using the LAV technique produces quite reasonable forecasting results; whereas the model with least-squares-techni que-estimated parameters generates completely unacceptable forecasting resu lts due to the effect of bad data.