A new robust estimation method for short-term load forecasting

This paper presents a new robust method to estimate the parameters of ARIMA models. This method makes use of the minimum Hellinger distance estimator (MHDE) together with a robust filter cleaner able to reject a large fraction of outliers, and a Gaussian maximum likelihood estimation which handles missing values. The main advantages of the procedure are its easiness, robustness, high efficiency and practical execution. Its effectiveness is demonstrated on Monte Carlo simulations and an example of the forecasting of the French daily electricity consumptions.