Accurate forecasting of electricity demand is important for generation and distribution planning, especially in Jordan, where distinct seasons, variable weather, a fast-growing economy, a rising population, and shifting consumption habits affect demand. This paper applies four univariate time-series methods (ARIMA, SARIMA, Holt-Winters triple exponential smoothing, and Prophet) to one year of aggregated national daily electricity consumption data collected by the Jordanian Electric Power Company (JEPCO). The forecasting models are trained and then tested on two horizons that span held-out periods of three months and six months. Fitting is performed both with dynamic rolling multi-step forecasts across the entire held-out period and with one-step-ahead out-of-sample forecasts whose parameters are frozen at their training-window values. All models are compared with a weekly seasonal-naive forecast, and pairwise accuracy differences are assessed with Diebold–Mariano tests. The main finding in this work shows that model performance is dependent on evaluation mode. In one-step-ahead mode, Holt-Winters is the most accurate model on both horizons (MAPE of 1.90% and 2.27%; R2≥0.91); weekly SARIMA is statistically indistinguishable from it at three months, whereas ARIMA and Prophet are significantly less accurate. In dynamic multi-step mode, accuracy degrades sharply across all models (MAPE of 7.7–16.8%); no model attains a positive held-out R2; and none significantly outperforms the seasonal-naive benchmark. Exponential smoothing with weekly seasonality is therefore the strongest univariate choice for short-lead operational prediction, whereas reliable medium-term multi-step forecasting requires exogenous information.
BaniMustafa et al. (Fri,) studied this question.