Short-term peak demand forecasting in fast developing utility with inherit dynamic load characteristics. I. Application of classical time-series methods. II. Improved modelling of system dynamic load characteristics

Abstract
Estimates of the peak demand pertaining to a typical fast-growing system with inherit dynamic load characteristics are derived from three classical time-series forecasting methods. These demand estimates are compared with corresponding actual values. It is shown that application of sophisticated technological classical forecasting techniques to the forecasting problem of a typical fast-growing utility with dynamic load characteristics gives peak demand forecasts with varying degree of accuracy over the forecasting periods considered. This is mainly due to the inherent inability of these methods to simulate the complex load characteristics arising from the interactions of seasonality, trend, and cyclic moving special events. An attempt is made to isolate the effects of these events and to separately forecast the static and dynamic components of the system demand. The accuracy of the forecasted demand thus obtained is comparatively better than that of the forecast obtained.>