Identification of temperature and social events effects on weekly demand behavior

The accuracy of weekly load forecasts can have vital effects on power system operations. Saudi Consolidated Electric Company of the Central region of Saudi Arabia (SCECO-C) has a special weekly load behavior. Two main load components can be identified. The first component is an inherent static temperature-dependent load while the other is a highly dynamic load. The dynamic load component results from the load contribution of cyclic events related to the social events. Those social events, in Saudi Arabia, are partially moving in relation to the lunar calendar. This paper describes a linear regression-based model for the estimation of parameters that affect weekly peak demand in electrical utilities. It includes an identification methodology for statistically significant social events. Accurate model building, including accurate social events modeling using binary variables and temperature modeling using heating and cooling degree-day functions are presented in the paper