Abstract
Spatial load forecasting is a process distributing the total forecasted load to one area. Because load forecasting of the areas are complex in spatial electrical load forecasting, rough set reasoning rule usually deals with more influential factors. In traditional method of spatial load forecasting, decisions mainly depend on the judgment of expert. In this paper a new method of spatial load forecasting is presented with the help of rough set data mining approach. It is theoretically demonstrated that for any condition attribute set, the finer the decision attribute value of a decision table is, the lower the information granularity is also. Finally, an actual case study illustrates the efficiency of this method.