Long-Term Load Forecast Using Decision Tree Method

Accurate long-term load forecast is important in planning, especially for developing countries where the demand is increased with dynamic and high growth rate. As a data mining method, the decision tree is very useful in a sense that it allows to extract if-then rules and clarify the relationship between input and output variables easily. In this paper, a decision tree based method was used to clarify the relationship between the load and relative variables. A set of decision rules were obtained and stored in the knowledge base to forecast. Finally comparative forecasting results with a conventional approach in real system are presented, demonstrating the usefulness of the developed system