Research on Power System Load Forecasting Model Based on Data Mining Technology

In order to efficiently improve the prediction accuracy by selecting input variables and the training pattern, a load forecasting model based on data mining technique is presented. The model consists of three stages: firstly, the rough set theory and the genetic algorithm are applied to find relevant factors to the load; secondly, the active selection of the training pattern is carried out; last, the artificial neural network is used to predict load. Testing results on a real power system show that the proposed model is promising for load forecasting and is more accurate than the traditional one.