Predicting electrical power output by using Granular Computing based Neuro-Fuzzy modeling method
Wenyue Sun, Jianhua Zhang, Rubin Yu-Wen Wang · 2015
The accurate prediction of electrical power output is crucial to reduce the cost for the power plant. Granular Computing (GrC) is a new data mining method. It can combine objects which have the similar characteristics to form granules. In such procedure, the core information can be extracted while the redundant information and the complexity of target problem are both reduced. In this paper, GrC is used to extract relational information and the data characteristics of a complex multidimensional data set. The extracted knowledge is translated into an initial fuzzy system and the parameters of the system are optimized by using the Adaptive Neuro-Fuzzy Inference System (ANFIS) learning methods. The use of GrC based Neuro-Fuzzy modeling (GrC-NF) can not only reduce the complexity of the target problem but also keep the interpretability characteristics of fuzzy logic. Moreover, the use of ANFIS can improve the performance of the model. Finally, a model for predicting electrical power output is built. The result comparison demonstrates the superiority of the method.