Application of adaptive neuro-fuzzy inference system based on data field clustering in load forecasting

This paper proposed a method of adaptive neuro fuzzy inference system based on the data field to solve the drawbacks of the general fuzzy neural network that can not optimize fuzzy rules and consume too much time in optimizating networks. Initialize fuzzy inference and network structure can be determined through the data field. The neural network learning mechanism is introduced to the logical reasoning, and the antecedent and conclusive parameters are adjusted using a hybrid learning algorithm to generate fuzzy rules automatically. The proposed method was applied to load forecasting in an area of Jiangsu, and the results showed its superior performance in modeling in the view of applicability.