ADAPTIVE NETWORK-BASED FUZZY INFERENCE SYSTEM SHORT-TERM LOAD FORECASTING

Akshay K. Saha, Sunetra Chowdhury, Shyamapada Chowdhury, and Alexander Domijan

Keywords

Adaptive network, artificial neural network (ANN), Sugeno models, adaptive network-based fuzzy inference system (ANFIS), short-term load forecasting

Abstract

A number of computing models based on adaptive network-based fuzzy inference system (ANFIS) is proposed in this paper for peak load forecasting. They have been formed with zero order and first order Sugeno model of ANFIS using various types of membership functions (MFs) and optimization method combinations. The models respond well even when the data pattern changes which may occur in case the load demand pattern changes or the weather parameters change. The proposed models have been validated using demand data of power utilities to forecast peak demand and it has been observed that they are capable of producing good forecasting accuracy. Comparison of forecasting accuracy for the models with that of other methodologies has also been depicted to illustrate the effectiveness of the ANFIS-based models.

Important Links:

Go Back