Title :
Fuzzy Bayes predictor in electric load forecasting
Author :
Teixeira, Marcelo Andrade ; Zaverucha, Gerson ; Silva, Victor Navarro Araújo Lemos da ; Ribeiro, Guilherme Ferreira
Author_Institution :
Syst. Eng. & Comput. Sci. Program, Univ. Fed. do Rio de Janeiro, Brazil
Abstract :
We present the fuzzy Bayes predictor (FBP), a hybrid system for the task of monthly electric load forecasting. The FBP is a modification we introduce in the naive Bayes classifier in order to enable it to predict numerical values. We consider three versions of the FBP, each one with a different dependence among the input data: independence, first-order and second-order dependence. For verifying the efficiency of the FBP´s prediction, we compare it with two fuzzy systems and two traditional forecasting methods, Box-Jenkins and Winters exponential smoothing
Keywords :
Bayes methods; fuzzy set theory; fuzzy systems; learning (artificial intelligence); load forecasting; electric load forecasting; first-order dependence; forecasting; fuzzy Bayes predictor; fuzzy set theory; learning; second-order dependence; Computer science; Electric variables measurement; Fuzzy systems; Load forecasting; Niobium compounds; Power engineering and energy; Predictive models; Smoothing methods; Systems engineering and theory; Testing;
Conference_Titel :
Neural Networks, 2001. Proceedings. IJCNN '01. International Joint Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-7044-9
DOI :
10.1109/IJCNN.2001.938728
