Load Forecasting Using Hybrid Models

Abstract—This paper presents two hybrid neural networks de-rived from fuzzy neural networks (FNN): wavelet fuzzy neural net-work (WFNN) using the fuzzified wavelet features as the inputs to FNN and fuzzy neural network (FNCI) employing the Choquet in-tegral as the outputs of FNN. The learning through FNCI is sim-plified by the use of q-measure and the speed of convergence of the parameters is increased by reinforced learning. The under-lying fuzzy models of these hybrid networks are a modified form of fuzzy rules of Takagi-Sugeno model. The number of fuzzy rules is found from a fuzzy curve corresponding to each input-output by counting the total number of peaks and troughs in the curve. The models can forecast hourly load with a lead time of 1 h as they deal with short-term load forecasting. The results of the two hy-brid networks using Indian utility data are compared with ANFIS and other conventional methods. The performance of the proposed WFNN is found superior to all the other compared methods. Index Terms—Fuzzy systems, neural networks, short-term load forecasting, wavelet transforms and Choquet integral. I