Forecasting studies by designing Mamdani interval type-2 fuzzy logic systems: With the combination of BP algorithms and KM algorithms
This paper aims at using interval type-2 fuzzy logic systems (IT2FLSs) for one-day ahead load forecasting task. It introduces an optimal type reduction (TR) algorithm for IT2FLSs to improve their approximation capability. Flexibility and adaptiveness are the key features of the proposed nonparametric optimal TR algorithm. Lower and upper firing strengths of rules as well as their consequent coefficients are fed into a neural network (NN). NN output is a crisp value that corresponds to the optimal defuzzified output of IT2FLSs. The NN type reducer is trained through minimization of an error-based cost function with the purpose of improving forecasting performance of IT2FLS models. Once the optimal NN-based type reducer is trained, IT2FLS models can be straightforwardly forecast the next-day load demand. Numerical testing using real load datasets indicate IT2FLS models equipped with the new optimal TR algorithm outperform IT2FLS models using traditional TR algorithms in terms of forecast accuracies. This benefit is achieved in no cost, as the computational requirement of the proposed optimal TR algorithm is the same as for traditional TR algorithms.