Fuzzy type-1 and type-2 TSK modeling with application to solar power prediction

The random nature of solar energy resources is an obstacle to their penetration in power systems. The most practical way to predict this renewable source of energy is to use meteorological data. However, such data are usually provided in a linguistic form that cannot be exploited using traditional quantitative methods but which can be modeled using fuzzy logic. This paper proposes type-1 and type-2 Takagi-Sugeno-Kang (TSK) fuzzy systems for the modeling and prediction of solar power plants. The paper considers TSK models with type-1 antecedents and crisp consequents, type-1 antecedents and consequents, and type-2 antecedents and crisp consequents. The design methodology for tuning the antecedents and consequents of each model is described. Finally, input-output data sets from a solar plant are used to obtain the three TSK models and their prediction results are compared. The results show that type-2 TSK models with type2 antecedents and crisp consequents provide the best performance based on the solar plant data.