Fuzzy Inference Systems Applied to LV Substation Load Estimation

This paper describes a system for estimating load curves at low-voltage (LV) substations. The system is built by the aggregation of individual fuzzy inference systems of the Takagi-Sugeno type. The model was developed from actual measurements forming a base of raw data of consumer behavior. This database allowed one to build large test and training sets of simulated LV substations, which led to the development of the fuzzy system. The results are compared in terms of accuracy with the ones obtained with a previous artificial neural network approach, with better performance.