Hydraulic plant generation forecasting in Colombian power market using ANFIS

In this paper an ANFIS model is proposed to forecast the monthly ideal generation of an agent with a hydraulic plant within the Colombian power market. The proposed model considers several factors as the plant's reservoir level, the expected hydraulic contributions of the rivers which feed it, and the expected weather conditions represented by the SST anomaly forecast in Niño 3.4 zone. The fitness of such model is measured with real data of a particular agent from period 2002–2007 and it is compared against a multiple linear regression model. The obtained results show a considerable decrease of the mean percentage error, which is an evidence of its validity and possible application to other agents.