This paper presents an adaptive-network-based fuzzy inference system (ANFIS)for long-term natural Electric consumption prediction. Six models are proposed to forecastannual Electric demand. 104 ANFIS have been constructed and tested in order to find thebest ANFIS for Electric consumption. Two parameters have been considered in theconstruction and examination of plausible ANFIS models. The type of membership functionand the number of linguistic variables are two mentioned parameters. Six differentmembership functions are considered in building ANFIS, as follows: the built-inmembership function composed of the difference between two sigmoidal membershipfunctions (dsig), the Gaussian combination membership function (gauss2), the Gaussiancurve built-in membership function (gauss), the generalized bell-shaped built-inmembership function (gbell), the Π-shaped built-in membership function (pi), psig. Also, anumber for linguistic variables has been considered between 2 and 20. The proposedmodels consist of input variables such as: Gross Domestic Product (GDP) and Population(POP). Six distinct models based on different inputs are defined. All of the trained ANFISare then compared with respect to the mean absolute percentage error (MAPE). To meetthe best performance of the intelligent based approaches, data are pre-processed (scaled)and finally our outputs are post-processed (returned to its original scale). The ANFISmodel is capable of dealing with both complexity and uncertainty in the data set. To showthe applicability and superiority of the ANFIS, the actual Electric consumption inindustrialized nations including the Netherlands, Luxembourg, Ireland, and Italy from 1980to 2007 are considered. With the aid of an autoregressive model, the GDP and populationby 2015 is projected and then with yield value and best ANFIS model, Electric consumptionby 2015 is predicted.