Reservoir management is an essential task aimed at the challenge of optimizing the exploration of petroliferous reservoirs. In response to such a challenge, the oil and gas industry has been developing new technologies, such as intelligent wells. These wells areintended to reduce the costs of the more commonplace restoring operations by controlling their technology. This work studies the development of intelligent fields and introduces a decision taking support system able to optimize, through evolutionary algorithms, the intelligent well technology control process considering the technical uncertainties: in valves and geological failures. Moreover, the system proposes to support decision taking, to use or not intelligent wells, given a reservoir ready to be explored or to receive expansion investments. The optimization seeks a strategy of pro-active control, in other words, act before the effect, seeking in the initial production times a configuration of valves capable of delaying the arrival of the water cut of the production wells, accelerate the oil production or to improve the oil recovery. As a result, an operation that maximizes the NPV (Net present value). The model was tested in three reservoirs, the first being a synthetic reservoir, and the others with more realistic characteristics.