Introduction A smart (or intelligent) well is a nonconventional well that is completed with downhole instruments such as pressure and temperature sensors coupled with donwhole control devices. The smart well can be a segmented, single horizontal well where every segment is controlled by independent control valves or a multi-lateral well where each lateral is controlled separately. Real time pressure, temperature and flow rate data obtained from the downhole sensors can be used to evaluate the performance of the well and to conduct various well surveillances such as well testing and optimization analysis. Using the variable positions of flow control valves, the well can be managed to optimize oil production. Smart wells can meet reservoir and production main objectives but not limited to: · Sustain well productivity · Improve sweep · Selective control of multiple layers · Manage water production Statement of the problem The superiority of smart completions over conventional completions is apparent in highly fractured reservoir where the degree of coning or cusping of water and gas varies between laterals. For example, water cut was reduced from 30% to 0% in a smart well in Saudi Arabia as a result of successful manipulation of downhole control valves. Reaching an optimum control valves setting combination requires fair to high number of trials depending on the complexity of the well (tri-lateral or quad-lateral) and reservoir (heterogeneity). This in turn results in decelerating production and hence lowering NPV. This research intends to lower the time required to reach the optimum combinations of valves setting by providing possible optimum combinations using genetic algorithm as a search mechanism in conjunction with a predictive reservoir model.