A genetic algorithm-based deployment optimization model was proposed for anti-low-slow-small unmanned aerial vehicle (anti-LSS-UAV) systems in key low-altitude areas. It focused on key low-altitude areas and integrated UAV trajectory and force requirement models. An objective function was constructed by comprehensively considering factors such as environmental score, enemy attack probability distribution, and target detection/engagement success probability. Through comparative analysis with the compressed factor particle swarm optimization-genetic hybrid algorithm and the compressed factor particle swarm optimization algorithm, the genetic algorithm achieved a higher probability of reaching the global optimal deployment scheme within 50 iterations under the same environment, a lower average deviation, and thus higher reliability. To improve the reliability, the 100-iteration genetic algorithm was adopted as the algorithm for the deployment optimization model.