Particle Swarm Optimization (PSO) is a heuristic optimization algorithm based on the modeling of the behavior of fishes and birds flock. This paper proposes a better version of PSO, named Dynamic Cognitive-Social PSO “DCS-PSO”, for global minima search by introducing optimal and dynamic cognitive and social scaling parameters without taking into consideration the inertia term. Furthermore, the velocity of each particle is controlled systematically at each iteration to avoid local minimum traps and to converge quickly and reliably towards the global minimum. The proposed algorithm is more suitable for high dimensional optimization problems and it has gotten over the limitations of classical Particle Swarm Optimization. Several experiments have been carried out, using the proposed DCS-PSO, to optimize thirteen benchmark functions and an important improvement has been observed, not only in terms of reaching the best global solutions but also in terms of convergence speed, compared to the existing benchmark approaches.