In this paper, an effective and reliable algorithm, based on Shuffle Frog Leaping Algorithm (SFLA) and Simulated Annealing (SA) is proposed for solving the optimal power flow (OPF) problem with non-smooth and non-convex generator fuel cost characteristics. Also, the proposed OPF formulation contains detailed generator constraints including active and reactive power generation limits, valve loading effects, and Prohibited Operating Zones (POZs) of units. OPF is spontaneously a complicate optimization problem, and becomes more and more complex considering the above constraints. Therefore, it needs to be solved with an accurate algorithm. Recently researchers have presented a new evolutionary method called SFLA algorithm. The original SFLA often converges to local optima. In order to avoid this shortcoming we propose a new method that profits from SA algorithm to improve local search near the global optima. The possibility of convergence to global optima is increased using the proposed method. For validating the proposed algorithm, it has been examined on the standard IEEE 30-bus test systems. The hybrid SFLA-SA provides better results compared to the original SFLA. SA, and other methods recently reported in the literature as demonstrated by simulation results. (C) 2012 Elsevier Ltd. All rights reserved.