Most of the controllers for FACTS devices are based on the PI controller. Although the PI controllers are simple and easy to design, their performance deteriorates when the controlled object is highly nonlinear. This paper aims to propose an On-Line Self-Learning PID (OLSL-PID) controller design of SSSC for power system stability enhancement and to overcome the PI controller problems. The PID controller parameters are updated in on-line mode using BP algorithm based on the information provided by the Adaptive Sef-Recurrent Wavelet Neural Network (ASRWNNI) which is a powerful fast-acting identifier because of its local nature, self-recurrent structure and stable training algorithm with Adaptive Learning Rates (ALRs) based on discrete lyapunov stability theorem. The proposed control scheme is applied to multi-machine power system and simulation results are also presented to complement the theoretical discussion.