A Model Free Estimation Based Neurocontroller for Synchronous Generator Excitation to Enhance Transient Stability

Synchronous generator output is proportional to generator load angle but as the parameter moved up the power system security is at stack. Hence, generators are operated well below their steady state stability limit. This raises demand for efficient and fast controllers. Artificial intelligence, specifically Artificial Neural Network (ANN) is emerging very rapidly and has become an efficient tool for researchers working in realm of operation and control of power system. ANN requires quite considerable time to tune weights but it is fast and accurate once tuned properly. In this paper, model free estimation-based adaptive and nonlinear approach is proposed to replace conventional controller compensated automatic voltage regulator. Thus reduces complexity and risk involved in indirect adaptive on line trained neurocontrollers used to drive dynamical systems.