01759nam a22001097a 4500100006400000245013300064260003000197300001100227500133600238700004201574856003301616  aJamshed, Ahmed a13MPE13aSupervisor Dr. Aslam Pervez Memon  aProbabilistic Feed foreword  Neural Network Based Power System Stabilizer For Excitation Control System Of Synchronous Generator  aNawabshsh:bQUEST,c2015.  a58p, :  aABSTRACT

An economical and reliable power system is responsible to generate and deliver Eletric power in an efficient way by controlling terminal voltage and load frequency within permissible limits. An excitation system plays major role in the stability of power system. The high gain and fast action of an automatic voltage regulator (AVR) produces negative damping oscillation in the power system. To reduce these oscillations power system PSS) is connected in conjunction with exitation system. The PSS must be tuned to cope with the changing load conditions.
For this purpose, probabilistic feedforward neural network (PFFNN) based power system stabilizer is proposed in this research work. The conventional PSS is designed and developed in Matlab and the data of frequency deviation and terminal voltage (Vt) is stored as input in order to train the probabilistic neural network (PNN) as PSS.
The simulation results of terminal voltage (Vt) and load frequency with conventional PSS and PNN-PSS are compared and discussed. The simulation results, when compared with conventional PSS, show that the proposed PSS has good control on the oscillations. It is also observed that PNN-PSS can enhance the dynamic and the transient stability of power system more easily and efficiently during the wide range of operating conditions.
  aDepartment of Electrical Engineering   uhttps://tinyurl.com/22ujkkj7