Use of Accurate GPS Timing Based on Radial Basis Probabilistic Neural Network in Electric Systems

GPS based time reference provides inexpensive but highly-accurate timing and synchronization capability and meets requirements in power system fault location, monitoring, and control. In the present era of restructuring and modernization of electric power utilities, the applications of GIS/GPS technology in power industry are growing and covering several technical and management activities. Because of GPS receivers error sources are time variant, it is necessary to remove the GPS measurement noise. In this paper a Radial Basis Probabilistic Neural Network (RBPNN) has been applied to GPS receivers timing data for modeling of their timing error sources. This method estimates GPS receivers timing errors from their previous values. The efficiency of this algorithm is illustrated by experiments. For real-time restitution of GPS timing accuracy, the proposed method is implemented on designed hardwares. The experimental tests results on collected real data emphasizes that GPS timing RMS errors can be reduced from 300 nsec and 200 nsec to less than 160 nsec and 41 nsec, with and without SA, respectively.