Error Reduction for GPS Accurate Timing in Power Systems using Kalman Filters and Neural Networks

The Global Positioning System (GPS) based time reference provides inexpensive but highly-accurate timing and synchronization capability and meets requirements in power system fault location, monitoring, and control. Precision satellite clocks and time measurements are the keys to the accuracy of GPS. A stand-alone civilian user enjoys an accuracy of 25 meters and 200 nanoseconds. Five methods, including two methods using Kalman Filter (KF), Recurrent Neural Network (RNN), Pi-Sigma Neural Network (PSNN) and Sigma-Pi Neural Network (SPNN), are proposed for error reduction of GPS receivers timing data. We use actual data to evaluate the performance of the proposed methods. An experimental test setup is designed and implemented for this purpose. Results using the five methods are discussed. The experimental results obtained from a Coarse Acquisition (C/A)-code single-frequency GPS receiver strongly support the potential of the method using PSNN to give high accurate timing. The GPS timing RMS error reduces to less than 38 nanoseconds. Streszczenie. Opisano zastosowanie system pozycjonowania GPS lokalizacji uszkodzeń i monitorowania sieci przesyłowej. System cywilny GPS oferuje dokładność rzędu 25 m i 200 nanosekund. Opracowano szereg metod poprawy dokładności, wykorzystujących filtry Kalmana i sieci neuronowe. Zredukowano błąd taktowania do około czterdziestu nanosekund. (Metody zmniejszenia błędów systemu GPS przy wykorzystaniu filtrów Kalmana i sieci neuronowych)