Generating High Quality Pseudo-Measurements to Keep State Estimation Capabilities

This paper proposes a methodology for providing real-time high quality pseudo-measurements to be used by the State Estimation function. A forecasting step is added to the estimation process in which one-step-ahead forecasts, obtained considering recent past State Estimation results, are adopted as pseudo-measurements. The model used to make forecasts is based on an artificial neural network. Test results using the IEEE-24 bus test system are presented to illustrate the performance of the proposed methodology.