Identification of measurement variances based on test equations using ANN

Abstract

The paper addresses the methods for identification of random error variances in measurements. Consideration is given to the algorithms of identifying variances using a numerical method and ANN. The numerical methods based on calculation of discrepancy correlation in a pair of test equations with a common measurement are presented. Application of ANN allows identification of variances early at the stages of implementing the algorithms of state estimation for the larger part of the existing measurements as well as identification of measurements variances involved in one test equation only. Recommendations on application of the two offered algorithms for EPS state estimation in real conditions are given based on the their study and comparison. Index Termselectric power system, real time, identification of error variances, test equations, Kohonen maps.

Non-Iterative estimation of the AC overhead line state by relinearization method

“…is the state vector, consisting of magnitudes U and phase angles δ of voltages of all nodes of the EPS circuit, except the basic node phase; = ( )measured mode parameters; = ( )unmeasured mode parameters; y R -is a diagonal matrix, the elements of which are the measurement dispersions [1][2][3][4]. The state equations are nonlinear, therefore, the SE problem is solved by the iterative method, for example, the weighted least-squares method.…”

“…The main trend in development of the modern electric power industry is a control intellectualization. Traditionally, information about the current EPS mode Y = [Pij, Qij, Iij, Pi, Qi] entered the dispatcher control centers in the form of telemetries and tele-signals [1][2][3][4].…”